改进粒子群优化神经网络的变压器故障诊断 

乔维德 
无锡开放大学，江苏 无锡 214011 
 

摘 要：在分析传统误差反向传播(BP) 算法和标准粒子群优化(PSO) 算法的特征及其问题基础上，提出一种改进粒子群优化(IPSO) 算法和改进BP(IBP) 算法，建立基于IPSO-IBP 混合算法的电力变压器神经网络故障诊断模型。通过85 组训练样本和16 组测试样本的仿真对比分析，该方法能够实现电力变压器不同故障的有效诊断，提高了电力变压器故障模式的识别能力及故障诊断准确率。
关键词：电力变压器；IPSO-IBP；故障诊断
中图分类号：TM407 文献标识码：A 文章编号：1007-3175(2015)12-0024-04

Transformer Fault Diagnosis Based on Neural Network with Improved Particle Swarm Optimization 

QIAO Wei-de 
Wuxi Open University, Wuxi 214011, China 
 

Abstract: Based on analysis characteristics and problems of traditional error back propagation (BP) algorithm and standard particle swarm optimization (PSO) algorithm, this paper proposed an improved particle swarm optimization (IPSO) algorithm and an improved BP (IBP) algorithm, and established a model of neural network for power transformer fault diagnosis based on IPSO-IBP hybrid algorithm. By simulation comparison and analysis of 85 groups training samples and 16 groups test samples, this method can realize the effective diagnosis for different power transformer faults and improve the recognition ability of power transformer fault mode with high accuracy
Key words: power transformer; improved particle swarm optimization-improved back propagation; fault diagnosis

参考文献
[1] 乔维德. 基于改进PSO-BP神经网络的短期电力负荷预测研究[J]. 继电器，2007，35(17)：17-21.
[2] 程加堂，熊伟，徐绍坤，艾莉. 基于改进粒子群优化神经网络的电力变压器故障诊断[J]. 高压电器，2012，48(2)：42-45.
[3] 付宝英，王启志. 自适应粒子群优化BP神经网络的变压器故障诊断[J]. 华侨大学学报：自然科学版，2013，34(3)：262-266.