An applications of adaptive neural networks for an in-process monitoring and supervising system

The authors report on a monitoring and supervising system for machining operations by using in-process regressions and adaptive feedforward artificial neural networks. The system uses different sensors. It is designed for tool life measurement and prediction, supervision of machining operations, and catastrophic tool failure monitoring. Adaptive feedforward artificial neural networks (AF-ANNs) are used for supervising, and in-process regressions for monitoring machining operations. The supervision of machining operations is studied within the framework of multiple criteria decision making. The decision maker (operator) considers several criteria, such as cutting quality, production rate, and tool life. To make the optimal decision with several criteria, the decision maker's preferences have to be elicited and assessed. The AF-ANN is used to determine the preferences.<<ETX>>