Discriminating Threshold Selection Method and Diagnosis of Deteriorated Porcelain Insulator Based on Decision Tree

FU Weiping; SHI Fengxiang; WANG Wei; LIU Yunpeng; ZHANG Kaiyuan; PEI Shaotong

doi:10.13296/j.1001-1609.hva.2019.04.021

您当前的位置：

首页 >

文章列表页 >

Discriminating Threshold Selection Method and Diagnosis of Deteriorated Porcelain Insulator Based on Decision Tree

更新时间：2025-04-26

- Discriminating Threshold Selection Method and Diagnosis of Deteriorated Porcelain Insulator Based on Decision Tree
- High VoltageApparatus Vol. 55, Issue 4, Pages: 149-154(2019)
- 作者机构：
  
  1. 国网河北省电力公司检修分公司
  2. 华北电力大学电气工程系
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2019.04.021
  CLC： TM216
- Published：2019
- 稿件说明：
移动端阅览
[1]付炜平,施凤祥,王伟,刘云鹏,张凯元,裴少通.基于决策树的劣化瓷质绝缘子的判定阈值选择方法与诊断[J].高压电器,2019,55(04):149-154.

FU Weiping, SHI Fengxiang, WANG Wei, et al. Discriminating Threshold Selection Method and Diagnosis of Deteriorated Porcelain Insulator Based on Decision Tree[J]. High voltageapparatus, 2019, 55(4): 149-154.
[1]付炜平,施凤祥,王伟,刘云鹏,张凯元,裴少通.基于决策树的劣化瓷质绝缘子的判定阈值选择方法与诊断[J].高压电器,2019,55(04):149-154. DOI： 10.13296/j.1001-1609.hva.2019.04.021.

FU Weiping, SHI Fengxiang, WANG Wei, et al. Discriminating Threshold Selection Method and Diagnosis of Deteriorated Porcelain Insulator Based on Decision Tree[J]. High voltageapparatus, 2019, 55(4): 149-154. DOI： 10.13296/j.1001-1609.hva.2019.04.021.

摘要

通过观察辨识不同电压等级下输电线路中瓷质绝缘子的原始红外图像的特征

提出了一种基于决策树的劣化瓷质绝缘子的识别与判定的方法。在不同湿度温度下

传统的检测阈值变化较大

通过提取原始红外图像的数据

选取绝缘子串中单片绝缘子的钢帽温度、最大温度、钢帽瓷件温度差、绝缘子瓷件环境温度差、单片绝缘子的最大温升百分比及单片绝缘子温度方差这6个变量作为输入参数

以绝缘子绝缘程度的优劣作为输出

利用决策树

选择了最优检测阈值组合

建立了裂化绝缘子的智能检测模型。得出钢帽瓷件温度差及瓷件环境温度差为最优检测阈值组合这一结论

并利用这一阈值组合对红外图片进行了检测

测试结果显示平均正确率达到98.2%。该方法为劣化绝缘子的智能检测提供了新的思路

并通过实际实验证明了其可行性。

Abstract

By discerning the original infrared pictures of insulator strings under transmission lines of different voltage level

a deteriorated insulator diagnose model based on decision tree is proposed. As the traditional threshold changes a lot under different weather conditions

by utilizing decision tree

this paper selects the premium threshold combination and builds the deteriorated insulator diagnose model

choosing from the six alternative thresholds: the max temperature of single piece of insulator

the temperature of insulators steel-cap

the temperature difference between insulator steel-cap and porcelain

the temperature difference between insulator porcelain and environment

the temperature variance of single piece of insulator and the max temperature rise percentage of single piece of insulator. A conclusion that the temperature difference between insulator steel-cap and porcelain and the temperature difference between insulator porcelain and environment consist the premium threshold combination is obtained. The average accuracy reaches up to 98.2%. This method provides new approach for further research in detecting deteriorated insulator and tests in the laboratory attest the feasibility of the model.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Detection Method of Series Arc Fault Based on Instantaneous Reactive Power Theory

Fault Diagnosis of Transmission Line Icing Based on Decision Tree

Partial Discharge Pattern Recognition of High-voltage Cables Based on Random Forest Method

Related Author

REN Xue

GUO Fengyi

ZHU Lianyong

ZHANG Hongbo

FANG Zhipeng

LIANG Haihong

ZHOU ZANDong

GONG Hao

Related Institution

Liaoning Technical University

Huludao Power Supply Company,State Grid Liaoning Electric Power Supply Co.,Ltd.

Beichen Xinhui Company,State Grid Liaoning Electric Power Supply Co.,Ltd.

State Grid Liaoning Electric Power Supply Co., Ltd.

NARI Group Corporation

⁰