Neural network for adapting nuclear power plant control for wide-range operation

A new concept of using neural networks has been evaluated for optimal control of a nuclear reactor. The neural network uses the architecture of a standard backpropagation network; however, a new dynamic learning algorithm has been developed to capture the underlying system dynamics. The learning algorithm is based on parameter estimation for dynamic systems. The approach is demonstrated on an optimal reactor temperature controller by adjusting the feedback gains for wide-range operation. Application of optimal control to a reactor has been considered for improving temperature response using a robust fifth-order reactor power controller. Conventional gain scheduling can be employed to extend the range of good performance to accommodate large changes in power where nonlinear characteristics significantly modify the dynamics of the power plant. Gain scheduling is developed based on expected parameter variations, and it may be advantageous to further adapt feedback gains on-line to better match actual plant performance. A neural network approach is used here to adapt the gains to better accommodate plant uncertainties and thereby achieve improved robustness characteristics