On Model Based Adaption of Deep Drawing Processes to Increase Process Stability and Resource Efficiency

In industrial deep drawing processes, stochastic fluctuations and disturbances in the manufacturing can result in a decreasing overall equipment effectiveness (OEE). The sensitivity to a fluctuation in component quality is further intensified in car body manufacturing due to complex geometries with small radii and the processing of high strength steels. The resistance to negative influences is referred to as resilience. This work presents and evaluates various smart stamping approaches that enhance the resilience of deep drawing processes. The focus is on the prediction of optimal press settings based on the incoming mechanical material properties. The mechanical material properties and component quality are continuously measured and fed into a model for analyzing the effects of fluctuations and disturbances on product quality through a feedback loop. Due to the ability to autonomously adapt to fluctuating environmental conditions and the automatic feedback, the meta model is considered as a digital twin.