According to statistic data, machinery faults contribute to largest proportion of High-voltage circuit breaker failures, and traditional maintenance methods exist some disadvantages for that issue. Therefore, based on the wavelet packet decomposition approach and support vector machines, a new diagnosis model is proposed for such fault diagnoses in this study. The vibration eigenvalue extraction is analyzed through wavelet packet decomposition, and a four-layer support vector machine is constituted as a fault classifier. The Gaussian radial basis function is employed as the kernel function for the classifier. The penalty parameter c and kernel parameter δ of the support vector machine are vital for the diagnostic accuracy, and these parameters must be carefully predetermined. Thus, a particle swarm optimization-support vector machine model is developed in which the optimal parameters c and δ for the support vector machine in each layer are determined by the particle swarm algorithm. The validity of this fault diagnosis model is determined with a real dataset from the operation experiment. Moreover, comparative investigations of fault diagnosis experiments with a normal support vector machine and a particle swarm optimization back-propagation neural network are also implemented. The results indicate that the proposed fault diagnosis model yields better accuracy and efficiency than these other models.
Xiaofeng Li
,
Shijing Wu
,
Xiaoyong Li
,
Hao Yuan
,
Deng Zhao
. Particle Swarm Optimization-Support Vector Machine Model for Machinery Fault Diagnoses in High-Voltage Circuit Breakers[J]. Chinese Journal of Mechanical Engineering, 2020
, 33(1)
: 6
-6
.
DOI: 10.1186/s10033-019-0428-5
[1] A Janssen, D Makareinis, C Sölver. International surveys on Circuit-Breaker reliability data for substation and system studies. IEEE Transactions on Power Delivery, 2014, 29(2): 808-814.
[2] E Ramentol, I Gondres, S Lajes, et al. Fuzzy-rough imbalanced learning for the diagnosis of High Voltage Circuit Breaker maintenance: The SMOTE-FRST-2T algorithm. Engineering Applications of Artificial Intelligence, 2016, 48(C): 134-139.
[3] E A L Vianna, A R Abaide, L N Canha, et al. Substations SF6 circuit breakers: Reliability evaluation based on equipment condition. Electric Power Systems Research, 2017, 142: 36-46.
[4] S Erkaya, İ Uzmay. Modeling and simulation of joint clearance effects on mechanisms having rigid and flexible links. Journal of Mechanical Science & Technology, 2014, 28(8): 2979-2986.
[5] Y Chen, Y Sun, C Chen. Dynamic analysis of a planar slider-crank mechanism with clearance for a high speed and heavy load press system. Mechanism and Machine Theory, 2016, 98: 81-100.
[6] A L Brodersson, J H Jürgensen, P Hilber. Towards health assessment: Failure analysis and recommendation of condition monitoring techniques for large disconnector populations. Cired Workshop IET, 2016, 6: 1-4.
[7] W Liu, B Xu, H Y Yang. Hydraulic operating mechanisms for high voltage circuit breakers: Progress evolution and future trends. Science in China Series E: Technological Sciences, 2011, 54(1): 116-125.
[8] J Lopez-Roldan, R Pater, S Poirier, et al. Development of non-intrusive monitoring for reactive switching of high voltage circuit breaker. International Journal of Electrical Power & Energy Systems, 2014, 61: 219-228.
[9] H Xue, S L Wang, L Yi, et al. Tool life prediction based on particles swarm optimization -back-propagation neural network. Proceedings of the Institution of Mechanical Engineers, Part B, 2014, 10: 1742-1752.
[10] V H Ferreira, R Zanghi, M Z Fortes, et al. A survey on intelligent system application to fault diagnosis in electric power system transmission lines. Electric Power Systems Research, 2016, 136: 135-153.
[11] X Y Lu, P J Lin, S Y Cheng. Fault diagnosis for photovoltaic array based on convolutional neural network and electrical time series graph. Energy Conversion and Management, 2019, 196(15): 950-965.
[12] X Niu, X Zhao. The study of fault diagnosis the high-voltage circuit breaker based on neural network and expert system. Procedia Engineering, 2012, 29: 3286-3291.
[13] K Zhu, F Mei, J Zheng. Adaptive fault diagnosis of HVCBs based on P-SVDD and P-KFCM. Neurocomputing, 2017, 240: 127-136.
[14] M A V Ricardo, J V M Lara. Circuit breakers 500 kV degradation in substation reactors caused by inductive current. Engineering Failure Analysis, 2018, 90.
[15] S W Fei, X B Zhang. Fault diagnosis of power transformer based on support vector machine with genetic algorithm. Expert Systems with Applications, 2009, 36(8): 11352-11357.
[16] Z Y Yin, J Hou. Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes. Neurocomputing, 2016, 22: 643-650.
[17] J Huang, X G Hu, F Yang. Support vector machine with genetic algorithm for machinery fault diagnosis of high voltage circuit breaker. Measurement, 2011, 44(6): 1018-1027.
[18] D Y Li, M Z Rong, T Wang. A new method for mechanical fault recognition of Extra-high Voltage Circuit Breaker. Physics Procedia, 2012, 24: 397-403.
[19] L Jian, T Y Tian. LS-SVM based substation circuit breakers maintenance scheduling optimization. International Journal of Electrical Power & Energy Systems, 2015, 64: 1251-1258.
[20] J Huang, X G Hu, X Geng. An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine. Electric Power Systems Research, 2011, 81(2): 400-407.
[21] M L Liu, K Q Wang, L J Sun, et al. Applying empirical mode decomposition (EMD) and entropy to diagnose circuit breaker faults. Optik, 2015, 126(20): 2338-2342.
[22] S Zajam, T Joshi, B Bhattacharya. Application of wavelet analysis and machine learning on vibration data from gas pipelines for structural health monitoring. Procedia Structural Integrity, 2019, 14: 712-719.
[23] Y Li, K Ding, G He, et al. Non-stationary vibration feature extraction method based on sparse decomposition and order tracking for gearbox fault diagnosis. Measurement, 2018, 124: 453-469.
[24] X Liu, Y Yang, J Zhang. Resultant vibration signal model based fault diagnosis of a single stage planetary gear train with an incipient tooth crack on the sun gear. Renewable Energy, 2018, 122: 65-79.
[25] K Jafarian, M Mobin, R Jafari-Marandi, et al. Misfire and valve clearance faults detection in the combustion engines based on a multi-sensor vibration signal monitoring. Measurement, 2018, 128: 527-536.
[26] F Ahmed, S B Kandagal. Modal identification of aircraft wing coupled heave-pitch modes using wavelet packet decomposition and logarithmic decrement. Procedia Engineering, 2016, 144: 435-443.
[27] Z Y Zhang, Y Wang, K S Wang. Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network. Journal of Intelligent Manufacturing, 2013, 24(6): 1213-1227.
[28] J D Wu, C H Liu. An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network. Expert Systems with Applications, 2009, 36: 4278-4286.
[29] T D Chanvalon, Manon. Quantum symmetry groups of Hilbert modules equipped with orthogonal filtrations. Journal of Functional Analysis, 2014, 266(5): 3208-3235.
[30] V Vapnik. The nature of statistical learning theory. New York: Springer-Verlag Press, 2000.
