基于鲸鱼优化算法改进随机森林的电弧故障检测方法

doi:10.16628/j.cnki.2095-8188.2024.02.004

摘要/Abstract

摘要：

基于电器种类繁多,不同电器发生电弧故障时电流波形相似难以检测,容易引起保护的误动和拒动,提出基于鲸鱼优化算法(WOA)改进随机森林(RF)的电弧故障检测方法。按照GB 14287.4—2014,设计并搭建了故障电弧实验平台,采集故障电弧信号,提取特征值,引入改进WOA对RF进行参数智能优化并求解。对比经典RF算法实验结果,共收集7种负载组合320组正常、故障数据进行实验,实验结果表明优化模型的识别效果优于经典RF算法,可以有效地诊断电弧故障。

关键词: 电弧故障, 鲸鱼优化算法, 特征提取, 改进随机森林

Abstract:

Based on the wide variety of appliances, it is difficult to detect similar current waveforms when different appliances experience a fault arc, which can easily lead to misoperation and rejection of protection. A arc fault detection method based on whale optimization algorithm (WOA) to improve random forest (RF) algorithm is proposed. According to the national standard GB14287.4—2014, a arc fault experimental platform is independently designed and built to collect fault arc signals and extract feature values. Introducing an improved WOA to intelligently optimize and solve RF parameters. Comparing the experimental results of the classical random forest algorithm, a total of 320 sets of normal fault data from seven load combinations are collected for experiments. The experimental results show that the recognition effect of the optimized model is better than that of the classical random forest algorithm, and it can effectively diagnose arcs fault.

Key words: arc fault, whale optimization algorithm(WOA), feature extraction, improved random forest

中图分类号:

TM501.2

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, 0(2): 21-27.

ZHU Hai. Arc Fault Detection Method Based on Whale Optimization Algorithm to Improve Random Forest[J]. LOW VOLTAGE APPARATUS, 2024, 0(2): 21-27.

