Application of Neural Network Based on Improved Particle Swarm Optimization in the Condition Monitoring of Transformer

JIA Rong1; LI Hong-bin2; KANG Hui-xi2; HONG Gang1

doi:10.13296/j.1001-1609.hva.2010.05.026

您当前的位置：

首页 >

文章列表页 >

Application of Neural Network Based on Improved Particle Swarm Optimization in the Condition Monitoring of Transformer

更新时间：2025-04-26

- Application of Neural Network Based on Improved Particle Swarm Optimization in the Condition Monitoring of Transformer
- High VoltageApparatus Vol. 46, Issue 5, Pages: 14-17+21(2010)
- 作者机构：
  
  1. 西安理工大学电力工程系
  2. 甘肃电投河西水电开发有限责任公司
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2010.05.026
  CLC： TM407
- Published：2010
- 稿件说明：
移动端阅览
[1]贾嵘,李宏斌,康会西,洪刚.改进粒子群优化神经网络在变压器故障诊断中的应用[J].高压电器,2010,46(05):14-17+21.

JIA Rong1, LI Hong-bin2, KANG Hui-xi2, et al. Application of Neural Network Based on Improved Particle Swarm Optimization in the Condition Monitoring of Transformer[J]. High voltageapparatus, 2010, 46(5): 14-17+21.
[1]贾嵘,李宏斌,康会西,洪刚.改进粒子群优化神经网络在变压器故障诊断中的应用[J].高压电器,2010,46(05):14-17+21. DOI： 10.13296/j.1001-1609.hva.2010.05.026.

JIA Rong1, LI Hong-bin2, KANG Hui-xi2, et al. Application of Neural Network Based on Improved Particle Swarm Optimization in the Condition Monitoring of Transformer[J]. High voltageapparatus, 2010, 46(5): 14-17+21. DOI： 10.13296/j.1001-1609.hva.2010.05.026.

摘要

变压器绕组早期故障的诊断是实现安全生产、避免大事故的技术前提。由于变压器器身振动信号包含有丰富的信息

所以可以通过监测变压器振动信号来预估绕组的状况。笔者首先利用小波包分解原理将变压器振动信号分解到不同的频段中

然后计算各频段的能量熵值

并将其作为BP神经网络的输入向量

同时利用改进粒子群算法（IPSO）对BP神经网络进行优化。最后利用训练好的BP神经网络对变压器进行故障诊断。试验结果表明:与传统BP神经网络法和PSO-BP神经网络方法相比

该方法克服了BP神经网络的一些缺陷

具有较快的收敛速度和较高的诊断精度

对变压器绕组的早期故障具有良好的预测能力。

Abstract

Incipient fault diagnosis in windings is the technical prerequisite for safety operation.The vibration signal of transformer winding is correlative with the conditions of winding compression and loosening

and vibration method is an effective method used for monitoring the conditions of winding.In this paper

wavelet packet is used to decompress the vibration signal into different frequency bands.Wavelet packet-energy entropy（WP-EE）is then extracted to construct characteristic vectors of signals and is used as an input of the back propagation（BP）neural network

which is optimized by improved particle swarm optimization（IPSO）.Finally

the fault diagnosis is accomplished by the BP neural network based on IPSO.The experimental results show that the IPSO-BP improves the BP neural network generalization capacity

and the convergence of method is faster and forecast accuracy is higher than that of the traditional BP neural network and PSO-BP.Therefore

the method can be used to forecast the fault diagnosis of transformer’s winding.

关键词

Keywords

references

Views

499

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Power Transformer Fault Diagnosis via Neural Network Based on Particle Swarm Optimization with Neighborhood Operator

Dissolved Gas Analysis Based QPSO-BP Model for Transformer Fault Diagnosis

Improved Mechanical Fault Diagnosis Technology of Transformer Based on Similarity of Vibration Signal Characteristic Matrix

Fault Diagnosis Model of Transformer Based on GJO Feature Optimization and AO-RF

Research on Diagnosis Method of Transformer Winding Deformation Fault Based on Dynamic Time Warping

Related Author

JIA Rong

XU Qi-hui

LI Hui

LIU Wei

CHENG Jiatang

DUAN Zhimei

XIONG Yan

AI Li

Related Institution

College of Electrical Engineering,Xi’an University of Technology

西安理工大学电力工程系陕西西安710048

The Engineering College of Honghe University

State Grid Shanxi Yangquan Power Supply Company

Sichuan University

⁰