基于GRU和GWO-KELM的电力线路故障诊断

doi:10.3969/j.issn.2097-0706.2024.03.007

摘要/Abstract

摘要：

为实现电力线路故障的高精度检测和分类，设计并实现了基于机器学习的电力线路故障诊断系统，核心模块是机器学习经典算法中门控循环单元（GRU）神经网络和核极限学习机（KELM）。利用GRU对电力数据进行故障诊断，将正常数据与故障数据高精度地区分开来；利用灰狼优化（GWO）算法对KELM的核参数和惩罚因子进行寻优，使KELM获得了最佳参数；利用KELM进行故障分类，成功将不同种类的故障区分开。试验证明，GRU在数据集的准确率高达98%，得到了最优参数的KELM在数据集中准确率高达99%；利用模拟退火算法（SA）进行了准确率比对，证实了GWO算法的优越性。还对数据集中的电压和电流进行了数据可视化，简洁直观地表达了数据集，为电力线路故障诊断提供了一个切实有效的方法。

关键词: 门控循环单元神经网络, 极限学习机, 灰狼优化算法, 电力线路, 故障诊断, 机器学习

Abstract:

To improve the detection precision and classification accuracy of power line faults， a power line fault diagnosis system based on machine learning is designed and implemented， whose core modules are Gated Recurrent Unit （GRU）neural network—A classical algorithm of machine learning， and Kernel Extreme Learning Machine（KELM）. First，GRU is used to separate fault data from normal data accurately in electrical fault diagnosis. Then，the kernel parameters and penalty factors of KELM are optimized by Grey Wolf Optimization（GWO）. The KELM with optimal parameters can successfully distinguish different types of faults. Proven by experimental data， GRU's accuracy in dataset classification is as high as 98%，and the KELM with the optimal parameters has an accuracy of 99%. Comparing the accuracies of the algorithms obtained by Simulated Annealing（SA），the superiority of GWO can be confirmed. The voltage and current data are visualized，presenting the dataset concisely and intuitively. This article provides a practical and effective method for diagnosing power line faults.

Key words: gated recurrent unit, extreme learning machine, grey wolf optimizer, power lines, fault diagnosis, machine learning

中图分类号:

TP18：TM77：TK01

任一鸣, 杜董生, 邓祥帅, 连贺, 赵哲敏. 基于GRU和GWO-KELM的电力线路故障诊断[J]. 综合智慧能源, 2024, 46(3): 54-62.

REN Yiming, DU Dongsheng, DENG Xiangshuai, LIAN He, ZHAO Zhemin. Power line fault diagnosis based on GRU and GWO-KELM[J]. Integrated Intelligent Energy, 2024, 46(3): 54-62.

