Tool wear predicting based on weighted multi-kernel relevance vector machine and probabilistic kernel principal component analysis

Abstract

This paper proposes a novel tool wear predicting method based on weighted multi-kernel relevance vector machine (WMKRVM) and the integrated radial basis function-based probabilistic kernel principal component analysis (PKP-CA_IRBF). The proposed WMKRVM model constructs the optimal multi-kernel model by seeking the weight parameter of the optimized single kernel RVM. As a new dimension increment technique, PKPCA_IRBF can extract the noise information of the process data and incorporate the noise information into the model. Moreover, this work first proposes using PKPCA_IRBF to fuse monitoring feature to improve the CI provided by the WMKRVM model. Besides, the parameter selection region and model accuracy of the PKPCA_IRBF are better than the conventional PKPCA_RBF technique, which helps improve the efficiency of model construction. The cutting experiment is conducted to validate the effectiveness of the proposed tool wear predicting technique. Experimental results show that the proposed tool wear predicting technique can accurately monitor the tool wear width with strong robustness under various cutting conditions, laying the foundation for applying to the industrial field.

Tool Wear Prediction Based on Multi-Information Fusion and Genetic Algorithm-Optimized Gaussian Process Regression in Milling

“…In this study, considering the complementarity of different domain features, multidomain features are extracted from multisensor signals. To further reduce the redundant information contained in initial features, various dimension reduction techniques have been applied for feature selection and fusion, such as kernel principal component analysis (KPCA) [30], [34], [57], minimum redundancy maximum relevance (MRMR) [58], and locally linear embedding (LLE) [59]. Among them, KPCA can effectively fuse principal components from numerous features, and it is a popular technique for nonlinear dimensionality reduction in tool wear monitoring [30], [34], [57].…”

“…To further reduce the redundant information contained in initial features, various dimension reduction techniques have been applied for feature selection and fusion, such as kernel principal component analysis (KPCA) [30], [34], [57], minimum redundancy maximum relevance (MRMR) [58], and locally linear embedding (LLE) [59]. Among them, KPCA can effectively fuse principal components from numerous features, and it is a popular technique for nonlinear dimensionality reduction in tool wear monitoring [30], [34], [57]. Thus, in this study, the KPCA algorithm is adopted to fuse candidate features and obtain the most sensitive characteristics related to tool wear.…”

A 3-layered nonlinear process monitoring strategy with a novel fault diagnosis approach

“…By combining Optimized Wavelet Multi-Resolution Analysis (OWMRA), PCA, and Neuro-Fuzzy techniques, the proposed method proves its reliability in accurately classifying different types of bearing faults, surpassing other classification methods in terms of efficiency and classification accuracy. Song et al (2022) [12] proposed a novel tool wear prediction method using a Weighted Multi-Kernel Relevance Vector Machine (WMKRVM) and Integrated Radial Basis Function-Based Probabilistic KPCA (PKPCA_IRBF). Zhang et al (2017) [13] proposed a fault detection and diagnosis strategy for a hot rolling mill.…”