Application of Machine Learning to Bending Processes and Material Identification

The increasing availability of data, which becomes a continually trend in multiple fields application, has given machine learning approaches renewed interest recent years. Accordingly, manufacturing processes and sheet metal forming follow such directions, having mind the efficiency control many parameters involved, processing material characterization. In this article, two applications are considered to explore capability modeling through shallow artificial neural networks (ANN). One consists developing an ANN identify constitutive model using force–displacement curves obtained with standard bending test. second one concentrates on springback problem press-brake air bending, objective predicting punch displacement required attain desired angle, including additional information angle. data for designing solutions collected from numerical simulation finite element methodology (FEM), turn was validated by experiments.