Unternehmen&Trends - Ausgabe zur HANNOVER MESSE 2019

Using our proven PLUGandWORK 5 -solution components, we also turn components and machinery into data suppliers which have not been networked yet. In addition, we provide know-how in the fields of data security and data protection be- cause a larger degree of networking includes a higher risk of cyber attacks. Today, however, we have a lot of technologies which ensure, when used in the right way, that you remain the owner of your own data. The decisive fac- tor is a tailor-made and secure IT architecture for collecting, storing and evaluating the data. Machine learning In production processes, we use machine learning to generate “knowledge“ from “ex- perience” in a very general sense. Learning algorithms develop a complex model from sample data with the largest possible degree of representation. Subsequently, this model can be applied to new and potentially un- known data of the same kind. Whenever pro- cesses are too complicated to describe them in an analytic way, but there is a sufficient amount of sample data such as sensor data or images, machine learning is an appropriate method. 6 The models are matched with the data flow from operational business and ulti- mately enable forecasts or recommendations and decisions. Examples of how machine learning can im- prove quality and reduce time or costs: › Discovering anomalies in the behavior of machines or components because the pro- cedures reliably discover deviations from the normal behavior of a process and con- sequently enable predictive maintenance. › Making better decisions in complex situa- tions because the models can identify the complete connections spanning several manufacturing stages so they can be en- hanced to serve as assistant systems. › Adapting manufacturing and assembly processes to current situations quickly be- cause clear correlations between measur- ing results and process parameters allow for automated control. Further application areas machine learning where we are developing for our customers are human-robot cooperation, autonomous intralogistics and self-organization in manu- facturing. We support you in selecting the right learn- ing and modelling algorithms, defining, edit- ing and storing representative training data, generating meaningful models from the train- ing data, then comparing these models with runtime data. All these tasks require appro- priate sensor technology, software tools and architectures. We support you in establishing these instruments in a future-proof and sus- tainable way. Research on machine learning is proceeding. For example, the relevant issues are machine learning with extremely large or very small amounts of data, the combination of machine learning with physical or expert knowledge as well as security and transparency of ma- chine learning models. Autonomous Systems One of the areas where Industrie 4.0 is ap- plied in practice is ‚‘self-organizing produc- tion‘ Even in the first documents about In- dustrie 4.0 we can find the vision that “smart products (…) owing to ad hoc networking and possessing a digital product description are capable of navigating through production autonomously.” The underlying idea is that workpieces, machines and conveyor sys- tems negotiate the processing sequence in a decentralized way on the basis of a set of rules. This means that no central control unit has to calculate a plan in advance. If there are any disruptions, it is assumed that the par- ticipants can identify alternative solutions ad hoc – which is, in turn, faster that a central unit having to generate a new plan. Some practical examples such as a cylin- der head line in a motor plant have shown that these decentralized mechanisms deliver good results indeed. However, the flexibil- ity that had to be added to machinery and conveyor systems was too expensive so at the end of the day the costs outweighed the positive effects. ■ 1) PaiCE (Ed.): Study on the potential of artificial intelligence in manufactur- ing industry in Germany 2) Strategy Artificial Intelligence oft he Federal Government, see www.ki-strategie-deutschland.de 3) WorldManufacturingForum:The2018WorldManufacturingForumReport – Recommendations for the Future of Manufacturing. 4) Werthschützky, R. (ed.): Sensor Technologien 2022. AMA Verband für Sensorik und Messtechnik (AMA association for sensor and measuring technolgoy) e.V., 2018 5) see www.plugandwork.fraunhofer.de 6) Fraunhofer Gesellschaft (ed.): Machine learning – an analysis of compe- tences, research and application. Munich, 2018 Source: IDC: Artificial Intelligence 2018. Big Data, Machine Learning and Data Analytics http://t1p.de/2hzc Website Unternehmen & Trends  53