An Industrial Vision System to Analyze the Wear of Cutting Tools

Christina Gillmann,Bernd Hamann,Benjamin Kirsch,Tobias Post,Hans Hagen,Thomas Wischgoll,Jörg Hartig,Jan Christian Aurich

doi:10.4028/www.scientific.net/amm.869.183

Abstract

The wear behavior of cutting tools directly affects the quality of the machined part. The measurement and evaluation of wear is a time consuming and process and is subjective. Therefore, an image-based wear measure that can be computed automatically based on given image series of cutting tools and an objective way to review the resulting wear is presented in this paper. The presented method follows the industrial vision system pipeline where images of cutting tools are used as input which are then transformed through suitable image processing methods to prepare them for the computation of a novel image based wear measure. For multiple cutting tool settings a comparative visualization of the wear measure outputs is presented. The effectiveness of the presented approach is shown by applying the method to measure the wear of four different cutting tool shapes.

Highlights

Cutting tools, as applied in turning, milling or drilling processes, are exposed to wear due to the loads they are subjected to in cutting processes [1]
Their common drawback is the additional hardware required to obtain the wear measurement. These sensors can be expensive and require maintenance. In contrast to these methods, this paper presents a wear measurement that is computed solely on the basis of images captured from the cutting tools
This paper presented an industrial vision system that is able to use arbitrary images of cutting edges, prepare them with suitable image processing methods and apply a novel wear measurement to identify the amount and location of wear without considering further sensors

Summary

Introduction

As applied in turning, milling or drilling processes, are exposed to wear due to the loads they are subjected to in cutting processes [1]. The width of the flank wear land is determined manually via optical microscopes To solve this problem, an objective measure can be accomplished by different sensors [2] as shown in Section Related Work. An objective measure can be accomplished by different sensors [2] as shown in Section Related Work These sensors can be expensive, require maintenance, and are not available commonly in the shop floor. The approach should have low computational costs so that it can be run on a common computer This measure should be embedded in a visual system that allows the review of the computational output during operation. This system has to provide an intuitive visualization of the evolved measure that allows an interactive exploration and comparison of wear behavior for decision making [4]

Methods

Discussion

Conclusion