Remaining Useful Life Prediction for Heterogeneous Wearing Cutting Tools Based on Inverse Gaussian Process and Bayesian Inference

The wear of cutting tools can lead to tool failures, and thus accurate remaining useful life (RUL) prediction for tools is important. Meanwhile, the wear process of tools from a same population usually present heterogeneous patterns. Therefore, this paper proposes a RUL prediction method for heterogeneous wearing cutting tools based on Inverse Gaussian (IG) process and Bayesian inference. The IG process is used to model the tool wear process. To characterize the heterogeneity among the tool wear processes, the reciprocal of tool wear rate is assumed to follow the truncated normal distribution, and its posterior distribution can be dynamically estimated based on the Bayesian method using online tool wear data. On this basis, the closed expression for the probability density function (PDF) of the tool RUL is derived. Finally, a case study is conducted to demonstrate that the proposed method can accurately predict the RUL of heterogeneous wearing tools.