Increasing Energy Efficiency in Hot Forming Processes Through Multivalent Data Use

The energy policy requirements help to make industrial production more sustainable and environmentally friendly, reduce energy consumption and lower the overall costs for businesses. There is a great need for action to increase energy efficiency in production in press hardening processes through efficient technologies along entire process chains. In such production processes and process chains, data accumulates from a wide variety of sources, including machine controls, sensors, material data and simulation data from process design. The logical next step is to utilize this data along with machine learning and optimization methods to control the process and pursuing objectives like optimal quality, minimal energy, or fast cycle times. This is where the proposed method of this work comes in. The main contribution of this work is a methodology to schematically describe and handle process optimizations model-based. In addition, this method is demonstrated on a hot forming process using hybrid (simulation and experimental) data. It is shown that the process can be optimized regarding its energy consumption while complying with additional technical and quality boundary conditions.