Prediction of laser clad parameters based on neural network

Abstract

Since laser cladding is a multivariable coupling process, the relation between clad bead and process parameters is non-linear. Moreover, it is very difficult to find out an exact analytic model to express this relation. In this study, a neural network model, which is often used for non-linear problems, is developed to explain the relationship between process variables and clad parameters. A normal backpropagation (BP) algorithm and an amended BP one are trained, and it is found that the amended BP algorithm has advantages over the normal BP one. The experimental results well agreed with those predicted by the neural network model, indicating that the developed BP neural network model can be used for prediction in applications.