Identification of Inrush Current and Fault Current Based on Long Short-Term Memory Neural Network

doi:10.16183/j.cnki.jsjtu.2022.352

Abstract

Abstract:

The problem of differential protection maloperation caused by inrush current during no-load closing of transformer has not been completely solved so far. To solve this problem, a method using long short-term memory (LSTM) neural network to identify inrush current and fault current is proposed. First, the simulation model of no-load closing and internal fault of transformer is built on the PSCAD software platform, and a large amount of three-phase current instantaneous sampling data is generated through simulation as the sample set to train the neural network. Then, the LSTM neural network model is built and trained by using the Keras platform. Finally, the new simulation data and fault recorder data is used to test the trained LSTM neural network. The results show that the LSTM neural network can quickly and accurately distinguish the inrush current and fault current under various conditions, which proves the effectiveness of the proposed method.

Key words: transformer differential protection, long short-term memory (LSTM) neural network, inrush current identification, fault current identification

CLC Number:

TM406
TP305

ZHANG Guodong, LIU Kai, PU Haitao, YAO Fuqiang, ZHANG Shuaishuai. Identification of Inrush Current and Fault Current Based on Long Short-Term Memory Neural Network[J]. Journal of Shanghai Jiao Tong University, 2024, 58(5): 730-738.

