基于VMD和样本熵的高压断路器故障特征提取及分类

PDF(1904 KB)

振动与冲击 ›› 2018, Vol. 37 ›› Issue (20) : 32-38.

论文

万书亭1，豆龙江1，李聪1，刘荣海2

作者信息 +

Fault feature extraction and classification of high voltage circuit breakers based on VMD and sample entropy

WAN Shuting1,DOU Longjiang1,LI Cong1,LIU Ronghai2

Author information +

文章历史 +

摘要

本文提出了一种基于变分模态分解（Variational Mode Decomposition, VMD）和样本熵的高压断路器振动信号的特征向量提取方法，并采用支持向量机（Support Vector Machine, SVM）对故障类型进行识别。首先将断路器振动信号进行滤波处理，对信号进行变分模态分解，利用分解得到的固有模态函数分量(Intrinsic Mode Function, IMF)表征断路器各个振动事件，然后计算其样本熵作为特征向量，最后利用SVM对断路器不同运行状态进行分类识别。仿真信号表明，VMD对于处理瞬态非周期性的振动信号具有优越的分解特性。利用该方法在实验室条件下对四类故障状态进行特征提取和识别，对比结果表明应用该方法能有效提取高压断路器的故障特征并准确地识别出故障类型。

Abstract

A new method for fault feature extraction of high voltage circuit breakers was proposed based on variation mode decomposition (VMD) and sample entropy, and the support vector machine (SVM) was utilized to recognize the fault types.Firstly, after the vibration signal of the circuit breakers s preprocessed, the signal was decomposed by VMD.The decomposed IMFs were used to characterize various vibration events of the circuit breakers.Then the feature vector was acquired by calculating the sample entropy of IMFs.Finally, SVM was used to classify different operating states of circuit breakers.Simulation signals show that VMD has superior decomposition characteristics to deal with transient aperiodic vibration signals.Four types of fault states were extracted and recognized using the above method.The comparison results show that this method can extract fault characteristics effectively and classify fault types of high voltage circuit breaker accurately.

导出引用

万书亭1，豆龙江1，李聪1，刘荣海2. 基于VMD和样本熵的高压断路器故障特征提取及分类[J]. 振动与冲击, 2018, 37(20): 32-38

WAN Shuting1,DOU Longjiang1,LI Cong1,LIU Ronghai2. Fault feature extraction and classification of high voltage circuit breakers based on VMD and sample entropy[J]. Journal of Vibration and Shock, 2018, 37(20): 32-38

