Transformer Fault Prediction Based on Time Series and Support Vector Machine

HUANG Xinbo; JIANG Weitao; ZHU Yongcan; TIAN Yi

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Transformer Fault Prediction Based on Time Series and Support Vector Machine

更新时间：2025-12-08

- Transformer Fault Prediction Based on Time Series and Support Vector Machine
- Vol. 46, Issue 7, Pages: 2530-2538(2020)
- 作者机构：
  
  西安工程大学电子信息学院
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published Online：31 July 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
HUANG Xinbo, JIANG Weitao, ZHU Yongcan, et al. Transformer Fault Prediction Based on Time Series and Support Vector Machine[J]. 2020, 46(7): 2530-2538.
DOI：

HUANG Xinbo, JIANG Weitao, ZHU Yongcan, et al. Transformer Fault Prediction Based on Time Series and Support Vector Machine[J]. 2020, 46(7): 2530-2538. DOI：

摘要

电力变压器故障预测可实现对变压器故障的早期预警

对保证电力系统的正常运行具有重要意义。该文提出了一种基于时间序列和支持向量机（SVM）的变压器故障预测模型。该模型以时间序列分析中的自回归积分滑动平均模型（ARIMA）为基础

采用遗传算法（GA）对ARIMA模型参数p和q进行定阶

并利用定阶后的时间序列模型对变压器油中溶解气体进行预测

然后利用基于网格搜索算法（GS）优化后的SVM模型对预测出的油中溶解气体进行诊断。运行结果表明

该模型的预测准确率可达89.66%

而利用GM–SVM、ARIMA–SVM和GA–ARIMA–ANN得到的预测准确率分别为58.62%、79.31%、75.86%。因此

所提出模型有更高的预测准确率。

Abstract

The fault prediction of power transformer can realize the early warning of transformer fault

which is vital to ensure the normal operation of the electric power system. A transformer fault prediction model based on time series and support vector machine（SVM） is presented in this paper. The model is based on the autoregressive integral moving average（ARIMA） model in time series analysis

and the parameters p and q of ARIMA model are determined by genetic algorithm（GA）. The dissolved gas in transformer oil is predicted by the time series model after parameter determination. Then the SVM model optimized by grid search algorithm（GS） is used to predict the dissolved gas in oil. The running results show that the accuracy of transformer fault prediction model can reaches 89.66%

while the prediction accuracy of GM-SVM

ARIMA-SVM and GA-ARIMA-ANN is 58.62%

79.31% and 75.86%

respectively. So the method proposed in this paper has the higher prediction accuracy.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application of Bagging-CART Algorithm Optimized by Genetic Algorithm in Transformer Fault Diagnosis

Short-term Forecast for Transmission Line Icing by Time Series Analysis and Kalman Filtering

Transformer Fault Identification Method Based on VSRP and β-GWO-SVM

Prediction Model of Dissolved Gas in Transformer Oil Based on Variational Modal Decomposition and Recurrent Neural Network with Gated Recurrent Unit

变压器健康状态实时预警方法及可解释性分析

Related Author

HUANG Xinbo

LI Wenjunzi

SONG Tong

WANG Yanmei

HUANG Xinbo

LI Hongbo

ZHU Yongcan

WANG Yuxin

Related Institution

School of Electronic Information, Xi’an Polytechnic University

Henan Special Equipment Safety Inspection Institute

College of Electronics and Information, Xi’an Polytechnic University

School of Electro-Mechanical Engineering,Xidian University

College of Electrical and Control Engineering, Liaoning Technical University

AI问答

⁰