Automation

These innovations make industrial robots significantly better

Robots can now be used for applications that previously could only be done manually. Not only AI and sensors play the main role.

Automated processes are now possible in robotics, above all thanks to AI and image processing systems, which previously could only be carried out manually
industrial robots

The possibilities of automation are constantly expanding and are moving into focus for robot applications that could previously only be carried out manually. Sorting waste on a conveyor belt, for example. And just as in the past two years with solutions for automated welding has developed into a large market, automated screwdrivers will now also automate many processes in assembly and, above all, make them more precise.
Among other things, in addition to being equipped with AI, image processing systems and sensors, the new robot generations are easier to install, program and network – the best prerequisites for combining traditional production with digital strategies. Below you can find out which six components of the robot improve your application or make it possible in the first place.

Despite their compact design, the 3FG15 grippers have a load capacity of 15 kg
industrial robots

Gripper

Grippers are becoming increasingly intelligent in order to be able to communicate with their technical environment via IO-Link, Profinet, EtherCat or EtherNet/IP for sensitive use. Not only do they receive information, the sensor data from a gripper, such as a temperature or acceleration, can also be sent to the system controller or stored in the data cloud.
The vacuum gripping systems from Schmalz, for example, provide important data on the condition of the system and enable functions such as condition monitoring and predictive maintenance. A comprehensive IO-Link configuration file IODD (IO Device Description) is available to the user for this purpose, which includes information on identification, device parameters, process and diagnostic data as well as communication profiles. The exchange of devices is also simplified since the IO-Link protocol contains an automatic data transfer mechanism.

Integration and operation significantly simplified

To simplify integration and operation, grippers are increasingly being designed as plug-and-produce solutions that are fully operational right out of the box on robots. This is made possible, for example, by the standard integration of a quick-change system in its tools (Quick Changer) and by providing a uniform programming logic (One System – Zero Complexity). Schmalz is also increasingly supplying software plugins that guide the user through the configuration with graphical support.
The greater compatibility of the grippers with robot arms from different manufacturers also makes integration easier for users and also expands the possible applications. New areas of application always result in new approaches to handling components. With the help of adhesive forces, such as with the new Adheso gripper technology from Schunk, sensitive components can be gripped completely energy-free, gently and without leaving any residue.

Drives

In order to extend the possible uses of an industrial robot to work environments in which potential contamination, for example from hydraulic oils, is excluded, pneumatic/compressed air-based grippers are replaced by electrically operated actuators in the pharmaceutical or food industry. Grippers with an electric motor reduce maintenance costs and simplify handling since they do not require external hoses that are prone to wear.
Drives that are compatible with intelligent interfaces such as RS232 or CAN enable communication between a gripper and the higher-level controller for the purpose of grip monitoring and gripping part recognition as well as flexible adjustment of gripping force and gripper stroke. Maintenance-free drives with high reliability and performance at the lowest possible weight are particularly important for lightweight robots/robots asked. The reason: the lower the weight of the EOT (End of Arm Tool), the more load a robot can lift.

Compact designs make jobs easier for grippers

More compact designs also reduce the interfering contours of the gripper. Faulhaber’s BXT series external rotor motors are an example of a unique ratio of torque to weight and construction volume. The iron-core motors with 14 high-performance rare-earth magnets on the rotor and 12 teeth on the stator are only 14 mm, 16 mm and 21 mm long, respectively, and are therefore suitable for applications that require a short drive solution with a high torque of up to 134 mm require.

Sensors

Cobots are becoming more and more sensitive and are now also taking on tasks in precision assembly or surface processing, such as deburring, grinding or polishing; the sensors can be integrated into the gripper itself or mounted as an external module on the tool flange of the robot arm.
Sensor technology right at your fingertips, for example, gives OnRobot’s RG2-FT grippers so much intelligence that they recognize the exact workpiece position. The previous programming of the parameters is therefore not necessary. The e-Series models from Universal Robots, on the other hand, have a force-torque sensor integrated into the tool flange: The highly sensitive sensor registers even the smallest of movements and gives the cobot a delicate touch.

Vision Systems

Artificial intelligence helps to optimize performance through algorithms and self-learning systems, from which vision solutions such as camera-supported bin picking benefit in particular. The ready-to-connect bin picker SBPG from Schmalz has proven itself for automated bin picking. It works in combination with a 3D camera system that performs visual part recognition allowed. Weighing only a few hundred grams, the bin picker reliably picks workpieces out of the container – regardless of whether they are stored randomly or pre-sorted.
More and more suppliers are bringing image processing systems onto the market, with the help of which robots capture their surroundings visually and multi-dimensionally. This allows them to recognize objects even if they are stacked or overlapping. Vision systems such as On Robots Eyes allow robots to visually recognize parts and perceive their surroundings spatially. This allows them to pick and pick in a more targeted manner.

AI and deep learning in action

Here, too, AI and deep learning are used in some cases: UR+ partners from Universal Robots have developed a sensor-based vision solution with which UR cobots master ‘bin picking’. Users no longer learn the robot for individual objects, but for the gripping process itself.
Equipped with a camera, gripper and appropriate software, a cobot can recognize any object regardless of coordinates and independently identify optimal gripping points. An AI vision sensor integrated into the camera is constantly learning, so that the process runs more and more smoothly – it is not necessary to teach in the components to be gripped.

Robot controllers from the Omni-Core family offer the necessary flexibility to integrate the latest digital technologies
Robot controllers

Steering

New control strategies based on AI – more specifically on machine learning – make it possible to automate manual production steps. For example, the AI-powered robotic controller Mirai from Micropsi Industries extends the robot’s native control and gives it the valuable ability of eye-hand coordination.
In contrast to classic vision systems, in which a camera remeasures every situation and every workpiece, AI-driven controls react to variances in real-time in the environment and continuously steer the robot through its path. This is made possible by the interaction of camera and software: In the future, robots can increasingly be ‘trained’ with AI-based solutions instead of being programmed.

Positioning tasks faster and easier to solve

Mirai has also recently acquired what is known as positioning skills, with which positioning tasks can be solved even more quickly and easily. To do this, the human employee guides the robot to the target and then ‘shows’ it the area around the target with the camera, whereby the robot ignores its own path. The AI ​​​​control then independently decides on the best path and guides the robot through its path each time anew.
The operation of collaborating robots is also becoming increasingly easier, such as with the handy Teach Pendant control unit from UR. The intuitive user interface also enables users without previous knowledge to control the robot and adapt the respective application to the situation. Operator panels of the latest controller generations also offer enormous flexibility thanks to the hot-plug function, for example. In this way, the tablet can be disconnected during operation and connected to another controller.

Connectivity to the digital platform and cloud solutions

Customization options are also flexible, as are the diverse assembly options that result from smaller footprints. One of the most important control features is the connectivity to digital platforms and cloud solutions, which can be used to improve the performance and reliability of individual robots through to entire robot fleets.
The digital ABB Ability platform includes networked services as well as the ABB safety solution SafeMove. With that, the controls offer basic functions that can enable collaboration with a connected industrial robot.

Human-Robot Collaboration

‘Hybrid’ collaborative robots are full-fledged industrial robots that can work at high speed but fall back to a safely reduced speed as soon as the human is directly in the workspace. After all, permanent human-robot interaction is only required for very few automation tasks.
In fact, in many cases, the human is rather ‘in the way’ of the robot since the robot has to work slowly – at a safely limited speed – in direct contact with its operator, which leads to long cycle times. Yaskawa’s Motoman HC models, for example, are such hybrid robots with a handling weight of 10 or 20 kg. The required safety in direct contact with the operator is guaranteed by its power and force limit circuit board, which enables flexible interaction between the robot and its environment.

Classic robot systems also work without a protective fence

However, classic robot systems can also work without a protective fence, provided they are equipped with a safe robot controller. The only difference to an HRC-capable hybrid robot is that the classic industrial robot has to stand still in the presence of humans, while the collaborative hybrid robot continues to work slowly and safely. Standard safety technology (such as safety laser scanners, safety curtains or safety mats) can be used to detect whether a person is present or not.

Applications

Automation beginners do not ask for individual components, but for applications. Here application kits, Which means a standardized component bundle with supplementary software services, solutions that are optimally coordinated with each other and with the robot. In addition, online platforms network end-users, system integrators and component manufacturers and offer standardized, attractively priced robot cells that automate processes that were previously carried out manually with little installation effort. With the CoLab, Schunk offers an essential building block for these platforms, because this is where these applications are validated and provided with the right components and software building blocks.

Industry 5.0: more human, more sustainable and more resilient

Industry 5.0, also known as the fifth industrial revolution, is a new model developed and promoted by the European Commission. They aim to encourage an industrial activity that goes beyond technical or economic objectives such as productivity and efficiency. Industry 5.0 also wants to promote other objectives essential for the future of the sector, such as human well-being, sustainability and resilience.

Industry 5.0: definition and origin

The term Industry 5.0, which was developed by the European Commission, emerged as a supplementary concept to Industry 4.0. This new approach encourages industrial development towards a production model geared not only to technological innovation and economic growth but also to a commitment to environmentally

responsible practices 

supports resilience strategies that strengthen the sector in the face of sudden disruptions such as the emergence of the Covid-19 pandemic.
This program, the main features of which are summarized in the report Industry 5.0 – Towards a sustainable, human-centric and resilient European industry, is the result of discussions during two virtual workshops that took place in July 2020. Various research and technology organizations and funding institutions from across Europe took part in these two gatherings. All participants agreed on the need to better integrate social and environmental priorities of the European Union into technological innovation, by shifting the focus from an individual technology to a systemic perspective.

