Prediction of forming accuracy in incremental sheet forming using artificial neural networks on local surface representations

Abstract

While incremental sheet metal forming offers the potential for producing sheet metal parts in small lot sizes, the relatively low forming accuracy prevents widespread industrial use. For improving the forming accuracy, research institutes are using machine learning techniques to predict the geometric accuracy and modify the toolpath based on the prediction. A critical challenge is it to ensure the generalizability of the prediction model as only a small amount of process data is available to train the model due to the lack of industrial collaborations. This publication presents a highly transferable feature engineering approach where surface representations of the part’s geometry around each toolpath point are transferred into a standardized coordinate system. Several artificial neural networks were trained and used for predicting the forming accuracy and modifying the toolpath. During the validation experiments, the forming errors of parts which were independent of the training process were reduced by up to 68.5 %. The framework for computing the surface representations alongside with several pre-trained artificial neural networks is publicity available for download.