Diagnosis of Stator Winding Inter-Turn Circuit Faults in Induction Motors Based on Wavelet Packet Analysis and Neural Network

Abstract:

Aiming at the problem of the traditional stator current frequency spectrum analysis method cannot completely guarantee the accurate identification of stator winding inter-turn faults,the diagnosis method of stator winding inter-turn based on wavelet packet analysis (WPA) and Back Propagation (BP) neural network is put forward. The finite element model of the three-phase asynchronous motor which is based on Magnet is established, and analysis the magnetic flux density and current of the motor through simulation in normal and in the situation of short-circuit fault of stator winding inter-turn, the current signal of stator is analysised by wavelet packet , and the feature vector of frequency band energy is extracted as the basis to judge the state of induction motor running, and the motor state is identified by BP neural network, and the mapping from feature vector to the motor state is established. Simulation results show that: The diagnosis system of inter-turn fault based on WPA and BP neural network can effectively identify short-circuit fault between ratios. This is to say that the method has a high fault diagnosis rate.

• Periodical: Advanced Materials Research (Volume 529)
• Pages: 37-42
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.529.37
• Online since: June 2012
• Authors: Jun Yong Sang, Chen Hao, Peng Chao Wang
• Keywords: Fault Diagnosis, Stator Winding Inter-Turn Fault, Wavelet Packet Analysis Neural Network

References

[1] HENG Lingyan, DAI Peng, FU Xiao, etal: Rotor Bar Breaking Fault Diagnosis for Motor Based onWavelet Packet Frequency Band- Energy Reconstruction[J]. Electric Machines & Control Application. 37(10), (2010), pp.56-60.

[2] MAN Hong; JIA Shijie: Early Fault Diagnosis in Asynchronous Motors Based on Wavelet Analysis and Neural Network [J]. Journal of Dalian Jiaotong University, 32(3), (2011), pp.80-83.

[3] Karmakar A, Kumar A, Patney R K: Design of optimal wavelet packet trees based on auditory perception criterion [J]. IEEE Signal Processing Letters, 14(4), (2007), pp.240-243.

DOI: 10.1109/lsp.2006.884129

[4] Antonino Daviu J A, Riera Guasp M, Folch J R, etal: Validation of a new method for the diagnosis of rotor bar failures via wavelet transform in industrial induction machines[J]. IEEE Transactions on Industry Applications. 42(4), (2006).

DOI: 10.1109/tia.2006.876082

[5] Arkan M, Kostic-Perovic D, Unsworth P J: Modeling and simulation of induction motors with inter-turn faults for diagnostics [J]. Electric Power Systems Research, 75(1), (2005), pp.57-66.

DOI: 10.1016/j.epsr.2004.08.015

[6] Penman J, Sedding H G, Lloyd B A, et al: Detection and location of interturn short circuits in the stator windings of operating motors [J]. IEEE Transactions on Energy Conversion, 9(4), (1994), pp.652-658.

DOI: 10.1109/60.368345

[7] Dong Jianyuan, Duan Zhishan, Xiong Wanli: Researching on the stator windings faults of asynchronous motor and its diagnosticmethod [J]. Proceedings of the CSEE, 19(3), (1999), pp.26-30(in Chinese).