Differences between Industry 4.0 and Industry 5.0

Industry 5.0 is not an evolution of Industry 4.0, nor is it an alternative model to replace it. In a way, it underscores the path that Industry 4.0 has taken. As explained by the European Commission, the fourth industrial revolution has focused on the digitization of processes and the use of artificial intelligence to increase productivity and efficiency, neglecting the role of workers involved in the production process or the shift to more sustainable development models.
In Industry 5.0, the human factor once again plays a major role and is once again at the centre of the production process. 

According to this premise, technology must serve people and not the other way around. Therefore, the goal is to arrive at a full human-machine collaboration scenario. In other words: If Industry 4.0 is based on the networking between machines and computer systems, then Industry 5.0 strives for the connection of the roles of humans and machines in order to strengthen and complement each other.

Industry 5.0 promotes sustainable robotization
Industry 5.0

Characteristics of Industry 5.0

The growth and development model promoted by Industry 5.0 is based on three pillars:

  • Sustainability. The development of production systems that use renewable energies is one of the requirements of Industry 5.0. With the target of reducing CO2 emissions by 55% by 2030, the European Commission states in its report that industry must be sustainable to respect the limits of our planet. For this reason, she recommends the development of circular processes that reuse and recycle natural resources, reduce waste and minimize environmental impact.
  • focus on the human: Industry 5.0 puts people at the centre of the production model. The premise is clear: instead of asking ourselves what we can do with the new technologies, we should consider what the technology can do for us. In addition, this more social and humane perspective confirms that the use of technology must not violate the fundamental rights of workers, such as their right to privacy, autonomy and human dignity.
  • resilience: Resilience has become a key factor in fighting the COVID-19 pandemic. The European Commission report states that geopolitical changes and natural crises such as the COVID-19 pandemic are revealing the vulnerability of our industries. For this reason, a commitment of the new concept of Industry 5.0 is to have the ability to adapt to adverse situations and obtain positive results from them.

With its sustainable, human and resilient approach, Industry 5.0 wants to successfully overcome disruptions and challenges and uses technology to do so.

Technologies on the way to Industry 5.0

According to the European Commission and within the technological framework, there are six key factors to drive Industry 5.0 forward:

⦁ 1) Individualized interaction between man and machine.
⦁ 2) Bio-inspired technologies and smart materials.
⦁ 3) Digital twins and simulation.
⦁ 4) Transmission, storage and analysis technologies.
⦁ 5) Artificial Intelligence (AI).
⦁ 6) Energy efficiency, renewable energy, storage and autonomy technologies.

This technological framework must be a strategy to achieve the goals of Industry 5.0. For example, the predictive analysis offers tools to strengthen the resilience of the sector with the aim of preparing for possible unforeseen events such as climate changes or fluctuations in demand.
Furthermore, cobots (collaborative robots) – machines designed to collaborate with workers and relieve them of the most strenuous, dangerous or repetitive jobs – are increasingly playing an important role in manufacturing plants and warehouses. This is encouraging, as the cobot boom confirms the feasibility of a technological model in which machines and humans co-star and work in harmony.

Industry 5.0, a paradigm shift

Industry 5.0 is still in its infancy as we are currently busy improving and optimizing Industry 4.0 using the technologies available in the market. Nonetheless, the ultimate goal is to foster a more resilient, sustainable and human-focused industry.
Industry 5.0 offers benefits for employees, companies and our planet. At this moment of a paradigm shift that we are in, not only are efficiency and productivity sought, but the goal is a production that respects the limits of our planet and values ​​the worker.

Industry 4.0 | an overview

Which technology makes the Internet of Things possible for industry

In this guide we give a comprehensive introduction to Industry 4.0 and the Internet of Things (IoT). Take a look with us at past technological developments and the challenges of tomorrow!
Industry 4.0

contents

  • What is the Internet of Things?
  • What separates the IIoT from the IoT?
  • What exactly is the difference between Industry 4.0 and the Internet of Things?
  • What is the Industrial Internet of Things currently being used for?
  • Why switching to Industry 4.0 is worthwhile
  • What challenges does Industry 4.0 face?
  • IIoT networks and protocols
  • IIoT data protocols
  • frequently asked Questions

What is the Internet of Things?

In short, it is the general term for connecting devices, much more than just PCs, smartphones or other telecommunications devices, to the Internet. These are often referred to as “smart devices” or smart devices, such as fitness trackers or voice assistants.
The abbreviation IoT ( Internet of Things ) is also common in German and English. The term has been on everyone’s lips for years and the industrial sector, in particular, has long since discovered it for itself.

What does IIoT mean?

This brings us to the so-called Industrial Internet of Things, which is often equated with Industry 4.0. The IIoT takes the concept of internet-connected devices and extends it to factories, manufacturing and industrial plants to share data quickly from near or far. For example, sensors can collect information and transmit it to the local network via a gateway and from there upload it to a cloud server so that you can access it from anywhere at any time. Incidentally, the direct, automatic control of networked devices is also referred to as a cyber-physical system.

What separates the IIoT from the IoT?

The main difference between IoT and Industry 4.0 lies in the application. While the former is for comfort, health and entertainment, the latter is all about collecting and processing sensor data in real-time to increase efficiency, optimize processes and save costs. It is not for nothing that one also speaks of a fourth industrial revolution.
The Industrial Internet of Things is based on a well-known form of computer-aided control, the distributed control system, which connects several autonomous devices and assigns them functions. These devices are thus able to continue to adjust and optimize the section of the production line they monitor independently, without the risk that a single fault in the system will bring the entire production to a standstill, as is the case with a centrally regulated controller would. The IIoT takes advantage of modern cloud computing to enable data sharing, visualization, and analysis—all in near real-time.
Within a few years, Industry 4.0 has developed into a huge sector. More than 60 per cent of global manufacturers now use IIoT-Tec.

What exactly is the difference between Industry 4.0 and the Internet of Things?

Although the terms Industry 4.0 and Internet of Things are sometimes used interchangeably, they are not synonymous. In fact, the Internet of Things and IIoT are part of Industry 4.0.
Industry 4.0 is generally used to describe the accelerated use of all advanced automation technologies available to industry and intelligent manufacturing today and the resulting benefits. The key components are:

  • Machine-to-Machine Communication (M2M)
  • Implementation of autonomous systems
  • Seamless cloud computing
  • Artificial intelligence and related ‘cognitive’ technologies such as image recognition

The history of the IoT and Industry 4.0

The Internet of Things may seem like a very modern concept but in fact some of the core technologies that make up Industry 4.0 date back to the 1960s. As early as 1968, programmable logic controllers (PLC’s) – essentially early industrial computers – were developed to fine-tune the manufacturing process. From the 1970s, the first industrial process control systems appeared, which gradually supplemented the manual work in the factories.
The Internet of Things as we know it today first came into focus in the following decade. In the early 2000s, the IoT gradually left research institutions such as universities and laboratories to reach the end-user. The development of enabling technologies such as Bluetooth, Near Field Communication (NFC) and 3G cellular networks accelerated the growth of this market. At the beginning of the millennium, cloud computing technologies, in particular, favoured the development of the IIoT.

What exactly does Industry 4.0 mean?

The term “Industry 4.0” first appeared in public at the Hanover Fair in 2011 to describe the use of information technology in production. The neologism was intended to place the impact of modern technologies on automation and data exchange in the wake of earlier industrial revolutions. These are:

  • The development of steam and water-powered manufacturing technology in the second half of the 18th and the first half of the 19th century,
  • The use of electrical energy, especially in connection with assembly line work between about 1870 and the beginning of the First World War,
  • The third, so-called digital revolution, with the creation of modern IT in the second half of the 20th century and the developments already described above.

What is the Industrial Internet of Things currently being used for?

Industry 4.0 can bring a variety of benefits to a wide range of industries and sectors, including:

  • Smart production facilities and buildings
  • Supply chain and inventory optimization
  • data analysis
  • condition monitoring

The IoT has already found its way into various sectors, of which pure production is by far not the only sector that can benefit from Industry 4.0. The energy industry and retail can also participate in the revolution thanks to ever-smaller smart devices and intelligent solutions.

Why switching to Industry 4.0 is worthwhile

Despite the boom, not everyone is aware of the concrete benefits Industry 4.0 is supposed to bring. Therefore, we would like to give some examples below of how the manufacturing industry has benefited from the implementation of IIoT so far:

  • Production line optimization: Industrial IoT sensors enable continuous monitoring of the production line from start to finished product. This allows operators to continuously fine-tune the manufacturing process, saving time and money.
  • Inventory and Supply Chain Management: Manufacturing depends on the delivery of raw materials and components. ⦁ Radio Frequency Identification ( RFID) tags and similar wireless technologies enable real-time tracking of components and shipments from site to site, making inventory and reconciliation monitoring much easier.
  • Packaging assessment: Industrial IoT sensors enable manufacturers to monitor the condition of packaging during transport and storage, and even assess how customers typically interact with it. The data submitted is extremely valuable because it allows for design improvements.
  • Real-time manufacturing data: By transmitting operational data, suppliers can remotely manage the factory units at any time, conveniently.
  • Maintenance data: Smart devices and sensors can issue alerts as soon as an error occurs and maintenance work is required. In the same way, malfunctions or the exceeding of limit values, such as excessive operating temperatures or excessive vibrations, can be reported. In this way, maintenance can be planned in advance, downtime can be minimized and the risk of accidents can be significantly reduced. When combined with health and safety records, such sensor data can contribute even more to safety.
  • Quality Control: Combining IIoT data from various sources, including suppliers, manufacturing processes and end-users, provides a more comprehensive picture that can be used to drive overall improvements from production and delivery processes to optimized user experience.

