Fraunhofer Institute IEM Researchers Introduce RoboGrinder, First Smart Grinding Machine

Nowadays, although entrepreneurs are aware of the potential for artificial intelligence to increase their competition, many are reluctant to question the reliability of AI solutions. The goal of the Fraunhofer Institute for the Design of Mechatronic Systems (IEM) is to build confidence in artificial intelligence systems. Its teams have combined AI and control technology to create a completely reliable system: RoboGrinder, a grinding machine that eliminates up to 40% of grinding processes.

Fraunhofer-Gesellschaft, founded by representatives of industry and academia in Munich on March 26, 1949, has 76 institutes and universities in the Bavarian government and the Federal Republic of Germany, Germany, focusing on various areas of research application that have become a leader and approximately 30,000 employees. , Mainly engineers and scientists. A pioneer of innovative products, it holds numerous patents. 70% of its revenue comes from contracts with industrialists or specific contracts with the government.

Fraunhofer Institute for the design of Mechatronic Systems

Mechatronics is a synergistic and systemic combination of mechanics, electronics, automation and real-time computing. It is used in all major sectors of the industry: transportation, consumer goods, capital goods … robots, autonomous vehicles, ABS, hard drives, smart washing machines … examples of system mechatronics.

Fraunhofer IEM researchers have set themselves the goal of tackling skepticism and building confidence in artificial intelligence, especially through technology to control these systems.

Fraunhofer explains Steven Coppert, head of IEM’s Trusted Machine Intelligence Group:

“We combine proven control technology with new artificial intelligence. Although many control technologies are based on physical and mathematical models that can be analyzed and trusted, artificial intelligence – which at first is not particularly reliable – usually relies exclusively on data and also solves creative tasks. A

RoboGrinder: Intelligent grinding machine designed by Fraunhofer Institute IEM

RoboGrinder is a definite example of the reliability of an automated system that integrates AI. The institute designed it for Düspohl, a mechanical engineering company.

Until then, profile wrapping rolls, which have a very complex shape and often need to be grounded, were grounded manually because automation using control technology alone is not easily achievable for rubber components. In fact, the roller element is so elastic that it comes back after grinding, making it very difficult to model this behavior and integrate it into the control technology method. Although one might think that by multiplying the grinding process, it would be easier, on the contrary, the process becomes ineffective. In addition, the surface quality of rollers can deteriorate with the number of grinding processes. The use of AI solves this problem.

Steven Copert explains:

“We document all the grinding errors that occur during each grinding process and use it to train an artificial intelligence model – so AI takes responsibility for the correction, especially when making fine adjustments. By comparison, you could say that control technology works like a railroad, while artificial intelligence ensures that the road curve is discussed in the best way. A

Thus, the process can be reliably automated, which is the first. Profile coating companies in the building materials and furniture industry will be able to reproduce spare parts in their factories, the prototype measuring two by just one meter in a matter of minutes.

Wei Wagner, managing director of Daspohl, said:

“Using our machines, our customers in the building materials and furniture industry create a wide range of different designs and materials. At the same time, they must be able to respond quickly and easily to new order situations. So smart shading systems will be a key component of automation.”

Reduces grinding process by up to 40%

Fraunhofer IEM researchers began by digitally mapping the grinding process. According to researchers, ” RoboGrinder can eliminate 15% grinding activity when re-sharpening from approximate size to specific size. The advantage of re-sharpening used rollers becomes even more pronounced when the grinding process is performed directly on the sensitive area – which means that re-sharpening should be done very carefully so as not to remove too much material. A

Steven Coppert says:

“With the digital twin, we have been able to show that we can eliminate up to 40% of the grinding process.”

Thanks to RoboGrinder: Specific sizes are respected, part shapes are detected independently by a laser scanner and, as a further advantage, very fast automatic machine processing.

Researchers are currently conducting parametric studies and working on construction-related topics, among other topics. The first prototypes of RoboGrinder will be presented at the Hanover Fair in late May.

Leave a Comment