The Industrial Internet of Things will profoundly change automated production processes. How do machine vision technologies help to cope with these challenges? By Dr Maximilian Lückenhaus, director, marketing and sales, MVTec Software
The Industrial Internet of Things (IIoT, aka Industry 4.0) stands for the digital networking of humans, objects, and systems to create integrated production processes.
In this context, industrial companies have to cope with several new trends that will fundamentally change production and logistics processes. The IIoT means that all technologies, systems, and components that are involved in the industrial value creation process are connected to each other as well as to company networks and the Internet.
Another important trend in this connection is the smart factory. It refers to a manufacturing environment in which machines, installations, and logistics systems interact independently, without human influence. Here, all systems involved communicate through an integrated network connected to the IIoT.
Robotics plays a very important role in the smart factory and IIoT environments. The 2015 World Robot Statistics from the International Federation of Robotics illustrates this fact. The survey expects that around 1.3 million industrial robots will be in use worldwide by 2018. The current global market value of robot systems is US$32 billion across all industries.
Robotics is very strong in the automotive industry. In this sector, investments increased by 43 percent from 2013 to 2014. Robots are particularly well represented in the manufacturing industry. An average of 66 robotic units come to 10,000 workers worldwide. South Korea is the world leader in automating processes using industrial robots, followed by Japan and Germany. The USA takes seventh place, and China ranks 28th.
Cobots Work Closely
There is a current trend within the robotics segment: A new generation of smaller, lighter, and more compact industrial robots are finding their way into the automation and manufacturing industry.
These collaborative robots, called cobots, work very closely with human staff. They often possess one or two arms and sometimes even a head. Besides, they are much cheaper than large stationary five-axis robots. Owing to their light weight, they can also be used as mobile units. The robots can take over further tasks such as supporting their human colleagues or even replacing them when they get sick.
There is a technology which plays a key role in accompanying the new production trends and supporting the further development of automated processes: Machine vision, which has grown by leaps and bounds in the past few years.
The technology uses image acquisition devices, such as high-resolution cameras and sensors. These devices record the production processes from different perspectives and generate digital image data. Special machine vision software is used to process this data. The technology makes it possible to monitor all manufacturing processes and to identify weak spots and optimisation potential.
Another benefit: The technology is very fast. Algorithms process the digital image data in milliseconds, thus paving the way for real-time applications. Besides, machine vision facilitates very robust identification processes and a high detection rate.
Creating Machine Vision Applications
Machine vision technology makes the interaction between humans and the new generation of robots much more efficient. Most of the new industrial robots are already equipped with one or more cameras and integrated machine vision functions. The robots should be prepared rapidly and flexible for different application scenarios—without long training of the various tasks and without cumbersome set-up processes.
In addition, it is essential to easily create machine vision applications. Software such as MVTec’s Merlic can be used, for example. The software’s central element is an image-centric user interface, which guides the user through the application. While conventional programming tools work with complex codes, command- and parameter lists, users benefit from an easy-to-read visual display, similar to a “what you see is what you get” editor.
Moreover, the software also contains a collection of standard vision tools such as image acquisition, calibration, alignment, matching, measuring, counting, checking, reading, position determination, and defect detection.
An integrated feature called easyTouch is able to detect, highlight, and select objects with a single click by simply moving the mouse cursor over an image. This means that configuration of complex parameters is no longer needed, thus saving time and money during the development process. Therefore, employees without in-depth programming experience or image processing knowledge are able to create comprehensive machine vision applications. It is no longer necessary to write a completely new program for each new task.
Optimising The Industrial Value Chain
Machine vision streamlines numerous processes in the industrial value chain. For instance, it precisely detects objects in manufacturing processes, identifies the exact position of workpieces, and finds the optimum alignment for the same. Thus, robots can accurately grasp and process any kind of object. As a result, safety and efficiency in automated production processes will rise significantly.
Two-dimensional processes have so far been the standard method in this area. In this way solely the position of horizontally moving objects (such as on a conveyor belt) can be determined. However, 2D methods cannot identify three-dimensionally acting objects such as interacting cobots. Therefore, the 2D technology is only restrictedly suitable for highly automated production scenarios.
Three-dimensional vision technologies fit better with such scenarios. The method is integrated into the machine vision software, uses a multiple camera setup: Several cameras positioned in various locations view production processes from different perspectives.
As a result, a three-dimensional movement profile is generated. This determines not just the accurate position of objects, but also their movements in three-dimensional space and their speed. The 3D technology optimises robot-supported, highly automated manufacturing processes. The collaboration between humans and machines will become more efficient and safer. For instance, the technology can exactly determine the movement direction of mobile robots that are moving independently through factory buildings, avoiding potential collisions with humans or vehicles.
There is another benefit: The 3D technology is able to optimise the work of stationary and large five-axis robots used for welding and other assembly processes. For example, in the automotive industry these robots operate in separate areas that are inaccessible to human staff. If a person nevertheless steps over a certain line, sensors will stop the robot to ensure that the employee is not hurt.
Valuable time goes by before the robot starts up again, which leads to expensive interruptions in production processes. Using the innovative 3D technology, these processes now become much safer and efficient. The three-dimensional movement profile precisely determines the action radius of the robot. In this way, imminent collisions with human beings are detected in time. Thus, the company can increase safety and additionally save costs, since the frequency of robot shutdowns can be reduced with the precise, three-dimensional monitoring of production processes.
Powerful machine vision technologies not only assist production processes but also optimise quality assurance within numerous industries. For instance, they can be used for the precise scanning and inspection of tool surfaces in the metal industry. The software can safely identify and automatically reject any defective parts before entering downstream process chains. Thanks to the high speed of the image processing systems, automated inspections of large batch sizes take less time.
Furthermore, the technology supports processes in the electronics industry: Machine vision can help safely identify and detect errors for many different components and electronic parts. In addition, packaging processes are optimised: The quantity of products in packages can now be reliably determined, ensuring completeness.
Integrated Logistics And Transfer Processes
Last but not least, logistics and transfer processes also benefit from machine vision software, particularly for communication between products and manufacturing equipment in modern IIoT- resp. Industry 4.0 scenarios. In this context, products contain all manufacturing information in machine-readable form, such as bar codes, QR codes, or color-coding.
Machine vision systems can accurately read this coded information—even with defective codes (such as overexposure, excessively narrow, blurry or partly occluded code bars). The product’s path through the production equipment and individual process steps can be controlled automatically using this data.