An Orthogonal Wavelet Transform-Based K-Nearest Neighbor Algorithm to Detect Faults in Bearings

Abstract

We aim to address the issues of difficult acquisition of bearing fault data, few feature data sets, and low efficiency of intelligent diagnosis. In this paper, an orthogonal wavelet transform K-nearest neighbor (OWTKNN) diagnosis method has been proposed. The (OWT) method extracts the peaks of each detail signal as training samples and uses the K-Nearest Neighbor (KNN) method for fault classification. The classification results of the multiple fault test data obtained through rolling bearing tests show that the method can reach a fault recognition rate of 100%, and compared with KNN without extracted eigenvalues, it significantly improves the classification effects from various unknown fault data of the bearing inner ring and ball, shortens classification time, and improves the intelligent diagnosis efficiency. In addition, it achieves an overall recognition rate exceeding 95%, Comparing OWT, EMD, and VMD feature extraction methods, both the OWTKNN and k-center point clustering algorithm do not exceed 80% (KCA), also bearing testimony of the effectiveness of this method.

Comparative Analysis of Improved Dirichlet Process Mixture Model

“…Therefore, this paper uses high-dimensional data: (1) PCA for dimension reduction processing: first, the data matrix is solved, using the SVD method to solve the covariance matrix, and then generating the principal components by the eigenvalues and eigenvectors to; finally, DPMM clustering analysis was carried out for principal components. (2) The internal structure of the data as much as possible is maintain by t-SNE, the similarity in high-dimensional space is calculated by Gaussian distance, and the similarity in low-dimensional space is calculated by t-distribution to achieve dimensionality reduction. DPMM cluster analysis was performed on the dimensionally reduced data at last.…”

“…In the recent years, clustering-based methods have been widely used in various problems such as anomaly detection and image recognition, which has led to an active research area in clustering algorithms for high-dimensional and multi-source data. In the field of clustering analysis for multi-source data, various clustering methods have been proposed, including partitioning-based methods such as Kmeans [1] and K-centroids clustering [2], hierarchical-based methods, density-based methods, gridbased methods, and model-based methods. Among the various proposed methods, the K-means method is often sensitive to outliers, while K-centroids clustering improves upon this issue.…”

Orthogonal Wavelet Transform-Based Gaussian Mixture Model for Bearing Fault Diagnosis

“…Te orthogonal wavelet transform involves choosing an orthogonal wavelet function to transform, which can fully refect the local characteristics of the time domain and frequency domain, thus enabling the efective and reliable comprehension of the characteristic information contained in the original data. Terefore, OWT [15,16] and GMM [17,18] are combined herein to form OWTGMM, and the construction method is given [19,20]. In the application of OWTGMM in fault diagnosis, the orthogonal wavelet transform is used to extract the hierarchical features of the vibration signal and then extract the peak-to-peak feature signal as the training samples of the GMM to train the GMM classifer.…”