Method of Sag Type Recognition Based on Deep Learning SDAE-BP

doi:10.11985/2022.03.022

Abstract

Abstract:

The types of sags caused by different short-circuit faults are different, and the impact on users is different. Accurately identifying the types of sags can analyze, compensate and suppress the actual voltage sags, which is of great significance to the management of voltage sags. At the same time, it can also be used as a basis for the coordination of disputes between power supply departments and users. Considering that there may be a phase jump when a short-circuit fault occurs in the actual system, based on the classification of the sag caused by the short-circuit fault in the original literature, the type of the voltage sag caused by the short-circuit fault is derived when the impedance angle of the system impedance and the line impedance are not equal. The expression and its characteristics are analyzed. In order to accurately identify the type of voltage sag and avoid the problem of information loss in the process of artificial feature extraction, a sag type recognition method based on stacked denoised autoencoder-back propagation(SDAE-BP) is proposed. A certain probability of noise is added to the input signal, and then a multi-layer noise reduction self-encoding network is trained layer by layer by constructing to achieve signal feature extraction with the smallest error, and BP neural network is used to identify the type of sag. The correctness of the above-mentioned propagation characteristics and voltage sag type identification method is verified by Matlab simulation.

Key words: Short circuit fault, voltage sag type, stack noise reduction autoencoder, BP neural network, voltage sag type recognition

CLC Number:

ZHANG Jinluan, DENG Zuqiang, ZHANG Xin, WANG Liang. Method of Sag Type Recognition Based on Deep Learning SDAE-BP[J]. Journal of Electrical Engineering, 2022, 17(3): 184-193.

