Single-ended Fault Diagnosis of Flexible DC Grid Based on Swin Transformer

doi:10.12204/j.issn.1000-7229.2023.05.006

Abstract

Abstract:

In this study, a single-ended fault diagnosis method for flexible DC power grids based on Swin Transformer is proposed to address the problems of low precision, susceptibility to transition resistance, and requiring manual input to set the threshold in the existing fault detection methods of flexible DC power grids. First, we collect the transient voltage time-domain data at fault and convert it into a two-dimensional gramian angular field(GAF) image with a better recognition effect after data processing, which is used for offline training of the Swin Transformer; Second fault features are extracted using the moving window of the Swin Transformer, and different fault diagnoses are realized according to the training results. This method does not require manual setting of the threshold. Finally, after many simulations, it is proven that the method proposed in this study satisfies the quick action requirement, can accurately diagnose faults, and has strong transition resistance and anti-noise ability.

Key words: flexible DC grid, swin transformer, fault diagnosis, Gramian angular field, single-ended

CLC Number:

TM773

YANG Junhao, WEI Yanfang, WANG Peng, WANG Xiaowei, ZENG Zhihui. Single-ended Fault Diagnosis of Flexible DC Grid Based on Swin Transformer[J]. ELECTRIC POWER CONSTRUCTION, 2023, 44(5): 53-60.

Figures/Tables 15

Fig.1 Topology of four-terminal MMC-HVDC system

Fig.2 Voltage of positive ground fault

Fig.3 Voltage of negative ground fault

Fig.4 Waveform of interpole fault voltage

Fig.5 Structure diagram of swin transformer

Fig.6 Swin transformer block

Fig.7 GADF image voltage data

Fig.8 Flow chart of fault diagnosis

Table 1 System parameters

Table 2 Training results of swin transformer

Fig.9 Comparison results of GADF and GASF

Table 3 Influence of different transition resistances

Fig.10 Positive voltage with 30 dB noise added

Fig.11 Comparison results of different artificial intelligence algorithms

Table 4 Comparison of different protection methods

References 30

[1]	严胜, 罗湘, 贺之渊. 直流电网核心装备及关键技术展望[J]. 电力系统自动化, 2019, 43(3):205-215.
	YAN Sheng, LUO Xiang, HE Zhiyuan. Prospect of core equipment and key technology for DC power grid[J]. Automation of Electric Power Systems, 2019, 43(3):205-215.
[2]	杨志勇, 杨炳元, 任永峰, 等. 基于单端高频电流量的MMC-MTDC输电线路保护方案[J]. 电力系统保护与控制, 2022, 50(14):151-160.
	YANG Zhiyong, YANG Bingyuan, REN Yongfeng, et al. Transmission line protection scheme of MMC-MTDC based on single terminal high frequency current[J]. Power System Protection and Control, 2022, 50(14):151-160.
[3]	陆晶晶, 贺之渊, 赵成勇, 等. 直流输电网规划关键技术与展望[J]. 电力系统自动化, 2019, 43(2):182-191.
	LU Jingjing, HE Zhiyuan, ZHAO Chengyong, et al. Key technologies and prospects for DC power grid planning[J]. Automation of Electric Power Systems, 2019, 43(2):182-191.
[4]	徐政, 刘高任, 张哲任. 柔性直流输电网的故障保护原理研究[J]. 高电压技术, 2017, 43(1):1-8.
	XU Zheng, LIU Gaoren, ZHANG Zheren. Research on fault protection principle of DC grids[J]. High Voltage Engineering, 2017, 43(1):1-8.
[5]	张怿宁, 陈可傲, 罗易萍, 等. 基于暂态电流相关系数的混合多端高压直流输电线路保护[J]. 电力建设, 2021, 42(5):113-121. doi: 10.12204/j.issn.1000-7229.2021.05.012
	ZHANG Yining, CHEN Keao, LUO Yiping, et al. Hybrid multi-terminal HVDC transmission line protection based on transient current correlation coefficient[J]. Electric Power Construction, 2021, 42(5):113-121.
[6]	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.
[7]	文卫兵, 魏争, 赖佳祥, 等. 柔性直流电网直流侧故障下500 kV混合式直流断路器暂态电流特性分析[J]. 电力建设, 2022, 43(10):48-57. doi: 10.12204/j.issn.1000-7229.2022.10.005
	WEN Weibing, WEI Zheng, LAI Jiaxiang, et al. Analyze of transient current characteristics of hybrid DC circuit breaker in 500 kV VSC-HVDC grid[J]. Electric Power Construction, 2022, 43(10):48-57. doi: 10.12204/j.issn.1000-7229.2022.10.005
[8]	李斌, 何佳伟. 多端柔性直流电网故障隔离技术研究[J]. 中国电机工程学报, 2016, 36(1):87-95.
	LI Bin, HE Jiawei. Research on the DC fault isolating technique in multi-terminal DC system[J]. Proceedings of the CSEE, 2016, 36(1):87-95.
[9]	ELSEROUGI A A, ABDEL-KHALIK A S, MASSOUD A M, et al. A new protection scheme for HVDC converters against DC-side faults with current suppression capability[J]. IEEE Transactions on Power Delivery, 2014, 29(4): 1569-1577. doi: 10.1109/TPWRD.2014.2325743 URL
[10]	王振浩, 李金伦, 王欣铎, 等. 风电接入真双极MMC-MTDC系统直流故障穿越协调控制策略[J]. 电力建设, 2022, 43(10):26-36. doi: 10.12204/j.issn.1000-7229.2022.10.003
	WANG Zhenhao, LI Jinlun, WANG Xinduo, et al. DC Fault ride-through coordinated control strategies for bipolar MMC-MTDC system with wind power connected[J]. Electric Power Construction, 2022, 43(10):26-36. doi: 10.12204/j.issn.1000-7229.2022.10.003
[11]	宋国兵, 陈哲鸿, 侯俊杰, 等. 基于电荷量变化特征的高压直流线路纵联保护[J]. 电力系统及其自动化学报, 2020, 32(10):9-16.
	SONG Guobing, CHEN Zhehong, HOU Junjie, et al. Pilot protection for HVDC transmission lines based on charge variation characteristics[J]. Proceedings of the CSU-EPSA, 2020, 32(10):9-16.
[12]	戴志辉, 严思齐, 张程, 等. 基于电流特征量相关系数的UHVDC线路纵联保护新原理[J]. 电力系统保护与控制, 2018, 46(22):31-38.
	DAI Zhihui, YAN Siqi, ZHANG Cheng, et al. A new pilot protection for UHVDC lines based on correlation coefficient of designed current variables[J]. Power System Protection and Control, 2018, 46(22):31-38.
[13]	戴文睿, 林圣. 基于线模电流故障分量的高压直流输电线路纵联保护方案[J]. 电力系统自动化, 2020, 44(19):142-149.
	DAI Wenrui, LIN Sheng. Pilot protection scheme for HVDC transmission line based on fault component of aerial mode current[J]. Automation of Electric Power Systems, 2020, 44(19):142-149.
[14]	王思华, 赵磊, 王军军, 等. 基于MMC的直流输电系统双极短路故障保护策略研究[J]. 电力系统保护与控制, 2021, 49(11):9-17.
