基于多源信息融合的配网故障外部原因识别

doi:10.12204/j.issn.1000-7229.2023.03.008

摘要/Abstract

摘要：

配网故障原因的准确识别对于缩短故障查找时间、提高供电恢复速度和供电可靠性有重要意义。根据责任归属可将配网故障原因分为内部原因和外部原因,内部原因指设备绝缘弱化、过电压等电气相关原因,而外部故障通常由于天气、动物或人类活动引起。由于外部原因导致的故障是多种因素共同作用的结果,为此提出融合线路参数、天气、时间等非电气量信息及动作电流、故障相数等电气量信息的故障外部原因识别方法,首先对5种典型外部故障原因的特点及相关影响因素进行分析,构建识别模型,然后使用无监督学习训练得到深度信念网络各层的最优参数,利用有监督学习对全局参数进行微调,得到基于深度信念网络的配网故障外部原因识别模型,最后利用西部某地区的实际故障数据对算法的准确性进行了验证,结果显示识别准确率可达94.82%,证明了方法的正确性。

关键词: 配网故障, 外部原因, 原因识别, 深度学习, 多源信息融合

Abstract:

Accurate identification of distribution network fault causes is of great significance to shorten the time of fault search and improve the speed of power supply recovery and power supply reliability. According to the attribution of responsibility, the causes of distribution network fault can be divided into internal causes and external causes. Internal causes refer to electrical related causes such as equipment insulation weakening and overvoltage, while external faults usually refer to weather, animal or human activities. Faults caused by external causes are the result of a combination of many factors. In this paper, a fault external cause identification method is proposed, which integrates the non-electrical information such as line parameters, weather and time, and the electrical information such as fault current and phase number. Firstly, the characteristics and related influencing factors of five typical external fault causes are analyzed to build the basis of identification model. Then unsupervised learning training is used to obtain the optimal parameters of each layer of deep belief network, and supervised learning is used to fine-tune the global parameters, and the classification model of external causes of distribution network faults based on deep belief network is obtained. Finally, the accuracy of the algorithm is verified by using the actual fault data of a certain area in western China. The result shows that the recognition accuracy can reach 94.82%, which proves the correctness of the method.

Key words: distribution system fault, external fault causes, fault cause identification, deep learning, multi-source information fusion

中图分类号:

TM773

谭媛, 张文海, 王杨. 基于多源信息融合的配网故障外部原因识别[J]. 电力建设, 2023, 44(3): 77-84.

TAN Yuan, ZHANG Wenhai, WANG Yang. Distribution System External Fault Causes Identification based on Multi-Source Information Fusion[J]. ELECTRIC POWER CONSTRUCTION, 2023, 44(3): 77-84.

图/表 14

图1 某区2015—2021年不同故障原因占比

Fig.1 Proportion of different fault causes in a district from 2015 to 2021

图2 外部故障原因与天气相关性对比

Fig.2 Correlation analysis of external fault causes with weather

图3 外部故障原因与最低、最高温度相关性对比

Fig.3 Correlation analysis of external fault causes with minimum and maximum temperature

图4 外部故障原因与每周多云/阴天、雨天数相关性对比

Fig.4 Correlation analysis of external fault causes with number of cloudy and rainy days per week

