基于改进经验小波变换和XGBoost的电能质量复合扰动分类

doi:10.19595/j.cnki.1000-6753.tces.201363

摘要
图/表
参考文献
相关文章 (5)

全文: PDF (2165 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要针对电能质量复合扰动分类方法在分类数目和分类性能方面存在的不足,提出一种基于改进经验小波变换（MEWT）和极限梯度提升（XGBoost）的电能质量复合扰动分类方法。首先,对传统经验小波变换进行改进,使之适用于复合扰动特征提取;然后,根据基本扰动MEWT分析结果,从时频域多角度提取能够有效刻画不同扰动特性的特征序列;最后,基于问题转换策略构造以XGBoost为子分类器的多标签复合扰动分类模型,并通过特征选择与超参数优化相结合的模型训练方法进一步提升分类效果。实验结果表明,所提方法可实现48类扰动的有效辨识,较之传统多标签扰动分类方法在分类精度和噪声鲁棒性方面表现更优,且运算速度更快,适用于工程实践。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	吴建章
	梅飞
	郑建勇
	张宸宇
	缪惠宇

关键词 ：电能质量复合扰动, 经验小波变换, 尺度空间表示, 多标签分类, 极限梯度提升

Abstract：Aiming at the shortcomings of multiple power quality disturbances classification method in terms of classification number and classification performance, a recognition method of multiple power quality disturbances based on modified empirical wavelet transform (MEWT) and extreme gradient boosting (XGBoost) was proposed. Firstly, the traditional empirical wavelet transform was improved to make it suitable for feature extraction of multiple disturbances. Then, according to the MEWT analysis results of basic disturbances, feature sequences which can effectively depict different disturbance characteristics were extracted from time and frequency domain. Finally, a multi label classification model for multiple disturbances with XGBoost as sub classifier was constructed based on the problem transformation strategy, and the model training method combining feature selection and hyperparameter optimization was used to further improve the effect of classification. The experimental results show that the proposed method can effectively identify 48 types of disturbances. Compared with the traditional multi label disturbance classification method, the proposed method performs better in classification accuracy and noise robustness, and has faster operation speed, which is suitable for engineering practice.

Key words： Multiple power quality disturbances empirical wavelet transform scale-space representation multi label classification XGBoost

收稿日期: 2020-10-12

PACS:

TM76

基金资助:江苏省重点研发计划（BE2020027）、国家电网公司科技（52199918000C）和国家重点研发计划（2018YFB0905000）资助项目

通讯作者: 吴建章男,1996年生,博士研究生,研究方向为电能质量信号检测与分析。E-mail：wujianzhang@seu.edu.cn

作者简介: 梅飞男,1982年生,讲师,博士,研究方向为新能源发电技术、电气设备在线监测与故障诊断。E-mail：meifei@hhu.edu.cn

引用本文:

吴建章, 梅飞, 郑建勇, 张宸宇, 缪惠宇. 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, Zhang Chenyu, Miao Huiyu. Recognition of Multiple Power Quality Disturbances Based on Modified Empirical Wavelet Transform and XGBoost. Transactions of China Electrotechnical Society, 2022, 37(1): 232-243.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.201363 https://dgjsxb.ces-transaction.com/CN/Y2022/V37/I1/232

