Fault diagnosis of gearbox based on RBF-PF and particle swarm optimization wavelet neural network

• Published in: Neural computing & applications Vol. 31; no. 9; pp. 4463 - 4478
• Main Authors: Yang, Liu, Chen, Hanxin
• Format: Journal Article
• Language: English
• Published: London Springer London 01.09.2019; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Back propagation; Back propagation networks; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Convergence; Damage detection; Data Mining and Knowledge Discovery; Diagnostic systems; Fault diagnosis; Fracture mechanics; Gearboxes; Image Processing and Computer Vision; Neural networks; Particle swarm optimization; Probability and Statistics in Computer Science; Radial basis function; S.I. : Emergence in Human-like Intelligence towards Cyber-Physical Systems; Wave propagation; Wavelet analysis; Fault diagnosis; Wavelet neural network; Particle swarm optimization; Particle filter
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-018-3525-y

The gear cracks of gear box are one of most common failure forms affecting gear shaft drive. It has become significant for practice and economy to diagnose the situation of gearbox rapidly and accurately. The extracted signal is filtered first to eliminate noise, which is pretreated for the diagnostic classification based on the particle filter of radial basis function. As traditional error back-propagation of wavelet neural network with falling into local minimum easily, slow convergence speed and other shortcomings, the particle swarm optimization algorithm is proposed in this paper. This particle swarm algorithm that optimizes the weight values of wavelet neural network (scale factor) and threshold value (the translation factor) was developed to reduce the iteration times and improve the convergence precision and rapidity so that the various parameters of wavelet neural network can be chosen adaptively. Experimental results demonstrate that the proposed method can accurately and quickly identify the damage situation of the gear crack, which is more robust than traditional back-propagation algorithm. It provides guidances and references for the maintenance of the gear drive system schemes.