Title :
Using genetic algorithms to select inputs for neural networks
Author :
Guo, Zhichao ; Uhrig, Robert E.
Author_Institution :
Corp. Adv. Syst., Carrier Corp., Syracuse, NY, USA
fDate :
6/6/1992 12:00:00 AM
Abstract :
The application of neural networks to nuclear power plants for fault diagnostics is a very challenging task. How to select proper input variables for neural networks from hundreds of plant processing variables is crucially important to the success. Genetic algorithms are used in this study to guide the search for optimal combination of inputs for the neural networks to reach the criteria of fewer inputs, faster training, and more accurate recall. Data from Tennessee Valley Authority (TVA) Watts Bar Nuclear Power Plant simulator are used to demonstrate the potential applications of genetic algorithms and neural networks to nuclear power plants
Keywords :
accidents; digital simulation; fission reactor safety; genetic algorithms; neural nets; nuclear engineering computing; nuclear power stations; PWR; Tennessee Valley Authority; Watts Bar Nuclear Power Plant simulator; accidents; digital simulation; fault diagnostics; genetic algorithms; neural networks; nuclear engineering computing; nuclear power plants; recall; safety; Accidents; Computational modeling; Condition monitoring; Genetic algorithms; Input variables; Neural networks; Pattern classification; Power engineering and energy; Power generation; Sensor systems;
Conference_Titel :
Combinations of Genetic Algorithms and Neural Networks, 1992., COGANN-92. International Workshop on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-8186-2787-5
DOI :
10.1109/COGANN.1992.273937