Figures/Tables 12

References 21

[1]	肖湘宁, 韩民晓, 徐永海. 电能质量分析与控制[M]. 北京: 中国电力出版社, 2010.
	XIAO Xiangning, HAN Minxiao, XU Yonghai. Analysis and control of power quality[M]. Beijing: China Electric Power Press, 2010.
[2]	王玲, 高倩倩, 陶顺, 等. 基于暂降类型判断的短路故障类型识别研究[J]. 电测与仪表, 2013, 50(6):8-13.
	WANG Ling, GAO Qianqian, TAO Shun, et al. Research on short-circuit fault type identification based on sag type judgment[J]. Electrical Measurement & Instrumentation, 2013, 50(6):8-13.
[3]	肖湘宁, 陶顺. 中性点不同接地方式下的电压暂降类型及其在变压器间的传递(一)[J]. 电工技术学报, 2007, 22(9):143-153.
	XIAO Xiangning, TAO Shun. Types of voltage sags and their transmission between transformers with different neutral grounding methods (1)[J]. Transactions of China Electrotechnical Society, 2007, 22(9):143-153.
[4]	陶顺, 肖湘宁. 中性点不同接地方式下的电压暂降类型及其在变压器间的传递(二)[J]. 电工技术学报, 2007, 22(10):156-159.
	TAO Shun, XIAO Xiangning. Types of voltage sags and their transfer between transformers with different neutral grounding methods (2)[J]. Transactions of China Electrotechnical Society, 2007, 22(10):156-159.
[5]	WANG Y, BOLLEN M H J, XIAO X Y. Calculation of the phase-angle-jump for voltage dips in three-phase systems[J]. IEEE Transactions on Power Delivery, 2015, 30(1):480-487. doi: 10.1109/TPWRD.2014.2352358
[6]	徐永海, 兰巧倩, 孔祥雨, 等. 电压暂降特征值统计分析及暂降传播特性[J]. 电工技术学报, 2016, 31(11):165-175.
	XU Yonghai, LAN Qiaoqian, KONG Xiangyu, et al. Statistical analysis of voltage sag eigenvalues and sag propagation characteristics[J]. Transactions of China Electrotechnical Society, 2016, 31(11):165-175.
[7]	罗珊珊, 杜晓彤, 张军, 等. 电压暂降通过多级变压器的传播规律研究[J]. 电力电容器与无功补偿, 2019, 40(5):170-175.
	LUO Shanshan, DU Xiaotong, ZHANG Jun, et al. Study on the propagation rule of voltage sag through multi-stage transformers[J]. Power Capacitors and Reactive Compensation, 2019, 40(5):170-175.
[8]	郑智聪, 王红, 齐林海. 基于深度学习模型融合的电压暂降源识别方法[J]. 中国电机工程学报, 2019, 39(1):97-104.
	ZHENG Zhicong, WANG Hong, QI Linhai. A method for identifying voltage sag sources based on deep learning model fusion[J]. Proceedings of the CSEE, 2019, 39(1):97-104.
[9]	贾勇, 何正友, 赵静. 基于小波熵和概率神经网络的配电网电压暂降源识别方法[J]. 电网技术, 2009, 33(16):63-69.
	JIA Yong, HE Zhengyou, ZHAO Jing. A method for identifying the source of voltage sag in distribution network based on wavelet entropy and probabilistic neural network[J]. Power System Technology, 2009, 33(16):63-69.
[10]	祁博, 邹金慧, 范玉刚, 等. 基于 Hilbert-Huang 变换和小波包能量谱的电压暂降源识别[J]. 中国电力, 2013, 46(8):112-117.
	QI Bo, ZOU Jinhui, FAN Yugang, et al. Identification of voltage sags source based on Hilbert-Huang transform and wavelet packet energy spectrum[J]. Electric Power, 2013, 46(8):112-117.
[11]	吕干云, 方奇品, 蔡秀珊. 基于多分类支持向量机的电压暂降源识别[J]. 电力系统保护与控制, 2010, 38(22):151-155.
	LÜ Ganyun, FANG Qipin, CAI Xiushan. Source identification of voltage sag based on multi-class support vector machine[J]. Power System Protection and Control, 2010, 38(22):151-155.
[12]	赵光权, 刘小勇, 姜泽东, 等. 基于深度学习的轴承健康因子无监督构建方法[J]. 仪器仪表学报, 2018(6):82-88.
	ZHAO Guangquan, LIU Xiaoyong, JIANG Zedong, et al. An unsupervised construction method of bearing health factors based on deep learning[J]. Chinese Journal of Scientific Instrument, 2018(6):82-88.
[13]	WANG Shouxiang, CHEN Haiwen. A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network[J]. Applied Energy, 2019, 235:1126-1140. doi: 10.1016/j.apenergy.2018.09.160
[14]	李丹奇, 梅飞, 张宸宇, 等. 基于深度置信网络的电压暂降特征提取及源辨识方法[J]. 电力系统自动化, 2020, 44(4):150-157.
	LI Danqi, MEI Fei, ZHANG Chenyu, et al. Voltage sag feature extraction and source identification method based on deep belief network[J]. Automation of Electric Power Systems, 2020, 44(4):150-157.
[15]	BENGIO Y, LAMBLIN P, DAN P, et al. Greedy layer-wise training of deep networks[C]//International Conference on Neural Information Processing Systems, 2007:153-160.
[16]	VINCENT P, LAROCHELLE H, LAJOIE I, et al. Stacked denoising autoencoders:Learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010, 11(12):3371-3408.
[17]	VINCENT P, LAROCHELLE H, BENGIO Y, et al. Extracting and composing robust features with denoising autoencoders[C]//Proceedings of the 25th international conference on Machine learning. ACM, 2008:1096-1103.
[18]	PASCAL V, HUGO L, ISABELLE L. Stacked denoising autoencoders:Learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010, 11(12):3371-3408.
[19]	朱乔木, 陈金富, 李弘毅, 等. 基于堆叠自动编码器的电力系统暂态稳定评估[J]. 中国电机工程学报, 2018, 38(10):2937-2946,3144.
	ZHU Qiaomu, CHEN Jinfu, LI Hongyi, et al. Power system transient stability assessment based on stacked autoencoders[J]. Proceedings of the CSEE, 2018, 38(10):2937-2946,3144.
[20]	丁宁, 蔡维, 锁娟, 等. 电压暂降源识别方法研究[J]. 电网技术, 2008, 32(S2):55-59.
	DING Ning, CAI Wei, SUO Juan, et al. Research on voltage sag sources recognition method[J]. Power System Technology, 2008, 32(S2):55-59.
[21]	储佳伟, 袁晓冬, 陈兵, 等. 结合小波分析和改进型DTW距离的配电网电压暂降源辨识方法[J]. 电网技术, 2018, 42(2):637-643.
	CHU Jiawei, YUAN Xiaodong, CHEN Bing, et al. A method for distribution network voltage sag source identification combining wavelet analysis and modified DTW distance[J]. Power System Technology, 2018, 42(2):637-643.

