Research on fault diagnosis of active distribution network based on parallel fusion deep residual shrinkage network

doi:10.3969/j.issn.2097-0706.2024.06.002

Abstract

Abstract:

Since the faults of the distribution networks with distributed generators present diversity，and the fault diagnoses are vulnerable to nonlinear factors such as the type of distributed generators and their outputs， a fault diagnosis model based on a parallel fusion deep residual shrinkage network（P-FDRSN） is proposed. The P-FDRSN is constructed by two parallel networks， a fault identification branch and a fault location branch. The parallel structure introduces shrinkage mechanism into its residual module to reduce the influence of noise or redundant information on the network and to improve the robustness of the network against noise. After transforming fault recording signal waveforms into grayscale images and time-frequency images，the signals are fed into the DRSN for deep feature extraction， and then， the acquired features are fused in the convergence layer， so as to enhance the feature learning capability on the fault recording signals. Finally， the simulation results show that the fault location and identification accuracies of the proposed model for various types of distributed generators of different outputs can be maintained above 98.75% and 97.25%， respectively. Even under the interference of noise，the diagnosis accuracy of the model will be kept above 96.75%，showing a high accuracy and decent robustness.

Key words: active distribution network, distributed generator, fault diagnosis, parallel network structure, fusion deep residual shrinkage network

CLC Number:

TM614

FENG Ji, YANG Guohua, SHI Lei, PAN Huan, LU Yuxiang, ZHANG Yuanxi, LI Zhen. Research on fault diagnosis of active distribution network based on parallel fusion deep residual shrinkage network[J]. Integrated Intelligent Energy, 2024, 46(6): 8-15.

Figures/Tables 13

Fig.1

Fig.2

Fig.3

Table 1

Features of different fault types

故障类型	$I a$	$I b$	$I c$	$U a$	$U b$	$U c$
A单相接地	√
B单相接地		√
C单相接地			√
AB相间短路	√	√
BC相间短路		√	√
CA相间短路	√		√
AB接地短路	√	√		降低	降低	上升
BC两相接地短路		√	√	上升	降低	降低
CA两相接地短路	√		√	降低	上升	降低
三相短路	√	√	√

