基于时序卷积残差网络的主动配电系统线路短路故障诊断方案

doi:10.19595/j.cnki.1000-6753.tces.211990

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (2133 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The fault characteristics of active distribution system (ADS) are weak due to its complex structure and flexible control strategy, so the diagnosis method with strong adaptability and high precision is urgently needed. This paper examines a new fault diagnosis scheme for lines of active power distribution system founded on a time-sequence convolution residual network, which is used to detect, select and locate short circuit fault. According to the strong correlation between each feature channel signals measured at corresponding time of pre-fault and post-fault period, a residual network model based on time-sequence convolution (T-Conv) is built. For the proposed T-Conv residual network model, each time-sequence convolution kernel transverse telescopic width based on the number of adaptive features matching the input channel, ensure the receptive field lateral coverage to all the characteristics of the channel, to fully mix the channel between the features of information, enhance the receptive field, reducing the loss of information, and save the calculation process of convolution kernels lateral translation, save calculation time and improve calculation efficiency. The kernel size and step size are set according to the temporal morphological characteristics of fault transient and sampling frequency, and convolved downward along the time axis. The fault local features on the time axis are successively mined, mutation details are extracted from multiple directions, and complex, abstract and weak features of ADS fault signals are extracted efficiently. Furthermore, the short nature of residual network is used to generate a backoff mechanism to solve the problem of gradient disappearance in deep neural networks. Thus, each network layer can obtain enough gradients to update its parameters, which reduces the difficulty of model training. Fault selection and fault location belong to both classification tasks, and the front part of the network belongs to feature extraction. After mining corresponding features through training, only the corresponding number of neurons are needed to output the discriminant probability of each category according to the different task objectives. Therefore, this paper realizes fault selection and fault location functions by modifying the structure of the output layer of the model. In addition, the fault detection function can be realized and the reliability of fault diagnosis can be further improved by considering the normal category and combining with Boolean operator in the selection and location discrimination results. The fault diagnosis scheme results guide the staff to find abnormalities and repair faults in time, accelerate system recovery, and form an active fault diagnosis scheme for the distribution system that integrates fault detection, selection, and location functions. Finally, an electromagnetic transient model of 10 kV active distribution system is built using EMTDC. Experimental results show that for different transition resistance, fault location and fault initial Angle, this article proposed fault diagnosis scheme based on time-sequence convolution were diagnosed with high precision, fast computing speed, the advantages of without expert experience, avoid working condition of fault signal feature selection, time and frequency domain transformation, such as complicated process, direct "end-to-end" build a diagnosis model, implement exemption threshold diagnosis. Compared with other similar diagnosis methods based on recurrent neural network (RNN), artiflcal neutral networks (ANN) and convolutional neutral networks (CNN), which have single function and do not consider multi-function combination, this method effectively integrates and realizes the functions of fault detection, fault selection and fault location, and has advantages in diagnosis accuracy and calculation efficiency. In addition, as the proportion of training set samples decreases, the model still has high diagnostic accuracy, showing adaptability to different sample sizes and good generalization ability.

Key words： Active distribution system fault diagnosis time-sequence convolution residual network

Received: 10 December 2021

PACS:

TM75

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Chu Xu
	Bao Zehong
	Xu Liqiang
	Yan Yabing

Cite this article:

Chu Xu,Bao Zehong,Xu Liqiang等. Fault Line Diagnosis Scheme of Active Distribution System Based on Time-Sequence Convolution Residual Network[J]. Transactions of China Electrotechnical Society, 2023, 38(8): 2178-2190.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.211990 OR https://dgjsxb.ces-transaction.com/EN/Y2023/V38/I8/2178

