Effective Operating Life Estimation Method of Lightning Arrester Based on Adaptive Neural Fuzzy Reasoning System

LIU Wei

doi:10.13296/j.1001-1609.hva.2024.06.017

您当前的位置：

首页 >

文章列表页 >

Effective Operating Life Estimation Method of Lightning Arrester Based on Adaptive Neural Fuzzy Reasoning System

Research & Analysis | 更新时间：2025-04-26

- Effective Operating Life Estimation Method of Lightning Arrester Based on Adaptive Neural Fuzzy Reasoning System
- High Voltage Apparatus Vol. 60, Issue 6, Pages: 129-137(2024)
- 作者机构：
  
  国家管网集团西气东输公司，上海　 200122
- 作者简介：
- 基金信息：
  
  Key Project of Science and Technology Department of Gansu Province(20228100871)
- DOI：10.13296/j.1001-1609.hva.2024.06.017
  CLC：
- Received：21 January 2024，
  
  Revised：29 March 2024，
  
  Published：16 June 2024
- 稿件说明：
移动端阅览
LIU Wei. Effective Operating Life Estimation Method of Lightning Arrester Based on Adaptive Neural Fuzzy Reasoning System[J]. High voltage apparatus, 2024, 60(6): 129-137.
DOI：

LIU Wei. Effective Operating Life Estimation Method of Lightning Arrester Based on Adaptive Neural Fuzzy Reasoning System[J]. High voltage apparatus, 2024, 60(6): 129-137. DOI： 10.13296/j.1001-1609.hva.2024.06.017.

摘要

估算金属氧化物避雷器的使用寿命一直是一项挑战，它决定着输电系统的安全稳定运行。基于此，文中提出了一种基于自适应神经模糊推理系统（adaptive neuro-fuzzy inference system，ANFIS）和支持向量机回归（support vector machine for regression，SVR）组成的组合时间序列预测模型，用于估算金属氧化物避雷器（metal oxide surge arrester，MOSA）的使用寿命。首先，文中进行了现场测量，考虑到该分量是避雷器监测中最常用的MOSAs劣化水平指标之一，以建立由泄漏电流三次谐波分量值组成的时间序列数据库；接着，利用ANFIS、SVR和仿真数据库，建立组合预测模型；随后，文中使用3种类型的误差：即

MSE

、

MAE

和

MAPE

评估预测模型的性能。最后，在对模型进行评估之后，利用所提模型对MOSA的使用寿命估算，研究结果表明，使用组合模型预测比基于ANFIS和SVR的模型提供的预测更准确，可提升估算MOSA使用寿命的精度18.9%。

Abstract

It is always a challenge to estimate the service life of metal oxide arrester

which determines safe and stable operation of transmission systems. Based on this

a kind of combined time series prediction model (SVR) consisting of adaptive neural-fuzzy inference system (ANFIS) and support vector machine for regression (SVM) is proposed in this paper for estimating the service life of the metal oxide surge arrester (MOSA). Firstly

the measurement at site is carried out in this paper. Considering that this component is one of the most commonly used data of MOSAs deterioration level in arrester monitoring

a time series database which is composed of

the third harmonic component values of leakage current is set up; Then

the combined prediction model using ANFIS

SVR and simulation database is set up; After that

such three types of errors as

MSE

MAE

and

MAPE

are used to assess and predict performance of the model. Finally

after assessment of the model

the proposed model is used to estimate the service life of the MOSA. The research results show that the use of combined model for prediction is more accurate than the model based on ANFIS and SVR

and the service life estimation accuracy of the MOSA can be improved by 18.9%.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Design and Development of 1 200 kV Compact DC High Voltage Generator with Closed Gas Insulation Structure

Aging State Assessment of Cable Sheath Protector Based on High-order Harmonic Ratio of Leakage Current

Leakage Current Analysis and Classification of Discharge State Identification of Insulator Based on HHT

A Digital Counter for Lightning Surge and Switching Surge Recording

ON-LINE MONITORING OF POLLUTION LEAKAGE CURRENT FOR OUTDOOR INSULATORS IN SUBSTATION

Related Author

张杰

聂德鑫

程林

吴维宁

ZHANG Yilin

ZHUANG Li

HU Tao

SUN Aoqi

Related Institution

State Grid Electric Power Research Institute

Wuhan Nari Limited Liability Company of State Grid Electric Power Research Institute

School of Electrical and New Energy, China Three Gorges University

School of Electrical Engineering and New Energy, Three Gorges University

武汉水利电力大学

⁰