Prediction of Laser Formed Shaped Surface Characteristics Using Computational Intelligence Techniques

Abstract

The main purpose of this study was to establish a prediction model for parameters of shaped surface based on laser forming process. Shape modelling from a flat sheet by lasers forming process needs numerous irradiations along surface paths with different heating parameters. Since the prediction of the parameters of shape modelling could be very complex task, computational intelligence techniques could be used for the prediction process. In this article support vector regression (SVR) was applied for the shaped surface parameters prediction. The SVR model was compared with other computational intelligence models like artificial neural network (ANN) and genetic programming (GP) techniques as benchmark models. Laser power, laser scan speed and spot diameter were used as inputs. The crucial aim of the study was to predict favourable and unfavourable shape forms according to the machining parameters. By the way one should make optimal machining conditions in order to avoid unfavourable shape forms. Based on the results, SVR model outperformed ANN and GP models for the shaped surface parameters prediction.