图5 外部故障原因与季节相关性对比

Fig.5 Correlation analysis of external faults causes with season

图6 外部故障原因与月份相关性对比

Fig.6 Correlation analysis of external faults causes with month

图7 外部故障原因与昼夜相关性对比

Fig.7 Correlation analysis of external faults causes with time of day

表1 故障原因与特征信息关系

Table 1 Relationship between fault causes and feature information

图8 深度信念网络架构

Fig.8 Structure of DBN

表2 故障原因编码

Table 2 Coding table of failure causes

图9 故障原因识别流程

Fig.9 Process of fault cause identification

表3 网络层数对识别准确率的影响

Table 3 Influence of the number of network layers on recognition accuracy

图10 迭代次数对识别准确率的影响

Fig.10 The effect of iteration number on recognition accuracy

图11 不同算法对识别准确率的影响

Fig.11 The effect of different algorithms on the recognition accuracy

参考文献 24

[1]	王玲, 邓志, 马明, 等. 基于状态估计残差比较的配电网故障区段定位方法[J]. 电力系统保护与控制, 2021, 49(14): 132-139.
	WANG Ling, DENG Zhi, MA Ming, et al. A method for locating fault sections in distribution networks based on the comparison of state estimation residual errors[J]. Power System Protection and Control, 2021, 49(14): 132-139.
[2]	白星振, 宋昭杉, 葛磊蛟, 等. 含分布式电源的复杂配电网相间故障定位等效解耦模型[J]. 电力建设, 2022, 43(2): 45-53. doi: 10.12204/j.issn.1000-7229.2022.02.006
	BAI Xingzhen, SONG Zhaoshan, GE Leijiao, et al. An equivalent decoupling model for fault location in complex distribution network with distributed generation[J]. Electric Power Construction, 2022, 43(2): 45-53. doi: 10.12204/j.issn.1000-7229.2022.02.006
[3]	刘健, 张志华, 黄炜, 等. 分布式电源接入对配电网故障定位及电压质量的影响分析[J]. 电力建设, 2015, 36(1): 115-121. doi: 10.3969/j.issn.1000－7229.2015.01.018
	LIU Jian, ZHANG Zhihua, HUANG Wei, et al. Influence of distributed generation on fault location and voltage quality of distribution network[J]. Electric Power Construction, 2015, 36(1): 115-121. doi: 10.3969/j.issn.1000－7229.2015.01.018
[4]	雷倩, 吉兴全, 文福拴, 等. 利用暂态分量的含分布式电源配电系统故障诊断[J]. 电力建设, 2016, 37(2): 42-49. doi: 10.3969/j.issn.1000-7229.2016.02.006
	LEI Qian, JI Xingquan, WEN Fushuan, et al. Fault diagnosis of distribution system with distributed generation employing transient component[J]. Electric Power Construction, 2016, 37(2): 42-49. doi: 10.3969/j.issn.1000-7229.2016.02.006
[5]	XU L, CHOW M Y. A classification approach for power distribution systems fault cause identification[J]. IEEE Transactions on Power Systems, 2006, 21(1): 53-60. doi: 10.1109/TPWRS.2005.861981 URL
[6]	MINNAAR U J, NICOLLS F, GAUNT C T. Automating transmission-line fault root cause analysis[J]. IEEE Transactions on Power Delivery, 2016, 31(4): 1692-1700. doi: 10.1109/TPWRD.2015.2503478 URL
[7]	BARRERA NÚÑEZ V, KULKARNI S, SANTOSO S, et al. Feature analysis and classification methodology for overhead distribution fault events[C]// IEEE PES General Meeting. July 25-29, 2010, Minneapolis, MN, USA. IEEE, 2010: 1-8.
[8]	秦雪, 刘亚东, 孙鹏, 等. 基于故障波形时频特征配网故障识别方法研究[J]. 仪器仪表学报, 2017, 38(1): 41-49.
	QIN Xue, LIU Yadong, SUN Peng, et al. Study on the line fault root-cause identification method in distribution networks based on time-frequency characteristics of fault waveforms[J]. Chinese Journal of Scientific Instrument, 2017, 38(1): 41-49.
[9]	KULKARNI S, LEE D, ALLEN A J, et al. Waveform characterization of animal contact, tree contact, and lightning induced faults[C]// IEEE PES General Meeting. July 25-29, 2010, Minneapolis, MN, USA. IEEE, 2010: 1-7.
[10]	XU L, CHOW M Y, TAYLOR L S. Data mining and analysis of tree-caused faults in power distribution systems[C]// 2006 IEEE PES Power Systems Conference and Exposition. October 29 - November 1, 2006, Atlanta, GA, USA. IEEE, 2007: 1221-1227.
