Forward and inverse predictions of deformations in laser forming of shaped surfaces under coupling mechanism

This article deals with out-of-plane and in-plane deformations of an American Iron and Steel Institute 304 stainless steel sheet in laser forming under the coupling mechanism, which is required to make any three-dimensional (3D) part from a flat sheet. Experiments were carried out based on face centered central composite design of experiments to develop statistical regression models based on experimental data for both the types of deformations, i.e., in-plane and out-of-plane, as a function of input parameters, such as laser power, scan speed, and spot diameter. Adaptive neuro-fuzzy inference system-based models were also developed to predict bending or out-of-plane and thickening or in-plane deformations. Process synthesis or inverse analysis, that is, to decide the process parameters to laser form a 3D shape from flat sheet metal was performed using an adaptive neuro-fuzzy inference system. Prediction accuracy of the developed models was verified through experiments and good correlation was found in estimating deformations and process parameters for both forward and inverse analyses. The effect of Fourier number on deformation in making a three-dimensional surface was also studied, and it was found to be an important factor in obtaining a three-dimensional shape with desired accuracy.