TOOL CONDITION MONITORING IN MACHINING - NEURAL NETWORKS Mo A. Elbestawi McMaster University elbestaw@mcmaster. ca Mihaela Dumitrescu McMaster University dumitrm@mcmasler. ca Condition monitoring and diagnosis systems capable of identifying machining system defects and tiieir location are essential for unmanned machining Unattended (or minimally manned) machining would result in increased capital equipment utilization, thus substantially reducing the manufacturing costs. A review of tool monitoring systems and techniques and their components and the Multiple Principle Component fuzzy neural network for tool condition monitoring machining are presented. 1. INTRODUCTION Increased demands for even higher product quality, reliability, and manufacturing efficiency levels have imposed stringent requirements on automated product measurement and evaluation. Manufactured products of the modem day command ever-higher precision and accuracy, therefore automated process monitoring becomes cmcial in successfully maintaining high quality production at low cost. The automated tool condition monitoring processes imply the identification of cutting tool condition without interrupting the manufacturing process operation, under minimum human supervision. Unattended or minimally manned machining leads to increased capital equipment utilization, thus substantially reducing the manufacturing costs. Both these situations require intelligent sensor systems. An "Intelligent Sensor System" was defined by (Dornfeld, 1986)' as an integrated system consisting of sensing elements, signal conditioning devices, signal processing algorithms, and signal interpretation and decision making procedures. In the absence of a human operator, the system should sense signals indicating the process status and its changes, interpret incoming sensed information, and decide on the appropriate control action. A system could be defined as Automated/Intelligent Monitoring System if sensing, analyzing, knowledge learning, and error correction abilities, essential to machining tool condition monitoring, are incorporated. Please use the followingformat when citing this chapter: Elbestawi, M. A., Dumitrescu, M., 2006, in IFIP International Federation for Information Processing, Volume 220, Infor- mation Technology for Balanced Manufacturing Systems, ed. Shen, W., (Boston: Springer), pp. 5-16.