Title :
Hybrid identification of unlabeled nuclear power plant transients with artificial neural networks
Author :
Embrechts, Mark J. ; Benedek, Sandor
Author_Institution :
Dept. of Decision Sci. & Eng. Syst., Rensselaer Polytech. Inst., Troy, NY, USA
Abstract :
Proper and rapid identification of malfunctions (transients) is of premier importance for the safe operation of nuclear power plants. Feedforward neural networks trained with the backpropagation algorithm are frequently applied to model simulated nuclear power plant malfunctions. The correct identification of unlabeled transients-or transients of the “don´t-know” type-have proven to be especially challenging. A novel hybrid neural network methodology is presented which correctly classifies unlabeled transients. From this analysis the importance for properly accommodating practical aspects such as the drift of electronics elements, numerical integration accumulating errors, and the digitization of simulated and actual plant signals became obvious. Various ANN based models were successfully applied to identify labeled and unlabeled malfunctions of the Hungarian Paks nuclear power plant simulator
Keywords :
backpropagation; digital simulation; feedforward neural nets; nuclear engineering computing; nuclear power stations; pattern classification; transient analysis; Hungarian Paks nuclear power plant simulator; backpropagation algorithm; drift; electronics elements; feedforward neural networks; hybrid identification; malfunctions; unlabeled nuclear power plant transients; Aggregates; Artificial neural networks; Backpropagation algorithms; Feedforward neural networks; Neural networks; Nuclear power generation; Power engineering and energy; Power generation; Signal analysis; Systems engineering and theory;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.685987