The Research UL-P of Loss-of-Excitation Protection for Generator Based on the Artificial Neural Networks

Simulated model of loss-of-excitation protection for generator is established in Matlab, and then taking advantage of BP neural networks which are most advantageous in recognizing patterns, the operation zone of the active power rotor criterion for loss-of-excitation protecting of generator is recognized. Comparing with conventional microcomputer protection using linear approximation, the result shows that the method of BP neural networks is accurate and superior.