Application of Neural Network in Sheet Metal Bending Process

Abstract

The sheet metal bending is an important form of sheet metal forming process, widely used in various industrial applications like aircraft, automobiles, household items, power industries,
etc. This study predicts the responses of the sheet metal bending process using artificial neural network. Based on44 cases analysedusing finite element method, a neural network was trained. Sheet thickness and die radius were the input, and stresses, strains, springback, loads, etc were the output for the neural network. The trained neural network was tested for five new patterns. It was found that most ofthe results were quite close to the simulation results. Such a technique of response prediction helps in reducing the, computational time.