Title: The fault diagnosis method of RVM based on FOA and improved multi-class classification algorithm

Authors: Kun Wu; Jianshe Kang; Kuo Chi

Addresses: Department of Management Engineering, Mechanical Engineering College, No. 97 Heping West Road, Shijiazhuang, Hebei 050003, China ' Department of Management Engineering, Mechanical Engineering College, No. 97 Heping West Road, Shijiazhuang, Hebei 050003, China ' Department of Management Engineering, Mechanical Engineering College, No. 97 Heping West Road, Shijiazhuang, Hebei 050003, China

Abstract: In order to solve the current problem of fault diagnosis and improve the traditional diagnosis models, an intelligent fault diagnosis approach of relevance vector machine (RVM) based on fruit fly optimisation algorithm (FOA) and improved multi-class classification algorithm is proposed. The optimal parameter values of RVM kernel function are determined by FOA and an improved multi-class classification algorithm of RVM based on the traditional one-against-one (OAO) and one-against-rest (OAR) algorithm is presented. The above classification method translates the multi-class classification problem into multiple three-classification problems to accelerate the running speed with high classification accuracy. Theoretical analysis and experiment results both demonstrate that the proposed method performs better than traditional methods in terms of diagnosis accuracy and running time with more model sparsity and higher diagnosis efficiency.

Keywords: fault diagnosis; relevance vector machine; RVM; fruit fly optimisation algorithm; FOA; multi-class classification.

DOI: 10.1504/IJHPCN.2018.094362

International Journal of High Performance Computing and Networking, 2018 Vol.12 No.2, pp.118 - 127

Available online: 22 Aug 2018 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article