Investigation of material removal rate and surface roughness in wire electrical discharge machining process for cementation alloy steel using artificial neural network

摘要

Investigating the effect of process parameters on material removal rate and surface roughness is very important for process planing in wire electro-discharge machining. In this study, wire electro-discharge machining of cementation alloy steel 1.7131 is experimentally studied, then linear regression model and feedforward backpropagation neural network were established to predict surface roughness and material removal rate for effective machining. The full factorial experiment was chosen for experiments. Experiments were performed under different cutting conditions of pulse current, frequency of pulse, wire speed, and servo speed. The optimized neural network with the best performance for prediction had eight neurons in the hidden layer, capability with 0.773 % overall mean prediction error, while 2.547 % errors was revealed by regression model. Totally, the comparison of the results showed that the neural network is more robust with better accuracy.