A Modified PSO-BP Algorithm in Hydraulic System Fault Diagnosis Application

Abstract:

BP neural network for failure pattern recognition has been used in hydraulic system fault diagnosis.However, its convergence rate is relatively small and always trapped at the local minima. So a new modified PSO-BP hydraulic system fault diagnosis method was proposed,which combined the respective advantages of particle swarm algorithm and BP algorithm. Firstly, the inertia weight and learning factor of the standard particle swarm algorithm was improved, then BP neural network’s weights and thresholds were optimized by modified PSO algorithm. BP network performance was ameliorated. The simulation results showed that this method improved the convergence rate of the BP network, and it could reduce the diagnostic errors.

• Periodical: Applied Mechanics and Materials (Volumes 182-183)
• Pages: 1145-1148
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.182-183.1145
• Online since: June 2012
• Authors: Zeng Shou Dong, Xiao Yu Zhang, Jian Chao Zeng
• Keywords: BP Neural Network (BPNN), Fault Diagnosis, Hydraulic System, PSO Algorithm

References

[1] Pan Hao, Hou Qinglan. A BP Neural Networks Learning A lgorithm Research Based on Particle Swarm Optimizer. COMPUTER ENGINEERING AND APPLICATIONS, 2006. 41(3), 41-43. In Chinese.

[2] Wang Tao, Wang Xiaoxia. Power transformer fault diagnosis based on modified PSO-BP Algorithm. ELECTRIC POWER, 2009. 42(5)13-16. In Chinese.

[3] Chatterjee A, Siarry P. Nonlinear inertia weight variation for dynamic adaptation in particle swarm optimization. Computers and Operations Research, 2006, 33(3): 857-871.

DOI: 10.1016/j.cor.2004.08.012

[4] Wang Lihong, Hou Qingjian. Improved Particle Swarm Optimization Algorithm and Its Simulation. PROCESS AUTOMATION INSTRUMENTATION 2009, 30(7): 28-31. In Chinese.

[5] Shi Yuhui, Eberhart R C. A modified particle optimizer Proc. of the IEEE Conf. on Evolutionary Computation, 1998: 69-74.

[6] Xu Lei, Zhang fengming. Research on fault diagnosis method based on PSO neural network. Computer Engineering and Design. 2007, 28(15): 3640-3641. In Chinese.