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

被引：0
作者：
Wan S. [1 ]
Dou L. [1 ]
Li C. [1 ]
Liu R. [2 ]
机构：
[1] Department of Mechanical Engineering, North China Electric Power University, Baoding
[2] Electricity Science Research Institute of Yunnan Power Grid Company Limited, Kunming
来源：
Zhendong yu Chongji/Journal of Vibration and Shock | 2018年 / 37卷 / 20期
关键词：
Circuit breaker; Fault feature extraction; Sample entropy; VMD;
D O I：
10.13465/j.cnki.jvs.2018.20.005
中图分类号：
学科分类号：
摘要：
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. © 2018, Editorial Office of Journal of Vibration and Shock. All right reserved.
引用
收藏
页码：32 / 38
页数：6
相关论文
共 23 条
  • [1] Runde M., Ottesen G.E., Skyberg B., Et al., Vibration analysis for diagnostic testing of circuit breakers, IEEE Trans on Power Delivery, 11, 4, pp. 1816-1823, (1996)
  • [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, 11, 2, pp. 848-857, (1996)
  • [3] Li P., Zhou W., Zeng G., Et al., The Dynamic characteristics and energy storage state detection method of high-voltage circuit breaker closing spring, Transactions of China Electrotechnical Society, 31, 3, pp. 104-112, (2016)
  • [4] Huang N., Chen H., Zhang S., Et al., Mechanical Fault diagnosis of high voltage circuit breakers based on wavelet time-frequency entropy and one-class support vector machine, Entropy, 18, 1, pp. 1-17, (2015)
  • [5] Lin C.C., Liu P.L., Yeh P.L., Application of empirical mode decomposition in the impact-echo test, NDT & E International, 42, 7, pp. 589-598, (2009)
  • [6] Zhao H., Wang F., Hu X., Application of wawelet packet-energy spectrum in mechanical fault diagnosis of high voltage circuit breakers, Power System Technology, 28, 6, pp. 46-48, (2004)
  • [7] Huang X., Wang X., Fang S., Et al., Design on status monitoring ied of circuit breaker for smart substation, Automation of Electric Power Systems, 36, 22, pp. 95-99, (2012)
  • [8] Guo L., Li K., Liang Y., Et al., HV circuit breaker state assessment based on gray-fuzzy comprehensive evaluation, Electric Power Automation Equipment, 34, 11, pp. 161-167, (2014)
  • [9] Liu M., Wang K., Sun L., Et al., Applying empirical mode decomposition (EMD) and entropy to diagnose circuit breaker faults, Optik-International Journal for Light and Electron Optics, 126, 20, pp. 2338-2342, (2015)
  • [10] Xu J., Zhang B., Lin X., 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, High Voltage Engineering, 38, 6, pp. 1299-1306, (2012)
123