A hybrid method for cutting tool RUL prediction based on CNN and multistage Wiener process using small sample data

Abstract

Based on the multistage and nonlinear characteristics of cutting tool wear, a hybrid method for cutting tool remaining useful life (RUL) prediction based on convolutional neural network (CNN) and multistage Wiener process using small sample data is proposed in this paper. First, wavelet transform is used to analyse the vibration data collected for cutting tools in the time–frequency domain to obtain an initial image data set. A CCVAE (conditional variational autoencoder with CNN) network is built to expand the initial data set and solve the problem of unbalanced data in different stages of cutting tool wear. The expanded data is used as the input of the CNN to monitor the tool wear state and amount of wear. Then, a nonlinear multistage Wiener process is established to describe the cutting tool wear degradation process and achieve accurate RUL prediction for the cutting tool. Specifically, a nonlinear Wiener process model corresponding to different degradation stages based on the change points between the cutting tool wear states output by the CNN is established. Maximum likelihood estimation and Bayesian methods are used to estimate and update the parameters, respectively, and the RUL value and corresponding probability density function (PDF) are obtained under different wear conditions. Finally, through experimental research and comparative analysis, it is found that the multistage nonlinear Wiener model accurately simulates cutting tool wear degradation, which verifies the feasibility and performance of the method proposed in this paper.