Electric Shock Recognition Method Based on Cyclic Spectrum Features and Cluster Analysis
Li Chunlan1, Luo Jie1, Wang Changyun1, Wang Haiyang2, Du Songhuai3
1. College of Mechanical and Electrical Engineering Xinjiang Agricultural University Urumqi 830052 China; 2. School of Mechanical and Electronic Engineering Xinjiang Vocational University Urumqi 830013 China; 3. College of Information and Electrical Engineering China Agricultural University Beijing 100083 China
Abstract：In order to solve the problems that electric shock accidents are difficult to identify due to its' randomness, this paper proposes a new method based on cyclic power spectral density characteristics and cluster analysis. First, the cyclic power spectrum is used to analyze the residual current signal to obtain a three-dimensional cyclic spectrum diagram of the residual current signal before and after the electric shock. According to the slice spectral analysis of the 150Hz component of the residual current, the line spectrum proportion of the characteristic cycle frequency, 1 200Hz, is extracted, and four kinds of cycle spectrum features are defined to describe electric shock accidents. In order to extract the shock recognition criterion, K-means clustering analysis was used to cluster the combined features of the cyclic spectrum of different dimensions. At the same time, it is proposed that the Euclidean distance measure with offset term improves the accuracy of cluster recognition. The result shows that the combined features of cyclic spectrum 2, 3, and 4 in single-phase circuits have the highest recognition rate for electric shock accidents compared with other dimensional features, which is 94.67%. The corresponding cluster centers of residual current before and after electric shock are 20.597, 57.682, 4.773 and 4.102, 11.387, 0.923 respectively. The best recognition feature for three-phase circuits is the cyclic spectrum feature 4, the corresponding cluster centers of residual current before and after electric shock are 16.136 and 2.197 respectively. The Euclidean distance with offset term has a 99.33% recognition rate for electric shock accidents. The research results provide some theoretical reference for effective identification of electric shock accidents.
李春兰, 罗杰, 王长云, 王海杨, 杜松怀. 基于循环谱特征和聚类分析的触电识别[J]. 电工技术学报, 2021, 36(22): 4677-4687.
Li Chunlan, Luo Jie, Wang Changyun, Wang Haiyang, Du Songhuai. Electric Shock Recognition Method Based on Cyclic Spectrum Features and Cluster Analysis. Transactions of China Electrotechnical Society, 2021, 36(22): 4677-4687.
[1] 杜松怀, 张筱慧. 电力系统接地技术[M]. 北京: 中国电力出版社, 2011. [2] 武一, 李奎, 王尧, 等. 磁调制式剩余电流传感器的动态励磁过程分析与仿真[J]. 电工技术学报, 2014, 29(7): 244-252. Wu Yi, Li Kui, Wang Yao, et al.Analysis and simulation of dynamic process of excitation current of magnetic modulation residual current transformer[J]. Transaction of China Electrotechnical Society, 2014, 29(7): 244-252. [3] 熊晓祎, 肖先勇, 左金威, 等. 触电事故特征改进近似熵检测方法[J]. 电力系统保护与控制, 2017, 45(13): 27-33. Xiong Xiaoyi, Xiao Xianyong, Zuo Jinwei, et al.Electrical shock feature detection method based on improved approximate entropy[J]. Power System Protection and Control, 2017, 45(13): 27-33. [4] 熊晓祎, 肖先勇, 赵恒. 