Automatic Tool Wear Monitoring System Based on Validated Corner Detection and Taguchi’s Method

• Main Authors: Yu-Teng Liang, 梁有燈
• Other Authors: Yih-Chih Chiou
• Format: Others
• Language: en_US
• Published: 2011
• Online Access: http://ndltd.ncl.edu.tw/handle/51375537926609076997

博士 === 中華大學 === 工程科學博士學位學程 === 99 === This study proposes a tool wear monitoring system based on multi-parameter analysis of cutting force and machine vision techniques. The tool wear of drills with different coatings under various drilling parameters such as coating layer, feed rate, spindle speed, and number of holes drilled in drilling 28 mm × 140 mm × 160 mm steel plates was experimentally investigated in this study. All of the experiments were designed using the Taguchi method in order to obtain robust results. In order to realize the level of importance of each machining parameter, the L9(34) orthogonal array, analysis of variance (ANOVA), and signal-to-noise (S/N) ratio were determined. The tool wear images are captured using a machine vision system incorporated with an effective vertex detection algorithm. Finally, the Statistical Process Control (SPC) technique is applied to detect vertices. The experimental results indicated that a TiAlN-coated drill, with a spindle speed of 764 rpm and a feed rate of 0.12 mm/rev, resulted in minimum drill wear and thus maximum tool life. Confirmation tests demonstrated that this is a feasible and effective method for evaluating tool wear in drilling processes.