图/表 11

图1

表1

图2

图3

图4

图5

图6

图7

图8

图9

表2

参考文献 26

[1]	公安部消防局. 中国消防年鉴 2018版[M]. 昆明: 云南人民出版社, 2018.
[2]	曹红伟. 低压配电系统故障电弧在线检测及智能断路器研究[D]. 秦皇岛: 燕山大学, 2018.
[3]	李兴文, 吴艺红, 陈思磊, 等. 低压直流空气电弧研究进展综述[J]. 电器与能效管理技术, 2017(15):67-74.
[4]	王尧, 田明, 牛峰, 等. 低压交流故障电弧检测方法研究综述[J]. 电器与能效管理技术, 2018(10):8-13,44.
[5]	何志鹏, 李伟林, 邓云坤, 等. 低压交流串联故障电弧辨识方法[J]. 电工技术学报, 2023, 38(10):2806-2817.
[6]	WANG Z, BALOG R S. Arc fault and flash signal analysis in DC distribution systems using wavelet transformation[J]. IEEE Transactions on Smart Grid, 2015, 6(4):1955-1963. doi: 10.1109/TSG.2015.2407868
[7]	陈照, 王尧, 牛峰, 等. 基于神经网络和D-S证据理论的故障电弧检测[J]. 高压电器, 2019, 55(3):29-36.
[8]	高小庆, 陈晓军, 鲍光海. 考虑故障电弧电流高频特征的阻抗电弧模型[J]. 电器与能效管理技术, 2021(3):6-12.
[9]	余琼芳, 胡亚, 杨艺. 低压交流串联故障电弧检测概述[J]. 电器与能效管理技术, 2020(1):24-30.
[10]	WANG Y, DING X, ZENG Q, et al. Intelligent rolling bearing fault diagnosis via vision ConvNet[J]. IEEE Sensors Journal, 2020, 21(5):6600-6609. doi: 10.1109/JSEN.7361
[11]	WANG H, LIU Z, PENG D, et al. Understanding and learning discriminant features based on multiattention 1DCNN for wheelset bearing fault diagnosis[J]. IEEE Transactions on Industrial Informatics, 2019, 16(9):5735-5745. doi: 10.1109/TII.9424
[12]	GUO M F, ZENG X D, CHEN D Y, et al. Deep-learning-based earth fault detection using continuous wavelet transform and convolutional neural network in resonant grounding distribution systems[J]. IEEE Sensors Journal, 2017, 18(3):1291-1300. doi: 10.1109/JSEN.2017.2776238
[13]	YUAN X, QI S, WANG Y, et al. A dynamic CNN for nonlinear dynamic feature learning in soft sensor modeling of industrial process data[J]. Control Engineering Practice, 2020, 104:104614. doi: 10.1016/j.conengprac.2020.104614
[14]	LIU R, MENG G, YANG B, et al. Dislocated time series convolutional neural architecture: An intelligent fault diagnosis approach for electric machine[J]. IEEE Transactions on Industrial Informatics, 2016, 13(3):1310-1320. doi: 10.1109/TII.2016.2645238
[15]	王毅, 陈进, 李松浓, 等. 基于时频域分析和随机森林的故障电弧检测[J]电子测量与仪器学报, 2021, 35(5):62-69.
[16]	孙鹏, 郑志成, 闫荣妮, 等. 采用小波熵的串联型故障电弧检测方法[J]. 中国电机工程学报, 2010, 30(增刊1):233-237.
[17]	单潇洁, 郑昕. 基于小波分析的低压电弧特性识别模型的研究[J]. 电器与能效管理技术, 2021(6):7-14.
[18]	陈照, 李奎, 张洋子, 等. 基于电弧电磁辐射的故障电弧识别[J]. 电工电能新技术, 2017, 36(3):70-74.
[19]	王志斌, 曹红伟, 刘佳佳, 等. 基于小波包去噪与 EMD 的故障电弧检测算法研究[J]. 电测与仪表, 2019, 56(6):117-122.
[20]	JIANG J, LI W, WEN Z H, et al. Series arc fault detection based on random forest and deep neural network[J]. IEEE Sensors Journal, 2021, 21(15):17171-17179. doi: 10.1109/JSEN.2021.3082294
[21]	SALEH S A, ALJANKAWEY A S, ERROUISSI R, et al. Extracting the phase of fault currents: A new approach for identifying arc flash faults[J]. IEEE Transactions on Industry Applications, 2016, 52(2):1226-1240.
[22]	LE V, YAO X, MILLER C, et al. Series DC arc fault detection based on ensemble machine learning[J]. IEEE Transactions on Power Electronics, 2020, 35(8):7826-7839. doi: 10.1109/TPEL.63
[23]	汪洋堃. 低压交流电弧的动态特性与故障检测方法研究[D]. 上海: 上海交通大学, 2021.
[24]	赵怀军, 秦海燕, 刘凯, 等. 基于相关理论及零休特征融合的串联故障电弧检测方法[J]. 仪器仪表学报, 2020, 41(4):218-228.
[25]	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(9):1820-1825.
[26]	曹正凤. 随机森林算法优化研究[D]. 北京: 首都经贸大学, 2014.

负载类别	负载名称
线性负载	电水壶1 600 W
线性负载	电吹风1 000 W
非线性负载	电磁炉1 300 W
	调压电路800 W
	计算机100 W
混合负载	计算机(支路电弧)+水壶
混合负载	计算机(干路电弧)+水壶

批次	经典算法准确率/%	改进算法准确率/%	批次	经典算法准确率/%	改进算法准确率/%
1	90.2	97.0	6	87.9	95.8
2	87.8	96.2	7	91.3	97.5
3	79.5	96.1	8	92.5	97.8
4	83.5	97.6	9	91.1	98.4
5	89.4	99.3	10	92.1	97.6