Motor Inverter Fault Diagnosis Using Wavelets Neural Networks

Diagnosis and location of the power transistor open switch and short circuit switch faults in inverter are studied. Wavelet transform is used to extract diagnostic indices from the current, speed and torque waveforms of brushless DC drive system. RBF neural network is developed to identify and locate the fault. RBF neural networks are trained offline using simulation results under various healthy and faulty conditions from a simulation model. Simulation results confirm the effectiveness of the proposed methodology.

[1]  R. Peuget,et al.  Fault detection and isolation on a PWM inverter by knowledge-based model , 1997, IAS '97. Conference Record of the 1997 IEEE Industry Applications Conference Thirty-Second IAS Annual Meeting.

[2]  Bowen Cui.  Open-circuit fault diagnosis of transistor in inverter based on wavelet neural network , 2010, Proceedings of the 29th Chinese Control Conference.

[3]  Fiorenzo Filippetti,et al.  Recent developments of induction motor drives fault diagnosis using AI techniques , 2000, IEEE Trans. Ind. Electron..

[4]  M. M. Morcos,et al.  Application of AI tools in fault diagnosis of electrical machines and drives-an overview , 2003 .

[5]  M.M. Morcos,et al.  Automatic diagnosis and location of open-switch fault in brushless DC motor drives using wavelets and neuro-fuzzy systems , 2006, IEEE Transactions on Energy Conversion.

[6]  R. Spee,et al.  Remedial strategies for brushless DC drive failures , 1988, Conference Record of the 1988 IEEE Industry Applications Society Annual Meeting.

[7]  S. Gopalakrishnan,et al.  A neuro-fuzzy approach to automatic diagnosis and location of stator inter-turn faults in CSI-fed PM brushless DC motors , 2005, IEEE Transactions on Energy Conversion.