Experimental testing of a neural-network-based turn-fault detection scheme for induction machines under accelerated insulation failure conditions

Stator winding turn-fault detection schemes reported in the literature have been validated on experimental data obtained on specially re-wound machines, which have taps in the winding to create faults externally. Based on these results, it cannot be ascertained if the methods would detect a turn-fault in an incipient stage of development, before it propagates to ground. An estimate of the time interval between fault detection and the flow of significant ground current would be useful for a commercial application to carefully shut-down the machine and controlled process and for maintenance scheduling. In this paper, an experimental test is carried out to accelerate insulation failure by thermally-induced stress, while simultaneously monitoring the voltages and currents for a turn fault. Using a previously proposed neural-network-based method. Results are provided to show that the fault could be clearly detected ahead of failure of winding-to-ground insulation.

[1]  R. M. Tallam.  Neural network based stator winding turn fault detection for induction motor , 2000 .

[2]  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.

[3]  T. G. Habetler,et al.  Self-commissioning training algorithms for neural networks with applications to electric machine fault diagnostics , 2002 .

[4]  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).

[5]  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).