[1]郑 宏,鲍美军,李 孟,等. 基于线圈电流相轨迹-XGBoost的高压断路器故障诊断方法[J].机械与电子,2026,44(02):72-78.
　ZHENG Hong,BAO Meijun,LI Meng,et al. Fault Diagnosis Method for High-voltage Circuit Breakers Based on Coil Current Phase Trajectory and XGBoos[J].Machinery & Electronics,2026,44(02):72-78.
点击复制

 基于线圈电流相轨迹-XGBoost的高压断路器故障诊断方法()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
44
期数:
2026年02期
页码:
72-78
栏目:
智能检测
出版日期:
2026-02-26

文章信息/Info

Title:
 Fault Diagnosis Method for High-voltage Circuit Breakers Based on Coil Current Phase Trajectory and XGBoos
文章编号:
1001-2257(2026)02-0072-07
作者:
 郑 宏1; 鲍美军1; 李 孟1; 孙文星2; 卓坚熊2; 郭胡森3; 万书亭3
 (1.杭州柯林电气股份有限公司,浙江 杭州 310015;2.广东电网有限责任公司,广东 广州 510080;
3.华北电力大学 河北省电力机械装备健康维护与失效预防重点实验室,河北 保定 071003)
Author(s):
 ZHENG Hong1; BAO Meijun1; LI Meng1; SUN Wenxing2; ZHUO Jianxiong2; GUO Husen3; WAN Shuting3
 (1.Hangzhou Kelin Electric Co.,Ltd.,Hangzhou 310015,China;
2.Guangdong Power Grid Co.,Ltd.,Guangzhou 510080,China;3.Hebei Key Laboratory of Electric Machinery
Health Maintenance and Failure Prevention,North China Electric Power University,Baoding 071003,China)
关键词:
高压断路器; 线圈电流; XGBoost模型; 相空间重构; 故障诊断
Keywords:
 ; high voltage circuit breaker; coil current; XGBoost model; phase space reconstruction; fault diagnosis
分类号:
TM561
文献标志码:
A
摘要:
针对高压断路器故障识别中存在的特征提取较为单一、诊断算法依赖参数选择等问题,提出一种基于线圈电流相轨迹XGBoost的高压断路器故障诊断方法。首先分析分/合闸线圈电流的李雅普诺夫指数,指出了断路器发生故障时的线圈电流混沌变化特性,基于平均互信息计算方法优化重构的延迟时间参数,进行电流信号的相空间重构。然后基于电流信号的相空间重构轨迹提取故障特征,形成由线圈电流相轨迹横坐标最大值、纵坐标最大值、内转折点到原点的欧氏距离和原点矩组成的特征向量,作为XGBoost识别模型的特征向量进行训练和故障识别,得到了准确的诊断结果。最后与峰值谷值特征、全局特征,以及SVM、KNN、RF和BP等模型进行对比分析,结果显示了所提方法在高压断路器故障诊断方面的优越性。
Abstract:
To address issues in high voltage circuit breaker fault identification,such as relatively singular feature extraction and diagnostic algorithms’ dependency on parameter selection,a fault diagnosis method based on coil current phase trajectory and XGBoost is proposed.Firstly,the Lyapunov exponent of the opening/closing coil current is analyzed,revealing the chaotic variation characteristics of the coil current when a circuit breaker fault occurs.The delay time parameter for reconstruction is optimized using the average
mutual information calculation method,followed by phase space reconstruction of the current signal.Subsequently,the fault features are extracted based on the phase space reconstruction trajectory.A feature vector is formed,comprising the maximum abscissa value and maximum ordinate value of the coil current phase trajectory,the Euclidean distance from internal turning points to the origin,and the origin moment.This vector serves as the input for the XGBoost identification model for training and fault recognition,yielding accurate diagnostic results.Finally,comparative analyses with the peak valley features,global features,and models such as SVM,KNN,RF and BP demonstrate the superiority of the phase trajectory XGBoost fault identification method based on coil current signals for high voltage circuit breaker fault diagnosis.

参考文献/References:

 [1] 曹健,陈杉杉,包锡军,等.基于声谱图与改进残差网络的断路器故障诊断研究[J].机械与电子,2025,43(3):9 15.
[2] 顾广民,赵力可,张炜,等.基于声纹识别技术的开关柜断路器分合闸状态辨识方法[J].机械与电子,2025,43(9):74 80.
[3] NASRI F R,ASGHAR A K R,ALIYARI M S.Fault analysis of high voltage circuit breakers based on coil current and contact travel waveforms through modified SVM classifier[J].IEEE Transactions on power delivery,2019,34(4):1608 1618.
[4] 范想,吐松江·卡日,王德金,等.基于VMD模态分量的高压断路器分合闸线圈电流特征值提取[J].现代电子技术,2023,46(20):107 112.
[5] LI T F,ZHANG W H,MI K,et al.Fault diagnosis method of energy storage unit of circuit breakers based on EWT ISSA BP[J].Energy engineering,2024,121(7):1991 2007.
[6] 钟声,李晓洋,梁胜乐,等.基于线圈电流信号及动态时间规整的高压断路器状态评估方法[J].高压电器,2023,59(4):24 31.
[7] 杨帅,张岩,梁永春,等.基于多维特征与优化SVM 在高压断路器故障分类中的应用[J].国外电子测量技术,2024,43(8):150 159.
[8] WU Q,WANG Y,WANG Y P,et al.Ablation state assessment of SF6 circuit breaker contacts based on BP neural network and mean impact value[J].Energy reports,2022,8(5):874 883
[9] 郭成,陈波,陈慧,等.基于相空间重构的中性点非有效接地系统铁磁谐振故障辨识研究[J].电力系统保护与控制,2024,52(15):131 141.
[10] 李琼,陈亚奇,范瑞祥,等.基于线圈电流改进相轨迹特征的断路器故障分类方法[J].高压电器,2024,60(12):32 40.
[11] CHEN Y Q,LI Q,ZOU Y,et al.Circuit breaker fault diagnosis method based on coil current time sequence phase trajectory characteristics[J].Processes,2023,11(4):1241 1258.
[12] 张丽,王建,许守东,等.基于XGBoost特征筛选和决策树多标签分类的配电网拓扑辨识方法[J].电网与清洁能源,2025,41(2):10 21.
[13] COSTA S D L L,NASCIMENTO D F F.Regression in extremes using the four parameter Kappa distribution[J].Communications in statistics simulation and computation,2025,54(4):954 966.
[14] 黄冬梅,王子豪,胡伟,等.基于Kappa融合系数排序选择性集成的窃电检测[J].电子设计工程,2025,33(7):90 94.

备注/Memo

备注/Memo:
 收稿日期:2025-10-19
基金项目:国家自然科学基金资助项目(52275109)
作者简介:郑 宏 (1979-),男,浙江衢州人,高级工程师,研究方向为电气设备状态监测与故障诊断;万书亭 (1970-),男,山西长治人,博士,教授,博士研究生导师,研究方向为电力设备状态监测与故障诊断,通信作者,E-mail:52450809@ncepu.edu.cn。
更新日期/Last Update: 2026-04-28