基于VMD-SAST的电能质量扰动分类识别方法

doi:10.11930/j.issn.1004-9649.202311091

摘要/Abstract

摘要：

新能源大规模并网以及电力电子设备广泛应用引起的复杂电能质量扰动（power quality disturbances，PQDs）会威胁电力系统的安全稳定运行。针对复杂PQDs难以精准检测识别的问题，提出了一种基于变分模态分解（variational mode decomposition，VMD）与同步压缩自适应S变换（synchrosqueezing adaptive S-transform，SAST）的PQDs检测识别方法。首先，使用VMD将PQDs信号分解为多个模态分量，每个分量只保留局部扰动特征，降低PQDs信号的复杂度；其次，提取一种SAST时频分析方法，改善时频分辨率，集中频谱中的能量分布，提高对PQDs信号的检测精度；最后，基于VMD-SAST提取扰动特征，利用3种不同算法实现对PQDs信号的分类识别。通过仿真分析表明：所提出的方法具有较高的PQDs分类识别精度、较高的适用性和较强的抗噪声能力。

关键词: 电能质量扰动, 变分模态分解, 特征提取, 机器学习

Abstract:

Complex power quality disturbances (PQDs) caused by large-scale grid-connection of renewable energy and wide application of power electronic equipment will threaten the safe and stable operation of power system. Aiming at the difficulty of accurate detection and recognition of complex PQDs, a PQDs detection and recognition method based on variational mode decomposition (VMD) and synchrosqueezing adaptive S-transform (SAST) is proposed. Firstly, the VMD is used to PQDs signals into multiple modal components, with each component only preserving local disturbance features so as to reduce the complexity of PQDs signals. Secondly, a SAST time-frequency analysis method is proposed to improve the time-frequency resolution, concentrate the energy distribution in the spectrum and improve the detection accuracy of PQDs signals. Finally, the disturbance features are extracted based on VMD-SAST, and the PQDs signals are classified and recognized by 3 algorithms respectively. The simulation results show that the proposed method has high PQDs classification and recognition accuracy, high applicability and strong anti-noise ability.

Key words: power quality disturbances, variational mode decomposition, feature extraction, machine learning

张博智, 张茹, 焦东翔, 王龙宇, 周一凡, 周丽霞. 基于VMD-SAST的电能质量扰动分类识别方法[J]. 中国电力, 2024, 57(2): 34-40.

Bozhi ZHANG, Ru ZHANG, Dongxiang JIAO, Longyu WANG, Yifan ZHOU, Lixia ZHOU. Power Quality Disturbance Identification Method Based on VMD-SAST[J]. Electric Power, 2024, 57(2): 34-40.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202311091

