Use of neural networks in the operation of nuclear power plants

Application of neural networks to the operation of nuclear power plants is being investigated under a US Department of Energy sponsored program at the University of Tennessee. Projects include the feasibility of using neural networks for the following tasks: (a) diagnosing specific abnormal conditions, (b) detection of the change of mode of operation, (c) signal validation, (d) monitoring of check valves, (e) modeling of the plant thermodynamics, (f) emulation of core reload calculations, (g) analysis of temporal sequences in NRC's licensee event report,'' (h) monitoring of plant parameters, and (i) analysis of plant vibrations. Each of these projects and its status are described briefly in this article. the objective of each of these projects is to enhance the safety and performance of nuclear plants through the use of neural networks. 6 refs.