What challenges does Industry 4.0 face?

Industry 4.0 is basically an interaction of several network technologies. The three main challenges can therefore be summarized as follows:

  • The selection of strong signal networks, both wireless and wired
  • Adoption of standardized protocols, e.g. OPC UA
  • Network security vigilance to ward off any cyber threats

The technological requirements such as procurement of the devices are therefore the least of the problems in the transition, but there is a high demand for uninterrupted connectivity. In addition, an understanding of IT security and data storage when implementing IoT in industrial operations is essential to ensure smooth and efficient implementation.

What are the risks of the industrial Internet of Things?

As with any other digital solution, cyber security is critical for the IIoT, but with the appropriate precautions such as staff training and encryption of data transmissions, these risks can be minimized.
With this in mind, it is important to stay current with the latest technologies and updates. So you can be sure that you are always keeping up with the new developments regarding Industry 4.0 and derive the greatest benefits from them.

IIoT networks and protocols

Like any other information technology, the Industrial IoT uses a variety of protocols (data communication formats) and network types. Therefore, it is important to get clarity about each individual protocol when planning to create an IIoT infrastructure for your production facilities.

IIoT networks: how to choose the right hardware!

Internet-enabled devices each use different technologies for networks. Which of these offers the best solution depends on a number of factors, such as the distances to be bridged, the amount of data to be transmitted, the location and power consumption.
New networks are constantly being added to the list of networks suitable for Industry 4.0 and IoT. We have compiled the currently most important ones for you:

WLAN

Both in private households and in the industrial sector, WLAN is the common radio transmission standard for PCs, smartphones, tablets and more. WLAN networks are integrated into networks via routers, similar to wired Ethernet networks. Most devices use the 802.11 standards defined by the IEEE Association (Institute of Electrical and Electronics Engineers), also known as Wi-Fi.

Bluetooth

Bluetooth is a connection standard developed by the Bluetooth Special Interest Group, an interest group of more than 34,000 companies, and is also widely used in the consumer sector. It is based on ultra-high-frequency radio waves (between 2.402 GHz and 2.480 GHz) with a relatively short range. The advantage is the extremely interference-free radio transmission. It is, therefore, suitable for a number of different applications.

Zigbee

Zigbee is one of the leading protocols for connecting smart devices. This is a low-power network that is widely used, especially in industry. It is related to the Dotdot protocol developed by the same team and uses the IEEE 802.15.4 standard, which has a transmission range of up to 300 meters under ideal conditions. In buildings, it still reaches an impressive 75 to 100 meters. The current version 3.0 offers 128-bit encryption for secure data transmission.

LoRaWAN

LoRaWAN is the abbreviation for Lo ngRange Wide Area Network, an extremely energy-efficient MAC protocol with a transmission range of up to ten kilometres. It offers secure two-way connections over very large networks and can also be applied to digital radio transmission using FSK modulation.

Sigfox

The French telecommunications company Sigfox uses extremely low-power technology for a comprehensive network, similar to the Low Power Wide Area Network (LPWAN). In this way, small smart devices in continuous operation, such as electricity meters and smart-watches, can exchange data in a particularly efficient manner. The power consumption is only a thousandth of that of other radio technologies

IIoT data protocols

  • MQTT (Message Queue Telemetry Transport) is an open, low-power message protocol used to transfer simple data sets between sensors and applications. It is based on the common network protocol TCP/IP (Transmission Control Protocol/Internet Protocol).
  • AMQP (Advanced Message Queuing Protocol) is an internationally recognized open-source standard for transferring messages between devices.
  • OPC UA (OPC Unified Architecture) is an open M2M communication protocol that combines cross-platform shared data exchange in industrial automation with robust system interoperability.

Frequently asked Questions

Can the IIoT replace MES?

MES (Manufacturing Execution System) is an established hardware-based control system for complex manufacturing processes, typically used to ensure efficiency and improve productivity. This is a closed system. It, therefore, does not have the cloud-based analysis and external network functions that are important for Industry 4.0. An extension of the traditional MES with such makes sense, but a complete replacement with IIoT infrastructure is hardly worthwhile for economic reasons alone

What is the advantage of the Industrial Internet of Things for engineers?

The IIoT enables the collection and analysis of a large amount of data that can be collected in several phases of the manufacturing process. In this way, the continuous optimization and improvement of systems can be promoted.

How does the IIoT work?

An IIoT network consists of multiple sensors connected via different wireless protocols to exchange data with the cloud and each other. The basic structure of an IIoT network is as follows:

  • Devices and hardware equipped with sensors, each connected to the local network,
  • The local network itself, which in turn is connected to the Internet and cloud services,
  • Cloud-connected servers that process relevant data such as operating temperatures, mechanical faults and power consumption. Such smaller amounts of data condense over time into big data, which can be analyzed to gain deeper insights into your operations.

What is the difference between Industry 4.0 and Lean Manufacturing?

Lean manufacturing is a production organization method aimed at minimizing waste and maximizing productivity. The principles go back to the 18th century and were formulated in the early 1990s as part of an MIT study of the Japanese automotive industry. Industry 4.0 can support lean manufacturing but is not absolutely necessary for it.

How much does it cost to implement an Industry 4.0 solution?

The costs depend on how large and type of manufacturing processes you want to optimize. Therefore, there is no definitive answer to this question.

5 tips on how to quickly make your product IoT-compatible

This is how you make your products fit for the IoT (Internet of Things)! 5 strategy tips that you should consider when engineering to secure your market share in the digital transformation.

we have the most important tips for implementing your product's IoT connectivity
IoT

More and more companies want to better position their products for the digital transformation. This year alone, around 26 billion IoT devices will go online worldwide. On the one hand, making them IoT-capable is not always easy and, on the other hand, it does not always make sense. Many are trying to make their existing products smarter and more connected. This is possible in many cases, but not always the most appropriate way. Because in digital engineering, too often products are created that offer no added value either for the company or for the end-user. For the product development of a successful IoT device, the approach must be customer-centric. Furthermore, suitable digitization skills and, last but not least, the right digitization strategy are essential. Because studies show: Around 25-45 per cent of all new IoT device developments fail. In dynamic digitization, some products are very well received, while others are already doomed to fail when they are launched.
So what separates successful IoT devices from the rest? If we look at companies that are successful in digitization, we get an idea of ​​​​how products can become compatible with the Internet of Things. We can learn from this and transfer experiences of such digitization strategies to product development. Implementing IoT connectivity to digital devices can be difficult. Especially if it’s the first time. So what does it take to make an existing product IoT compatible? And what are the advantages of product development of an innovative digital device for the Internet of Things?

Digitization: check the added value of connectivity!

Before you start developing an IoT product, you should ask yourself the following questions: If the product is smart after engineering, does it add value for you and your customers? And can the product collect useful data? Most products today can already collect data in some way. However, not all of this data is of any value to you or your end-users. For companies, the following must be clarified:

⦁ Can you integrate IoT data into your business processes?
⦁ Will you be able to effectively use the data collected to improve service to your customers? Because: A new IoT device is only successful when it is clear how the data will offer added value after engineering.

Product development: Include the cost of the IoT device!

Smart devices generate costs that a conventional product would not have. It is important to include these costs in the digitization strategy for product development:

  • What are the manufacturing costs? Is it clear how the connectivity costs will be covered? Normally, this happens through a higher sales price, but more and more often through service or subscription fees over the product life.
  • What are the ongoing costs for device support? Does the product generate large amounts of data that need to be stored in the cloud? Does the product require computationally intensive cloud services such as speech recognition?
  • What support does you as a company have to provide the end-user with product defects or upgrades?

Check the marketability of your intelligent device!

From a technology point of view, you can make any product IoT compatible. But is it worth it? While a WiFi-enabled watering can certainly be a nice idea, the demand for product development of such a device would be rather limited.

  • When it is clear what value your smart system will have for you and the end-users and you know the costs, you need to ensure that the product is marketable after engineering.
  • Can the value of product development be communicated to your potential customers quickly and easily? Do you understand this and are you willing to pay for it?
  • In particular, when innovating in a new category, you should answer the following questions: What is the greatest single value that your IoT device offers to the end-user? Can you simply communicate this value in terms of your product digitization strategy?
  • Be careful with new features in your engineering strategy. Each function is associated with development costs and makes the digital product more complex. Many companies add features hoping it will make the product more attractive. But often a simpler product offers more enjoyment and thus has a higher overall value.
  • To know if your product is IoT-ready, you should develop ⦁ prototypes of your digital devices. Do not develop the whole product at once, but proceed step by step in engineering. User experience testing and surveys of existing customers will help you create a more valuable digital product and better understand potential costs. That way, you’ll spot problems where you never expected them. And the digital product that comes out will be better.

Digital engineering: What you should pay attention to when it comes to technology and design

As soon as you are sure that the digitization strategy for your product is understandable to your customers, the device has added value and the costs fit into the business model, you can start planning – taking a few other points into account.
So there are different connectivity options for your digital innovation that you have to consider. Most IoT devices connect to a network via an app via Bluetooth or WiFi. The user then controls the device via the app. However, smart home devices often also use their own protocols (eg Zigbee) and there are also more and more devices that connect to the Internet on a mobile basis (eg NB-IoT or LTE- m). Each technology has advantages and disadvantages depending on where and how the device is used and the costs that the digitization strategy can support. Safety is important here, for example. The sheer number of IoT devices and the inconsistent security practices of device manufacturers have increasingly made the devices targets of cyberattacks.