Figures/Tables 14

Fig.1

Fig.2

Fig.3

Tab.1

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Tab.2

Fig.12

References 28

[1]	王阳, 许志红. 基于组合式开关的三相变压器励磁涌流抑制策略[J]. 电力自动化设备, 2019, 39(7): 99-106.
	WANG Yang, XU Zhihong. Inrush current suppression strategy of three-phase transformer based on combined-switches[J]. Electric Power Automation Equipment, 2019, 39(7): 99-106.
[2]	方春恩, 曾俊龙, 陈川江, 等. 基于三相联动断路器的空载变压器选相关合[J]. 高电压技术, 2020, 46(3): 898-905.
	FANG Chun’en, ZENG Junlong, CHEN Chuanjiang, et al. Controlled closing of unloaded transformer with ganged three operated circuit breaker[J]. High Voltage Engineering, 2020, 46(3): 898-905.
[3]	陈川江, 方春恩, 李伟, 等. 计及剩磁的中性点不接地变压器选相合闸仿真与实验[J]. 高电压技术, 2019, 45(11): 3521-3528.
	CHEN Chuanjiang, FANG Chun’en, LI Wei, et al. Simulation and experiment of controlled switching for isolated neutral transformer considering residual flux[J]. High Voltage Engineering, 2019, 45(11): 3521-3528.
[4]	李春艳, 周念成, 王强钢, 等. 基于软启动的变压器励磁涌流抑制方法[J]. 电工技术学报, 2020, 35(17): 3640-3651.
	LI Chunyan, ZHOU Niancheng, WANG Qianggang, et al. A method to eliminate transformer inrush currents using soft-starter-based controlled energization[J]. Transactions of China Electrotechnical Society, 2020, 35(17): 3640-3651.
[5]	黄景光, 赵娇娇, 林湘宁, 等. 基于SPWM的变压器励磁涌流抑制技术研究[J]. 高压电器, 2019, 55(10): 210-215.
	HUANG Jingguang, ZHAO Jiaojiao, LIN Xiang-ning, et al. Research on inrush current suppression technology of transformer based on SPWM[J]. High Voltage Apparatus, 2019, 55(10): 210-215.
[6]	张瑞, 甘战, 张鹏, 等. 换流变压器空载励磁涌流选相关合控制策略[J]. 电力系统保护与控制, 2019, 47(15): 69-77.
	ZHANG Rui, GAN Zhan, ZHANG Peng, et al. Controlled switching strategies to eliminate the inrush current of converter transformer[J]. Power System Protection & Control, 2019, 47(15): 69-77.
[7]	姚东晓, 张凯, 贺要锋, 等. 变压器多特征励磁涌流识别方案研究[J]. 电力系统保护与控制, 2017, 45(13): 149-154.
	YAO Dongxiao, ZHANG Kai, HE Yaofeng, et al. Research on multi feature recognition scheme of transformer inrush current[J]. Power System Protection & Control, 2017, 45(13): 149-154.
[8]	黄少锋, 李姗姗, 肖远清, 等. 基于非周期分量衰减速率的变压器励磁涌流鉴别方法[J]. 电力系统保护与控制, 2018, 46(15): 9-15.
	HUANG Shaofeng, LI Shanshan, XIAO Yuanqing, et al. A novel identification criterion for transformer inrush current based on decay rate of aperiodic component[J]. Power System Protection & Control, 2018, 46(15): 9-15.
[9]	李斌, 彭伍龙, 姚斌, 等. 基于复合环流与零序电流特征的换流变压器励磁涌流波形相关性识别方法[J]. 中国电机工程学报, 2020, 40(24): 8027-8038.
	LI Bin, PENG Wulong, YAO Bin, et al. An algorithm of identifying inrush current of converter transformer based on waveform cross-correlation of composite circulation and zero sequence current charateristics[J]. Proceedings of the CSEE, 2020, 40(24): 8027-8038.
[10]	叶志军, 于旺, 郑荣显, 等. 变压器空充下的励磁涌流二次谐波特征分析[J]. 电力系统自动化, 2020, 44(24): 145-150.
	YE Zhijun, YU Wang, ZHENG Rongxian, et al. Characteristic analysis of second harmonic of magnetizing inrush current with no-load transformer energization[J]. Automation of Electric Power Systems, 2020, 44(24): 145-150.
[11]	翁汉琍, 梅瀚予, 郭袆达, 等. 基于差流符号序列特征的变压器励磁涌流识别判据[J]. 电力自动化设备, 2022, 42(6): 206-211.
	WENG Hanli, MEI Hanyu, GUO Yida, et al. Identification criterion of transformer magnetizing inrush current based on symbol sequence characteristic of differential current[J]. Electric Power Automation Equipment, 2022, 42(6): 206-211.
[12]	王育学, 潘远林, 刘玮, 等. 电流互感器暂态特性对涌流传变的影响[J]. 电力系统保护与控制, 2018, 46(18): 80-86.
	WANG Yuxue, PAN Yuanlin, LIU Wei, et al. Effect of CT transient characteristics on transfer of inrush[J]. Power System Protection & Control, 2018, 46(18): 80-86.
[13]	李春艳, 周念成, 廖建权, 等. 基于MEMD-MMFE的双馈风电场送出变压器励磁涌流识别方法[J]. 中国电机工程学报, 2019, 39(17): 5061-5073.
	LI Chunyan, ZHOU Niancheng, LIAO Jianquan, et al. Identifying inrush current for wind form outgoing transformer based on MEMD-MMFE[J]. Proceedings of the CSEE, 2019, 39(17): 5061-5073.
[14]	胡松, 江亚群, 黄纯, 等. 基于PWM波形特征的励磁涌流识别方法[J]. 电力自动化设备, 2018, 38(9): 135-140.
