Application of BPNN optimized by chaotic adaptive gravity search and particle swarm optimization algorithms for fault diagnosis of electrical machine drive system

Background: The effective diagnosis of wind turbine gearbox fault is an important means to ensure the normal and stable operation and avoid unexpected accidents. Methods: To accurately identify the fault modes of the wind turbine gearbox, an intelligent diagnosis technology based on BP neural network trained by the Improved Quantum Particle Swarm Optimization Algorithm (IQPSOBP) is proposed. In IQPSO approach, the random adjustment scheme of contractionexpansion coefficient and the restarting strategy are employed, and the performance evaluation is executed on a set of benchmark test functions. Subsequently, the fault diagnosis model of the wind turbine gearbox is built by using IQPSO algorithm and BP neural network. Results: According to the evaluation results, IQPSO is superior to PSO and QPSO algorithms. Also, compared with BP network, BP network trained by Particle Swarm Optimization (PSOBP) and BP network trained by Quantum Particle Swarm Optimization (QPSOBP), IQPSOBP has the highest diagnostic accuracy. Conclusion: The presented method provides a new reference for the fault diagnosis of wind turbine gearbox.

Download Full-text

Retraction Note to: Integral Backstepping Control of LPMSM Drive System Using Revised Recurrent Fuzzy NN and Mended Particle Swarm Optimization

International Journal of Fuzzy Systems ◽

10.1007/s40815-021-01067-0 ◽

2021 ◽

Author(s):

Chih-Hong Lin

Keyword(s):

Particle Swarm Optimization ◽

Particle Swarm ◽

Backstepping Control ◽

Drive System ◽

Swarm Optimization

Download Full-text

Quantitative Analysis for SF6 and its Compositions in GIS

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.562-564.1336 ◽

2012 ◽

Vol 562-564 ◽

pp. 1336-1339

Author(s):

Hai Lun Wang ◽

Jian Wei Shen

Keyword(s):

Neural Network ◽

Particle Swarm Optimization ◽

Quantitative Analysis ◽

Fault Diagnosis ◽

Traditional Method ◽

Particle Swarm ◽

Prediction Errors ◽

Swarm Optimization ◽

Training Analysis ◽

Derivatives Of

In this paper, a method for GIS equipment fault diagnosis by the analysis of volume fractions of the derivatives of SF6 gas inside GIS equipment is presented. For the method, based on the differential spectra method, a neural network model and the particle swarm optimization are used for training analysis of infrared spectra, to realize the quantitative analysis of specific derivatives. The experimental results show that the prediction errors obtained by particle swarm optimization training are markedly superior to prediction errors obtained using the traditional method.

Download Full-text

Power Transform Fault Diagnosis Based on the Adaptive Mutation Particle Swarm Optimization

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.756-759.3804 ◽

2013 ◽

Vol 756-759 ◽

pp. 3804-3808

Author(s):

Zhi Mei Duan ◽

Jia Tang Cheng

Keyword(s):

Neural Network ◽

Particle Swarm Optimization ◽

Fault Diagnosis ◽

Power Transformer ◽

Recognition Rate ◽

Particle Swarm ◽

Adaptive Mutation ◽

Bp Network ◽

Swarm Optimization ◽

Fault Recognition

In order to improve the accuracy of fault diagnosis of power transformer, in this paper, a method is proposed that optimize the weight of BP neural network by adaptive mutation particle swarm optimization (AMPSO). According to the characteristic of transformer fault, the optimized neural network is used to diagnose fault of the power transformer. Individual particles action is amended by this algorithm and local minima problems of the standard PSO and BP network are overcooked. The experimental results show that, the method can classify transformer faults, and effectively improve the fault recognition rate.

Download Full-text