Assessment of Aging State of Transformer Oil-paper Insulation Based on Time Domain Dielectric Method and Dynamic Bayesian Network

WU Jinyuan; XIA Guoqiang; LI Tong; GAO Bo; WU Guangning

doi:10.13296/j.1001-1609.hva.2019.10.032

您当前的位置：

首页 >

文章列表页 >

Assessment of Aging State of Transformer Oil-paper Insulation Based on Time Domain Dielectric Method and Dynamic Bayesian Network

更新时间：2025-04-26

- Assessment of Aging State of Transformer Oil-paper Insulation Based on Time Domain Dielectric Method and Dynamic Bayesian Network
- High VoltageApparatus Vol. 55, Issue 10, Pages: 196-203(2019)
- 作者机构：
  
  西南交通大学电气工程学院
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2019.10.032
  CLC： TM855
- Published：2019
- 稿件说明：
移动端阅览
[1]吴晋媛,夏国强,李通,高波,吴广宁.基于时域介电法和动态贝叶斯网络的变压器油纸绝缘老化状态评估[J].高压电器,2019,55(10):196-203.

WU Jinyuan, XIA Guoqiang, LI Tong, et al. Assessment of Aging State of Transformer Oil-paper Insulation Based on Time Domain Dielectric Method and Dynamic Bayesian Network[J]. High voltageapparatus, 2019, 55(10): 196-203.
[1]吴晋媛,夏国强,李通,高波,吴广宁.基于时域介电法和动态贝叶斯网络的变压器油纸绝缘老化状态评估[J].高压电器,2019,55(10):196-203. DOI： 10.13296/j.1001-1609.hva.2019.10.032.

WU Jinyuan, XIA Guoqiang, LI Tong, et al. Assessment of Aging State of Transformer Oil-paper Insulation Based on Time Domain Dielectric Method and Dynamic Bayesian Network[J]. High voltageapparatus, 2019, 55(10): 196-203. DOI： 10.13296/j.1001-1609.hva.2019.10.032.

摘要

为了能够实现对变压器油纸绝缘老化状态的准确评估

文中在极化/去极化电流方法的基础上

提出6种表征油纸老化的特征量

并将动态贝叶斯网络引入到油纸绝缘老化状态评估问题中

建立了相应的老化阶段预测模型

针对该模型进行了实例验证。结果表明:从PDC及拓展Debye模型提取的绝缘纸电量Q

paper

、稳定平均电导电流■以及平均极化时间常数■对油纸老化状态反映敏感

且与聚合度有良好的拟合关系

可作为表征绝缘纸老化的特征量;油纸绝缘老化状态评估问题符合动态贝叶斯网络的应用条件

通过划分特征量状态及老化阶段

可以反映变量之间的时序关系;油纸老化状态评估模型验证的准确度为91.3%

平均相对误差为0.108

故验证了动态贝叶斯网络应用于油纸绝缘老化状态评估的准确性和稳定性。

Abstract

In order to make an accurate assessment of the oil-paper insulation aging state of transformers

six characteristic quantities are extracted based on polarization/depolarization current method.Dynamic Bayesian network is introduced into the assessment of oil-paper insulation aging state

and an aging step prediction model that verified by the experiment is established.The results indicate that:the quantity of insulation paper electricity Q

paper

the stable average conduction current ■

and the average polarization characteristic time ■ are sensitive to oil-paper insulation aging state

and fit well

with the degree of polymerization

so that

these can be used as characteristics to represent the aging of insulation paper.The assessment of oil-paper insulation is in accordance with the application conditions of dynamic Bayesian network

by dividing the characteristics state and aging stage

it can reflect the timing relationship between variables.The accuracy of the assessment model of oil-paper insulation aging state is 91.3%

relative average error is 0.108.So the accuracy and stability of applying dynamic Bayesian network to the assessment of oil-paper insulation aging state.

关键词

Keywords

references

Views

143

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Influencing Factors on Frequency-domain Dielectric Spectroscopy of Oil-paper Insulation System

Research on Vibration Defect Detection Method of GIS Based on Singular Spectrum Analysis and Decision Tree

Spatial Localization of Dry-type Reactor Discharge Based on Push-sweep SiC Solar-blind Ultraviolet Array

Research on Mechanical Fault Mechanism Analysis and Feature Extraction Technology Based on Low Voltage DC Circuit Breaker

Identification of Typical Construction Defects in 10 kV Cable Intermediate Joints Based on Canny Algorithm and Image Processing

Related Author

PENG Hua-dong1

DONG Ming1

WU Xue-zhou1

MIAO Jin1

LI Hong-jie1

DENG Wei2

LIU Wei-dong2

TENG Yun

Related Institution

State Key Laboratory of Electrical Insulation and Power Equipment, Xi’an Jiaotong University

The UHV Administration of Hunan Electric Power Corporation

State Grid Laboratory of GIS Operation and Maintenance Technology, State Grid Jiangsu Electric Power Co., Ltd. Research Institute

Shanghai Rhythm Electronics Technology Co., Ltd.

Wuling Power Corporation Limited

⁰