“Hardware is hard” is a popular saying among hardware engineers. However, it is becoming increasingly easier to develop a new IoT device or to make existing devices IoT-capable. Prototyping has also become easier as companies now have affordable development boards and prototyping kits at their disposal. Standardized hardware components mean that companies don’t have to start from scratch when it comes to engineering and can start testing ideas quickly.

If the ideas prove successful, standardized development boards and 3D printers can be replaced with optimized custom boards and injection moulded parts that can be produced in high volumes. These individual design and engineering phases to create a product that can be mass-produced require many different skills and high investments. Good research beforehand and prototyping to get real user feedback gives you confidence that your system is on the right track and the investment will pay off.

The single largest item of an IoT solution is often the software. For an IoT device, there is embedded software for the device hardware, IT for cloud services (IoT platforms) and app software on the smartphone or computer. All of these and other elements must interact seamlessly with one another, like in a network. This ecosystem requires a lot of coding and testing to ensure the system performs optimally under a variety of conditions.

Great design and a carefully crafted user experience are not the only things that make an attractive product. The task of setting up a new IoT device can seem daunting at times. It is therefore important to make the first user experience after digitization as convincing and simple as possible. The entire digitization process, ie every step from connecting the device and installing the IT to using the product for the first time, must be carefully planned and implemented. Support calls and product returns can erode the profits of a new product. The response rate for consumer devices is estimated at 11-20 per cent. And 95 per cent of returns are not due to defects or defects. The product can work as desired and yet it does not satisfy the user. While industrial products don’t have the same response rates, user expectations are now just as high. And since many IoT products are based on service fees or subscription models, it is important that the products are used for a long time.

After product development: How to properly deal with competitors

You have completed all of the above steps. You know what to do with your hardware and software. You know how to make your product IoT-enabled. But then you discover that someone else has already developed the product you are planning to implement. A horror scenario! What should you do now?

It’s not necessarily a bad idea to develop something that already exists. Because that means: There is already a market for the innovative product. What you need to do is position your device in a way that offers value to your customers. What can your device do that the other cannot? What overall value can you offer your end-users, ie how do you show them that you really have their needs in mind?

If you can show your customers how your product differs from those of your competitors, you can better position and sell your product in the market. Turning your product into an IoT device is not always a good idea. However, if you have a marketable product that adds value and you can integrate the necessary hardware and software, you are well on your way to creating a successful smart digital device.

Artificial intelligence | SMEs need help with technical implementation

Artificial intelligence is still little used in production – especially in medium-sized companies. These challenges still exist in companies.

Artificial intelligence
Artificial intelligence

In industrial companies, the expectations of artificial intelligence (AI) are high, but it is still not used much in production – especially in medium-sized companies. There is ambiguity, for example, in the assessment of the economic benefit, the applicability in one’s own production environment as well as in the collection and use of data. This is the result of an online survey conducted by the AI ​​innovation project IIP-Ecosphere with the support of the project partner VDW.
The Federal Ministry of Economics is funding IIP-Ecosphere as part of the AI ​​innovation competition to accelerate the use of AI in production. The aim of the survey was to determine the current status and practical challenges of companies with regard to the use of AI and related topics such as data collection, cloud use, selection and framework conditions of AI solutions and Industry 4.0 platforms. “With the survey, we wanted to show necessary, real fields of action in which IIP-Ecosphere can now actively act as an accelerator for the utilization of AI methods,” explains Dr. Claudia Niederée from the L3S research center, project leader of IIP-Ecosphere. 75 companies took part in the survey, two thirds of them from the machine tool industry.
The podcast episode with AI expert Markus Ahorner is also about artificial intelligence:

More than half have not yet had time to deal with AI

What is striking is the high participation of larger and very large companies, at 70 percent. The background could be a greater preoccupation with AI topics compared to medium-sized companies. Compared to other surveys, a relatively high proportion of over 37 percent of those surveyed stated that they were already involved in AI-based solutions in their company. In contrast, however, there are more than half of those surveyed who find the topic of AI exciting but have not yet had the time or opportunity to deal with it.
Overall, the answers show high expectations of AI and its benefits for products and services. 60Percent of the respondents express themselves accordingly. Only 7 percent state that AI is overrated. Most of those surveyed agreed that AI should be used to support and not replace people in production.

Assessment of practical use difficult

The number of providers and solutions for the implementation of AI projects in production is growing steadily; the market is becoming increasingly confusing for users. What makes the selection even more difficult: Often several AI solutions have to be integrated into hardware components, such as machine controls. This complexity is reflected in the classification of solutions: the most common obstacle in identifying suitable AI solutions, at 65 percent, was problems in evaluating the economic benefit of an AI solution for their own application context.
At 64 percent, in second place is the question of whether the respective AI solution can be used at all in its own context. “In order to offer companies a faster overview of available AI solutions and their applications, IIP-Ecosphere is developing an AI solution catalogue, which addresses the problems of those surveyed and includes aspects of benefit and applicability,”

Legal uncertainty on the subject of data sharing

The survey results show that over 90 percent of companies already collect production data. However, almost half of those surveyed say that collecting the data needed for AI solutions poses problems for their company. There is therefore a clear need to catch up when it comes to the needs-based collection of AI-relevant data.
A mixed picture emerges when it comes to data sharing: On the one hand, 57 percent of those surveyed think that the Other companies’ data could benefit, but only 16 percent would purchase non-company data. 59 percent still see a need for clarification on the legal issues. “The responses of those surveyed also make it clear how necessary it is to understand the legal regulations in order to be able to clarify the framework conditions for the use of external data,” says Hans-Dieter Schmees, project manager for technology and standardization at the VDW.
Almost half of those surveyed stated that they use cloud solutions to handle internal company data. Interestingly, however, around two thirds of the companies also agree that production data must not leave the company. Just under 10 percent of those surveyed who commented on cloud solutions primarily rely on an on-site solution and would not use a cloud solution.

IIoT platform mainly used by larger companies

Industrial production is increasingly using IIoT platforms that support the coordinated control of machines and the centralized collection of data. Almost a third of the companies surveyed are already using such a software solution, and almost 45 percent have not planned to use it. Almost 7 percent of the companies that use a platform use their own development. According to survey results, however, it is primarily larger companies that are already actively using IIoT platforms. dr However, Holger Eichelberger from the Software Systems Engineering working group at the University of Hildesheim estimates a trend towards the increased use of IIoT platforms, which is also confirmed by the survey: “In the medium term it can be expected that around half of those surveyed Companies from large corporations to SMEs will soon be using such software.”
An obstacle to the use of AI, which was mentioned in particular in the free comments, is the age of the company’s own production machines, with which the necessary data cannot be recorded or can only be recorded with great effort. Concerns are therefore arising, especially among SMEs, that they could miss out on Industry 4.0 and AI. In addition, some companies are afraid that research and business development will lose sight of them or that they have no opportunities to (help) shape relevant developments. “Cooperation in a spirit of partnership across disciplines is therefore essential for future clout and for securing a competitive advantage, at least in the classic, economically strong disciplines,” says Dr. Alexander Broos, head of research and technology at the VDW.
The open ecosystem approach of IIP-Ecosphere with many participation opportunities and offers offers companies the chances and opportunities they need to tackle challenges together and to develop technological alternatives that make AI accessible to as many companies as possible.

Human robot collaboration | where cobots really pay off

Collaborative robots don’t need humans. Because they enable automation where it used to be too narrow or too expensive. What they can do on their own.

Human-robot
Human-robot

The robot manufacturer Kuka developed the first cobot together with the German Aerospace Center for applications in industrial production. That was in 2004 and it was a predecessor of today’s LBR iiwa.
Lightweight robots helped achieve a breakthrough, however, the Danish start-up Universal Robots. That was in 2008 when the Danes launched the UR5.

What is a cobot and why are collaborative robots popular?

A cobot is a robot that can work directly with human colleagues without a protective fence. According to Torsten Woyke, Managing Director of the distributor i-Botics, they have a few advantages over large industrial robots: “They are light, can be transported and can therefore also be used flexibly.”
Furthermore, cobots could feel and, in combination with cameras, also seen. You save space since a safety fence is no longer necessary. The associated infrastructure will also become more compact. The biggest plus, according to Woyke, is their ease of programming.
There are different approaches to make this programming work even faster. At the ‘Technical University of Nuremberg’, for example, there is a project in which future robots will be programmed offline with the help of virtual reality and a motion-capturing studio. As scientist Christian Deuerlein explains, this could simplify programming when welding with the cobot, for example.

The company Drag & bot, on the other hand, offers a software platform for the simple, graphical commissioning and programming of robot systems. “This should also enable economical automation of small batch sizes,” says company founder Martin Naumann. Even non-experts are able to program collaborative robots.
The International Federation of Robotics (IFR) always speaks of cobots when the robots are designed according to ISO 10218-1 for collaborative use. The associated ISO TS 15066 also contains guideline values ​​for the maximum speed and biomechanical limit values for the collision between human and collaborating robot included.
“It should be emphasized that cobots are not commonly used as a replacement for traditional industrial robots in established processes, ” explains Dr. Susanne Bieller from the IFR. Instead, new markets and new applications could be opened up with cobots. They are therefore of enormous importance for the further development of the market.

In which applications do cobots show their strengths?

