Automated Detection of Production Cycles in Production Plants using Machine Learning

Data-driven algorithms can be used to derive new information from data. In modern production plants, this can be used to reduce manual effort, e.g. to create a behavior model. In this work, one offline and one online algorithm are introduced that can determine the production cycles automatically. The algorithms use learned automaton to detect production cycles. A first evaluation is presented, which points out differences of the algorithms. However, overall the results are promising.