Sensitivity analysis and applications to nuclear power plant
暂无分享,去创建一个
Sensitivity analysis is used to ascertain important variables for a nuclear power plant system in order to control the variation of the plant thermal performance. In this project, thermal performance data have been taken weekly from the Tennessee Valley Authority (TVA) Sequoyah nuclear power plant units one and two, which include about 40 measured or calculated variables. Recorded data indicate that the heat rate is changing constantly, and the plant may lose some megawatts of electric power due to the heat rate variation. Hybrid neural networks and neural modeling provide useful information to power plant personnel in determining the cause of the deviation of thermal performance and heat rate, and provide a controlling basis for them in order to operate the plant more efficiently.<<ETX>>
[1] Anders Krogh,et al. Introduction to the theory of neural computation , 1994, The advanced book program.
[2] Geoffrey E. Hinton,et al. Learning representations by back-propagating errors , 1986, Nature.
[3] Teuvo Kohonen,et al. Self-Organization and Associative Memory , 1988 .
[4] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .