Abstract Aiming at the four typical defects of shunt capacitor,such as internal defect,contact defect,overlapping defect and oil defect,a fault diagnosis method of shunt capacitor based on Markov transfer field transformation of vibration signal is proposed. Firstly,four typical defect samples are made according to the field conditions,the mechanical vibration signals of the samples under different defects are tested,and the vibration data set is built. Then,the one-dimensional vibration signal is transformed into two-dimensional image based on Markov transfer field transform to improve the visibility of the signal. Finally,the feature Self Extraction and classification of Markov density map are carried out by convolution neural network. The visualization ability of signals under different quantiles is discussed and compared with common diagnosis methods. The results show that the Markov transfer field transformation of the vibration signal improves the visualization ability of the signal,and the deep learning algorithm can extract the signal features more comprehensively. The average recognition accuracy of the proposed method is about 98%,which can better realize the fault diagnosis of shunt capacitor,and is better than other common methods.
GAO Zhi,YANG Hai-yun,GONG Yan-chao, et al. Fault Diagnosis of Shunt Capacitor Based on Markov Transfer Field Transformation of Vibration Signal[J]. Acta Metrologica Sinica, 2023, 44(9): 1339-1346.
Wei X, Zhou Z C, Xie T X, et al. Overvoltage analysis and protection of vacuum circuit breaker into shunt capacitor［J］. High Voltage Engineering, 2014, 40 (10): 3193-3198.
Xu Q L, Cao Y Y, Shi H J, et al. Application of infrared detection in condition based maintenance of reactive power compensation capacitor bank ［J］. Power Capacitor & Reactive Power Compensation, 2013, 34(3): 39-42.
Guo M F, Xu L L, Miao X R, et al. Distribution switch vibration signal feature extraction method using time-frequency matrix singular value decomposition［J］. Proceedings of the CSEE, 2014, 34(28): 4990-4997.
Wu S Y, Ji S C, Sun J T, et al. Vibration monitoring and variation law of converter transformer in operation ［J］. High voltage engineering, 2022, 48(4): 1561-1570.
Lei B, Zheng H. Dynamic load identification method based on Bayesian estimation ［J］. Noise and Vibration Control, 2018, 38 (1): 215-219.
Jiang L, Liu J Y, Wei Z B, et al. Transmission line operation status and risk assessment based on Markov chain model ［J］. Automation of Electric Power Systems, 2015, 39 (13): 51-57, 80.
［17］
Ni J. Quantum Field Theory Formulated as a Markov Process Determined by Local Configuration［J］. Foundations of Physics, 2021, 51(3): 1-17.
［18］
Markovin P A, Trepakov V A, Guzhva M E, et al. A crystal optical study of short range polar order in the ferroelectric phase: doped incipient ferroelectrics［J］. Ferroelectrics, 2019, 538(1): 35-44.
Cheng S H, Lu J X, Zhang D F, et al. Wheel Hub Identification of Convolutional Neural Networks Based on Ring Features［J］. Acta Metrologica Sinica, 2022, 43(11): 1404-1411.
Chen J, Huang K X, Lv W Y, et al. Fault diagnosis method of variable condition bearing based on VMD and convolutional neural network ［J］. Acta Metrologica Sinica, 2021, 42 (7): 892-897.
Wang Y, Yang M H, Zhang H Y, et al. Data-driven prediction method for characteristics of voltage sag based on fuzzy time series［J］. International Journal of Electrical Power & Energy Systems, 2022, 134(3): 107394.
Chen W X, Cui C C, Li X J, et al. Fault diagnosis of wind turbine bearing based on one-dimensional convolutional recurrent neural network based on multiple wavelet transforms ［J］. Acta Metrologica Sinica, 2021, 42 (5): 615-622.
Hong C, Yang H F, Lu G Y, et al. Fault identification method of distribution transformer based on SVM classification of vibration signals ［J］. Chinese Journal of Scientific Instrument, 2016, 37 (6): 1299-1308.
Wang F Q. Influence of oval cross section of cylindrical capacitor plate on its withstand voltage capability ［J］. Power Capacitor & Reactive Power Compensation, 2020, 41 (4): 31-36
Zhu X Y, Luo X Z, Ye X F, et al. Steam turbine rotor state recognition method based on deep feature learning［J］. Proceedings of the CSEE, 2021, 41 (2): 432-442.
Wang J L, Sheng J J, Jiang J Y, et al. Bolt looseness identification method based on stft-ip time-frequency feature extraction technology ［J］. Noise and Vibration Control, 2021, 41 (3): 108-112.
Yang Q, Ouyang S, Sima W X, et al. Overvoltage mechanism of 10kV shunt capacitor with fast closing opening operation of vacuum circuit breaker ［J］. High Voltage Engineering, 2014, 40 (10): 3135-3140.
Zhu L Y, Ji S C, Shen Q, et al. Prediction method of shell vibration of power capacitor based on impulse discharge test ［J］. Transactions of China Electrotechnical Society, 2014, 29 (11): 239-246.
Xiao W B, Chen J, Zhou Y. Application of coupled hidden Markov model in bearing fault diagnosis ［J］. Noise and Vibration Control, 2011, 31 (6): 161-164, 198.
Yang J, Zhou B Y, Zhang Y, et al. Research on compressor fault diagnosis method based on recursive graph analysis［J］. Computer and digital engineering, 2013, 41(6): 984-986.
Yang D L, Zhang F Y, Li R J, et al. Influence of DBN parameters on feature extraction and comprehensive evaluation optimization of double rotor misalignment fault ［J］. Journal of Vibration and Shock, 2021, 40 (12): 151-158.
Ma X S, Long K H, Ma J X, et al. Research on partial discharge sampling test technology of AC capacitors for UHV ［J］. Power System Protection and Control, 2018, 46 (3): 145-151
Li D D, Liu Y H, Zhao Y, et al. Fault diagnosis method of fan planetary gearbox based on improved generation countermeasure network ［J］. : Proceedings of the CSEE, 2021, 41(21): 7496-7506.
2023, Vol. 44 
