Title :
Statistical model for power plant performance monitoring and analysis
Author :
Pan, Li ; Flynn, Damian ; Cregan, Michael
Author_Institution :
Queen´´s Univ. Belfast, Belfast
Abstract :
A novel approach for monitoring and analysing power plant operation and performance is presented utilizing statistical modelling technology, specifically linear partial least squares (PLS) and non-linear radial basis function (RBF-PLS) models. For the RBF neural network, a genetic algorithm (GA) is employed to optimise the model parameters. The potential of these models for signal and error prediction, and performance analysis is demonstrated utilizing data from a combined cycle gas turbine (CCGT).
Keywords :
combined cycle power stations; gas turbines; genetic algorithms; least squares approximations; power engineering computing; power plants; radial basis function networks; statistical analysis; RBF-PLS models; combined cycle gas turbine; genetic algorithm; linear partial least squares; nonlinear radial basis function models; power plant performance monitoring; statistical model; Computerized monitoring; Genetic algorithms; Least squares methods; Neural networks; Ocean temperature; Performance analysis; Power generation; Principal component analysis; Signal processing; Turbines; Genetic algorithm; Partial least squares; Performance analysis; Power plant modelling; Radial basis function;
Conference_Titel :
Universities Power Engineering Conference, 2007. UPEC 2007. 42nd International
Conference_Location :
Brighton
Print_ISBN :
978-1-905593-36-1
Electronic_ISBN :
978-1-905593-34-7
DOI :
10.1109/UPEC.2007.4468931
