DESIGN AND IMPLEMENTATION OF SENSOR-BASED TOOL-WEAR MONITORING SYSTEMS

This article addresses the design of sensor-based tool-wear monitoring systems and their implementation, and specifically focuses on interpr etation of signals from multiple sensors in terms of tool-wear level. Keeping in mind that the absence of a well-accepted reliable methodolo gy and the ignorance of practical issues in implementation are two maj or reasons to prevent a successful on-line monitoring system from bein g realised in industries, four critical issues are raised and discusse d, which are: (1) expensive information on correct tool condition; (2) troublesome off-line preselection of features from original sensor si gnals; (3) impractical fresh/worn dichotomy; and (4) fallible signal-i nterpretation with stationary sensor information. We provide a detaile d suggestion of methodology to handle each issue effectively; adoption of an unsupervised clustering-type method (issue 1), development of a customised feature evaluation algorithm (issue 2), tendency of our me thodology to avoid serious misinterpretation errors with a finer disti nction of wear level (issue 3), and cooperative interpretation with se nsor information from multiple time points close to each other (issue 4). Our methodology is evaluated with machining data from a simplified monitoring situation, and proves to be able to bridge the gap between academic enthusiasm and industrial needs for a practical and reliable sensor-based tool-wear monitoring system. (C) 1996 Academic Press Lim ited