[1] 刘树鑫, 卓裕, 李津, 等. 基于微型同步相量单元数据的配电线路故障测距方法[J]. 电气技术, 2020, 21(10): 63-70.
Liu Shuxin, Zhuo Yu, Li Jin, et al.Distribution line fault location method based on micro-synchronous phasor unit data[J]. Electrical Engineering, 2020, 21(10): 63-70.
[2] 叶畅, 苗世洪, 刘昊, 等. 联盟链框架下主动配电网电力交易主体合作演化策略[J]. 电工技术学报, 2020, 35(8): 1739-1753.
Ye Chang, Miao Shihong, Liu Hao, et al.Cooperative evolutionary game strategy for electricity trading stakeholders in active distribution network under consortium blockchain framework[J]. Transactions of China Electrotechnical Society, 2020, 35(8): 1739-1753.
[3] Giacomuzzi S, Langwasser M, de Carne G, et al. Smart transformer-based medium voltage grid support by means of active power control[J]. CES Transactions on Electrical Machines and Systems, 2020, 4(4): 285-294.
[4] 周念成, 谷飞强, 雷超, 等. 考虑合环电流约束的主动配电网转供优化模型[J]. 电工技术学报, 2020, 35(15): 3281-3291.
Zhou Niancheng, Gu Feiqiang, Lei Chao, et al.A power transfer optimization model of active distribution networks in consideration of loop closing current constraints[J]. Transactions of China Electrotechnical Society, 2020, 35(15): 3281-3291.
[5] 贾贞, 张维, 彭松. 含分布式电源的配电网方向保护研究[J]. 电气技术, 2020, 21(5): 55-57, 67.
Jia Zhen, Zhang Wei, Peng Song.Research on directional protection of distribution network with distributed power[J]. Electrical Engineering, 2020, 21(5): 55-57, 67.
[6] 杜云飞, 尹项根, 赖锦木, 等. 基于电能路由器的配电网稳定运行与故障恢复分层能量优化[J]. 电力自动化设备, 2022, 42(4): 154-164.
Du Yunfei, Yin Xianggen, Lai Jinmu, et al.Hierarchical energy optimization based on electric energy router for distribution network in stable operation and fault recovery[J]. Electric Power Automation Equipment, 2022, 42(4): 154-164.
[7] 王建元, 朱永涛, 秦思远. 基于方向行波能量的小电流接地系统故障选线方法[J]. 电工技术学报, 2021, 36(19): 4085-4096.
Wang Jianyuan, Zhu Yongtao, Qin Siyuan.Fault line selection method for small current grounding system based on directional traveling wave energy[J]. Transactions of China Electrotechnical Society, 2021, 36(19): 4085-4096.
[8] Lu Weining, Li Yipeng, Cheng Yu, et al.Early fault detection approach with deep architectures[J]. IEEE Transactions on Instrumentation and Measurement, 2018, 67(7): 1679-1689.
[9] Wang Xiaowei, Gao Jie, Wei Xiangxiang, et al.High impedance fault detection method based on variational mode decomposition and teager-Kaiser energy operators for distribution network[J]. IEEE Transactions on Smart Grid, 2019, 10(6): 6041-6054.
[10] 王晓卫, 高杰, 吴磊, 等. 柔性直流配电网高阻接地故障检测方法[J]. 电工技术学报, 2019, 34(13): 2806-2819.
Wang Xiaowei, Gao Jie, Wu Lei, et al.A high impedance fault detection method for flexible DC distribution network[J]. Transactions of China Electrotechnical Society, 2019, 34(13): 2806-2819.
[11] 韦明杰, 石访, 张恒旭, 等. 基于零序电流波形区间斜率曲线的配电网高阻接地故障检测[J]. 电力系统自动化, 2020, 44(14): 164-171.
Wei Mingjie, Shi Fang, Zhang Hengxu, et al.Detection of high impedance grounding fault in distribution network based on interval slope curves of zero-sequence current[J]. Automation of Electric Power Systems, 2020, 44(14): 164-171.
[12] 刘晓琴, 王大志, 江雪晨, 等. 利用行波到达时差关系的配电网故障定位算法[J]. 中国电机工程学报, 2017, 37(14): 4109-4115, 4290.
Liu Xiaoqin, Wang Dazhi, Jiang Xuechen, et al.Fault location algorithm for distribution power network based on relationship in time difference of arrival of traveling wave[J]. Proceedings of the CSEE, 2017, 37(14): 4109-4115, 4290.
[13] Shi Shenxing, Zhu Beier, Lei Aoyu, et al.Fault location for radial distribution network via topology and reclosure-generating traveling waves[J]. IEEE Transactions on Smart Grid, 2019, 10(6): 6404-6413.
[14] Chen Baichao, Yu Na, Chen Bo, et al.Fault location for underground cables in ungrounded MV distribution networks based on ZSC signal injection[J]. IEEE Transactions on Power Delivery, 2021, 36(5): 2965-2977.
[15] 贾科, 李论, 宣振文, 等. 基于扰动注入的柔性直流配电网主动故障定位及其仿真研究[J]. 电力系统保护与控制, 2019, 47(4): 99-106.
Jia Ke, Li Lun, Xuan Zhenwen, et al.Study on fault location method and simulation for VSC-DC distribution network based on disturbance injection[J]. Power System Protection and Control, 2019, 47(4): 99-106.
[16] 李泽文, 刘基典, 席燕辉, 等. 基于暂态波形相关性的配电网故障定位方法[J]. 电力系统自动化, 2020, 44(21): 72-79.
Li Zewen, Liu Jidian, Xi Yanhui, et al.Fault location method for distribution network based on transient waveform correlation[J]. Automation of Electric Power Systems, 2020, 44(21): 72-79.
