本文已被：浏览 1396次 下载 529次
投稿时间：2014-05-24
投稿时间：2014-05-24
中文摘要: 引入动态变异操作来优化粒子群算法,同时将改进的粒子群优化算法和误差反向传播的算法相结合,构成混合算法,用于训练人工神经网络,并将该混合算法应用于变压器的故障诊断.仿真结果表明,该算法具有较快的收敛速度和较高的计算精度;诊断结果表明,该算法有利于提高变压器故障诊断的正确率.
Abstract:A dynamic mutation operation is introduced to the particle swarm optimization(PSO), and the improved PSO and back propagation(BP) algorithm is combined to form hybrid algorithm for training artificial neural networks. Applying the hybrid algorithm to the transformer fault diagnosis, the results show that this hybrid algorithm has a faster convergence speed and higher accuracy. And the diagnostic results show that this hybrid algorithm can improve the accuracy of the transformer fault diagnosis.
keywords: particle swarm optimization error back propagation dynamic mutation transformer fault diagnosis
文章编号：20140311 中图分类号： 文献标志码：
基金项目:上海市"科技创新行动计划"高新技术领域重点科研项目(14511101200)
| 作者 | 单位 | |
| 张国祥 | 上海电力学院自动化工程学院 | zgx_1988@foxmail.com |
| 袁丹 | 国网浙江宁波市鄞州区供电公司 | |
| 张浩 | 上海电力学院自动化工程学院 | |
| 彭道刚 | 上海电力学院自动化工程学院 |
引用文本：
张国祥,袁丹,张浩,等.基于改进PSO-BP神经网络的变压器故障诊断[J].上海电力大学学报,2014,30(3):243-247.
ZHANG Guoxiang,YUAN Dan,ZHANG Hao,et al.Transformer Fault Diagnosis Based on the Improved PSO-BP Neural Network[J].Journal of Shanghai University of Electric Power,2014,30(3):243-247.
张国祥,袁丹,张浩,等.基于改进PSO-BP神经网络的变压器故障诊断[J].上海电力大学学报,2014,30(3):243-247.
ZHANG Guoxiang,YUAN Dan,ZHANG Hao,et al.Transformer Fault Diagnosis Based on the Improved PSO-BP Neural Network[J].Journal of Shanghai University of Electric Power,2014,30(3):243-247.