In recent years, Woyke from i-Botics – who sells products from Universal Robots among other things – has shown that only around two percent of all cobots are installed in collaborative applications. One speaks of a collaborative application when the workspace of humans and robots overlaps 100 per cent, i.e. humans and robots work in a shared workspace. This is the case, for example, when a human is working on a part while the robot is holding it in a certain position.
In Woyke’s experience, most cobots work in coexistence with humans and support the worker, so that the output within the application increases by up to 50 per cent through the use of a cobot. “They are just as suitable for simple as for complex tasks,” reports Woyke.
The robotics expert is certain that the most common cobot application is still loading and unloading machines. Many cobots are also used in assembly. Here they often also help with picking the right parts. “That directly increases the quality,” says Woyke. Because a robot does not reach into the wrong box and thereby hand over the wrong part. That can happen to a human worker.

Automation rate: where do most robots work?

Globally, an average of 74 robots work for every 10,000 employees in the manufacturing industry. This was announced by the International Federation of Robotics (IFR) in the latest statistics. Click through and see how Human robot density is distributed around the world according to the IFR.
At Schaeffler, HRC applications are already in operation in production. This was reported by an employee of the automotive supplier in his presentation at the ‘Innovative use of robots’ conference in industrial practice’ at the Technical University in Nuremberg.
An example is the supply of sensor covers for thermal management systems. A universal robot feeds the lids based on a camera. It is a co-existence because the collaborative robot is secured by a light grid.
Another application without a protective fence is found at Schaeffler for gripping and measuring housings for hydraulic support elements. In this application, the parts come out of the grinding machine and every 100th part has to be picked and measured for quality purposes. The reading is then fed back to the grinder.
Here a UR3 from the new e-Series from Universal Robots works in cooperative operation. To make this possible, Schaeffler carried out the necessary biomechanical measurements and avoided sharp edges in the entire HRC application.
Another area is welding. According to distributor Woyke, there is currently a great deal of demand in the area of ​​’welding with the cobot’. “This is really booming because it works more precisely than manual welding and also does not depend on the welder’s daily form,” explains the i-Botics managing director

What challenges are there when using cobots?

Due to the rules in the ISO TS 15066 technical specification applicable to human-robot collaboration (HRC), cobots are not allowed to move at full speed. This was also confirmed by Uwe Wachter from the automotive supplier ZF at the specialist conference ‘Innovative use of robots in industrial practice’ in Nuremberg.
“The challenge when it comes to human-robot collaboration is and remains speed because proper collaboration always increases the cycle time,” explains the head of the ‘Production Tech Center Robotic and Vision’. Current HRC applications at ZF, therefore, involve little interaction between the worker and the cobot.
The reasons are a lack of intelligence in the cobot systems and security requirements. According to Wachter, humans and robots work synchronously in 95 per cent of all cobot applications in the ZF Group. This means that although they have a shared workspace, there is usually no or very little interaction.
Humans and robots cooperate in five per cent of all cobot applications in the ZF Group. A collaboration – in which humans and robots work on the same product at the same time – does not currently exist in the group in series production. In most cases, cobots are used for pick-and-place tasks and palletizing, Wachter reveals.

How important are cobots in the market for industrial robots?

According to the IFR, the share of cobots in the industrial robot market is currently a good three per cent (as of 2018). “However, we see that this share continues to increase, with above-average growth rates compared to the industrial robot market,” says IFR General Secretary Susanne Bieller. From 2017 to 2018, the proportion had already increased by a good 20 per cent.
Cobots are not taking away any market share from industrial robots. “The areas in which we use classic industrial robots today will continue to be important in the future,” says Bieller. Because that’s where precision, repeatability, speed and payload are important. Bieller therefore expects robots to remain behind protective fences in the future.
Instead, according to the IFR, cobots will spread into new sectors, but also into new areas of application of established sectors that have been using industrial robots for many years. “It is also conceivable, for example, that more cobots will be used in the service area – and thus play a much more prominent role in our daily lives,” explains Bieller

How will the cobot market develop in the next few years?

Basically, the cobot market is developing very positively. “2019, for example, was a very difficult year economically,” explains woyke However, cobot integrators have increased their sales by up to 66 per cent, reports the robot expert. At the same time, the areas of application for cobots are increasing.
The manufacturer Rethink Robotics also wants to serve the service robotics market with its Cobot Sawyer and offers the so-called Cobot Café for this purpose. It is a barista solution for events or public areas where classic cafés would be interesting but cannot be implemented due to lack of space or for economic reasons.
Guests or customers can use an integrated tablet to choose from eight different coffee specialities and place their orders. Sawyer then moves, prepares the fresh coffee speciality in front of the customer and delivers it to the customer. “Possible places of use would be, for example, foyers of banks, museums or hotels, as well as lounges at airports or train stations,” explains Rethink Robotics CEO Daniel Bunse.
However, according to the IFR, there are also challenges. With the acquisition of SMEs and users from very different industries, a potentially very wide customer field has opened up in the cobot area. However, manufacturers and integrators would first have to develop certain process know-how.
In the early days of cobots, in particular, the impression often arose that cobots could do without any system integration at all, Bieller recalls. However, this is only the case for very simple applications. The risk assessment for more complex applications in particular requires a certain amount of experience.
It is also a misconception that cobots are the general answer to all questions. “Especially when high speeds, precision or high payloads are required, traditional industrial robots in combination with a sensor skin or similar cameras make more sense,” is Bieller’s conclusion.

These cobots are new to the market

Numerous manufacturers now offer collaborative robots. In addition to established companies such as Universal Robots, Kuka, ABB, Fanuc and Yaskawa, there are new companies such as Franka Emika, Doosan Robotics, Techman Robot and Yuanda Robotics. Cobot providers such as Elephant Robotics or Siasun are also emerging in China.
The collaborative lightweight robot CRX-10iA from Fanuc has been on the market since December 2019. It is lighter than all previous cobots from the Japanese manufacturer and can therefore also be used as a mobile robot on a driverless transport system. Its load capacity is 10 kilograms. The cobot’s user interface is designed in such a way that it is also suitable for users with little programming experience.
Yaskawa also launched a new cobot in December 2019 with the HC20. It offers a payload of 20 kilograms and is currently the strongest lightweight robot in the world. Yaskawa intended it as a so-called hybrid robot. Safe switching between industrial speed and collaborative speed – when supplemented with external safety technology – ensures optimal performance.
Torque sensors in each joint stop the robot safely in the event of a collision. According to the manufacturer, the so-called retract function ensures that in the event of a jamming situation, the robot moves back within its taught path so that the human colleague can free himself. The robot can also be gently pushed away during its movement if, for example, it should stand in the way of the employee during his or her work.

Rethink Robotics GmbH presented the new Sawyer Black Edition for the first time in October 2019.” After taking over the assets of the then insolvent Rethink Robotics Inc. just a year earlier, we modified the drives, for example,” reports CEO Daniel Bunse.
Individual mechanical components were also replaced and higher-quality materials were used. The result is that the Black Edition is more reliable and stable compared to the previous model. “In concrete terms, these improvements are reflected in a significantly lower failure rate and smoother running, which makes Sawyer’s movements more even and harmonious, and minimizes noise emissions,” says Bunse happily. This contributes to a quieter working environment.

Which IoT application scenarios are possible for 5G campus networks

Deutsche Telekom’s 5G campus network could in the future place many scenarios relating to Industry 4.0, the Industrial Internet of Things (IIoT) and digitization on a consistent communication platform. The new mobile communications standard also enables wireless technology in security-critical environments.

IoT
IoT

Industry 4.0 and digitization are also seen by more and more companies as an opportunity to bring production back to Europe. With new technologies, favourable personnel costs can be offset at other locations.
But the way in which production is carried out is also changing: “The trend towards smaller batch sizes and flexible product that can be quickly adapted to other orders increases the need for a wireless and secure network in the production facilities,” notes Christian Schilling, Senior Consultant at the management consultancy Detecon International GmbH, a wholly-owned T-Systems subsidiary.

Industry 4.0 requires low latency times

The public mobile network or private WiFi networks are often not sufficient for the requirements in the production environment – latency times and WiFi working on public, non-reserved frequencies often cause problems with data transmission. With the new 5G mobile communications standard, which allows important data to be prioritized, the requirements in the production area, in particular, can be better addressed.
With the 5G campus network, Telekom is presenting an alternative that can be used to integrate intelligent production in a radio network and with a standard (4G or 5G). With 5G campus networks, companies receive private mobile phone coverage with guaranteed, high transmission quality directly at their location. At the same time, public mobile phone coverage will also be improved locally. Campus networks are generally open to all technologies and can already serve as a springboard to 5G in the near future in the context of LTE (in combination with edge computing).

5G added value lies in the combination of different use cases

With the health check from T-Systems, companies can check what a 5G campus network can do for them in concrete terms. “Connectivity is an enabler. We work with the customer to develop concrete use cases that make production more efficient or simpler. We show how an investment pays off,” says Schilling.
This is usually not just based on one scenario, says the consultant: added value usually comes from the interaction of different use cases. A transformation strategy and roadmap will be developed for this purpose. “The Telekom campus network does not come off the peg, it will look different for each company,”

The classic areas of application for 5G include:

smart production

In many cases, 5G makes cabling in production redundant. Even security-critical applications with the lowest latency times can be covered by the standard designed for this purpose. This means that changeovers between orders can be faster and more flexible. Another problem is also solved: integrating the increasing machine-to-machine communication and sensors often poses challenges for existing radio technologies. The data is often collected in advance via a gateway. In the 5G campus network, information can be provided in real-time in conjunction with edge computing. In this way, computer performance can be shifted away from the devices to the edge cloud. If a campus edge cloud is operated, sensitive data does not have to leave the campus: an important security aspect in production.

