The Application of DPSO - BP Neural Network in GIS Partial Discharge Typical Defects Recognition

Abstract:

The BP neural network is a classifier commonly used in partial discharge type recognition, but the traditional BP algorithm with defects cannot satisfy the actual need. So the optimization algorithm of BP network was studied intensively. DPSO algorithm was used for optimizing the network, and DPSO-BP algorithm is applied to analyze typical defects of GIS, which can be identified by the types of partial discharge. Compared with traditional BP algorithm, DPSO-BP algorithm occupied obvious advantage in recognition effect. It has improved the learning speed of the algorithm, effectively avoid network training going into local minimum point, and maintain the generalization ability and fault tolerance of BP neural network at the same time.

• Periodical: Advanced Materials Research (Volumes 889-890)
• Pages: 1078-1084
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.889-890.1078
• Online since: February 2014
• Authors: Ze Kun Liu*, Hong Yu, Tie Qiao Guo, Cheng Long Xu, Zhi Wan Cheng
• Keywords: Defect, Dynamic Particle Swarm Optimization (PSO) Algorithm, GIS, Neural Network (NN), Partial Discharge (PD)

References

[1] Xiaorong Wang, Minzhong Yang, Ming Dong. Characteristic parameter selection method of the partial discharge pulse based on neural network[J]. Electrical Engineering Technology, 2002, 17(3). (in Chinese).

[2] Xiaorong Dan, Rui Wang, g Li Yan. Pattern recognition based on artificial neural network[J]. Image And Aided Design, 2007(2): 87-89. (in Chinese).

[3] Zhen Ji, Huilian Liao, Qinghua Wu. Particle swarm optimization (PSO) algorithm and its application [M]. Beijing: Science Press, 2009. (in Chinese).

[4] Wei-Dong Wang, Xianping Zhao, Dada Wang. Analysis and research of GIS partial discharge detection method[J]. High-Voltage Electrical Apparatus, 2012(48): 13-17. (in Chinese).

[5] Kai Gao, Hao Ni, Wenrong SI. Detection and characteristic analysis of GIS partial discharge[J]. East China Electric Power，2010，38(10)：1512-1517. (in Chinese).

[6] Yan Xiao, Weiyong Yu. Present search of on-line partial discharge monitoring system in GIS[J]. High Voltage Engineering，2005，31(1)：47-49. (in Chinese).