WSEAS Transactions on Systems
Print ISSN: 1109-2777, E-ISSN: 2224-2678
Volume 12, 2013
Intelligence Diagnosis Method Based on Particle Swarm Optimized Neural Network for Roller Bearings
Authors: , , , ,
Abstract: This paper presents an intelligent diagnosis approach based on the particle swarm optimized BP (PSO-BP) neural network and the rough sets to detect roller bearings faults and distinguish fault types, using symptom parameters of acoustic emission signals. The rough sets algorithm is used to reduce details of time-domain symptom parameters for the training of the neural network instead of principal component analysis. The PSO-BP neural network, which used for condition diagnosis of roller bearing, can obtain good convergence using the symptom parameters acquired by the rough sets when learning, and can automatically distinguish fault types when diagnosing. Using the PSO-BP neural network can increase the learning rate and the subtracting capability of the neural network. Practical examples are provided to verify the efficiency of the proposed method.
Search Articles
Keywords: Intelligence diagnosis, Particle Swarm Optimization, BP neural network, PCA, Rough set, Fault Diagnosis, Roller Bearings