Extensible and displaceable hyperdisk based classifier for gear fault intelligent diagnosis

• DOI: 10.1016/j.knosys.2020.106250
• Publication Date: 2020-07-10T15:38:37Z
• Authors: Tianzhen Hu; Junsheng Cheng; Ping Wang; Jian Wang; Yu Yang
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Abstract The support vector machine (SVM) method has been widely used in gear fault diagnosis. SVM is essentially a convex hull (CH) based classifier. However, using the CH to approximate the class region underestimates the true region, which leads to unsatisfactory classification performance of SVM. The use of hyperdisk (HD) based classifiers for classification can effectively avoid the above problem. But the compactness or looseness of the HD model is not adjustable and the HD based classifier has poor robustness to outliers. Therefore, to achieve better classification results in gear fault diagnosis, a classifier based on extensible and displaceable hyperdisk (EDHD) is proposed. By introducing the extensibility factor, the EDHD based classifier allows the compactness or looseness of the HD model to be adjusted to better approximate the class region. Besides, by introducing the displaceability factor, the EDHD based classifier can achieve higher robustness to outliers. Meanwhile, to extract features from unstable and nonlinear signals, a new entropy called multiscale fuzzy distribution entropy (MFDE) is proposed. Moreover, empirical mode decomposition (EMD) is used to preprocess the original signal before feature extraction, and Laplacian Score (LS) is used for feature selection after feature extraction. Finally, the EDHD and MFDE based gear fault diagnosis method is proposed. The results of gear fault diagnosis experiments fully prove the effectiveness of the proposed method.