Multi-Objective Optimization in End Milling Process of ASSAB XW-42 Tool Steel with Cryogenic Coolant Using Grey Fuzzy Logic and Backpropagation Neural Network-Genetic Algorithm (BPNN-GA) Approaches

Abstract

This study investigates the prediction and optimization of multiple performance characteristics in the end milling process of ASSAB XW-42 tool steel, i.e., surface roughness (SR), tool flank wear (VB) and material removal rate (MRR). The quality characteristics of SR and VB was the smaller the better, while MRR was the larger the better. Three methods, namely grey fuzzy logic, back propagation neural network (BPNN) and genetic algorithm (GA), were separately applied. The experimental studies were conducted by varying the end milling process parameters (cutting speed, feed rate and axial depth of cut) and liquid nitrogen cooling flow rate. Grey fuzzy logic was used to obtain a rough estimation of the optimum end milling parameters. The influences of end milling parameters on multiple performance characteristics were determined by using percent contributions. BPNN architecture was determined to predict the multiple performance characteristics. GA method was then applied to determine the optimum end milling parameters. The results of confirmation experiments showed a good agreement with the predicted responses.