Research on Condition Perception Method of Transformers via Information Attribute Reduction Technique

TAO Fengbo; WANG Tonglei; XU Yaoyu; WEI Chao; LI Yuan; ZHANG Guanjun

doi:10.13296/j.1001-1609.hva.2020.09.009

您当前的位置：

首页 >

文章列表页 >

Research on Condition Perception Method of Transformers via Information Attribute Reduction Technique

更新时间：2025-04-26

- Research on Condition Perception Method of Transformers via Information Attribute Reduction Technique
- High VoltageApparatus Vol. 56, Issue 9, Pages: 60-66(2020)
- 作者机构：
  
  1. 国网江苏省电力公司电力科学研究院
  2. 西安交通大学电力设备电气绝缘国家重点实验室
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2020.09.009
  CLC： TM41
- Published：2020
- 稿件说明：
移动端阅览
[1]陶风波,王同磊,徐尧宇,蔚超,李元,张冠军.基于信息属性约简技术的变压器状态感知方法研究[J].高压电器,2020,56(09):60-66.

TAO Fengbo, WANG Tonglei, XU Yaoyu, et al. Research on Condition Perception Method of Transformers via Information Attribute Reduction Technique[J]. High voltageapparatus, 2020, 56(9): 60-66.
[1]陶风波,王同磊,徐尧宇,蔚超,李元,张冠军.基于信息属性约简技术的变压器状态感知方法研究[J].高压电器,2020,56(09):60-66. DOI： 10.13296/j.1001-1609.hva.2020.09.009.

TAO Fengbo, WANG Tonglei, XU Yaoyu, et al. Research on Condition Perception Method of Transformers via Information Attribute Reduction Technique[J]. High voltageapparatus, 2020, 56(9): 60-66. DOI： 10.13296/j.1001-1609.hva.2020.09.009.

摘要

及时准确和高效地感知变压器健康状态对提升电网运行安全性和供电可靠性具有重要意义。针对当前变压器状态感知和故障诊断中状态信息不完备、多状态信息孤立和无法有效融合等问题

文中结合信息属性约简技术和遗传算法提出了一种变压器状态感知方法。通过分析变压器信息决策表中信息属性依赖度

结合遗传算法约简决策表中冗余的信息属性

求解获得变压器信息决策表的最优属性核

最后通过信息属性的优选

匹配待评估变压器的检测信息实现变压器状态感知及故障诊断。根据变压器实际故障案例验证了所述方法的可行性和有效性。与传统方法相比

通过该方法在变压器状态感知及故障诊断方面具有较高的计算效率和诊断准确率（诊断准确率为84%）。

Abstract

It is of great significance for power transformers to achieve accurate and efficient condition perception which can improve the reliability and safety of power system.In order to address the problems of incomplete

isolated and unable to effectively integrate information in condition perception of transformers

we propose an information reduction method based on attribute dependency theory and genetic algorithm to achieve the condition perception of transformers.This method employs attribute dependency theory to reduce redundant information attributes via genetic algorithm and obtains the optimal attribute cores.The optimal attribute cores are further used to match the undiagnosed data of a transformer for condition perception.Additionally

the feasibility and validity of the proposed method are verified by transformer fault cases in this paper.Compared with typical attribute reduction methods

our method has higher efficiency and accuracy in transformer state perception and fault diagnosis（fault diagnosis of transformers has 84% accuracy）.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Optimization Design on Spring Contact Finger Structure Based on Finite Element Method and Neural Network Method

Study on Diagnosis Method of Power Transformer Winding Deformation Based on Signal Distance Degree Model and SVM

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

OPTIMIZATION OF CURRENT TRANSFORMER’S PARAMETERS BASED ON GENETIC ALGORITHM

Artificial Intelligence Method for Transformer’s State Diagnosis Based on Oil-chromatogram Examination

Related Author

DAN Shuheng

SU Juntian

CHENG Junjie

TANG Xuan

XU Yanchun

ZHANG Lei

WU Lin

JI Yiwei

Related Institution

College of Electrical Engineering, Shanghai University of Electric Power

State Grid Hubei Electric Power Company Technology and Training Center

College of Electrical Engineering and New Energy, China Three Gorges University

School of Automation, Northwest University of Technology

Lijiang Power Supply Bureau of Yunnan Power Grid Co., Ltd.

⁰