ONLINE MONITORING OF TOOL BREAKAGE IN FACE MILLING USING A SELF-ORGANIZED NEURAL-NETWORK

This study introduces a new tool breakage monitoring methodology consi sting of an unsupervised neural network combined with an adaptive time -series modeling algorithm. Cutting force signals are modeled by a dis crete autoregressive model in which parameters are estimated recursive ly at each sampling instant using a parameter-adaptation algorithm bas ed on a recursive least square. The experiment shows that monitoring t he evolution of autoregressive pam meters during milling is effective for detecting tool breakage. An adaptive resonance network based on Gr ossberg's adaptive resonance theory (ART 2) is employed for clustering tool states using model parameters, and this network has unsupervised learning capability. This system subsequently operates successfully w ith a fast monitoring time in a wide range of cutting conditions witho ut a priori knowledge of the cutting process.