Adaptive Optimization of Face Milling Operations Using Neural Networks

Abstract

In intelligent machine tools, a computer based control system, which can adapt the machining parameters in an optimal fashion based on sensor measurements of the machining process, should be incorporated. In this paper, the method for adaptive optimization of the cutting conditions in a face milling operation for maximizing the material removal rate is proposed. The optimization procedure described uses an exterior penalty function method in conjunction with a multilayered neural network. Two neural networks are introduced: one for estimating tool wear length, and the other for mapping input and output relations from the experimental data during cutting. The adaptive optimization of the cutting conditions is then implemented using the tool wear information and predicted process output. The results are demonstrated with respect to each level of machining such as rough, fine, and finish cutting.