Augmented and Virtual Reality (AR/VR)

With 5G, large volumes of data can be transmitted securely, even in real-time-critical applications. A prime example of the data hunger and latency requirements of new technologies are augmented and virtual reality. They are becoming increasingly relevant for Industry 4.0, for example in the area of 2. connected workers. Employees are guided through processes using data glasses, and individual steps can be compared by the system for quality management. At the same time, the technology helps to carry out repairs on-site, with an expert providing support via data glasses and video, who may be working remotely with the machine manufacturer.

Remote monitoring and remote control

Another typical Industry 4.0 scenario is the complete networking of production, in which a 3. digital image (digital twin)  is created. Through planning and simulations based on the data that is continuously collected from machines and assets, production can be controlled, optimized and promptly adapted to changes. A 5G campus network can form the connectivity basis for secure data exchange based on uniform standards.

Safety Monitoring

In the area of ​​security and safety, systems with mobile cameras, among other things, ensure continuous monitoring of the production site. This involves the transmission of large amounts of data. In the future, AI technologies related to image recognition can help to automate security tasks. With the help of AI and machine learning, even the smallest deviations and irregularities can be detected. In the future, open spaces outside the factory building can also be monitored with drones.

Smart (inter)logistics

Autonomous transport systems and intelligently reacting vehicles that know the layout of locations and, in the event of a problem, choose alternative routes to continue supplying production with material, are increasingly being used. One challenge here is fleet management, with the control of different systems. Here, too, 5G can score with the extremely low latency times

How artificial intelligence optimizes laser processing

Artificial intelligence is currently a hot topic in all sectors – including laser technology. How to choose an AI solution for better processes.

laser processing
laser processing

How can data and algorithms be used to increase the quality and efficiency of processes in laser processing? Researchers, laser technology manufacturers and users are asking themselves this question at the same time, because with the emerging Industry 4.0, with solutions artificial intelligence (AI) are also becoming increasingly important. The first solutions in the field of laser technology that uses artificial intelligence already exist.

How is artificial intelligence used in laser material processing?

For example, machine builder Trumpf uses artificial intelligence to control laser systems using voice commands. With the system equipped with a marking laser, the system operator can issue all relevant control commands such as ‘Open/close the door’, ‘Start the marking process’ or ‘How many products have you marked today?’ speak directly into a microphone. The laser system responds accordingly and executes the voice command. You can find out more about the machine in our article ‘Trumpf: AI moves into laser material processing ‘.
However, significantly more researchers and manufacturers are dealing with AI systems in the field of quality assurance – some AI applications are already being developed, especially for laser welding. Most of the time it is about the quality control of the welds. The Fraunhofer Institute for Laser Technology (ILT) is also researching in this area.
“We want to use our AI solution to recognize different quality categories in laser welding,” reports Christian Knaak. The scientific employee of the Fraunhofer ILT deals with Zero Defect Manufacturing and in this context with Deep Learning and spoke about it at the first ‘AI for Laser Technology Conference ‘ in Aachen.
“We want to detect seam collapse, binding errors and incorrect seam widths,” Knaak continues. “And we also want to recognize when the seam is in order.” For this purpose, the measurement data from welding processes – in this example the camera images of the weld seams – are evaluated and the system is then supposed to make statements about the quality of the seams. There are two possible approaches: the classic machine learning approach and deep learning.

What do I need for a successful AI project?

“AI needs a sustainable database. And a team that implements the project together and in which the individual members have the necessary specialist knowledge from the departments involved.”
Christian Kohlschein, Hotsprings GmbH
 
“Machine learning sometimes needs bad process results. If too many results are good, then the algorithm says that everything is good. But then the AI ​​​​solution is useless.”
Stephan Schwarz, Mercedes Benz AG
 
“The biggest challenge when introducing AI solutions is the cultural transformation of the company. Faster technology and better algorithms alone cannot make a difference.”
Benjamin Kreck, Microsoft
 
“When selecting suitable algorithms for quality analysis, the domain knowledge of the employees is required. This is the only way to find suitable classifiers and algorithms.”
Christian Knaak, Fraunhofer Institute for Laser Technology

What is the difference between classic machine learning and deep learning?

In machine learning, knowledge about the area of ​​​​application (so-called domain knowledge) plays an important role. Image processing algorithms are used to extract and classify features from the camera images. “We have five classes,” explains Knaak. “These are typical images of welding tests with examples of lack of fusion, seam collapse, increased night width, OK seams and no seam.”
The features of these images are then used as a ‘fingerprint’ for the various seam conditions to be recognized by an algorithm. The appropriate algorithm is selected by determining the recognition rates of various algorithms using a training data set. The algorithm with the best detection rate can then be used for the process data.
Deep learning requires less domain knowledge but requires significantly more data. “The special thing about this method is that the task of extracting features, which was taken over by image processing algorithms in classic machine learning, is now handed over to a neural network,” explains Knaak.
This neural network recognizes the features and processes the data in several layers. This makes it possible to analyze very complex image features. “The end result is the same as with the classic approach, where you need a relatively large amount of domain knowledge,” reports Knaak. Both methods are therefore suitable for analyzing the seam quality, only the prerequisites differ.

Industry 4.0 | Economy in Digital Upheaval

After ten years of Industry 4.0, many German companies have achieved more in terms of networking and digitization than they think. Where is the journey going now?

Industry 4.0
Industry 4.0

Angela Merkel was immediately enthusiastic. Shortly before the Hanover Fair 2011, the President of the German Academy of Science and Engineering (acatech), Henning Kagermann, the Director of the German Research Center for Artificial Intelligence, Professor Wolfgang Wahlster, and the current State Secretary in the Federal Ministry of Education, Professor Wolf-Dieter Lukas, described the networking of machines via the Internet of Things (IoT) and the digitization of the processes running on them for the first time as Industry 4.0. The Chancellor found the concept so conclusive that she spontaneously used it in her opening speech at the industry show as proof of the performance of German technology providers.

Ten years later, in April 2021, a full 94 per cent of the companies surveyed by the digital association Bitkom on Industry 4.0 stated that they could only remain competitive by networking their processes. However, 65 per cent of the survey participants fear that they have missed the boat when it comes to digitizing their production or are laggards. “Medium-sized companies in particular answer the question of the status of Industry 4.0 in their companies with relentless honesty,” explains Dominik Rüchardt, Head of Business and Market Development in Central Europe at the provider of technologies for Industry 4.0, PTC. “They complain that they don’t have the IT know-how for the change and don’t know how to network and monitor their existing systems and machines.”
It’s different in larger industrial companies: Two out of three of the companies surveyed by Bitkom now use intelligent robots or systems for real-time communication between their machines. Four out of ten large companies also network their systems with IoT platforms on which they evaluate the data transmitted by the machines.

Today all future technologies of the year 2011 are in use

In addition, basically, all technologies have found their way into their production and development, their sales and purchasing, from cloud computing and augmented reality (AR) to digital twins, artificial intelligence (AI) and software solutions for product lifecycle management (PLM). held, with which acatech President Kagermann and his colleagues wanted to connect products and their manufacture in 2011 to so-called “cyber-physical systems”.
“The individual technologies interact with the physical product such as the nervous system, brain, memory and thinking abilities with the human body,” . The digital twin serves as a kind of brain. Because it reflects all the properties and behaviour of the product. “The IoT serves as a nervous system that connects it to the physical product, registers how it behaves and transmits signals between the analogue and the virtual world,” adds Rüchardt. With these impulses, the behaviour of the product can also be influenced.

AI is the mind of Industry 4.0

At the same time, AI and machine learning could correlate the received signals and recognize when changes in the behaviour of the product are necessary – for example, to achieve better manufacturing quality by adjusting the parameters of the process running on a machine. “So AI is, so to speak, the thinking ability of the cyber-physical system. As such, she recognizes at an early stage when repairs or the replacement of wearing parts will be necessary and thus helps to increase the availability of machines through predictive maintenance.
The PLM, in turn, remembers the findings of the AI. Similar to the human memory, it not only knows how the product should work but also how it has behaved and changed over time. The information it provides helps development engineers to optimize future product versions.
“Finally, augmented reality makes all this data usable and helps people to optimally influence devices and systems – for example, by providing a maintenance worker with the data needed to repair a machine on his tablet or showing him where with the help of AR glasses he has to lend a hand,” adds. This means that maintenance work can also be carried out by less experienced technicians. Machines fail for a shorter period of time if an employee from their manufacturer does not have to travel to repair them first.

The digital transformation of industry needs a reliable set of rules

“Anyone who wants to assess what German companies have achieved in the first ten years of Industry 4.0 must not only think technologically,” warns Rüchardt. In order for the smart networking of production, development and procurement processes to succeed, numerous participants must be integrated into a digital ecosystem – from the manufacturing company to its suppliers and clients to logistics service providers. “Industry 4.0 is therefore also a far-reaching structural change that changes the relationships between manufacturers, suppliers and customers and pushes new providers into established markets.
In order for this to be legally secure, a set of rules consisting of laws, contract models, reliable payment systems and active business relationships is needed that everyone involved can rely on. Only such a reliable framework for business relationships in Industry 4.0 allows new business models to be developed. According to the Bitkom survey, three out of four industrial companies are striving for this.