https://www.electricpower.com.cn/CN/Y2024/V57/I2/34

图/表 7

图 1 16种类型PQDs信号

Fig.1 16 types of PQDs signals

图 2 VMD和EMD对o类PQD信号的分解结果

Fig.2 VMD and EMD decomposition results of o-type PQD signal

图 3 SAST和ST对o类PQD信号的分析结果

Fig.3 SAST and ST analysis results of o-type PQD signal

图 4 3种方法提取的特征量分布

Fig.4 Distribution of features extracted by 3 methods

图 5 16种PQDs类型的分类精度

Fig.5 Classification accuracy of 16 types of PQDs

图 6 不同噪声下的分类精度

Fig.6 Classification accuracy with different noise

表 1 30 dB噪声下的4种PQDs类型分类精度

Table 1 Classification accuracy of 4 types of PQDs with 30 dB noise

扰动类型	分类精度/%
扰动类型	方法1	方法4
h	95.37	56.43
k	95.30	65.80
m	97.37	83.60
l	97.40	78.67

参考文献 26

1	杨嘉伟, 易杨, 姜浩, 等. 基于随机载波脉冲宽度调制的变换器群超高次谐波抑制机理[J]. 中国电力, 2023, 56 (11): 160- 167.
	YANG Jiawei, YI Yang, JIANG Hao, et al. Principle of supraharmonic elimination based on random carrier sinusoidal pulse width modulation for converter cluster[J]. Electric Power, 2023, 56 (11): 160- 167.
2	贺虎成, 王承海, 辛钟毓, 等. 一种组合重构的电能质量扰动特征提取方法[J]. 电力系统保护与控制, 2023, 51 (10): 34- 44.
	HE Hucheng, WANG Chenghai, XIN Zhongyu, et al. A feature extraction method for power quality disturbance based on reconstructed combination[J]. Power System Protection and Control, 2023, 51 (10): 34- 44.
3	车伟, 陈洁, 胡亚杰, 等. 光伏快速充电站配电变压器端电能质量综合控制研究[J]. 电力系统保护与控制, 2022, 50 (21): 128- 137.
	CHE Wei, CHEN Jie, HU Yajie, et al. Comprehensive control of power quality at the distribution transformer end of a photovoltaic fast charging station[J]. Power System Protection and Control, 2022, 50 (21): 128- 137.
4	奚鑫泽, 邢超, 覃日升, 等. 基于多层特征融合注意力网络的电能质量扰动识别方法[J]. 智慧电力, 2022, 50 (10): 37- 44.
	XI Xinze, XING Chao, QIN Risheng, et al. Power quality disturbance recognition method based on multi-layer feature fusion attention network[J]. Smart Power, 2022, 50 (10): 37- 44.
5	徐梓高, 杨桂森, 刘瑜超, 等. 模块化多电平换流器数学建模方法综述[J]. 东北电力大学学报, 2023, 43 (6): 8- 16.
	XU Zigao, YANG Guisen, LIU Yuchao, et al. Review of modeling method of modular multilevel converter[J]. Journal of Northeast Electric Power University, 2023, 43 (6): 8- 16.
6	李天辉, 庞先海, 范辉, 等. 基于IEMD和GA-WNN的断路器分合闸线圈故障诊断方法[J]. 中国电力, 2022, 55 (5): 111- 121.
	LI Tianhui, PANG Xianhai, FAN Hui, et al. Fault diagnosis method for circuit breaker opening and closing coil based on IEMD and GA-WNN[J]. Electric Power, 2022, 55 (5): 111- 121.
7	雷志勇, 江灏, 李中胜. 基于MEEMD-Prony联合算法的电力系统低频振荡模态辨识[J]. 东北电力大学学报, 2022, 42 (4): 50- 55.
	LEI Zhiyong, JIANG Hao, LI Zhongsheng. Low frequency oscillation mode identification of power system based on MEEMD-prony joint algorithm[J]. Journal of Northeast Electric Power University, 2022, 42 (4): 50- 55.
8	姚浩然, 李成鑫, 郑秀娟, 等. 集成自适应啁啾模态分解和BiLSTM的短期负荷组合预测模型[J]. 电力系统保护与控制, 2022, 50 (19): 58- 66.
	YAO Haoran, LI Chengxin, ZHENG Xiujuan, et al. Short-term load combination forecasting model integrating ACMD and BiLSTM[J]. Power System Protection and Control, 2022, 50 (19): 58- 66.
9	王汝田, 王世琪. 分裂源双级矩阵变换器及其调制策略的研究[J]. 东北电力大学学报, 2023, 43 (3): 47- 54.
	WANG Rutian, WANG Shiqi. Research on split-source two-stage matrix converter and its modulation strategy[J]. Journal of Northeast Electric Power University, 2023, 43 (3): 47- 54.
10	王常智, 张文海, 刘亮, 等. 基于差分波形奇异值极差的通用电力扰动检测方法[J]. 电网技术, 2023, 47 (5): 2147- 2155.
	WANG Changzhi, ZHANG Wenhai, LIU Liang, et al. A generic power disturbance detection method based on singular value range of differential waveform[J]. Power System Technology, 2023, 47 (5): 2147- 2155.
11	袁莉芬, 张成林, 尹柏强, 等. 基于最优Bohman窗的改进S变换电能质量扰动特征精确快速提取方法[J]. 电子与信息学报, 2022, 44 (11): 3796- 3805. DOI
	YUAN Lifen, ZHANG Chenglin, YIN Baiqiang, et al. Accurate and fast feature extraction method of power quality disturbances based on modified S-transform of optimal bohman window[J]. Journal of Electronics & Information Technology, 2022, 44 (11): 3796- 3805. DOI
