A Motor Rotary Fault Diagnosis System Using Dynamic Structural Neural Network

This study proposed an intelligent rotary fault diagnosis systems for motors. A sensor less rotational speed detection method and a dynamic structural neural network (DSNN) were used. This method can be employed to detect the rotary frequencies of motors with varying speeds and can enhance the discrimination of motor faults. To conduct the experiments, this work used wireless sensor nodes to transmit vibration data, and employed MATLAB to write codes for functional modules, including signal processing, sensor less rotational speed estimation, and neural networks. Additionally, Visual Basic was used to create an integrated human-machine interface. The experimental results regarding test equipment faults indicated that the proposed method can effectively estimate rotational speeds and provide superior discrimination of motor faults.

[1]  M. Blodt,et al.  Fault Indicators for Stator Current Based Detection of Torque Oscillations in Induction Motors at Variable Speed Using Time-Frequency Analysis , 1988 .

[2]  Arturo Garcia-Perez,et al.  The Application of High-Resolution Spectral Analysis for Identifying Multiple Combined Faults in Induction Motors , 2011, IEEE Transactions on Industrial Electronics.

[3]  Robert Beloiu,et al.  Vibration monitoring for diagnosis of electrical equipment's faults , 2010, 2010 12th International Conference on Optimization of Electrical and Electronic Equipment.

[4]  Ying-Tung Hsiao,et al.  Recognition of Multiple PQ Disturbances Using Dynamic Structure Neural Networks— Part 1: Theoretical Introduction , 2005, 2005 IEEE/PES Transmission & Distribution Conference & Exposition: Asia and Pacific.

[5]  Osman Bilgin,et al.  Effects of rotor faults in squirrel-cage induction motors on the torque-speed curve , 2010, The XIX International Conference on Electrical Machines - ICEM 2010.

[6]  Michael J. Devaney,et al.  Adjustable Speed Drive Bearing Fault Detection via Wavelet Packet Decomposition , 2006, 2006 IEEE Instrumentation and Measurement Technology Conference Proceedings.

[7]  W. Wang,et al.  A Smart Sensing Unit for Vibration Measurement and Monitoring , 2010, IEEE/ASME Transactions on Mechatronics.

[8]  Kenneth A. Loparo,et al.  Estimation of the running speed and bearing defect frequencies of an induction motor from vibration data , 2004 .

[9]  H.A. Toliyat,et al.  Condition Monitoring and Fault Diagnosis of Electrical Motors—A Review , 2005, IEEE Transactions on Energy Conversion.

[10]  Ching-Chi Hsu,et al.  Terminal attractor learning algorithms for back propagation neural networks , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.