Knowledge-based intelligent diagnostics of tool wear states

Flank wear is a form of tool wear that occurs when freshly cut workpiece slides pass the flank face of the tool in machining process. Increase in flank wear reduces the surface quality of machined workpiece; besides, it also causes the increase in power utilization of the machine tool. So it becomes necessary to replace the tool with a new one as the flank wear reaches a specific value. It is almost impossible to measure flank wear when machining process is in progress. In this paper, two strategies, for estimation of tool's flank wear at different stages of in-progress milling process, are presented and compared for accuracy. The offline strategy involves volume of material removed (VoM) as input parameter besides feed rate and depth of cut. The online strategy replaces VoM with the cutting force. Both the strategies make use of expert systems, each of them utilizing fuzzy logic as reasoning mechanism. Design of Experiments were worked out for testing 2 levels of feed rate, 3 levels of depth of cut, and 6 levels each of VoM and peak values of cutting force against maximum width of flank wear land (VB). Based upon the experimental results fuzzy rules were developed for both of the strategies. For the purpose of testing and comparison of both strategies, further milling experiments were done utilizing different depth of cut and feed rate values. The comparison results showed that estimation capability of both of strategies was very good but still the online strategy outperformed the offline one.