Nuclear power plant performance study by using neural networks

The thermal performance data, obtained from Tennessee Valley Authority (TVA) Sequoyah nuclear power plant showed that the heat rate was changing constantly and the power was probably losing some megawatts of electric power due to the variation of the heat rate. The model of the thermodynamic process was obtained using a neural network trained on actual measurements from the plant over a one-year period of time. The model represented the thermodynamic process as it actually existed in the plant, and the dynamic range of the data covered the normal range of variables during a typical annual cycle. A sensitivity study was applied to the neural network model to extract information about the key parameters which might strongly affect the plant thermal performance.< >