12	肖先勇, 桂良宇, 李成鑫, 等. 基于Wasserstein距离的多电压暂降事件同源检测方法[J]. 电网技术, 2020, 44 (12): 4684- 4693.
	XIAO Xianyong, GUI Liangyu, LI Chengxin, et al. Multiple voltage sag events homology detection based on Wasserstein distance[J]. Power System Technology, 2020, 44 (12): 4684- 4693.
13	何晋伟, 孟维奇, 蒋玮, 等. 新能源配电网电能质量典型问题分析及应对策略[J]. 高电压技术, 2023, 49 (7): 2983- 2994.
	HE Jinwei, MENG Weiqi, JIANG Wei, et al. Power quality problems in renewable energy power distribution systems: analysis and solutions[J]. High Voltage Engineering, 2023, 49 (7): 2983- 2994.
14	马文嘉, 王丰华, 党晓婧. 基于稀疏自适应S变换的变压器短路冲击绕组状态声信号检测[J]. 电网技术, 2021, 45 (9): 3755- 3762.
	MA Wenjia, WANG Fenghua, DANG Xiaojing. Acoustic signal detection of transformer winding under short-circuit impact based on sparse adaptive S-transform[J]. Power System Technology, 2021, 45 (9): 3755- 3762.
15	吴建章, 梅飞, 郑建勇, 等. 基于改进经验小波变换和XGBoost的电能质量复合扰动分类[J]. 电工技术学报, 2022, 37 (1): 232- 243.
	WU Jianzhang, MEI Fei, ZHENG Jianyong, et al. Recognition of multiple power quality disturbances based on modified empirical wavelet transform and XGBoost[J]. Transactions of China Electrotechnical Society, 2022, 37 (1): 232- 243.
16	PATTANAIK D, SWAIN S, SAMANTA I, et al. Synchrosqueezed wavelet transform based power quality disturbance detection and monitoring of solar integrated micro-grid[C]//2023 International Conference on Power Electronics and Energy (ICPEE). Bhubaneswar, India. IEEE, 2023: 1–6.
17	郝晓强, 刘文宇. 电池储能系统支撑电力系统频率调控策略研究[J]. 东北电力大学学报, 2023, 43 (5): 38- 42.
	HAO Xiaoqiang, LIU Wenyu. Research on frequency regulation strategy of battery energy storage system supporting power system[J]. Journal of Northeast Electric Power University, 2023, 43 (5): 38- 42.
18	LI P, ZHANG H, XIANG W X, et al. A fast adaptive S-transform for complex quality disturbance feature extraction[J]. IEEE Transactions on Industrial Electronics, 2023, 70 (5): 5266- 5276. DOI
19	张海锋, 李德鑫, 李秀杰, 等. 大规模风电接入对电网动态频率响应时空分布的影响[J]. 东北电力大学学报, 2022, 42 (5): 74- 82.
	ZHANG Haifeng, LI Dexin, LI Xiujie, et al. Impact of large-scale wind power integration on space-time distribution of power system dynamic frequency response[J]. Journal of Northeast Electric Power University, 2022, 42 (5): 74- 82.
20	SAHANI M, DASH P K. Deep convolutional stack autoencoder of process adaptive VMD data with robust multikernel RVFLN for power quality events recognition[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70, 9001912.
21	徐艳春, 高永康, 李振兴, 等. 基于VMD初始化S变换的混合动力系统电能质量扰动检测与分类[J]. 中国电机工程学报, 2019, 39 (16): 4786- 4798.
	XU Yanchun, GAO Yongkang, LI Zhenxing, et al. Power quality disturbance detection and classification of hybrid power system based on VMD initialization S-transform[J]. Proceedings of the CSEE, 2019, 39 (16): 4786- 4798.
22	刘洪波, 盖雪扬, 孙黎, 等. 计及数据降维和数据清洗的超短期风电功率预测[J]. 东北电力大学学报, 2023, 43 (4): 1- 9.
	LIU Hongbo, GAI Xueyang, SUN Li, et al. Ultra-short-term wind power prediction considering data reduction and data cleaning[J]. Journal of Northeast Electric Power University, 2023, 43 (4): 1- 9.
23	DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62 (3): 531- 544. DOI
24	BROWN R A, LAUZON M L, FRAYNE R. A general description of linear time-frequency transforms and formulation of a fast, invertible transform that samples the continuous S-transform spectrum nonredundantly[J]. IEEE Transactions on Signal Processing, 2010, 58 (1): 281- 290. DOI
25	IEEE. IEEE recommended practice for monitoring electric power quality: IEEE Std 1159-2019 (Revision of IEEE Std 1159-2009)[S]. New York: IEEE, 2019.
26	KHETARPAL P, NAGPAL N, AL-NUMAY M S, et al. Power quality disturbances detection and classification based on deep convolution auto-encoder networks[J]. IEEE Access, 2023, 11, 46026- 46038. DOI