图/表 17

图1

图2

图3

图4

图5

表1

图6

图7

图8

图9

图10

图11

图12

图13

图14

图15

图16

参考文献 28

[1]	许保瑜, 赵毅林, 陈庆宁, 等. 输电线路移动式不间断自主智能巡检技术研究[J]. 电测与仪表, 2021, 58(11): 157-163.
	XU Baoyu, ZHAO Yilin, CHEN Qingning, et al. Research on mobile uninterrupted autonomous intelligent inspection technology for transmission line[J]. Electrical Measurement and Instrumentation, 2021, 58(11): 157-163.
[2]	陈军, 隋佳闽, 赵子涵, 等. 输电线路断线故障保护逻辑分析及附加判别方法[J]. 电力系统保护与控制, 2022, 50(4):103-111.
	CHEN Jun, SUI Jiamin, ZHAO Zihan, et al. Protection logic analysis and additional judgment method of a transmission line break fault[J]. Power System Protection and Control, 2022, 50(4): 103-111
[3]	何攻, 何潜, 季巧宇, 等. 一种新型电力线路故障处理方法在重庆电网的实用化研究[J]. 电工技术, 2023(3):10-15.
	HE Gong, HE Qian, JI Qiaoyu, et al. Practical research on a new power line fault handling methods in Chongqing power grid[J]. Electric Engineering, 2023(3):10-15.
[4]	魏伟, 高赐威, 宋梦, 等. 基于HHO-SVM的电力线路故障检测分类系统[J]. 综合智慧能源, 2023, 45(3):1-8. doi: 10.3969/j.issn.2097-0706.2023.03.001
	WEI Wei, GAO Ciwei, SONG Wei, et al. Power line fault detection and classification system based on HHO-SVM[J]. Integrated Intelligent Energy, 2023, 45(3):1-8. doi: 10.3969/j.issn.2097-0706.2023.03.001
[5]	董诗焘, 路学刚, 孙华利, 等. 基于信号分析技术和人工智能算法的电力线路故障定位研究[J]. 能源与环保, 2022, 44(11):35-40.
	DONG Shitao, LU Xuegang, SUN Huali, et al. Research on power line fault location based on signal analysis technology and artificial intelligence algorithm[J]. China Energy and Environmental Protection, 2022, 44(11):35-40.
[6]	陈巍. 电力输配电线路的运行维护及故障排除分析[J]. 科技创新与应用, 2022, 12(7):125-127.
	CHEN Wei. Analysis of operation,maintenance,and troubleshooting of electric power transmission and distribution lines[J]. Technology Innovation and Application, 2022, 12(7): 125-127.
[7]	王沛. 基于大数据技术的输电线路运行故障诊断关键技术[J]. 电测与仪表, 2021, 58(5): 182-189.
	WANG Pei. Key technologies of fault diagnosis for transmission line operation based on big data technology[J]. Electrical Measurement & Instrumentation, 2021, 58(5): 182-189.
[8]	KAFEEL A, AZIZ S, AWAIS M, et al. An expert system for rotating machine fault detection using vibration signal analysis[J]. Sensors, 2021, 21(22): 7587. doi: 10.3390/s21227587
[9]	MAZZOLENI M, SARDA K, ACERNESE A, et al. A fuzzy logic-based approach for fault diagnosis and condition monitoring of industry 4.0 manufacturing processes[J]. Engineering Applications of Artificial Intelligence, 2022, 115: 105317. doi: 10.1016/j.engappai.2022.105317
[10]	WANG X Y. A fuzzy neural network-based automatic fault diagnosis method for permanent magnet synchronous generators[J]. Mathematical Biosciences and Engineering, 2023, 20(5): 8933-8953. doi: 10.3934/mbe.2023392 pmid: 37161228
[11]	ZHU G H, ZHANG J F, ZHENG Z, et al. Optimistic fault diagnosis in discrete event systems by labeled petri nets and basis markings[J]. International Journal of Control, Automation and Systems, 2022, 20(6): 1891-1903. doi: 10.1007/s12555-021-0215-9
[12]	LI Y Y, WANG Y, ZHU G H, et al. Fault diagnosis of PLC-based discrete event systems using Petri nets[J]. Measurement and Control, 2022, 55(9-10): 960-973. doi: 10.1177/00202940221117098
[13]	WEI M H, ZHENG Z H, BAI X, et al. Application of rough set and neural network in water energy utilization[J]. Frontiers in Energy Research, 2021, 9: 604660. doi: 10.3389/fenrg.2021.604660
[14]	ZHOU H, WANG Z, SHI C, et al. Study of fault diagnosis distribution network based on rough set and artificial intelligence[C]// Journal of Physics: Conference Series. IOP Publishing, 2021, 1754(1): 012204.