基于自适应算法的触电事故电流检测[J]. 电力系统保护与控制, 2017, 45(4): 139-144. Xiong Xiaoyi, Xiao Xianyong, Zhao Heng.Adaptive algorithm based electrical shock current detection method[J]. Power System Protection and Control, 2017, 45(4): 139-144. [5] 李春兰, 夏兰兰, 王成斌, 等. 基于椭圆域分割的触电电流混沌检测方法研究[J]. 电力系统保护与控制, 2017, 45(15): 69-76. Li Chunlan, Xia Lanlan, Wang Chengbin, et al.Study on chaos detection method of electric shock current based on elliptic domain segmentation[J]. Power System Protection and Control, 2017, 45(15): 69-76. [6] 李奎, 陆俭国, 武一, 等. 自适应漏电保护技术及其应用[J]. 电工技术学报, 2008, 23(10): 53-57. Li Kui, Lu Jianguo, Wu Yi, et al.Adaptive technology of leakage current operation protection and its application[J]. Transaction of China Electrotechnical Society, 2008, 23(10): 53-57 [7] 李春兰, 苏娟, 杜松怀, 等. 基于小波分析和BP神经网络的触电信号检测模型[J]. 农业工程学报, 2010, 26(增刊2): 130-134. Li Chunlan, Su Juan, Du Songhuai, et al.Detecting model of electric shock signal based on wavelet analysis and BP neural network[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2010, 26(Supp: 2): 130-134. [8] 韩晓慧, 杜松怀, 苏娟, 等. 触电信号暂态特征提取及故障类型识别方法[J]. 电网技术, 2016, 40(11): 3591-3596. Han Xiaohui, De Songhuai, Su Juan, et al.Fault transient feature extraction and fault type identitfication for electrical shock signals[J]. Power System Technology, 2016, 40(11): 3591-3596. [9] 韩晓慧, 杜松怀, 苏娟, 等. 基于参数优化的最小二乘支持向量机触电电流检测方法[J]. 农业工程学报, 2014, 30(23): 238-245. Han Xiaohui, Du Songhuai, Su Juan, et all. Determination method of electric shock current based on parameter-optimized least squares support vector machine[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2014 30(23): 238-245. [10] 刘永梅, 杜松怀, 盛万兴. 基于SVM-神经网络融合反馈的触电电流检测方法[J]. 电网技术, 2020, 44(5): 1972-1977. Liu Yongmei, Du Songhuai, Sheng Wangxin.Prediction method of electric shock current based on SVM and neural network fusion feedback[J]. Power System Technology, 2020, 44(5): 1972-1977. [11] 关海鸥, 杜松怀, 苏娟, 等. 一种触电信号的自动快速检测模型[J]. 电网技术, 2013, 37(8): 2328-2335. Guan Haiou, Du Songhuai, Su Juan, et al.An automatic and quick detection model of electric shock signals[J]. Power System Technology, 2013, 37(8): 2328-2335. [12] 夏兰兰, 李春兰, 王成斌, 等. 基于混沌系统功率谱特征的触电信号识别研究[J]. 华北电力技术, 2017(9): 1-7. Xia Lanlan, Li Chunlan, Wang Chengbin, et al.Study on detecting method of electric shock current based on chaotic system power spectrum feature[J]. North China Electric Power, 2017(9): 1-7. [13] 关海鸥, 李伟凯, 杜松怀, 等. 基于Hilbert-Huang变换的生物触电电流检测模型[J]. 农业工程学报, 2017, 33(14): 202-209. Guan Haiou, Li Weikai, Du Songhuai, et al.Detection model of biological electric shock current based on Hilbert-Huang transform[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(14): 202-209. [14] 李春兰, 高阁, 张亚飞, 等. 基于局部均值分解(LMD)的单通道触电信号盲源分离算法[J]. 农业工程学报, 2019, 35(12): 200-208. Li Chunlan, Gao Ge, Zhang Yafei, et al.Single channel electric shock signals blind source separation algorithm based on local mean decomposition[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2019, 35(12): 200-208. [15] Gardner W A.The spectral correlation theory of cyclosta-tionary time-series[J]. IEEE Transactions on Signal Pro-cessing, 1986, 11(7): 13-36. [16] 罗利春. 谱相关的原理、功能与α截面谱表示[J]. 