A modular, holistic optimization approach for industrial appliances

The need for more flexibility and energy efficiency in production systems motivated the development of balanced manufacturing (BaMa), a novel method for holistic optimization of operation strategies in the field of production engineering. It allows quick integration into existing production plants with hardly any requirements for additional hardware. We present a real-world application scenario from a semiconductor production plant. Black-box simulation models are created from monitoring data and technical specification documents and used to derive optimal operation strategies. Furthermore, machine learning approaches are applied for data preprocessing to improve model prediction quality and therefore increase optimization potential. We evaluate the method for the presented scenario, where potential savings due to increased energy efficiency are expected to amount to 15-40%. (C) 2019 The Authors. Published by Elsevier B.V.