OEM&Lieferant Ausgabe 1/2019

97 lected from the machine controls, from the existing sensor system of the machine and/ or from retrofitted sensors which we choose and install together with our customers. To- gether we will specify the level of granularity required for a specific task and define how data from multiple sources can be integrated smoothly and in what format the data is transferred and stored. Using our proven PLUGandWORK solution components, we also turn components and machinery into data suppliers which have not been networking yet. IOSB also offers know-how in the fields of data security and data protection, because a greater degree of networking includes a higher risk of cyber-attacks. The correct use of the wide range of technologies already available today ensures unrestricted data sovereignty. How important is machine learning for AI? Olaf Sauer: In manufacturing, we use machine learning to generate “knowledge” from “expe- rience” in a very general sense. Learning algo- rithms develop a complex model from sample data with the largest possible degree of rep- resentation. Subsequently, this model can be applied to new and potentially unknown data of the same kind. Machine learning is an appropriate method whenever processes are too complicated to describe them in an analytic way, and if there is a sufficient amount of sam- ple data such as sensor data or images. The models are matched with the data flow from operations and ultimately enable forecasts or recommendations and decisions. Examples of how machine learning can im- prove quality and reduce time or costs: the discovery of anomalies in the behavior of machines or components, whereby the pro- cedures reliably discover deviations from the normal behavior of a process; the making of better decisions in complex situations, be- cause the models can identify the complete connections spanning several manufacturing processes so they can be enhanced to serve as assistance systems; or the quick adaptation of manufacturing and assembly processes to current situations, because clear correlations between measuring results and process pa- rameters allow for automatic control. Further application areas of machine learning are human-robot cooperation, autonomous in- tralogistics and self-organization in manufac- turing. IOSB supports companies in selecting the right learning and modelling algorithms, defining, editing and storing representative training data, generating meaningful models from the training data and then comparing them with runtime data. Where will the data required for the use of AI methods be processed or the models be learned in the future? Olaf Sauer: Currently it becomes apparent that “edge-cloud-computer centers” will take over this task. Edge computing means that com- puting power, software applications, data processing or services are transferred directly to the logical edge of a network, e. g. a line or a complete factory. Studies predict that edge computing will increase by roughly 30 % per year by the year 2025, owing to the large vari- ety of data that can be expected, the required processing speed and power. Edge computer centers, inter-connected to form a cloud in- frastructure, are thus scalable, also enabling medium-sized enterprises to use cloud tech- nologies without having to invest in their own infrastructure. How can companies and research institu- tions jointly maximize the potential of AI? Olaf Sauer: Studies have shown that tar- geted cooperations between companies and research institutions result in the faster development of new products, services and processes. In the Fraunhofer „Enterprise Labs“, employees from enterprises work together with Fraunhofer scientists and en- gineers on a daily basis in one team, which results in specific product and process inno- vations. The employees contribute specific product and process know-how as well as knowledge about the business processes of their market. The IOSB experts have extensive technological know-how and application expertise relating to multiple in- dustries. This cooperation leads to targeted results and joint use cases with measurable customer benefits. What role do the IOSB research factories and laboratories play in this? Olaf Sauer: They are an ideal environment for shop-floor related AI projects, as they are equipped with state-of-the-art industrial components, ranging from sensor technology to cloud infrastructure, so that future applica- tions and products can be tested and improved under realistic conditions. Big Data, Machine Learning and Data Analytics http://t1p.de/2hzc Website Source: IDC: Artificial Intelligence 2018.