Data Analytics in Manufacturing Companies
With the introduction and use of comprehensive data-driven approaches, there is a paradigm shift in quality management from preventive to predictive. Predictive quality enables the user to make data-driven predictions of product and process-related quality in every phase of the product life cycle.
With regard to the product, the implementation of predictive quality allows future customer requirements to be systematically fed back into product development, thus avoiding dissonance among customers. On the other hand, predictive quality is an enabler for the introduction of new business models such as subscription. On the process side, predictive quality enables not only the control of complex processes but also a reduction of quality costs, resulting from quality checks, internal and external rework and loss of reputation.
In the course of the lecture, application examples from different industries, for the product and process-related implementation of predictive quality, will be presented. Based on these examples, concrete requirements for the successful implementation of predictive quality approaches will be derived. The focus is on the data basis itself as well as on the human being as user and information carrier. Finally, the greatest technical as well as corporate cultural and business management challenges during implementation are discussed.