Authors: Dr. B. Seyedan and R. Hynes
ASME Turbo Expo, 2006
Abstract
The objective of the paper is to assess the benefits of a neural network (NN) approach in CHP power plant process evaluation. A “feedforward” technique with a back propagation algorithm was applied to a gas turbine equipped with Heat Recovery Steam Generator (HRSG) cogeneration system. Data from physical and empirical simulators of plant components were used to train such a NN model. Results from the system simulation technique are compared with those based on the NN approach. The neural network is able to predict 50 percent of the data within ±1 percent, while the maximum error of any
data point is less than 3 percent.
The results indicate it is feasible to use NN to accurately predict plant-operating
conditions for improved performance management. The NN gives a good time response and performance prediction
capability with changes of boundary conditions. Significantly lower computation times are obtained with the NN compared to the physical simulations. The accuracy of the NN output and its suitability for on-line monitoring of a CHP plant are discussed.
