Maintaining tool availability is the key to ensure machining quality. To evaluate tool availability so as to improve its utilization, the tool diagnosis models for tool-remaining-useful-life (RUL) estimation and tool-state classification are required. These models need sufficient samples to cover all the variations of tool coating and chip friction. However, in general, it is not easy to collect enough samples in the early stage. This issue will delay the readiness of the tool diagnosis models. The purpose of this letter is to propose a gradual refreshing scheme for modeling, running, and refreshing tool diagnosis models. In addition, a sample extension method is presented for reducing modeling time and enhancing accuracy of tool-state classification. The examples of engine-case machining are adopted in this letter to illustrate how the system works for estimating tool-RUL, classifying tool-states, and further, improving tool utilization.
All Science Journal Classification (ASJC) codes