基于IBOA-RF的直流故障电弧诊断研究

doi:10.16628/j.cnki.2095-8188.2026.03.001

摘要/Abstract

摘要：

针对低压直流系统中不同工况下故障电弧特征微弱、难以准确识别的问题,提出一种基于改进蝴蝶优化算法-随机森林(IBOA-RF)的直流电弧故障诊断方法。首先,采用鲸鱼优化算法(WOA)优化改进自适应噪声完备集合经验模态分解(ICEEMDAN)参数,并对电流信号进行分解得到多个本征模态函数(IMF);其次,筛选有效分量,并提取层次加权排列熵(HWPE)构建特征向量;最后,引入反向学习机制与动态边界调整策略对蝴蝶优化算法(BOA)进行改进,并建立IBOA-RF诊断模型进行故障识别。结果表明,该方法在多种典型工况下的平均识别准确率达97.92%,验证了该方法在直流电弧故障诊断领域的有效性。

关键词: 直流故障电弧, 特征提取, 层次加权排列熵, 改进蝴蝶优化算法, 故障诊断

Abstract:

Aiming at the problem that the fault arc characteristics in low-voltage DC systems are weak and difficult to accurately identify under different operating conditions,a DC arc fault diagnosis method based on the improved butterfly optimization algorithm (IBOA) optimizing random forest (RF) is proposed.Firstly,the whale optimization algorithm (WOA) is employed to optimize and improve the parameters of the adaptive noise complete ensemble empirical mode decomposition (ICEEMDAN),and the current signal is decomposed to obtain multiple intrinsic mode functions (IMF).Secondly,the effective components are selected and the hierarchical weighted permutation entropy (HWPE) is extracted to construct the feature vector.Finally,the reverse learning mechanism and dynamic boundary adjustment strategy are introduced to improve the butterfly optimization algorithm,and the IBOA-RF diagnostic model is established for fault identification.The results show that the average recognition accuracy of this method reaches 97.92% under various typical working conditions.The research verifies the effectiveness of this method in the field of DC arc fault diagnosis.

Key words: DC fault arc, feature extraction, hierarchical weighted permutation entropy, improved butterfly optimization algorithm, fault diagnosis

中图分类号:

TM501.2

罗希元, 刘树鑫, 邢朝建, 李艳凯. 基于IBOA-RF的直流故障电弧诊断研究[J]. 电器与能效管理技术, 2026, 0(3): 1-9.

LUO Xiyuan, LIU Shuxin, XING Chaojian, LI Yankai. Research on DC Fault Arc Diagnosis Based on IBOA-RF[J]. LOW VOLTAGE APPARATUS, 2026, 0(3): 1-9.

