Simulation of surface milling of hardened AISI4340 steel with minimal fluid application using artificial neural network

Abstract

Surface roughness plays an important role in many areas and is a factor of great importance in the evaluation of cutting performance. In this paper an attempt was made to develop a model based on Artificial Neural Network to simulate surface milling of hardened AISI4340 steel with minimal fluid application. The model is expected to predict the surface roughness in terms of the fluid application parameters such as the pressure at the fluid injector, frequency of pulsing and the rate of fluid application. Such a model will be useful in the automatic control of the fluid application parameters to keep the surface roughness within the tolerance limits as required in computer assisted manufacturing. Networks with varying architecture were trained for a fixed number of cycles and were tested using a set of input / output data reserved for this purpose. The root mean square error was determined for each architecture. It was seen that a model with a 3-6-6-1 architecture gave the minimum RMSE value which could be approximated to 0.01. Accordingly this architecture was adopted for the analysis. It was also found that the predictions of the ANN model matched well with the experimental results. It is expected that such a model will be highly useful in research work connected with cutting fluid minimization during surface milling using high velocity pulsing jet of cutting fluid and to maintain the surface finish within the tolerance limits during automated hard milling operation with minimal fluid application.