Machine learning and simulation-based surrogate modeling for improved process chain operation

Abstract In this contribution, a concept is presented that combines different simulation paradigms during the engineering phase. These methods are transferred into operation phase by use of data-based surrogates. As an virtual production scenario, process combination thermoforming continuous fiber-reinforced thermoplastic sheets and injection overmolding polymers investigated. Since very sensitive regarding temperature, volatile transfer time considered in dynamic chain control. Based on numerical analyses molding process, surrogate model developed. It enables fast prediction product quality based temperature history. The physical to agent-based identifying lead time, bottle necks rates taking account whole chain. second step modeling, feasible soft sensor derived for control over stage. For specific uses case, rejection can be reduced 12% compared conventional static approaches.