Table 1

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Table 2

Fig.9

Table 3

Table 4

References 25

[1]	曲正伟, 张嘉曦, 王云静, 等. 考虑分布式电源不确定性的配电网改进仿射状态估计[J]. 电力系统自动化, 2021, 45(23): 104-112.
	QU Zhengwei, ZHANG Jiaxi, WANG Yunjing, et al. Improved affine state estimation for distribution network considering uncertainty of distributed generator[J]. Automation of Electric Power Systems, 2021, 45(23): 104-112.
[2]	晁晨栩, 郑晓冬, 高飘, 等. 含高比例光伏配电网的高频阻抗差动保护[J]. 中国电机工程学报, 2021, 41(20): 6968-6979.
	CHAO Chenxu, ZHENG Xiaodong, GAO Piao, et al. High frequency impedance differential protection with high proportion of photovoltaic power distribution network[J]. Proceedings of the CSEE, 2021, 41(20): 6968-6979.
[3]	CHEN K J, HU J, ZHANG Y, 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.
[4]	徐岩, 邹南, 马天祥. 逆变型分布式电源接入配电网单相断线故障零序电压分析[J]. 电力系统保护与控制, 2022, 50(2): 41-51.
	XU Yan, ZOU Nan, MA Tianxiang. Analysis of zero-sequence voltage of a single-phase disconnection fault of inverter interfaced distributed generation connected to a distribution network[J]. Power System Protection and Control, 2022, 50(2): 41-51.
[5]	马喜平, 贾嵘, 梁琛, 等. 高比例新能源接入下电力系统降损研究综述[J]. 电网技术, 2022, 46(11): 4305-4315.
	MA Xiping, JIA Rong, LIANG Chen, et al. Review of research on loss reduction in the context of high penetration of renewable power generation[J]. Power System Technology, 2022, 46(11): 4305-4315.
[6]	XIAO J, ZU G Q, ZHOU H, et al. Total quadrant security region for active distribution network with high penetration of distributed generation[J]. Journal of Modern Power Systems and Clean Energy, 2021, 9(1): 128-137.
[7]	SHARMA S, NIAZI K R, VERMA K, et al. Impact of battery energy storage,controllable load and network reconfiguration on contemporary distribution network under uncertain environment[J]. IET Generation, Transmission & Distribution, 2020, 14(21): 4719-4727.
[8]	詹惠瑜, 刘科研, 盛万兴, 等. 有源配电网故障诊断与定位方法综述及展望[J]. 高电压技术, 2023, 49(2): 660-671.
	ZHAN Huiyu, LIU Keyan, SHENG Wanxing, et al. Literature review and prospects of fault diagnosis in active distribution network[J]. High Voltage Engineering, 2023, 49(2): 660-671.
[9]	吉兴全, 张朔, 张玉敏, 等. 基于IELM算法的配电网故障区段定位[J]. 电力系统自动化, 2021, 45(22): 157-166.
	JI Xingquan, ZHANG Shuo, ZHANG Yumin, et al. Fault section location for distribution network based on improved electromagnetism-like mechanism algorithm[J]. Automation of Electric Power Systems, 2021, 45(22): 157-166.
[10]	高锋阳, 曾林, 李昭君, 等. 分布式智能协同和云计算相结合的配电网故障选线新方法[J]. 电网技术, 2021, 45(8): 2969-2978.
	GAO Fengyang, ZENG Lin, LI Zhaojun, et al. A new fault line selection method for distribution network based on distributed intelligent collaboration and cloud computing[J]. Power System Technology, 2021, 45(8): 2969-2978.
[11]	齐郑, 赵昕一, 陈艳波. 暂态与稳态相不对称信号相结合的配电网单相接地故障感知技术[J]. 高电压技术, 2022, 48(4): 1264-1276.
	QI Zheng, ZHAO Xinyi, CHEN Yanbo. Single phase grounding fault sensing technology in distribution network based on transient and steady state phase unsymmetrical signals[J]. High Voltage Engineering, 2022, 48(4): 1264-1276.
[12]	洪翠, 连淑婷, 郭谋发, 等. 经验小波变换在直流配电系统故障检测中的应用[J]. 电机与控制学报, 2021, 25(12): 65-74.
	HONG Cui, LIAN Shuting, GUO Moufa, et al. Application of empirical wavelet transform in fault detection of DC distribution system[J]. Electric Machines and Control, 2021, 25(12): 65-74.
[13]	张晨浩, 李洋, 宋国兵, 等. 基于模型识别的配电网谐波源定位方法[J]. 中国电机工程学报, 2021, 41(17): 5803-5813.
	ZHANG Chenhao, LI Yang, SONG Guobing, et al. Harmonic source location method for distribution networks based on model recognition[J]. Proceedings of the CSEE, 2021, 41(17): 5803-5813.
[14]	束洪春, 龚振, 田鑫萃, 等. 基于故障特征频带及形态谱的单相接地故障选线[J]. 电网技术, 2019, 43(3): 1041-1048.
	SHU Hongchun, GONG Zhen, TIAN Xincui, et al. Single line-to-ground fault line selection based on fault characteristic frequency band and morphological spectrum[J]. Power System Technology, 2019, 43(3): 1041-1048.
[15]	喻锟, 胥鹏博, 曾祥君, 等. 基于模糊测度融合诊断的配电网接地故障选线[J]. 电工技术学报, 2022, 37(3): 623-633.
	YU Kun, XU Pengbo, ZENG Xiangjun, et al. Grounding fault line selection of distribution networks based on fuzzy measures integrated diagnosis[J]. Transactions of China Electrotechnical Society, 2022, 37(3): 623-633.
[16]	和敬涵, 罗国敏, 程梦晓, 等. 新一代人工智能在电力系统故障分析及定位中的研究综述[J]. 中国电机工程学报, 2020, 40(17): 5506-5516.
	HE Jinghan, LUO Guomin, CHENG Mengxiao, et al. A research review on application of artificial intelligence in power system fault analysis and location[J]. Proceedings of the CSEE, 2020, 40(17): 5506-5516.
[17]	LIANG J F, JING T J, NIU H N, et al. Two-terminal fault location method of distribution network based on adaptive convolution neural network[J]. IEEE Access, 2020, 8: 54035-54043.
[18]	刘科研, 董伟杰, 肖仕武, 等. 基于电压数据SVM分类的有源配电网故障判别及定位[J]. 电网技术, 2021, 45(6): 2369-2379.
	LIU Keyan, DONG Weijie, XIAO Shiwu, et al. Fault identification and location of active distribution network based on SVM classification of voltage data[J]. Power System Technology, 2021, 45(6): 2369-2379.
[19]	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.
[20]	赵恺, 石立宝. 基于改进一维卷积神经网络的电力系统暂态稳定评估[J]. 电网技术, 2021, 45(8): 2945-2957.
	ZHAO Kai, SHI Libao. Transient stability assessment of power system based on improved one-dimensional convolutional neural network[J]. Power System Technology, 2021, 45(8): 2945-2957.
[21]	符金伟, 史常凯, 尹惠, 等. 基于综合特征矩阵的配电网故障判别方法[J]. 中国电力, 2021, 54(11): 125-132.
	FU Jinwei, SHI Changkai, YIN Hui, et al. Distribution network fault type identification method based on feature-summarizing matrix[J]. Electric Power, 2021, 54(11): 125-132.
[22]	徐艳春, 赵彩彩, 孙思涵, 等. 基于改进LMD和能量相对熵的主动配电网故障定位方法[J]. 中国电力, 2021, 54(11): 133-143.
	XU Yanchun, ZHAO Caicai, SUN Sihan, et al. Fault location for active distribution network based on improved LMD and energy relative entropy[J]. Electric Power, 2021, 54(11): 133-143.
[23]	ZENG X, GAO W, YANG G. High impedance fault detection in distribution network based on S-transform and average singular entropy[J]. Global Energy Interconnection, 2023, 6(1): 64-80.
[24]	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]// Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2016: 770-778.
[25]	马鑫, 尚毅梓, 胡昊, 等. 基于数据特征增强和残差收缩网络的变压器故障识别方法[J]. 电力系统自动化, 2022, 46(3): 175-183.
	MA Xin, SHANG Yizi, HU Hao, et al. Identification method of transformer fault based on data feature enhancement and residual shrinkage network[J]. Automation of Electric Power Systems, 2022, 46(3): 175-183.