[17] 邢晓东, 石访, 张恒旭, 等. 基于同步相量的有源配电网自适应故障区段定位方法[J]. 电工技术学报, 2020, 35(23): 4920-4930.
Xing Xiaodong, Shi Fang, Zhang Hengxu, et al.Adaptive section location method for active distribution network based on synchronized phasor measurement[J]. Transactions of China Electrotechnical Society, 2020, 35(23): 4920-4930.
[18] 邓丰, 李欣然, 曾祥君, 等. 基于多端故障行波时差的含分布式电源配电网故障定位新方法[J]. 中国电机工程学报, 2018, 38(15): 4399-4409, 4640.
Deng Feng, Li Xinran, Zeng Xiangjun, et al.A novel multi-terminal fault location method based on traveling wave time difference for radial distribution systems with distributed generators[J]. Proceedings of the CSEE, 2018, 38(15): 4399-4409, 4640.
[19] 谢李为, 李勇, 罗隆福, 等. 基于距离矩阵与分支系数的配电网故障定位方法[J]. 中国电机工程学报, 2020, 40(7): 2180-2191, 2397.
Xie Liwei, Li Yong, Luo Longfu, et al.Fault location method for distribution networks based on distance matrix and branch coefficient[J]. Proceedings of the CSEE, 2020, 40(7): 2180-2191, 2397.
[20] Ghaderi A, Mohammadpour H A, Ginn H L, et al.High-impedance fault detection in the distribution network using the time-frequency-based algorithm[J]. IEEE Transactions on Power Delivery, 2015, 30(3): 1260-1268.
[21] Baghaee H R, Mlakić D, Nikolovski S, et al.Support vector machine-based islanding and grid fault detection in active distribution networks[J]. IEEE Journal of Emerging and Selected Topics in Power Electronics, 2020, 8(3): 2385-2403.
[22] Guo Moufa, Gao Jianhong, Shao Xiang, et al.Location of single-line-to-ground fault using 1-D convolutional neural network and waveform concatenation in resonant grounding distribution systems[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-9.
[23] Chen Kunjin, Hu Jun, Zhang Yu, et al.Fault location in power distribution systems via deep graph convolutional networks[J]. IEEE Journal on Selected Areas in Communications, 2020, 38(1): 119-131.
[24] 李佳玮, 王小君, 和敬涵, 等. 基于图注意力网络的配电网故障定位方法[J]. 电网技术, 2021, 45(6): 2113-2121.
Li Jiawei, Wang Xiaojun, He Jinghan, et al.Distribution network fault location based on graph attention network[J]. Power System Technology, 2021, 45(6): 2113-2121.
[25] Li Wenchu, Liu Yanli, Li Ying, et al.Series arc fault diagnosis and line selection method based on recurrent neural network[J]. IEEE Access, 2020, 8: 177815-177822.
[26] Aslan Y, Yağan Y E.Artificial neural-network-based fault location for power distribution lines using the frequency spectra of fault data[J]. Electrical Engineering, 2017, 99(1): 301-311.
[27] Guo Moufa, Yang N C, Chen Weifan.Deep-learning-based fault classification using Hilbert-Huang transform and convolutional neural network in power distribution systems[J]. IEEE Sensors Journal, 2019, 19(16): 6905-6913.
[28] Zhao Minghang, Zhong Shisheng, Fu Xuyun, et al.Deep residual networks with adaptively parametric rectifier linear units for fault diagnosis[J]. IEEE Transactions on Industrial Electronics, 2021, 68(3): 2587-2597.
[29] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016: 770-778.
[30] Ioffe S, Szegedy C.Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//International Conference on Machine Learning, Lille, France, 2015: 1-11.
[31] Glorot X, Bordes A, Bengio Y.Deep sparse rectifier neural networks[C]//International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, USA, 2011: 315-323.
[32] Lin Min, Chen Qiang, Yan Shuicheng, Network in network[C]//International Conference on Learning Representations, Banff, Canada, 2013: 1-9.
[33] Krizhevsky A, Sutskever I, Hinton G E.ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[34] Kingma D, Lei B J.Adam: a method for stochastic optimization[C]//International Conference on Learning Representations, San Diego, USA, 2015: 1-15.
[35] He Lili, Shuai Zhikang, Chu Xu, et al.Waveform difference feature-based protection scheme for islanded microgrids[J]. IEEE Transactions on Smart Grid, 2021, 12(3): 1939-1952.
[36] Shuai Zhikang, Shen Chao, Yin Xin, et al.Fault analysis of inverter-interfaced distributed generators with different control schemes[J]. IEEE Transactions on Power Delivery, 2018, 33(3): 1223-1235.
[37] Shuai Zhikang, Huang Wen, Shen Chao, et al.Characteristics and restraining method of fast transient inrush fault currents in synchronverters[J]. IEEE Transactions on Industrial Electronics, 2017, 64(9): 7487-7497.
[38] Maaten L, Hinton G.Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(86): 2579-2605.