	HU Song, JIANG Yaqun, HUANG Chun, et al. Identification of inrush current based on characteristics of PWM waveform[J]. Electric Power Automation Equipment, 2018, 38(9): 135-140.
[15]	翁汉琍, 陈皓, 万毅, 等. 基于巴氏系数的变压器励磁涌流和故障差流识别新判据[J]. 电力系统保护与控制, 2020, 48(10): 113-122.
	WENG Hanli, CHEN Hao, WAN Yi, et al. A novel criterion to distinguish inrush current from fault current based on the Bhattacharyya coefficient[J]. Power System Protection & Control, 2020, 48(10): 113-122.
[16]	宋九渊, 符玲, 熊思宇, 等. 基于二阶泰勒系数的励磁涌流识别方法[J]. 中国电机工程学报, 2020, 40(3): 1020-1029.
	SONG Jiuyuan, FU Ling, XIONG Siyu, et al. Magnetizing inrush current identification method based on second-order Taylor derivative[J]. Proceedings of the CSEE, 2020, 40(3): 1020-1029.
[17]	张召峰, 孙庆森, 张海峰, 等. 变压器励磁涌流中的信息熵识别[J]. 电力系统保护与控制, 2017, 45(12): 107-111.
	ZHANG Shaofeng, SUN Qingsen, ZHANG Haifeng, et al. Identification of information entropy in transformer inrush current[J]. Power System Protection & Control, 2017, 45(12): 107-111.
[18]	杨挺, 赵黎媛, 王成山. 人工智能在电力系统及综合能源系统中的应用综述[J]. 电力系统自动化, 2019, 43(1): 2-14.
	YANG Ting, ZHAO Liyuan, WANG Chengshan. Review on application of artificial intelligence in power system and integrated energy system[J]. Automation of Electric Power Systems, 2019, 43(1): 2-14.
[19]	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): 5506-5515.
	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): 5506-5515.
[20]	接怡冰. 变压器励磁涌流的仿真及改进模糊Petri网识别方法研究[D]. 青岛: 山东科技大学, 2018.
	JIE Yibing. Research on simulation and improved fuzzy Petri net identification method of magnetizing inrush current in transformer[D]. Qingdao: Shandong University of Science and Technology, 2018.
[21]	许文杰. 变压器励磁涌流与故障识别研究[D]. 西安: 西安科技大学, 2018.
	XU Wenjie. Research on inrush current and identification of transformer[D]. Xi’an: Xi’an University of Science and Technology, 2018.
[22]	曾静. 一种基于小波包和支持向量机的励磁涌流识别新方法[D]. 南宁: 广西大学, 2019.
	ZENG Jing. A new method of magnetizing inrush current recognition based on wavelet packet and support vector machine[D]. Nanning: Guangxi University, 2019.
[23]	杨晨光. 基于卷积神经网络的变压器涌流识别[D]. 西安: 西安科技大学, 2020.
	YANG Chenguang. Transformer inrush current recognition based on convolutional neural network[D]. Xi’an: Xi’an University of Science and Technology, 2020.
[24]	孙黎霞, 白景涛, 周照宇, 等. 基于双向长短期记忆网络的电力系统暂态稳定评估[J]. 电力系统自动化, 2020, 44(13): 64-72.
	SUN Lixia, BAI Jingtao, ZHOU Zhaoyu, et al. Transient stability assessment of power system based on bi-directional long-short-term memory network[J]. Automation of Electric Power Systems, 2020, 44(13): 64-72.
[25]	李滨, 王靖德, 梁水莹, 等. 基于长短期记忆循环神经网络的AGC实时控制策略[J]. 电力自动化设备, 2022, 42(3): 128-134.
	LI Bin, WANG Jingde, LIANG Shuiying, et al. AGC real-time control strategy based on LSTM recurrent neural network[J]. Electric Power Automation Equipment, 2022, 42(3): 128-134.
[26]	黄蔓云, 王天昊, 卫志农, 等. 基于长短期记忆网络的UKF动态谐波状态估计[J]. 电力系统保护与控制, 2022, 50(11): 1-11.
	HUANG Manyun, WANG Tianhao, WEI Zhinong, et al. Dynamic harmonic state estimation of an unscented Kalman filter based on long short-term memory neural networks[J]. Power System Protection & Control, 2022, 50(11): 1-11.
[27]	COLOMBO E, SANTAGOSITINO G. Results of the enquiries on actual network conditions when switching magnetizing and small inductive currents and on transformer and shunt reactor saturation characteristics[J]. Electra, 1984, 94: 35-53.
[28]	PATEL D D, MISTRY K D, CHOTHANI N G. Transformer inrush/internal fault identification based on average angle of second order derivative of current[C]// 2017 IEEE PES Asia-Pacific Power and Energy Engineering Conference. Bangalore, India: IEEE, 2017: 1-6.

层	输出数据形状	参数/个
LSTM1	20×10	560
LSTM2	10	840
隐藏层1	10	100
隐藏层2	10	100
输出层	1	10

厂站名	采样频率/kHz	总点数	步长	样本数	正确率/%	备注
YH	3.2	1800	20	90	100	无
SC	3.2	1600	20	80	100	空充1
SC	3.2	1600	20	80	100	空充2
SC	3.2	1600	20	80	100	空充3
WJ	2.4	1080	20	54	100	无
CJ	5.0	400	20	20	100	保护误动