信噪比/dB	灰度图+P-DRN		时频图+P-DRN		灰度图+P-DRSN		时频图+P-DRSN		P-FDRN		P-FDRSN
信噪比/dB	定位准确率/%	识别准确率/%	定位准确率/%	识别准确率/%	定位准确率/%	识别准确率/%	定位准确率/%	识别准确率/%	定位准确率/%	识别准确率/%	定位准确率/%	识别准确率/%
37.36	94.75	94.17	95.25	93.33	95.33	96.42	96.67	94.50	97.08	96.42	99.00	98.50
31.30	93.83	93.83	94.58	92.67	95.17	95.17	95.75	93.92	96.67	96.08	98.58	98.33
27.01	93.08	92.67	93.67	91.75	94.42	94.33	94.17	93.42	95.25	95.17	98.25	97.42
25.57	92.42	92.08	93.00	90.42	93.67	93.58	94.58	92.75	94.83	94.42	97.83	97.00
23.54	91.28	91.50	92.58	88.25	92.75	93.50	94.50	92.25	94.00	93.50	97.25	96.75

模型	定位准确率	识别准确率
时频图+P-DRN	96.92	94.67
灰度图+P-DRN	95.75	95.42
时频图+P-DRSN	97.83	96.25
灰度图+P-DRSN	97.00	96.67
P-FDRN	98.67	97.83
P-FDRSN	99.25	98.83

DG接入情况	输出功率水平	灰度图+P-DRN		时频图+P-DRN		灰度图+P-DRSN		时频图+P-DRSN		P-FDRN		P-FDRSN
DG接入情况	输出功率水平	定位准确率	识别准确率	定位准确率	识别准确率	定位准确率	识别准确率	定位准确率	识别准确率	定位准确率	识别准确率	定位准确率	识别准确率
风电	40	90.75	91.92	93.50	89.67	92.25	93.92	95.33	91.75	96.17	95.17	97.67	97.17
风电	70	93.25	93.17	95.42	91.33	93.42	95.08	96.17	93.67	97.25	96.08	97.92	97.75
光伏	50	93.25	92.75	94.75	90.08	93.67	94.17	96.00	93.25	96.58	95.42	97.92	97.50
光伏	70	94.00	93.42	95.58	91.67	94.92	95.75	96.92	94.58	97.42	96.50	98.33	97.83
风电、光伏	50，70	93.67	94.67	96.25	91.50	94.25	95.67	96.42	93.83	96.33	95.75	98.58	98.08
风电、光伏	100，40	94.33	95.08	96.67	92.83	95.25	96.33	97.25	95.08	97.67	97.17	99.00	98.58