Assessment of sheet-metal bending requirements using neural networks

Abstract

The springback behaviour of a sheet-metal is dependent on the properties of the metal and the bending conditions, namely the thickness of the sheet-metal, geometry of the tooling and the amount of force used for bending. Sheet-metal component manufacturing often requires near zero springback angle to obtain the correct shape of the product. An attempt has been made to model the non-linear relation between properties of the metal, the springback angle, geometry of the tooling and the bending force applied. Multilayer perceptron neural networks with a backpropagation learning algorithm were used to model the bending process. One set of data from bending experiments in a laboratory environment was used to train the networks. The networks were tested with the remaining set of experimental results. Then, the neural networks were used to predict the forces required for a number of bending experiments to achieve a zero springback angle. Validation of the neural network predictions was performed by trying to apply the predicted amounts of bending force in the physical experiments. The springback angles achieved were within ±1 degree, which is an acceptable range for the work. The research clearly demonstrates the applicability of neural networks to modelling the sheet-metal bending process.