Transformer Fault Diagnosis Based on BP Neural Network Optimized by Fuzzy Clustering and LM Algorithm

SONG Zhi-Jie; WANG Jian

doi:10.13296/j.1001-1609.hva.2013.05.001

您当前的位置：

首页 >

文章列表页 >

Transformer Fault Diagnosis Based on BP Neural Network Optimized by Fuzzy Clustering and LM Algorithm

更新时间：2025-04-26

- Transformer Fault Diagnosis Based on BP Neural Network Optimized by Fuzzy Clustering and LM Algorithm
- High VoltageApparatus Vol. 49, Issue 5, Pages: 54-59(2013)
- 作者机构：
  
  华南理工大学电力学院
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2013.05.001
  CLC： TP18;TM407
- Published：2013
- 稿件说明：
移动端阅览
[1]宋志杰,王健.模糊聚类和LM算法改进BP神经网络的变压器故障诊断[J].高压电器,2013,49(05):54-59.

SONG Zhi-Jie, WANG Jian. Transformer Fault Diagnosis Based on BP Neural Network Optimized by Fuzzy Clustering and LM Algorithm[J]. High voltageapparatus, 2013, 49(5): 54-59.
[1]宋志杰,王健.模糊聚类和LM算法改进BP神经网络的变压器故障诊断[J].高压电器,2013,49(05):54-59. DOI： 10.13296/j.1001-1609.hva.2013.05.001.

SONG Zhi-Jie, WANG Jian. Transformer Fault Diagnosis Based on BP Neural Network Optimized by Fuzzy Clustering and LM Algorithm[J]. High voltageapparatus, 2013, 49(5): 54-59. DOI： 10.13296/j.1001-1609.hva.2013.05.001.

摘要

在变压器故障诊断中

目前BP神经网络算法存在训练样本分布不均匀

收敛速度慢、容易陷于局部极小点等问题

导致整体的诊断性能下降。通过对模糊聚类及LM算法改进的神经网络深入研究

并引入变压器故障诊断中

该算法应用模糊聚类对搜集到的样本预处理

提高样本的质量

再用LM算法改进的神经网络来优化搜索方向

可以实现网络训练速度及测试精度的提高。通过实例仿真实验

验证了该方法能够有效诊断出变压器的故障。

Abstract

Some problems of traditional BP neutral network algorithm existed in transformer fault diagnosis

such as uneven distribution of training samples

slow convergence speed and easy to fall into local minimum points

which resulted in the whole diagnosis performance slow.In this paper an improving neutral network based on fuzzy clustering and LM algorithm is proposed and applied to transformer fault diagnosis.The algorithm improves quality of the sample by pretreating collected samples using fuzzy clustering and speeds up network training and enhances accuracy of network training by optimizing the search direction using the neutral network based on LM algorithm. The simulation experiments show the method can effectively diagnose transformer fault.

关键词

Keywords

references

Views

990

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fault Diagnosis of Transformer Based on BP Neural Network and ACS-SA

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

Fault Diagnosis Algorithm on Spring Operating Mechanism for High Voltage Circuit Breaker and Load Switch Based on Motor Current

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

New Approach to Transformer Fault Diagnosis Based on ANN

Related Author

LI Xiaozhu

CHEN Zhijun

FAN Xiaochao

XU Qidan

LU Jian

HE Teng

YE Yulin

LIU Sen

Related Institution

Xinjiang University

China Nuclear Power Engineering Co., Ltd.

School of Electrical Engineering, Hebei University of Science and Technology

Hebei Provincial Key Laboratory of Electromagnetic & Structural Performance of Power Transmission and Transformation Equipment, Baoding Tianwei Baobian Electric Co., Ltd.

Baoding Tianweixinyu Technology Development Co., Ltd.

⁰