故障类型	相别	无噪声					加入50 dB噪声
故障类型	相别	WEE	WCE1	WCE2	WCE3	WCE4	WEE	WCE1	WCE2	WCE3	WCE4
A	A	0.135 2	0.505 4	0.291 9	0.177 1	0.313 4	0.164 8	0.808 6	0.849 1	0.349 1	0.361 7
	B	0.143 3	0.151 1	0.046 5	0.088 9	0.063 2	0.146 3	0.292 6	0.089 9	0.095 1	0.076 1
	C	0.146 1	0.171 3	0.050 1	0.088 5	0.066 0	0.147 2	0.306 4	0.095 6	0.094 5	0.074 6
B	A	0.135 4	0.506 0	0.291 4	0.176 4	0.313 1	0.170 0	0.886 4	0.857 5	0.449 1	0.370 2
	B	0.072 2	0.215 3	0.226 5	0.160 7	0.236 1	0.170 7	0.999 7	0.901 5	0.717 7	0.476 0
	C	0.070 1	0.215 3	0.226 2	0.148 5	0.237 9	0.171 4	0.995 2	0.894 5	0.639 8	0.442 0
C	A	0.071 2	0.215 6	0.226 4	0.154 1	0.236 2	0.183 5	0.994 5	0.871 9	0.432 4	0.331 8
	B	0.146 3	0.220 9	0.048 0	0.087 6	0.068 9	0.149 3	0.378 8	0.102 9	0.094 5	0.083 4
	C	0.146 3	0.220 8	0.048 0	0.088 0	0.073 9	0.149 3	0.378 0	0.104 7	0.096 7	0.091 5
E	A	0.071 2	0.215 3	0.226 4	0.154 1	0.236 2	0.183 8	1.000 0	0.874 2	0.393 6	0.319 7
	B	0.143 3	0.151 2	0.046 5	0.088 9	0.063 1	0.147 1	0.318 3	0.101 3	0.095 2	0.081 9
	C	0.146 1	0.171 4	0.050 1	0.088 5	0.066 0	0.149 6	0.337 4	0.104 5	0.096 5	0.076 6

暂降类型	测试样本数量	识别准确率(%)
		无噪声	加入噪声/dB
		无噪声	30	40	50
类型A	50	100	100	100	100
类型B	650	100	99.5	100	100
类型C	300	100	99	99.6	99.6
类型D	200	99.5	98.5	99	99
类型E	200	99.5	99	99.5	99.5
类型F	100	99	97	98	98
类型G	100	98	97	97	98

识别方法	识别准确率(%)
识别方法	类型A	类型B	类型C	类型E	平均值
小波熵和概率神经网络^[9]	90	100	90	90	92
S变换和支持向量机^[11]	96	96	96	96	96
深度置信网络^[14]	90	100	90	90	92.5
电压有效值^[20]	100	90	90	90	92.5
小波分析和改进型DTW距离^[21]	100	100	93.8	92.7	96.63
本文方法	100	100	100	99	99.75