图/表 13

图1

图2

图3

图4

表1

图5

图6

图7

图8

图9

图10

图11

表2

参考文献 23

[1]	汪倩, 陈思磊, 孟羽, 等. 低压直流系统故障电弧检测技术研究综述[J]. 高压电器, 2023, 59(5):93-103.
[2]	国家能源综合司.关于加强分布式光伏发电安全工作的通知(征求意见稿)[Z].2021.
[3]	AHN J B, JO H B, RYOO H J. Real-time DC series arc fault detection based on noise pattern analysis in photovoltaic system[J]. IEEE Transactions on Industrial Electronics, 2023, 70(10):10680-10689. doi: 10.1109/TIE.2022.3220883
[4]	AMIRI A, SAMET H, GHANBARI T. Recur- rence plots based method for detecting series arc faults in photovoltaic systems[J]. IEEE Transactions on Industrial Electronics, 2022, 69(6):6308-6315. doi: 10.1109/TIE.2021.3095819
[5]	YIN Z, WANG L, YANG S, et al. A series arc fault diagnosis method in DC distribution systems based on multiscale features and random forests[J]. IEEE Sensors Journal, 2023, 23(3):2605-2617. doi: 10.1109/JSEN.2022.3228551
[6]	王尧, 盛德杰, 李腾, 等. 低压直流串联故障电弧研究综述[J]. 电器与能效管理技术, 2024(8):11-20.
[7]	周学, 代文鑫. 基于时频域参数分析的直流电弧故障检测装置[J]. 电器与能效管理技术, 2024(8):86-90.
[8]	王毅, 刘黎明, 李松浓, 等. 基于经验小波变换复合熵值与特征融合的故障电弧检测[J]. 电网技术, 2023, 47(5):1912-1919.
[9]	杨帆, 宿磊, 杨志淳, 等. 基于改进CEEMDAN分解与时空特征的低压供电线路串联故障电弧检测[J]. 电力系统保护与控制, 2022, 50(12):72-81.
[10]	HE Z, XU Z, ZHAO H, et al. Detecting series arc Faults using high-frequency components of branch voltage coupling signal[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73:1-13.
[11]	周晶, 罗日成, 黄军. 基于改进小波阈值-CEEMDAN的变压器局部放电超声波信号白噪声抑制方法[J]. 高压电器, 2024, 60(1):163-171.
[12]	AHN J B, JEONG S J, CHO C G, et al. DC series arc fault detectorwith differential DWT and variable threshold method for photovoltaic systems[J]. IEEE Transactions on Industrial Informatics, 2024, 20(7):9343-9351. doi: 10.1109/TII.2024.3383541
[13]	孟羽, 陈思磊, 吴子豪, 等. 基于随机共振方法增强光伏直流故障电弧检测特征的研究[J]. 中国电机工程学报, 2022, 42(6):2396-2407.
[14]	武涵聪, 陈思磊, 孟羽, 等. 基于Chirplet稀疏表示的大电流光伏系统微弱故障电弧检测方法[J]. 中国电机工程学报, 2025, 45(3):1148-1159.
[15]	邬洲, 张军, 李隆, 等. 基于Kmeans++聚类的光伏系统直流电弧故障检测研究[J]. 太阳能学报, 2024, 45(11):320-329.
[16]	李岩, 刘鑫月, 乔俊杰, 等. 基于1DCNN和D-S多信息融合的光伏系统直流母线串联电弧故障检测[J]. 电工电能新技术, 2024, 43(5):58-67.
[17]	谢振华, 刘玉莹, 侯林明, 等. 基于注意力机制优化电弧特征的光伏直流电弧故障检测方法[J]. 电器与能效管理技术, 2024(8):50-56.
[18]	刘艳丽, 王浩, 张帆. 基于轻量卷积和模型优化的电弧故障检测方法[J]. 仪器仪表学报, 2024, 45(10):38-49.
[19]	余琼芳, 黄高路, 杨艺, 等. 基于AlexNet深度学习网络的串联故障电弧检测方法[J]. 电子测量与仪器学报, 2019, 33(3):145-152.
[20]	何键涛, 王兆锐, 鲍光海. 基于Filtering LSTM-Lightweight CNN的交流串联电弧故障检测方法[J]. 电器与能效管理技术, 2025(9):1-12.
[21]	刘磊, 白克强, 但志宏, 等. 一种全局搜索策略的鲸鱼优化算法[J]. 小型微型计算机系统2020, 41(10):1820-1825.
[22]	ARORA S, SINGH S. Butterfly optimization algorithm:A novel approach for global optimization[J]. Soft Computing, 2019, 23(3):715-734. doi: 10.1007/s00500-018-3102-4
[23]	朱海. 基于鲸鱼优化算法改进随机森林的电弧故障检测方法[J]. 电器与能效管理技术, 2024(8):21-17.

负载	数值
电阻/Ω	10、50、80、100
电感/mH	15
直流电机/W	375

算法模型	准确率/%	时间/s
WOA-ICEEMDAN-IBOA-RF	97.92	4.52
WOA-ICEEMDAN-BOA-RF	95.43	6.80
ICEEMDAN-IBOA-RF	94.46	10.40
ICEEMDAN-BOA-RF	92.10	12.10
ICEEMDAN-GWO-SVM	92.00	12.60
ICEEMDAN-WOA-ELM	89.23	14.60