“Machine as a Service” – the supreme discipline of Industry 4.0

Above all, “as a service” business models are a profound disruption for providers. “A mechanical engineering company, for example, then no longer collects the price for its product when it is sold, but spread over many years. This puts a lot of stress on his balance sheet. In order to be able to survive economically, the manufacturer would need new partners, such as financial holdings or leasing companies, who buy their machines and rent them out as operators according to an “as a service” model.
To do this, they must be able to guarantee customers that the devices will perform as promised in the rental or leasing contract. This presupposes that operators continuously monitor the machines and know at all times what condition they are in, what quality they are producing and how their economic operation is. The machine builder’s new partners must also be able to maintain their devices and, in the event of a fault, repair them reliably and, if possible, without a time-consuming journey by a service technician.
The manufacturer of a machine can sell all these services in addition to the machine. Because their rental company must be able to access the technical expertise of the machine builder as well as the complete technology stack of Industry 4.0. Otherwise, his business model will fail. In order for the interaction between the manufacturer of the machine, its operator and its customers to work, all those involved also need a legal framework in which liability issues and the respective rights and obligations in their business relationships are reliably regulated. “Machine as a Service is thus becoming the supreme discipline of Industry 4.0,” summarizes Dominik Rüchardt.

Industry 4.0 in brownfield environments – individual solutions lead to chaos

Companies encounter similar problems when they want to network and monitor older machines and systems in order to increase their availability and performance. In order to be able to develop its potential, Industry 4.0 also needs a framework in such brownfield environments – in this case, however, a technological one.
“Older machines and systems were mostly developed in a downstream process and trimmed for operational excellence. This makes it very easy to monitor and optimize each machine individually. However, the approach is not sufficient to use the existing systems to react quickly and flexibly to changes in demand for the products manufactured with them.
To do this, the machines must be networked via an IT architecture that can extract meaningful information from the data supplied by the devices even if the data follows the logic of the operating systems from different manufacturers and is available in different formats.
“This requires clearly structured and comprehensible IT architecture concepts that can deal with the heterogeneity of brownfield environments. Otherwise, there will be a lot of individual solutions and thus chaos,”. Networking of manufacturers, their suppliers and customers are then hardly possible.

The digital platform economy is not far away

“However, the first corresponding sets of rules are now available – for example, the reference architecture model Industry 4.0, RAMI,” assures Rüchardt. At the same time, the first consortia would implement these frameworks in practical cooperation between companies from sectors such as mechanical engineering, the process industry or automotive production.
“If things continue to develop like this, in three to four years the economic interaction between companies and their partners will mainly take place on digital platforms.

Artificial intelligence – clearly explained

Whether in industry or in the private sphere – artificial intelligence is on everyone’s lips. But what does artificial intelligence mean? In this article, we answer the most important questions on this topic

Artificial intelligence

Artificial intelligence is one of the really big future topics of our society

  • What is artificial intelligence?
  • How intelligent is artificial intelligence really?
  • How does artificial intelligence work?
  • How do you program artificial intelligence?
  • What do we need artificial intelligence for?
  • Where is artificial intelligence used?
  • Smart machines: How is artificial intelligence changing our lives?
  • How is artificial intelligence changing our society?

What is artificial intelligence?

When developing systems with artificial intelligence (abbreviated: KI, English: Artificial Intelligence), researchers and developers try to emulate human perception and human action using machines. An official definition of the term Artificial However, there is no such thing as intelligence, which is partly due to the abstract nature of the term intelligence and the rapid change in the subject area. Therefore, AI is mainly defined by its properties and the associated sub-areas, such as speech recognition, image processing or machine learning.
Properties that are characteristic of AI are autonomy and adaptivity. AI systems have the ability to perform tasks in complex environments without constant human guidance. They are also able to improve their performance independently by learning from their experiences.
In general, the systems are divided into weak and strong AI:

⦁ Weak AI refers to machines that can replace a single human cognitive ability. Systems with weak AI perform a specific task and behave intelligently.
⦁ A strong AI would be a machine that has the same abilities as a human or even surpasses human abilities. The system with strong AI could thus fulfil any intellectual task. It would be intelligent (compared to the weak AI that just behaves intelligently) and would be conscious.

The AI ​​​​solutions that exist to date all fall into the ‘weak AI’ category. Strong AI systems only exist in the field of science fiction.
The term artificial intelligence includes many sub-areas, which in turn include numerous AI methods and AI applications, for example:

⦁ knowledge acquisition and representation
robotics
⦁ Pattern recognition (images, text, speech)
⦁ Prediction (Big Data / Predictive Analytics)
Machine learning (deep learning/neural networks)

Machine learning or the special form of deep learning, in particular, are often regarded as the most important method of artificial intelligence, because learning from experience and the ability to generate new actions from it is evidence of intelligence.

How intelligent is artificial intelligence really?

The answer to this question is closely related to the definition of the word ‘intelligent’. Because the question is whether intelligence is the same as intelligent behaviour or whether intelligence requires a brain and a consciousness.
Provided that intelligence equals intelligent behaviour, the English mathematician and logician Alan Turing developed a test to determine whether a machine is intelligent. In the so-called Turing test, a human investigator interacts with two chat partners – one of them is human, one is a computer. If the investigator is not able to distinguish artificially from human intelligence by exchanging written messages, the computer has passed the test and must therefore have reached the level of human intelligence.
But even if a machine behaves intelligently and thus passes the Turing test, it still does not have a human brain. If this is assumed for real intelligence, then only strong AI systems would be really intelligent.
For the areas in which AI is currently being used, the question of ‘real intelligence’ is not that important. What is far more important is how well a system can perform the task for which it is designed. In this context, the following often applies: artificial intelligence is only as smart as the data with which it is trained

How does artificial intelligence work?

The topic of artificial intelligence includes many AI methods and AI applications, each of which has different functionalities. In general, the intelligent behaviour of the technologies is simulated using computer science and mathematics/statistics. The computers are trained for specific tasks, often by processing large amounts of data and recognizing patterns in it.
This requires certain skills that can be divided into four areas: perception, understanding, action and learning.

  1. Perceive: This skill creates the data that an AI-powered system operates on. 1. Sensors of all kinds, including cameras and microphones, are used for this purpose.
  2. Understanding: This part of the AI ​​​​is the processing component from which the control panel emanates. The data obtained is processed using statistical analysis, speech/image recognition, algorithms that define special rules, or machine learning.
  3. Action: This is the output component of the AI ​​​​that issues commands to connected devices, triggers follow-up processes, or outputs other things such as images, translations, and the like.
  4. Learning: This area is special about current AI technologies. You can learn from mistakes and feedback from the areas of ‘understanding’ and ‘acting’ during the training phase and also during operation.

Algorithms and neural networks play an important role in both ‘understanding’ and ‘learning’.

What are algorithms?

Algorithms are detailed and systematic instructions that define step by step how a mathematical problem can be solved. Algorithms are implemented, ie translated into a programming language, so that the computer/machine can generate the desired solution from the given information.
There are, for example, sorting or search algorithms (these include Google’s algorithms), but also algorithms that can make complex decisions based on all relevant factors. To do this, an algorithm takes all the factors (which have to be defined beforehand by a human) and links them in all possible variants. He then goes through every possible combination and its consequences and compares them with the programmed specifications. From this, the algorithm calculates the answer that is most likely to be correct.
The class of learning algorithms, which are summarized under the generic term machine learning, is particularly important for AI. You can learn from a large number of example cases and derive general rules. After the learning phase, you can apply these insights to real cases. Among the machine learning algorithms, there are also deep learning algorithms that are used to analyze and process particularly large amounts of data – in connection with neural networks.

How do neural networks work?

Artificial neural networks (ANN) are the attempt to artificially reproduce aspects of the human brain known from research. It is mainly about simulating and using the interaction of nerve cells (neurons) and their connections (synapses).
The goals of artificial neural networks are, on the one hand, a better understanding of the human brain and the processes taking place there and, on the other hand, advances in machine learning by linking huge amounts of data (big data) and deep learning techniques.
A single neuron is a simple information processor that can examine exactly one aspect of information. To process very complex information, many neurons are therefore connected to each other. These connections are called synapses, they form a complex network between the neurons. A neural network (regardless of whether it is biological or artificial) consists of a large number of neurons that can receive signals and transmit them to other neurons via connections.
There are three types of neuron layers in an ANN:

  1. Input Layer: The first layer of neurons for raw processing of the information. These neurons feed pre-processed information into the network.
  2. Hidden Layer(s): One to a finite number of neuron layers with linked neurons. During the training, you will learn how to read patterns from the raw information using examples. From these, complex typical characteristics are worked out in order to solve the task.
  3. Output Layer: The last neuron layer – the so-called output layer. It can represent any possible outcome.

The big advantage of artificial neural networks compared to ‘classical’ data processing is that they can consider several aspects at the same time. While a ‘simple’ algorithm analyzes each property of a data set one after the other, in the layers of the ANN all properties can be analyzed simultaneously.
ANN is used, for example, for image processing, speech recognition, early warning systems or process optimization. It is precisely this process optimization or error detection (via image processing or audio analysis) that is already being used in companies as part of Industry 4.0.

How do you program artificial intelligence?

How a system is programmed with artificial intelligence, depends a lot on what you want the system to do. As with the programming of any computer program, the first priority is choosing the right programming language. The most commonly used programming languages ​​​​for AI are:

  • Python has become the de facto standard for machine learning and big data analysis. It is very versatile and suitable for numerous fields of application, especially in the area of ​​​​artificial intelligence and the Internet of Things.
  • Prolog is considered the most important logical programming language and is therefore particularly suitable for simulators, generators, as well as systems for diagnosis and prognosis – exactly what should often be created in AI projects. For example, the language processing components of IBM’s AI ‘Watson’ are written in Prolog. In addition to Prolog, Watson and the associated DeepQA software engine are also based on Java and C++, among other things.
  • find out why IBM is opening its Watson IoT headquarters in Munich.
  • As an object-oriented programming language, Java is very versatile and can therefore also be used well for AI programming. Java is particularly suitable for natural language processing, search algorithms and neural networks. Java is slower than C++ but easier to program.
  • C++ is particularly relevant for time-critical AI projects, as it is the fastest computer language. It is also particularly extensive and strong in statistics. This makes it ideal for machine learning and neural networks.
  • LISP is particularly strong in inductive logic and machine learning, making it well-suited for AI as well.
  • R is mainly used in the context of big data for data analysis. The programming language is mainly suitable for statistical methods and allows the free calculation of statistics and graphics.

