An online intelligent algorithm pipeline for the elimination of springback effect during sheet metal bending

Abstract An intelligent control algorithm pipeline is proposed to eliminate the effects of variation of physical properties of sheet metals on bending. This pipeline can be applied to any conventional press brake without the necessity of additional sensors and/or equipment. The overall pipeline is capable of extracting features representing sheet metal during bending in an online manner, classifying it accordingly, running a neural network model specific to the classified material, and calculating the correct punch displacement in order to eliminate springback effect. Moreover, algorithm pipeline can also decide whether the material processed is already in the material database or not. If the material is not in the material database, it directs the user in order to generate a quick reference model for completing the bending procedure and adds this model in the material database. The overall algorithm pipeline provides an autonomous approach to material bending and saves time by eliminating tedious calibration and bending iterations.