Application of neural networks trained with an improved conjugate gradient algorithm to the turbine fast valving control

The paper primarily presents an improved conjugate gradient algorithm for the neural networks training. The improved conjugate gradient algorithm introduces an approximate method for step size calculation, which does not have the problems in the conjugate gradient algorithm (CG) caused by the line search technique and avoids explicitly calculating the Hassian-matrix (H-matrix). It takes much less time than the error back propagation algorithm (BP) and CG for the training. The neural networks trained with the improved CG are successfully used to the fast valving control for aiding the transient stability of power systems.