[11]	CHOW M Y, TAYLOR L S. Analysis and prevention of animal-caused faults in power distribution systems[J]. IEEE Transactions on Power Delivery, 1995, 10(2): 995-1001. doi: 10.1109/61.400829 URL
[12]	DOOSTAN M, CHOWDHURY B H. Power distribution system fault cause analysis by using association rule mining[J]. Electric Power Systems Research, 2017, 152: 140-147. doi: 10.1016/j.epsr.2017.07.005 URL
[13]	XU L, CHOW M Y, TIMMIS J. Power Distribution Outage Cause Identification using Fuzzy Artificial Immune Recognition Systems (FAIRS) algorithm[C]// 2007 IEEE Power Engineering Society General Meeting. June 24-28, 2007, Tampa, FL, USA. IEEE, 2007: 1-8.
[14]	CHOW M Y, YEE S O, TAYLOR L S. Recognizing animal-caused faults in power distribution systems using artificial neural networks[J]. IEEE Transactions on Power Delivery, 1993, 8(3): 1268-1274. doi: 10.1109/61.252652 URL
[15]	LI L N, CHE R F, ZANG H Z. A fault cause identification methodology for transmission lines based on support vector machines[C]// 2016 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC). October 25-28, 2016, Xi’an. IEEE, 2016: 1430-1434.
[16]	贾京龙, 余涛, 吴子杰, 等. 基于卷积神经网络的变压器故障诊断方法[J]. 电测与仪表, 2017, 54(13): 62-67.
	JIA Jinglong, YU Tao, WU Zijie, et al. Fault diagnosis method of transformer based on convolutional neural network[J]. Electrical Measurement & Instrumentation, 2017, 54(13): 62-67.
[17]	王功明, 乔俊飞, 关丽娜, 等. 深度信念网络研究现状与展望[J]. 自动化学报, 2021, 47(1): 35-49.
	WANG Gongming, QIAO Junfei, GUAN Lina, et al. Review and prospect on deep belief network[J]. Acta Automatica Sinica, 2021, 47(1): 35-49.
[18]	KARTHIGA R, USHA G, RAJU N, et al. Transfer learning based breast cancer classification using one-hot encoding technique[C]// 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS). March 25-27, 2021, Coimbatore, India. IEEE, 2021: 115-120.
[19]	石鑫, 朱永利. 深度学习神经网络在电力变压器故障诊断中的应用[J]. 电力建设, 2015, 36(12): 116-122. doi: 10.3969/j.issn.1000-7229.2015.12.018
	SHI Xin, ZHU Yongli. Application of deep learning neural network in fault diagnosis of power transformer[J]. Electric Power Construction, 2015, 36(12): 116-122. doi: 10.3969/j.issn.1000-7229.2015.12.018
[20]	DENIL M, SHAKIBI B, DINH L, et al. Predicting parameters in deep learning[C]// Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2. December 5 - 10, 2013, Lake Tahoe, Nevada. New York: ACM, 2013: 2148-2156.
[21]	杨杰, 吴浩, 董星星, 等. 基于电流故障分量特征和随机森林的输电线路故障类型识别[J]. 电力系统保护与控制, 2021, 49(13): 53-63.
	YANG Jie, WU Hao, DONG Xingxing, et al. Transmission line fault type identification based on the characteristics of current fault components and random forest[J]. Power System Protection and Control, 2021, 49(13): 53-63.
[22]	申元, 马仪, 孟见刚, 等. 基于BP神经网络的输电线路故障原因辨识研究[J]. 智能电网, 2017, 5(2): 134-141.
	SHEN Yuan, MA Yi, MENG Jiangang, et al. Research on transmission line fault reason recognition based on BP neural network[J]. Smart Grid, 2017, 5(2): 134-141.
[23]	XU L, CHOW M C, GAO X Z. Comparisons of logistic regression and artificial neural network on power distribution systems fault cause identification[C]// Proceedings of the 2005 IEEE Midnight-Summer Workshop on Soft Computing in Industrial Applications, 2005. SMCia/05. June 28-30, 2005, Espoo, Finland. IEEE, 2005: 128-131.
[24]	李宇, 杨柳林. 基于卷积神经网络的配电网单相接地故障识别[J]. 电气工程学报, 2020, 15(3): 22-30.
	LI Yu, YANG Liulin. Identification of single-phase-to-earth fault in distribution network based on convolutional neural network[J]. Journal of Electrical Engineering, 2020, 15(3): 22-30.