Prediction of Process Parameters Effect on MRR and Surface Roughness in Abrasive Water jet Cutting using Artificial Neural Network

Abstract

A machining operation is basically a material removal process, where material is removed in the form of chips. In a machining operation, the output parameter is achieved by controlling various input parameters. This paper discusses the effects of various input parameters in abrasive water jet cutting on the material removal rate and surface finish (as the output parameters). The results presented in the paper are obtained from an experimental study carried out on an abrasive water jet cutting machine. ANN based on back propagation (BP) is used to predict the effect of various input parameters on the outputs. Experiments are carried out on the mild steel and stainless steel. The five input parameters of the model consist of thickness, pressure, flow rate of abrasive, feed rate and SOD whereas the output are surface finish and material removal rate. In present work an attempt has been made to use Neuro solution for the ANN applying to abrasive water jet cutting process. The ANN is subsequently trained with experimental data. Testing of the ANN is carried out using experimental data not used during training. The result shows that the outcomes of the calculation are in good agreement with the experimental results; this indicates that the developed neural network can be used as an alternative way for knowing the process parameters effect on cutting performance.