22-09-2014, 04:19 PM
Abstracts: In thermal power plant, Boilers generate steam continuously and on a large scale. Controlling the process of Boiler is extremely difficult - it is a highly nonlinear process and it is vary with load and also strongly multivariable. So, it becomes inherently unstable due to the integrator effect of the drum. In addition, boilers are commonly used in situations where the load can change suddenly and without prior warning so that steam boiler drum water level needs very precise level control. This work investigates, whether boiler control can be improved by applying multivariable or nonlinear predictive control strategies and these nonlinear predictive controllers, based upon a single nonlinear plant model. The nonlinear predictive controllers use a neural network model. The Artificial neural network (ANN) is predicting the water level in drum of a steam boiler. The ANN model to be applied for the boiler feed system in the power plant will not only increases the efficiency of the system but shall considerably reduce the tripping of the power plant.