[15]	ENCALADA-DÁVILA Á, MOYÓN L, TUTIVÉN C, et al. Early fault detection in the main bearing of wind turbines based on Gated Recurrent Unit(GRU) neural networks and SCADA data[J]. IEEE/ASME Transactions on Mechatronics, 2022, 27(6): 5583-5593. doi: 10.1109/TMECH.2022.3185675
[16]	WANG C, PENG Z M, LIU R, et al. Research on multi-fault diagnosis method based on time domain features of vibration signals[J]. Sensors, 2022, 22(21): 8164. doi: 10.3390/s22218164
[17]	LV Y X, DONG Y W, LI Y, et al. Submarine cable fault identification based on FCN-GRU-SVM[C]// E3S Web of Conferences. EDP Sciences, 2022, 360.
[18]	LIANG R J, CHEN Y, ZHU R P. A novel fault diagnosis method based on the KELM optimized by whale optimization algorithm[J]. Machines, 2022, 10(2): 93. doi: 10.3390/machines10020093
[19]	FEI S W, LIU Y Z. Fault diagnosis method of bearing utilizing GLCM and MBASA-based KELM[J]. Scientific Reports, 2022, 12(1): 17368. doi: 10.1038/s41598-022-19209-1
[20]	GONG J C, YANG X Q, HAN J, et al. A new comprehensive automatic fault detection method for rotating machinery using HmvAAPE and VNWOA-KELM[J]. Applied Intelligence, 2023, 53(1): 204-225. doi: 10.1007/s10489-022-03505-4
[21]	HOU Y X, GAO H B, WANG Z J, et al. Improved grey wolf optimization algorithm and application[J]. Sensors, 2022, 22(10): 3810. doi: 10.3390/s22103810
[22]	SADEGHI A H, BANI E A, FALLAHI A, et al. Grey wolf optimizer and whale optimization algorithm for stochastic inventory management of reusable products in a two-level supply chain[J]. IEEE Access, 2023, 11:40278-40297. doi: 10.1109/ACCESS.2023.3269292
[23]	LIU X Y, WANG Y F, ZHOU M L. Dimensional learning strategy-based grey wolf optimizer for solving the global optimization problem[J]. Computational Intelligence and Neuroscience, 2022, 2022:3603607.
[24]	ALNOWIBET K A, MAHDI S, EL-ALEM M, et al. Guided hybrid modified simulated annealing algorithm for solving constrained global optimization problems[J]. Mathematics, 2022, 10(8): 1312. doi: 10.3390/math10081312
[25]	PEI J, XU L, HUANG Y T, et al. A Two-step simulated annealing algorithm for spectral data feature extraction[J]. Sensors, 2023, 23(2): 893. doi: 10.3390/s23020893
[26]	赵国涛, 钱国明, 王盛, 等. “双碳”目标下火电企业绿色低碳转型的对策分析[J]. 华电技术, 2021, 43(10): 11-21.
	ZHAO Guotao, QIAN Guoming, WANG Sheng, et al. Analysis on solution for green and low-carbon transformation of thermal power enterprises to achieve carbon peak and carbon neutrality[J]. Huadian Technology, 2021, 43(10): 11-21.
[27]	高明, 陈家豪, 王丽晓, 等. 考虑光伏不确定性因素的电力系统概率潮流三点估计法[J]. 综合智慧能源, 2022, 44(9): 1-10. doi: 10.3969/j.issn.2097-0706.2022.09.001
	GAO Ming, CHEN Jiahao, WANG Lixiao, et al. A three-point probabilistic load flow estimation algorithm for the power system considering photovoltaic uncertainties[J]. Integrated Intelligent Energy, 2022, 44(9): 1-10. doi: 10.3969/j.issn.2097-0706.2022.09.001
[28]	曾慧, 杜源, 李涛, 等. 考虑碳交易与绿证交易的电-热耦合园区低碳规划[J]. 综合智慧能源, 2023, 45(2): 22-29. doi: 10.3969/j.issn.2097-0706.2023.02.003
	ZENG Hui, DU Yuan, LI Tao, et al. Low-carbon planning of a park-level integrated electric and heating system considering carbon trading and green certificate trading[J]. Integrated Intelligent Energy, 2023, 45(2): 22-29. doi: 10.3969/j.issn.2097-0706.2023.02.003

G C B A	故障类型	样本数	说明
0 0 0 0	No Fault	2 365	无故障
1 0 0 1	LG Fault	1 129	A相和接地之间的故障
0 1 1 0	LL Fault	1 004	B相和C相之间的故障
1 0 1 1	LLG Fault	1 134	A相、B相和接地的故障
0 1 1 1	LLL Fault	1 096	所有三相之间的故障
1 1 1 1	LLLG Fault	1 133	三相之间对称的故障