物理学报, 2002(10): 2177-2182. Luo Lichun.Spectrum correlation: principle, functionand representation in α section[J]. Acta Physica Sinica, 2002(10): 2177-2182. [17] 王洪. 谱相关的数学关系与物理意义[J]. 电子学报, 2015, 43(4): 810-815. Wang Hong.Mathematical relationships and physical functions of spectral correlation[J]. Acta Electronica Sinica, 2015, 43(4): 810-815. [18] Swami A, Sadler B M.Hierarchical digital modulation classification using cumulants[J]. IEEE Transcation on Communication, 2000, 48(3): 416-429. [19] 明阳, 陈进. 基于谱相关密度切片分析和SVM的滚动轴承故障诊断[J]. 振动与冲击, 2010, 29(1): 196-199. Ming Yang, Chen Jin.Rolling element bearing fault diagnosis based on slice spectral correlation density and support vector machine[J]. Journal of Vibration and Shock, 2010, 29(1): 196-199. [20] Gupta C N, Palaniappan R.Denoising cyclostationary framework for enhanced Electrocardiogram analysis[C]// 2007 Computers in Cardiology, Durham, NC, 2007: 93-96. [21] 刘艳丽, 郭凤仪, 王智勇, 等. 基于信息熵的串联型故障电弧频谱特征研究[J]. 电工技术学报, 2015, 30(12): 488-495. Liu Yanli, Guo Fengyi, Wang Zhiyong, et al.Research on the spectral characteristics of series arc fault based on information entropy[J]. Transaction of China Electrotechnical Society, 2015, 30(12): 488-495. [22] 柯维, 张永祥, 郭彬. 柴油机振动信号二阶循环平稳特性分析[J]. 武汉理工大学学报(交通科学与工程版), 2012, 36(2): 328-331, 336. Ke Wei, Zhang Yongxiang, Guo Bin.Second order cyclostationary analysis for diesel vibration signal[J]. Journal of Wuhan University of Technology (Transportation Science & Engineering), 2012, 36(2): 328-331, 336. [23] 付海涛. 基于循环平稳的单信道时频重叠信号分析[D]. 成都: 电子科技大学, 2010. [24] 郑鹏, 王泽众, 刘锋. 循环谱时域平滑循环周期图法估计性能分析[J]. 计算机与数字工程, 2011, 39(11): 30-34. Zheng Peng, Wang Zezong, Liu Feng.Performance analysis for cyclic spectrum by temporally smoothed cyclic periodogram[J]. Computer & Engineering, 2011, 39(11): 30-34. [25] 叶豪, 李春兰, 高阁, 等. 基于多因素的动物触电电流特征试验与分析[J]. 江苏大学学报(自然科学), 2020, 41(1): 39-45. Ye Hao, Li Chunlan, Gao Ge, et al.Experiment and analysis of animal electric shock current characteristics based on multiple factors[J]. Journal of Jiangsu University(Natural Science Edition), 2020, 41(1): 39-45. [26] 李恩文, 王力农, 宋斌, 等. 基于混沌序列的变压器油色谱数据并行聚类分析[J]. 电工技术学报, 2019, 34(24): 5104-5114. Li Enwen, Wang Linong, Song Bin, et al.Parallel clustering analysis of dissolved gas analysis data based on chaotic sequences[J]. Transaction of China Electrotechnical Society, 2019, 34(24): 5104-5114. [27] 仇新艳, 李付亮. 基于ITD和K均值聚类的电能质量扰动分析与识别[J]. 电力系统及其自动化学报, 2015, 27(8): 54-59. Qiu Xinyan, Li Fuliang.Analysis and identification for power quality disturbance signals based on ITD and K-mean clustering algorithm[J]. Proceedings of the CSU-EPSA, 2015, 27(8): 54-59. [28] 严英杰, 盛戈皞, 刘亚东, 等. 基于滑动窗口和聚类算法的变压器状态异常检测[J]. 高电压技术, 2016, 42(12): 4020-4025. Yan Yingjie, Sheng Gehao, Liu Yadong, et al.Anomalous state detection of power transformer based on algorithm sliding wind-ows and clustering[J]. High Voltage Engineering, 2016, 42(12): 4020-4025. [29] 肖勇, 钱斌, 蔡梓文, 等. 电力物联网终端非法无线通信链路检测方法[J]. 电工技术学报, 2020, 35(11): 2319-2327. Xiao Yong, Qian Bin, Cai Ziwen, et al.Malicious wireless communication link detection of power internet of thing devices[J]. Transaction of China Electrotechnical Society, 2020, 35(11): 2319-2327.
2021, Vol. 36 
