Parametric Optimization in Drilling EN-8 Tool Steel and Drill Wear Monitoring Using Machine Vision Applied with Taguchi Method

Abstract Tool wear is highly correlated to production cost and efficiency. In this research, a drill wear monitoring system based on parametric optimization and machine vision technique is developed. A drilling model of cutting parameters (drill diameter, spindle speed and feed rate) and tool condition (focusing on drill wear measurement and analysis) is developed. To increase the tool life and for the required surface roughness in machining the parameters are to be optimized. The experimental design methods developed in this study can be used to optimize cutting parameters efficiently and reliably. The drilling model based on cutting parameters was constructed using Taguchi method. The derived relation is useful for in-process wear monitoring. Tool wear dynamics are extremely complex and not yet fully understood. Therefore, machine vision-based tool wear monitoring techniques can help elucidate wear progression. In this study, a drilling model based on the machine vision technique is used to establish a direct relation between cutting parameters and tool wear. Experimental results indicate that tool condition monitoring can be successfully accomplished by analyzing texture feature information extracted from the drill image.