[1] 陶顺, 罗超, 肖湘宁, 等. 电流物理分量理论改进方法及其在电能质量评估中的应用[J]. 电工技术学报, 2019, 34(9): 1960-1970.
Tao Shun, Luo Chao, Xiao Xiangning, et al. A modified current physical components theory and its application in power quality assessment[J]. Transactions of China Electrotechnical Society, 2019, 34(9): 1960-1970.
[2] 王鹤, 李石强, 于华楠, 等. 基于分布式压缩感知和边缘计算的配电网电能质量数据压缩存储方法[J]. 电工技术学报, 2020, 35(21): 4553-4564.
Wang He, Li Shiqiang, Yu Huanan, et al. Compression acquisition method for power quality data of distribution network based on distributed compressed sensing and edge computing[J]. Transactions of China Electrotechnical Society, 2020, 35(21): 4553-4564.
[3] 黄建明, 李晓明.结合短时傅里叶变换和谱峭度的电力系统谐波检测方法[J]. 电力系统保护与控制, 2017, 45(7): 43-50.
Huang Jianming, Li Xiaoming.Detection of harmonic in power system based on short-time Fourier transform and spectral kurtosis[J]. Power System Protection and Control, 2017, 45(7): 43-50.
[4] 肖贤贵, 李开成, 蔡得龙, 等. 一种电能质量扰动信号的联合去噪算法[J]. 电工技术学报, 2021, 36(21): 4418-4428.
Xiao Xiangui, Li Kaicheng, Cai Delong, et al. A combined de-noising method for power quality disturbances events[J]. Transactions of China Electrotechnical Society, 2021, 36(21): 4418-4428.
[5] 李建闽, 林海军, 梁成斌, 等. 基于双分辨率S变换和学习向量量化神经网络的电能质量扰动检测方法[J]. 电工技术学报, 2019, 34(16): 3453-3463.
Li Jianmin, Lin Haijun, Liang Chengbin, et al. Detection method of power quality disturbances based on double resolution S transform and learning vector quantization neural network[J]. Transactions of China Electrotechnical Society, 2019, 34(16): 3453-3463.
[6] Gilles J.Empirical wavelet transform[J]. IEEE Transactions on Signal Processing, 2013, 61(16): 3999-4010.
[7] Thirumala K, Umarikar A C, Jain T.Estimation of single-phase and three-phase power-quality indices using empirical wavelet transform[J]. IEEE Transactions on Power Delivery, 2015, 30(1): 445-454.
[8] Thirumala K, Shantanu S, Jain T, et al. Visualizing time-varying power quality indices using generalized empirical wavelet transform[J]. Electric Power Systems Research, 2017, 143: 99-109.
[9] Thirumala K, Umarikar A C, Jain T.An improved adaptive filtering approach for power quality analysis of time-varying waveforms[J]. Measurement, 2019, 131: 677-685.
[10] 吴建章, 梅飞, 陈畅, 等. 基于经验小波变换的电力系统谐波检测方法[J]. 电力系统保护与控制, 2020, 48(6): 136-143.
Wu Jianzhang, Mei Fei, Chen Chang, et al. Harmonic detection method in power system based on empirical wavelet transform[J]. Power System Protection and Control, 2020, 48(6): 136-143.
[11] 徐艳春, 樊士荣, 谭超, 等. 基于改进EWT-CMPE的高渗透率主动配电网电能质量扰动检测与分类[J]. 电网技术, 2020, 44(10): 3991-4000.
Xu Yanchun, Fan Shirong, Tan Chao, et al. Power quality disturbance detection and classification in high permeability active distribution network with improved EWT-CMPE[J]. Power System Technology, 2020, 44(10): 3991-4000.
[12] 周雒维, 管春, 卢伟国.多标签分类法在电能质量复合扰动分类中的应用[J]. 中国电机工程学报, 2011, 31(4): 45-50.
Zhou Luowei, Guan Chun, Lu Weiguo.Application of multi-label classification method to catagorization of multiple power quality disturbances[J]. Proceedings of the CSEE, 2011, 31(4): 45-50.
[13] 管春, 周雒维, 卢伟国.基于多标签RBF神经网络的电能质量复合扰动分类方法[J]. 电工技术学报, 2011, 26(8): 198-204.
Guan Chun, Zhou Luowei, Lu Weiguo.Recognition of multiple power quality disturbances using multi-label RBF neural networks[J]. Transactions of China Electrotechnical Society, 2011, 26(8): 198-204.
[14] Luo Yi, Li Kaicheng, Li Yuanzheng, et al. Three layer bayesian network for classification of complex power quality disturbances[J]. IEEE Transactions on Industrial Informatics, 2018, 14(9): 3997-4006.
[15] Lin W M, Wu C H, Lin C H, et al. Detection and classification of multiple power-quality disturbances with wavelet multiclass SVM[J]. IEEE Transactions on Power Delivery, 2008, 23(4): 2575-2582.
[16] 刘翊枫, 周国鹏, 刘昕, 等. 基于智能相似日识别及偏差校正的短期负荷预测方法[J]. 电力系统保护与控制, 2019, 47(12): 138-145.
Liu Yifeng, Zhou Guopeng, Liu Xin, et al. A short- term load forecasting method based on intelligent similar day recognition and deviation correction[J]. Power System Protection and Control, 2019, 47(12): 138-145.
[17] Guo Junqi, Yang Lan, Bie Rongfang, et al. An XGBoost-based physical fitness evaluation model using advanced feature selection and Bayesian hyper-parameter optimization for wearable running monitoring[J]. Computer Networks, 2019, 151(14): 166-180.
[18] Gilles J, Heal K.A parameter less scale-space approach to find meaningful modes in histograms -application to image and spectrum segmentation[J]. International Journal of Wavelets, Multiresolution & Information Processing, 2014, 12(6): 1450044.
[19] 黄南天, 彭华, 蔡国伟, 等. 电能质量复合扰动特征选择与最优决策树构建[J]. 中国电机工程学报, 2017, 37(3): 776-786.
Huang Nantian, Peng Hua, Cai Guowei, et al. Feature selection and optimal decision tree construction of complex power quality disturbances[J]. Proceedings of the CSEE, 2017, 37(3): 776-786.
[20] Juan José González de la Rosa, Muñoz A M, Gallego A, et al. Higher-order characterization of power quality transients and their classification using competitive layers[J]. Measurement, 2009, 42(3): 478-484.
[21] Bergstra J, Komer B, Eliasmith C, et al. Hyperopt: a Python library for model selection and hyperparameter optimization[J]. Computational Science & Discovery, 2015, 8: 1-24.
[22] Liu Zhigang, Cui Yan, Li Wenhui.A classification method for complex power quality disturbances using EEMD and rank wavelet SVM[J]. IEEE Transactions on Smart Grid, 2015, 6(4): 1678-1685.
[23] 张杨, 刘志刚.一种基于时频域多特征量的电能质量混合扰动分类新方法[J]. 中国电机工程学报, 2012, 32(34): 83-90, 13.
Zhang Yang, Liu Zhigang.A new method for power quality mixed disturbance classification based on time-frequency domain multiple features[J]. Proceedings of the CSEE, 2012, 32(34): 83-90, 13.
[24] 黄建明, 瞿合祚, 李晓明.基于短时傅里叶变换及其谱峭度的电能质量混合扰动分类[J]. 电网技术, 2016, 40(10): 3184-3191.
Huang Jianming, Qu Hezuo, Li Xiaoming.Classification for hybrid power quality disturbance based on STFT and its spectral kurtosis[J]. Power System Technology, 2016, 40(10): 3184-3191.
[25] 瞿合祚, 刘恒, 李晓明, 等. 一种电能质量多扰动分类中特征组合优化方法[J]. 电力自动化设备, 2017, 37(3): 146-152.
Qu Hezuo, Liu Heng, Li Xiaoming, et al. Feature combination optimization for multi-disturbance classification[J]. Electric Power Automation Equipment, 2017, 37(3): 146-152.
[26] 杨晓梅, 郭林明, 肖先勇, 等. 基于可调品质因子小波变换和随机森林特征选择算法的电能质量复合扰动分类[J]. 电网技术, 2020, 44(8): 3014-3020.
Yang Xiaomei, Guo Linming, Xiao Xianyong, et al. Classification of multiple power quality disturbances based on TQWT and random forest feature selection algorithm[J]. Power System Technology, 2020, 44(8): 3014-3020.