Title :
The application on the forecast of steam turbine exhaust wetness fraction with GA BP Neural Network
Author :
Shenglong, Wang ; Tonghui, Song
Author_Institution :
School of Energy and Power Engineering, Northeast Dianli University, Jilin, China
Abstract :
BP artificial neural network abbreviated as BP ANN is easy to fall into the local minimum point. But genetic algorithm abbreviated as GA could optimize the initial weights of BP ANN. So BP ANN with genetic algorithm abbreviated as GA BP ANN may overcome the shortcoming of pure BP ANN. However there are not researches on the forecast of steam turbine exhaust wetness fraction with GA BP ANN so far. By the research in this paper the prediction accuracy of GA BP ANN method is higher than pure BP method in the steam turbine exhaust wetness fraction forecast. Therefore GA BP ANN is a new method to calculate steam turbine exhaust wetness fraction and the method could meet the engineering applications demand.
Keywords :
BP neural network; exhaust wetness fraction; genetic algorithm; steam turbine;
Conference_Titel :
World Automation Congress (WAC), 2012
Conference_Location :
Puerto Vallarta, Mexico
Print_ISBN :
978-1-4673-4497-5