WPD and DE/BBO-RBFNN for solution of rolling bearing fault diagnosis

• Published in: Neurocomputing (Amsterdam) Vol. 312; pp. 27 - 33
• Main Authors: Zhang, Qing, Gao, Junwei, Dong, Honghui, Mao, Yunlong
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 27.10.2018
• Subjects: Biogeography-based optimization algorithm; Differential evolution; Radical basis function neural network; Rolling bearing fault diagnosis; Root-mean-square error; Wavelet packet decomposition; Differential evolution; Biogeography-based optimization algorithm; Radical basis function neural network; Root-mean-square error; Wavelet packet decomposition; Rolling bearing fault diagnosis
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2018.05.014

•A fault diagnosis method using WPD and DE/BBO-RBFNN is proposed.•WPD is used on extraction of feature vector.•A hybrid differential evolution with biogeography-based optimization algorithm based on RBFNN is developed.•The fault diagnosis accuracy of rolling bearing is improved using the proposed method. A new system of fault diagnosis which combines wavelet packet decomposition (WPD), radical basis function neural network (RBFNN) and a hybrid differential evolution with biogeography-based optimization (DE/BBO) algorithm is designed in this paper to improve the efficiency and accuracy of rolling bearing fault diagnosis. Biogeography-based optimization (BBO) is a new biogeography inspired algorithm, however it has the disadvantages of early-maturing and instable convergence. Combining BBO with differential evolution (DE) and making small modifications for the mutation strategy of DE, an improved DE/BBO algorithm is formed. Firstly, the fault feature vectors of original rolling bearing fault signals are effectively obtained by wavelet packet decomposition and reconstruction. Secondly, the RBF neural network is optimized by DE/BBO algorithm, the fault types of rolling bearing are trained and diagnosed next. The result of MATLAB simulation shows that in contrast to the traditional RBFNN, the fitness and precision of bearing fault diagnosis are higher and the root-mean-square error (RMSE) is lower because of the introduction of DE/BBO algorithm.