参考文献

[1] RUNDE M, OTTESEN G E, SKYBERG B, et al. Vibration analysis for diagnostic testing of circuit breakers. IEEE Trans on Power Delivery,1996,11(4):1816-1823.
[2] POLYCARPOU A A, SOOM A, PORTER J W, Event timing and shape analysis of vibration bursts from power circuit breakers. IEEE Trans on Power Delivery, 1996,11(2): 848-857.
[3] 李鹏飞，周文俊，曾国，等．高压断路器合闸弹簧动态特性及储能状态检测方法[J]．电工技术学报，2016，31(3)：104-112．
LI Peng-fei, ZHOU Wen-jun, ZENG Guo, et al. The Dynamic Characteristics and Energy Storage State Detection Method of High-voltage Circuit Breaker Closing Spring[J]. Transactions of China Electrotechnical Society, 2016, 31(3):104-112.
[4] Huang Nantian, Chen Huaijin, Zhang Shuxin, et al. Mechanical Fault Diagnosis of High Voltage Circuit Breakers Based on Wavelet Time-Frequency Entropy and One-Class Support Vector Machine[J]. Entropy, 2015,18(1):1-17.
[5] Lin Chiaching, Liu Peiling, Yeh Poliang. Application of empirical mode decomposition in the impact-echo test[J]. NDT & E International, 2009, 42(7): 589-598.
[6] 赵海龙，王芳，胡晓光．小波包－能量谱在高压断路器机械故障诊断中的应用[J]．电网技术，2004，28(6)：46-48．
ZHAO Hai-long, WANG Fang, HU Xiao-guang. Application of Wawelet Packet-Energy Spectrum In Mechanical Fault Diagnosis of High Voltage Circuit Breakers[J]. Power System Technology, 2004, 28(6): 46-48.
[7] 黄新波，王霄宽，方寿贤，等．智能变电站断路器状态监测IED设计[J]．电力系统自动化，2012，36(22)：95-99．
HUANG Xin-bo, WANG Xiao-kuan, FANG Shou-xian, et al. Design on Status Monitoring IED of Circuit Breaker for Smart Substation[J].Automation of Electric Power Systems, 2012, 36(22): 95-99.
[8] 国连玉，李可军，梁永亮，等．基于灰色模糊综合评判的高压断路器状态评估[J]．电力自动化设备，2014， 34(11)：161-167．
GUO Lian-yu, LI Ke-jun, LIANG Yong-liang, et al. HV circuit breaker state assessment based on gray-fuzzy comprehensive evaluation[J]. Electric Power Automation Equipment. 2014, 34(11): 161-167.
[9] Mingliang Liu, Keqi Wang, Laijun Sun, et al. Applying empirical mode decomposition (EMD) and entropy to diagnose circuit breaker faults[J]. Optik-International Journal for Light and Electron Optics. 2015, 126(20): 2338-2342.
[10] 徐建源，张彬，林莘，等. 能谱熵向量法及粒子群优化的RBF神经网络在高压断路器机械故障诊断中的应用[J]. 高电压技术,2012,38(6):1299-1306.
XU Jian-yuan, ZHANG Bin, LIN Xin, et al. Application of Energy Spectrum Entropy Vector Method and RBF Neural Networks Optimized by the Particle Swarm in High-voltage Circuit Breaker Mechanical Fault Diagnosis[J]. High Voltage Engineering, 2012, 38(6):1299-1306
[11] Huang Jian, Hu Xiaoguang, Yang Fan. Support vector machine with genetic algorithm for machinery fault diagnosis of high voltage circuit breaker[J]. Measurement.2011, 44(6):1018-1027.
[12] 杨凌霄，朱亚丽．基于概率神经网络的高压断路器故障诊断[J]．电力系统保护与控制，2015，43(10)：62-67．
YANG Ling-xiao, ZHU Ya-li. High voltage circuit breaker fault diagnosis of probabilistic neural network[J]. Power System Protection and Control, 2015, 43(10):62-67.
[13] 常广，王毅，王玮．采用振动信号零相位滤波时频熵的高压断路器机械故障诊断[J]．中国电机工程学报，2013，33(3)：155-162．
CHANG Guang, WANG Yi, WANG Wei. Mechanical Fault Diagnosis of High Voltage Circuit Breakers Utilizing Zero-phase Filter Time-frequency Entropy of Vibration Signal[J]. Proceedings of the CSEE, 2013,33(3): 155-162.
[14] 梅飞，梅军，郑建勇，等．粒子群优化的KFCM及SVM诊断模型在断路器故障诊断中的应用[J]．中国电机工程学报，2013，33(36)：134-141．
MEI Fei, MEI Jun, ZHENG Jian-yong, et al. Application of Particle Swarm Fused KFCM and Classification Model of SVM for Fault Diagnosis of Circuit Breaker[J]. Proceedings of the CSEE, 2013,33(36): 134-141.
[15] 吕超，于洪海，王立欣，等．基于人工免疫网络的断路器在线自学习故障诊断[J]．中国电机工程学报，2009，29(34)：128-134．
LV Chao, YU Hong-hai, WANG Li-xin, et al. On-line Self-learning Fault Diagnosis for Circuit Breakers Based on Artificial Immune Network[J]. Proceedings of the CSEE, 2009,29(34): 128-134.
[16] 程序，关永刚，张文鹏，等．基于因子分析和支持向量机算法的高压断路器机械故障诊断方法[J]．电工技术学报，2014，29(7)：209-215．
CHENG Xu, GUAN Yong-gang, ZHANG Wen-peng, et al. Diagnosis Method on the Mechanical Failure of High Voltage Circuit Breakers Based on Factor Analysis and SVM[J]. Transactions of China Electrotechnical Society, 2014, 27(7):209-215.
[17] 孙来军，胡晓光，纪延超．改进的小波包－特征熵在高压断路器故障诊断中的应用[J]．中国电机工程学报，2007，27(12)：103-108．
SUN Lai-jun, HU Xiao-guang, JI Yan-chao. Fault diagnosis for high voltage circuit breakers with improved characteristic entropy of wavelet packet[J]. Proceedings of the CSEE, 2007, 27(12): 103-108.
[18] 孙一航，武建文，廉世军，等．结合经验模态分解能量总量法的断路器振动信号特征向量提取[J]．电工技术学报，2014，29(3)：229-236．
SUN Yi-hang, WU Jian-wen, LIAN Shi-jun, et al. Extraction of Vibration Signal Feature Vector of Circuit Breaker Based on Empirical Mode Decomposition Amount of Energy[J]. Transactions of China Electrotechnical Society, 2014, 29(3):229-236.
[19] Dragomiretsliy K, Zosso D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
[20] ]马增强，李亚超，刘政，等. 基于变分模态分解和Teager能量算子的滚动轴承故障特征提取[J]. 振动与冲击,2016,35(13):134-139.
MA Zeng-qiang, LI Ya-chao, LIU Zheng, et al. Rolling bearings' fault feature extraction based on variational mode decomposition and Teager energy operator[J]. Journal of Vibration and Shock, 2016, 35(13):134-139.
[21] Aneesh C, Sachin K, Hisham P M, et al. Performance comparison of vatiational mode decomposition over empirical wavelet transform for the classification of power quality disturbances using support vector machine [J]. Procedia Computer Science, 2015,46:372-380.
[22] Richman J S, Moorman J R. Physiological time-series analysis using approximate entropy and sample entropy[J]. Am J Physiol Heart Circ Physiol, 2000, 278(3): 2039 -2049.
[23] 陶新民,李震,刘福荣,等. 基于精简集支持向量机的变压器故障检测方法[J]. 高电压技术, 2016, 42(10): 3199-3206.
TAO Xin-min, LI Zhen, LIU Fu-rong, et al. Fault Detection Method for Power Transformer Based on SVM Using Reduced Vector Set[J]. High Voltage Engineering, 2016, 42(10): 3199-3206.