Neural Network-Based IMC-PID Controller Design for Main Steam Temperature of a Power Plant

The main steam temperature in a power plant is it typical process with nonlinear, dead time, thine-varying parameters. Different methods have been employed to control (his process. among which one may refer to conventional Internal Mode Control (IMC). In this paper a new neural network-based adaptive IMC-PID controller is proposed. Two neural networks (NN) are employed to identify the plant's model and to tune the parameters of the IMC-PID controller. The parameters of IMC-PID controller are calculated by a neural network, while another neural network is Used to identify the plant. The weights of both neural networks are adjusted on-line and this will compensate the characteristics variation and uncertain non-linearity of the process. To show the performance of the proposed method. it is applied to a steam power plant. The simulations results show the effectiverness of the proposed strategy.