In addition to an AI-friendly programming language, program libraries and frameworks such as TensorFlow, Torch, Keras or Caffe are required for AI implementation. The most important subprograms, routines and algorithms for AI development are already implemented here, which can then be transferred to your own AI solution.

What do we need artificial intelligence for?

Algorithmic decision-making systems are intended to support or replace people in making decisions. In the area of big data, in particular, this is necessary in order to make decisions possible at all, because here people would not be able to make any well-founded decisions based on a large amount of data alone.
Processes can be accelerated with AI support, especially with the increasing computing capacity of computers. This makes it possible to carry out tasks that humans or machines without AI could not previously handle due to time constraints.
In addition, AI-based systems, especially machine learning, make it possible to predict what will happen in the future.
In general, artificial intelligence is one of many tools to solve problems. AI makes it possible to do things that were previously not possible. It allows overcoming long-standing borders. Therefore, AI systems make a strong contribution to competitiveness.

Where is artificial intelligence used?

The areas of application for artificial Intelligence are extremely diverse. They range from spam filters and product recommendations in e-commerce or streaming services to language assistants such as Alexa or Siri and chess computers to self-driving cars. With the digitization of industry, ie Industry 4.0, many companies are also adopting AI-based systems (although not all Industry 4.0 applications contain AI in the same way).
According to the Federal Association of the Digital Economy, AI solutions are generally found in the area of ​​​​data collection and analysis in the industrial environment. Examples for this are

  • optical inspections through AI applications in the field of quality assurance, which make error or process analyzes possible,
  • Process automation in manufacturing and assembly, which includes self-regulating adjustment of control parameters,
  • Robots with artificial intelligence, which can perform even better⦁ ‘bin picking’,
  • forward-looking data analysis in order to maintain machines and systems as required ( ⦁ predictive maintenance),
  • voice control of machines,
  • Chatbots for ⦁ virtual customer service other
  • ERP systems with AI strategies that optimize internal production structures and processes.

Smart machines: How is artificial intelligence changing our lives?

Spam filters, personalized advertising on the Internet, more relevant search results in online searches, chatbots for customer service inquiries and navigation devices that include traffic jams and construction sites in the route calculation – these are all systems that work with artificial intelligence and are changing our daily lives.
In many cases, it ensures greater efficiency: while in the past you could spend hours waiting in the manufacturer’s queue because of every small question or problem with a product, today chatbots can provide quick and uncomplicated help in some cases. Cars park automatically, stays in lane and keep their distance, and recognize street signs.
Our smartphones help us write messages, correct our spelling mistakes and even predict which words we will use. And you recognize our face and then unlock it automatically.

How does Face ID / facial recognition work?

What is certain is that artificial intelligence is and will be finding its way into many areas of life. Until autonomous driving spreads it will take a while, but smart home applications (eg for saving energy) and digital voice assistants are becoming more and more popular. While only 390 million people used AI-supported assistants in 2015, in 2019 there were almost 1.38 billion. According to a forecast by Tractica, the numbers will continue to rise; By 2021, voice assistants are expected to have 1.83 billion users.
Not only are the users of language assistants such as Apple’s Siri, Amazon’s Alexa or Google Assistant increasing, more and more people are also using AI systems in general: 73 per cent of those surveyed in a Bitkom study stated that they had already used a simple application based on builds AI.
And that’s no coincidence: The majority of Germans consider artificial intelligence to be useful – 88 per cent of the Germans questioned in a PwC survey stated that artificial intelligence will help to master the challenges of the future. They consider AI to be particularly helpful in the areas of cyber security (49 per cent), clean energy/climate change (45 per cent) and protection against diseases (43 per cent).
So if AI researchers manage to develop systems that can master these very challenges, they will be a thing of the past. The technologies can help reduce traffic congestion, speed up administrative tasks, and improve medical diagnosis and treatment.

How is artificial intelligence changing our society?

Artificial intelligence has an impact on almost all areas of our society. It changes how we communicate, meet new people, consume news and do our work – in positive and negative ways.
For example, many people consume News less via platforms aimed at the general public such as television, but in social networks, where they receive personalized content with AI. From 2013 to 2019, the use of social media as a news source in Germany has increased from 18 per cent to 34 per cent; This is according to the Digital News Report 2019 of the Reuters Institute for the Study of Journalism.
According to a Kantar study, the main reasons for this are easy access to a wide range of news sources and the ability to comment on news and share it with others. While on the one hand-personalized messages are very pleasant, they also encourage the emergence of so-called ‘filter bubbles’ and the separation of different social classes. This can lead to societal problems.
Autonomous means of transport and intelligent traffic control will not only support climate protection in the future but will also create more free time for people, which in turn can be used for work or hobbies. At the same time, people’s areas of responsibility are shifting to areas in which creativity and empathy are required.

How do self-driving cars work?

Likewise, artificial intelligence will transform policing and the justice system. Face recognition will become just as common as fingerprints. And analysis algorithms will also become more relevant: Courts in the USA, for example, already use software that calculates the risk of reoffending by criminals. The calculations are based on information about the person and their radius, but also on the Analysis of all similar crimes committed.
The emergence of many new technologies is changing our society not only directly, but also indirectly. For example, according to the KI-Bundesverband, the compulsory subject ‘digital education’ or ‘computer science’ urgently needs to be introduced in German schools. Because it is irresponsible to release young people into the increasingly digitized world without active support.

50% OFF ON ALL COURSES IN RAMZAN
This is default text for notification bar

of escort çukurova escort kozan escort seyhan escort yüreğir escort adana mutlu son masaj besni escort kahta escort gölbaşı escort adıyaman mutlu son masaj bolvadin escort dinar escort sandıklı escort emirdağ escort afyon mutlu son masaj diyadin escort doğubayazıt escort patnos escort ağrı mutlu son masaj ortaköy escort aksaray mutlu son masaj merzifon escort suluova escort taşova escort amasya mutlu son masaj çankaya escort keçiören escort yenimahalle escort mamak escort etimesgut escort sincan escort altındağ escort pursaklar escort gölbaşı escort polatlı escort çubuk escort kahramankazan escort beypazari escort ankara mutlu son masaj alanya escort manavgat escort serik escort antalya mutlu son masaj şehitkamil escort nizip escort ıslahiye escort antep mutlu son masaj ardahan mutlu son masaj artvin mutlu son masaj hopa escort borçka escort aydın mutlu son masaj efeler escort nazilli escort kuşadası escort söke escort didim escort incirliova escort çine escort germencik escort balıkesir mutlu son masaj karesi escort altıeylül escort edremit escort bandırma escort gönen escort ayvalık escort burhaniye escort bigadiç escort susurluk escort bartın mutlu son masaj batman mutlu son masaj kozluk escort sason escort beşiri escort bayburt mutlu son masaj bilecik mutlu son masaj bozuyuk escort bingöl mutlu son masaj solhan escort genç escort karlıova escort bitlis mutlu son masaj tatvan escort güroaymak escort ahlat escort bolu mutlu son masaj gerede escort burdur mutlu son masaj bucak escort bursa mutlu son masaj osmangazi escort yıldırım escort nilüfer escort inegöl escort gemlik escort mudanya escort mustafakemalpaşa escort gürsu escort karacabey escort orhangazi escort kestel escort iznik escort çanakkale mutlu son masaj biga escort can escort gelibolu escort ayvacık escort çankırı mutlu son masaj çerkes escort çorum mutlu son masaj sungurlu escort osmancık escort alaca escort iskilip escort denizli mutlu son masaj pamukkale escort merkezefendi escort çivril escort acıpayam escort tavas escort diyarbakır mutlu son masaj kayapınar escort bağlar escort yenişehir escort ergani escort bismil escort sur escort silvan escort çermik escort dicle escort düzce mutlu son masaj akçakoca escort kaynaşlı escort edirne mutlu son masaj keşan escort uzunköprü escort ipsala escort elazığ mutlu son masaj kovancılar escort karakoçan escort erzincan mutlu son masaj erzurum mutlu son masaj yakutiye escort palandöken escort aziziye escort horasan escort oltu escort pasinler escort odunpazarı escort tepebaşı escort eskişehir mutlu son masaj bulancak escort espiye escort tirebolu escort görele escort giresun mutlu son masaj gümüşhane mutlu son masaj kelkit escort hakkari mutlu son masaj yüksekova escort şemdinli escort hatay mutlu son masaj antakya escort iskenderun escort defne escort dörtyol escort samandağ escort kırıkhan escort reyhanlı escort arsuz escort altınözü escort hassa escort payas escort erzin escort yayladağı escort ığdır mutlu son masaj yalvaç escort eğirdir escort sarkıkaraağaç escort ısparta mutlu son masaj istanbul mutlu son masaj izmir mutlu son masaj buca escort karabağlar escort bornova escort karşıyaka escort konak escort bayraklı escort çiğli escort torbalı escort menemen escort gaziemir escort ödemiş escort kemalpaşa escort bergama escort menderes escort aliağa escort tire escort