[1]	高志远, 庄卫金, 李峰, 于芳, 张鸿, 王艳, 夏旻. 调控领域人工智能应用的高复用性验证平台[J]. 中国电力, 2025, 58(3): 142-150.
[2]	刘抒睿, 李培强, 陈家煜, 郭雅诗. 基于VMD分解下的皮尔逊相关性分析及T-tFD的混合储能容量配置[J]. 中国电力, 2024, 57(7): 82-97.
[3]	王宇飞, 杜桐, 边伟国, 张钊, 刘慧婷, 杨丽君. 基于DTW K-medoids与VMD-多分支神经网络的多用户短期负荷预测[J]. 中国电力, 2024, 57(6): 121-130.
[4]	郑鹏, 韩鹏程, 王国栋, 娄颖. 中压配电线路断线高阻接地故障精细化诊断方法[J]. 中国电力, 2024, 57(4): 220-228.
[5]	李丹, 梁云嫣, 缪书唯, 方泽仁, 胡越, 贺帅. 基于高斯混合聚类和改进条件变分自编码的多风电场功率日场景生成方法[J]. 中国电力, 2024, 57(12): 17-29.
[6]	陈庆斌, 杨耿煌, 耿丽清, 苏娟, 孙京生. 基于相似日选取和数据重构的短期光伏功率组合预测方法[J]. 中国电力, 2024, 57(12): 71-81.
[7]	张健宝, 王磊, 江伟建. 基于VMD和Duffing振子算法的配电网差动保护[J]. 中国电力, 2024, 57(11): 26-35.
[8]	王海燕, 钱林宇. 基于NGO-VMD的混合储能功率分配策略[J]. 中国电力, 2024, 57(11): 119-128.
[9]	杨晓峰, 方逸航, 赵鹏臻, 王承民, 谢宁. 基于K-means和BPNN的风机状态识别[J]. 中国电力, 2023, 56(6): 158-166,175.
[10]	柳守诚, 王淳, 邹智辉, 陈佳慧, 周晗, 刘伟, 张旭. 基于t-SNE降维和放射传播聚类算法的低压配电网相位识别[J]. 中国电力, 2023, 56(5): 108-117.
[11]	赵隆, 温冠儒, 刘志成, 袁鹏, 董新胜. 基于参数优化的VMD-SVD和LSTM的输电杆塔倾斜状态识别[J]. 中国电力, 2023, 56(12): 217-226, 237.
[12]	马海飞, 滕伟, 彭迪康, 柳亦兵, 靳涛. 基于DRS与改进Autogram的风电齿轮箱复合故障特征提取[J]. 中国电力, 2023, 56(10): 71-79.
[13]	吴宇辉, 张扬帆, 高峰, 王玙, 王耀函, 杨伟新, 张鸿. 基于工作模态分析的风电机组叶片裂纹损伤在线监测研究[J]. 中国电力, 2023, 56(10): 106-114.
[14]	李文武, 石强, 李丹, 胡群勇, 唐芸, 梅锦超. 基于VMD和PSO-SVR的短期电力负荷多阶段优化预测[J]. 中国电力, 2022, 55(8): 171-177.
[15]	胡京, 邓颖, 蒋兴良, 曾蕴睿. 输电线路覆冰垭口微地形的特征提取与识别方法[J]. 中国电力, 2022, 55(8): 135-142.