Multi-class fuzzy support matrix machine for classification in roller bearing fault diagnosis. (January 2022)

• Record Type: Journal Article
• Authors: Pan, Haiyang; Xu, Haifeng; Zheng, Jinde; Su, Jin; Tong, Jinyu
• Is Part Of: Advanced engineering informatics. Volume 51(2022)
• Publication Date: 2022-01
• Subjects: Multi-class fuzzy support matrix machine -- Nonparallel fuzzy hyperplane -- Fuzzy attribute -- Roller bearing -- Fault diagnosis; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2021.101445
• Languages: English
• ISSNs: 1474-0346

Abstract

Highlights: A multi-class fuzzy support matrix machine (MFSMM) is proposed. MFSMM can maximize the interval between any two fuzzy hyperplanes. MFSMM has stronger fault tolerance for samples with uncertain information. Abstract: As a new classification method with the matrix as the input, support matrix machine (SMM) makes full use of the structured information between rows and columns of the input matrix to establish an accurate prediction model, which has been widely used in the field of fault diagnosis. However, the principle of SMM is to construct two parallel hyperplanes to complete the segmentation between different types of samples. When there are noise and outliers in the sample data, it is difficult for SMM to construct an ideal parallel hyperplane. In view of this, this paper proposes a multi-class fuzzy support matrix machine (MFSMM) by establishing nonparallel hyperplane objective function and integrating fuzzy attributes. In MFSMM, MFSMM establishes two nonparallel fuzzy hyperplanes by objective function, which maximizes the interval between any two fuzzy hyperplanes while considering the sample structure information. Meanwhile, fuzzy plane assigns different membership degrees to different training samples, which greatly reduces the influence of noise on the construction of optimal classification hyperplane. By analyzing two kinds of roller bearing experimental data, the results show that MFSMM has higher classification accuracy and stronger fault tolerance for samples with uncertain information.