	WANG Sihua, ZHAO Lei, WANG Junjun, et al. Research on protection strategy of a bipolar short circuit fault in an HVDC transmission system based on MMC[J]. Power System Protection and Control, 2021, 49(11):9-17.
[15]	杨冬锋, 王鹤, 刘晓军, 等. 基于测量阻抗拟合特征的MTDC电网直流线路纵联保护[J]. 电网技术, 2022, 46(12):4699-4712.
	YANG Dongfeng, WANG He, LIU Xiaojun, et al. Pilot protection for MTDC grid based on fitting characteristics of measured impedance[J]. Power System Technology, 2022, 46(12):4699-4712.
[16]	贾科, 陈淼, 施志明, 等. 基于限流电抗器电压积分凹凸性的柔性直流输电线路单端量保护方案[J]. 电网技术, 2021, 45(11):4498-4505.
	JIA Ke, CHEN Miao, SHI Zhiming, et al. Single-ended protection scheme of flexible DC transmission lines based on concavity and convexity of the current-limiting reactor voltage integration[J]. Power System Technology, 2021, 45(11):4498-4505.
[17]	侯俊杰, 宋国兵, 常仲学, 等. 基于暂态功率的高压直流线路单端量保护[J]. 电力系统自动化, 2019, 43(21):203-212.
	HOU Junjie, SONG Guobing, CHANG Zhongxue, et al. Transient power based single-end protection for HVDC transmission line[J]. Automation of Electric Power Systems, 2019, 43(21):203-212.
[18]	戴志辉, 刘自强, 刘雪燕, 等. 基于首行波曲率的柔性直流输电线路单端量保护[J]. 电工技术学报, 2021, 36(9):1831-1841.
	DAI Zhihui, LIU Ziqiang, LIU Xueyan, et al. Single-ended protection for flexible DC transmission line based on curvature of initial traveling wave[J]. Transactions of China Electrotechnical Society, 2021, 36(9):1831-1841.
[19]	李斌, 何佳伟, 李晔, 等. 基于边界特性的多端柔性直流配电系统单端量保护方案[J]. 中国电机工程学报, 2016, 36(21):5741-5749.
	LI Bin, HE Jiawei, LI Ye, et al. Single-ended protection scheme based on boundary characteristic for the multi-terminal VSC-based DC distribution system[J]. Proceedings of the CSEE, 2016, 36(21):5741-5749.
[20]	权文杰, 童晓阳, 张广骁. 基于S变换行波能谱矩阵相似度的柔性直流单端保护方案[J]. 电力系统自动化, 2022, 46(7):178-186.
	QUAN Wenjie, TONG Xiaoyang, ZHANG Guangxiao. Single-end flexible DC protection scheme based on similarity of S-transform energy spectrum matrix of traveling wave[J]. Automation of Electric Power Systems, 2022, 46(7):178-186.
[21]	魏东, 龚庆武, 来文青, 等. 基于卷积神经网络的输电线路区内外故障判断及故障选相方法研究[J]. 中国电机工程学报, 2016, 36(S1):21-28.
	WEI Dong, GONG Qingwu, LAI Wenqing, et al. Research on internal and external fault diagnosis and fault-selection of transmission line based on convolutional neural network[J]. Proceedings of the CSEE, 2016, 36(S1):21-28.
[22]	王浩, 杨东升, 周博文, 等. 基于并联卷积神经网络的多端直流输电线路故障诊断[J]. 电力系统自动化, 2020, 44(12):84-92.
	WANG Hao, YANG Dongsheng, ZHOU Bowen, et al. Fault diagnosis of multi-terminal HVDC transmission line based on parallel convolutional neural network[J]. Automation of Electric Power Systems, 2020, 44(12):84-92.
[23]	HOSSAM-ELDIN A, LOTFY A, ELGAMAL M, et al. Artificial intelligence-based short-circuit fault identifier for MT HVDC systems[J]. IET Generation, Transmission & Distribution, 2018, 12(10):2436-2443. doi: 10.1049/gtd2.v12.10 URL
[24]	LIU Z, LIN Y T, CAO Y, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021:10012-10022.
[25]	XIE J, WU Z, ZHU R, et al. Melanoma detection based on swin transformer and SimAM[C]// 2021 IEEE 5th Information Technology,Networking,Electronic and Automation Control Conference(ITNEC). 2021:1517-1521.
[26]	LIU Z, TAN Y, HE Q, et al. SwinNet:swin transformer drives edge-aware RGB-D and RGB-T salient object detection[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 32(7):4486-4497. doi: 10.1109/TCSVT.2021.3127149 URL
[27]	LIANG J, CAO J, SUN G, et al. SwinIR: image restoration using swin transformer[C]// 2021 IEEE/ CVF International Conferenceon Computer Vision Workshops(ICCVW). 2021:1833-1844.
[28]	WANG W H, XIE E Z, LI X, et al. Pyramid vision transformer:a versatile backbone for dense prediction without convolutions[DB/OL].[2022-04-12]. https://arxiv.org/pdf/2102.12122.pdf.
[29]	WANG Z, OATES T. Imaging time-series to improve classification and imputation[C]// Proceedings of the Twen-ty-Fourth International Joint Conference on Artificial Intel-ligence.Buenos Aires,Argentina, 2015:3939-3945.
[30]	高本锋, 董沛毅, 刘辛晔, 等. 高压直流输电线路微分欠压保护特性与定值整定[J]. 电网技术, 2015, 39(8):2303-2311.
	GAO Benfeng, DONG Peiyi, LIU Xinye, et al. Research of HVDC transmission line differential under-voltage protection characteristics and value setting[J]. Power System Technology, 2015, 39(8):2303-2311.