Prediction of cutting force of AISI 304 stainless steel during laser-assisted turning process using ANFIS

Abstract

In this article, the adaptive neuro based fuzzy inference system (ANFIS) model has evolved to predict the cutting force of AISI 304 stainless steel during Laser-Assisted Turning (LAT) process. LAT experiments are accomplished with TiAlN carbide insert at different range of cutting speeds (25, 50 and 75 m/min), feed rates (0.025, 0.05 and 0.075 mm/rev) depth of cuts (0.5, 0.75, 1 mm) and laser powers (0, 150, 300 and 450 W) under laser-assisted dry cutting conditions. This neural network combines the fuzzy inference system with a backpropagation algorithm of the neural network. Gauss membership function (gaussmf) was used during the training process of ANFIS for the prediction of cutting force during LAT process. The comparison of ANFIS predicted values with experimental data signifies that the application of gaussmf in proposed system achieved satisfactory accuracy. Our result proves that ANFIS model with gaussmf is an excelling predictive tool for the prophecy of cutting forces during laser-assisted turning process with minimum average test error.