Dynamic nonlinear modelling of power plant by physical principles and neural networks

Dynamic modelling of power plants is fundamental to control system design a nd performance studies. This paper describes a nonlinear power plant model built by physical principles and neural network models by identification of the physical model. Every effort has been made to improve accuracy of the physical model without increasing its complexity. Practical aspects of neur al network modelling for selecting testing data of the self-unbalancing sys tem are investigated to ensure sufficient perturbations covering proper dyn amic and load conditions. As an example, the generic modelling strategies a re applied to a 200 MW oil-fired drum-type boiler-turbine-generator unit. T he simulation results of the neural network and physical models are compare d both at the trained and untrained conditions. It is shown that the accura cy of artificial neural network models depends greatly on the training data and is satisfactory within normal operating scope. (C) 1999 Published by E lsevier Science Ltd. All rights reserved.