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

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 networks 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.

关键词： power transformer fault diagnosis BP neural network PSO-BP algorithm

作者: Sun Huiqin Xue Zhihong Sun Kejun Wang Suzhi Du Yun

作者单位: Hebei University of Technology,Tianjin,China;Hebei University of Science and Technology,Shijiazhuang Hebei University of Science and Technology,Shijiazhuang,China

会议类型: 国际会议

会议名称: 2012 International Conference on Intelligent System and Applied Material(2012智能系统与应用材料国际会议)(GSAM2012)

会议地点: 太原

会议语种:英文

页码: 789-793

在线出版日期: 2012-01-13（万方平台首次上网日期，不代表论文的发表时间）