ADAPTIVE OPTIMIZATION OF FACE MILLING OPERATIONS USING NEURAL NETWORKS

In intelligent machine tools, a computer based control sq stem, which can adapt the machining parameters in an optimal fashion based on sens or measurements of the machining process, should be incorporated In th is paper, the method for adaptive optimization of the cutting conditio ns in a face milling operation for maximizing the material removal rat e is proposed. The optimization procedure described uses an exterior p enalty function method in conjunction with a multilayered neural netwo rk. Two neural networks are introduced: one for estimating tool wear l ength, and the other for mapping input and output relations from the e xperimental data during cutting. The adaptive optimization of the cutt ing conditions is then implemented using the tool wear information and predicted process output. The results are demonstrated with respect t o each level of machining such as rough, fine, and finish cutting.