Application of BP Neural Network Based on Immune Particle Swarm Optimization for Fault Diagnosis of Power Transformer

Abstract:

Cloing and hypermutation of immune theory were used in optimization on particle swarm optimization (PSO), an immune particle swarm optimization (IPSO) algorithm was proposed , which overcome the problem of premature convergence on PSO. IPSO was used in BP Neural Network training to overcome slow convergence speed and easily getting into local dinky value of gradient descent algorithm. BP Neural Network trained by IPSO was used to fault diagnosis of power transformer, it has high accuracy after experimental verification and to meet the power transformer diagnosis engineering requirements.

• Periodical: Applied Mechanics and Materials (Volumes 448-453)
• Pages: 3605-3609
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.448-453.3605
• Online since: October 2013
• Authors: Yu Xin Zhang*, Yu Liu
• Keywords: BP Neural Network (BPNN), Cloing, Fault Diagnosis, Hypermutation, PSO

References

[1] WANG Xiao-xia, WANG Tao: Ei. High Voltage Engineering. Vol. 34-11 (2008): 735~740. In Chinese.

[2] DUAN Hui-da, LIU Xue-jun, LIU Wen-bin: Electrotechnical Application. Vol. 26-7 (2007): 28~30. In Chinese.

[3] WANG Chu-jiao, XIA Shi-xiong, NIU Qiang: Ei. ACTA electronica sinica. Vol. 38-2A (2010): 94~98. In Chinese.

[4] LIU Yu, ZHANG Yu-xin: Metallurgical Industry Automation. Vol. 36-4 (2012): 20~22. In Chinese.

[5] WANG Qiao-ling, GAO Xiao-zhi, WANG Chang-hong, LIU Fu-rong: Ei. Control and Decision. Vol. 23-9 (2008): 1073~1076. In Chinese.