Research on Motor Fault Warning Technology Based on Second-Order Volterra Series

As important equipment for natural gas transmission stations, electric drive centrifugal compressor units are generally in continuous high-speed operation. Long-term high-load operation is easy to induce drive motor failure, resulting in huge economic losses and casualties. Compressor group condition monitoring, maintenance and repair are all closely related to motor fault diagnosis, making compressor group fault diagnosis very important. Therefore, the study of motor abnormal fault warning technology is of great significance for the prevention of centrifugal compressor accidents. In this paper, the motor fault warning model is established based on the multi-sensor data and second-order Volterra series. The obtained prediction data is compared with the fusion data collected by the sensor to obtain a range under the normal operation of the motor, that is, the numerical set [66, 67]. Predicting the development trend of motor running based on motor monitoring data. The model is used to predict the simulation data and motor data, and the results verify the correctness of the model.

[1]  Javad Poshtan,et al.  Fault isolation and diagnosis of induction motor based on multi-sensor data fusion , 2015, The 6th Power Electronics, Drive Systems & Technologies Conference (PEDSTC2015).

[2]  Wang Dong.  Fault diagnosis of aero-engine bearings based on wavelet package analysis , 2009 .

[3]  M. Verleysen,et al.  Classification in the Presence of Label Noise: A Survey , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Guan-Wei Wang,et al.  Research and application of manifold learning to fault diagnosis of reciprocating compressor , 2010, 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery.

[5]  Linzheng Zhang,et al.  A new prototype of diagnosis system of inner-faults for three-phase induction motors developed by expert system , 2001, ICEMS'2001. Proceedings of the Fifth International Conference on Electrical Machines and Systems (IEEE Cat. No.01EX501).

[6]  Swagatam Das,et al.  Multi-sensor data fusion using support vector machine for motor fault detection , 2012, Inf. Sci..

[7]  T.G. Habetler,et al.  Motor bearing damage detection using stator current monitoring , 1994, Proceedings of 1994 IEEE Industry Applications Society Annual Meeting.

[8]  Amar Bousbaine,et al.  Fault diagnostic testing using Partial Discharge measurements on High Voltage rotating machines , 2009, 2009 44th International Universities Power Engineering Conference (UPEC).

[9]  Seishi Ninomiya,et al.  Landslide early warning system for rural community as an application of Sensor Asia. , 2008 .

[10]  P. Hammond,et al.  Contribution to the study of leakage fields at the ends of rotating electrical machines , 1978 .

[11]  Krishna R. Pattipati,et al.  A Rough Set-Theory-Based Fault-Diagnosis Method for an Electric Power-Steering System , 2018, IEEE/ASME Transactions on Mechatronics.