Self-commissioning training algorithms for neural networks with applications to electric machine fault diagnostics

The main limitations of neural network (NN) methods for fault diagnostics applications are training data and data memory requirements, and computational complexity. Generally, a NN is trained offline with all the data obtained prior to commissioning, which is not possible in a practical situation. In this paper, three novel and self-commissioning training algorithms are proposed for online training of a feedforward NN to effectively address the aforesaid shortcomings. Experimental results are provided for an induction machine stator winding turn-fault detection scheme, to illustrate the feasibility of the proposed online training algorithms for implementation in a commercial product.

[1]  T. G. Habetler,et al.  Neural network based on-line stator winding turn fault detection for induction motors , 2000, Conference Record of the 2000 IEEE Industry Applications Conference. Thirty-Fifth IAS Annual Meeting and World Conference on Industrial Applications of Electrical Energy (Cat. No.00CH37129).

[2]  J. L. Kohler,et al.  Experimental investigation of on-line methods for incipient fault detection [in induction motors] , 2000, Conference Record of the 2000 IEEE Industry Applications Conference. Thirty-Fifth IAS Annual Meeting and World Conference on Industrial Applications of Electrical Energy (Cat. No.00CH37129).

[3]  William James Premerlani,et al.  A new approach to on-line turn fault detection in AC motors , 1996, IAS '96. Conference Record of the 1996 IEEE Industry Applications Conference Thirty-First IAS Annual Meeting.

[4]  A.M. Trzynadlowski,et al.  Instantaneous stator power as a medium for the signature analysis of induction motors , 1995, IAS '95. Conference Record of the 1995 IEEE Industry Applications Conference Thirtieth IAS Annual Meeting.

[5]  T. G. Habetler,et al.  High bandwidth direct adaptive neurocontrol of induction motor current and speed using continual online random weight change training , 1999, 30th Annual IEEE Power Electronics Specialists Conference. Record. (Cat. No.99CH36321).

[6]  J.L. Kohler,et al.  Alternatives for assessing the electrical integrity of induction motors , 1989, Conference Record of the IEEE Industry Applications Society Annual Meeting,.

[7]  Thomas G. Habetler,et al.  An integrated, on-line, motor protection system , 1994, Proceedings of 1994 IEEE Industry Applications Society Annual Meeting.

[8]  Thomas G. Habetler,et al.  Transient model for induction machines with stator winding turn faults , 2000, Conference Record of the 2000 IEEE Industry Applications Conference. Thirty-Fifth IAS Annual Meeting and World Conference on Industrial Applications of Electrical Energy (Cat. No.00CH37129).