OEM&Lieferant Ausgabe 1/2019

96 Artificial intelligence for the production of the future OEM&Lieferant spoke with Dr. Olaf Sauer from the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB, Karlsruhe, on methods and potential applications of artificial intelligence. Artificial intelligence is undisputedly one of the key drivers of the digital revolution today. Productivity, quality and consequently the international competitiveness of the entire manufacturing industry, depend on its targeted use in industrial manufacturing processes. Mr. Sauer, what is the correlation between Industry 4.0 and the dimension of artificial intelligence? Olaf Sauer: One significant feature of Industry 4.0 is the consistent networking and imple- mentation of all factory components as well as complete value-added chains with sensor technology, embedded systems and commu- nication technology – known as cyber-physical systems. This results in large amounts of data, usually generated by machines, ranging from planning the products to bemanufactured and the production resources to actual production and the uses of the products. This data forms the basis of modern and powerful analysis and evaluation methods, which are currently called “artificial intelligence” (AI). Today, it is widely accepted that AI is a key technology that allows all users to make use of large po- tentials for improvement in all stages of the value chain. When it comes to AI research in Germany, how do we compare internationally? Olaf Sauer: Even though current studies cer- tify that Germany holds a good position in AI research, they also state that AI applications in the USA are far more competitive. China is making tremendous investment in artifi- cial intelligence – and Chinese companies will enter the German market for AI applications in manufacturing in a few years. Therefore, the Federal Government is absolutely right to state, in the context of its AI strategy, that they intend to make Germany and Europe a leading AI location. Industrial production is one of the most important fields of applica- tion in this context. Which innovative AI methods and tools are you currently working on in your in- stitute and how do you solve the problem of generating data relevant for the use of AI methods? Olaf Sauer: In manufacturing, data always has to be interpreted in the context of the products or the processes. If this is the case, data forms precious resources to improve the value-added process or to develop new business models. This also means that each practical use case requires its specific data. For this very reason, it is so important to an- alyze the right, high-quality data. It is only under these preconditions that we can make efficient use of AI. Our experience has shown that one of the major obstacles in the use of AI today is to extract the very data from the processes. Fraunhofer IOSB supports manufacturing companies in gathering AI-relevant data from their machinery and equipment as well as their components. This data is either col- Dr. Olaf Sauer Images/Graphic: © IOSB Industry 4.0