Fault Diagnosis Analysis of Power Transformer Based on PSO-BP Algorithm

被引：1

作者：

Sun Huiqin ^{[1
,2
]}

Xue Zhihong ^{[2
]}

Sun Kejun ^{[2
]}

Wang Suzhi ^{[2
]}

Du Yun ^{[2
]}

机构：

[1] Hebei Univ Technol, Tianjin, Peoples R China

[2] Hebei Univ Sci & Technol, Shijiazhuang, Hebai, Peoples R China

来源：

INTELLIGENT SYSTEM AND APPLIED MATERIAL, PTS 1 AND 2 | 2012年 / 466-467卷

关键词：

power transformer; fault diagnosis; BP neural network; PSO-BP algorithm;

D O I：

10.4028/www.scientific.net/AMR.466-467.789

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

BP neural network is currently the most widely used of neural network models in practical application in transformer fault diagnosis. BP algorithm is a local search algorithm which is easy to make the network into the local minimum values. Network training results are poor. It discusses PSO-BP algorithm which combines the particle swarm optimization (PSO) algorithm with the BP algorithm in this paper. It uses PSO algorithm to optimize the BP network's weights and threshold. It is used in power transformer fault diagnosis. Experimental data results show that PSO-BP network fault diagnosis accuracy is higher than BP algorithm.

引用

页码：789 / +

页数：2