skip to main content

Title: Nuclear power plant status diagnostics using artificial neural networks

In this work, the nuclear power plant operating status recognition issue is investigated using artificial neural networks (ANNs). The objective is to train an ANN to classify nuclear power plant accident conditions and to assess the potential of future work in the area of plant diagnostics with ANNS. To this end, an ANN was trained to recognize normal operating conditions as well as potentially unsafe conditions based on nuclear power plant training simulator generated accident scenarios. These scenarios include; hot and cold leg loss of coolant, control rod ejection, loss of offsite power, main steam line break, main feedwater line break and steam generator tube leak accidents. Findings show that ANNs can be used to diagnose and classify nuclear power plant conditions with good results.
Authors:
 [1] ;  [2]
  1. Iowa State Univ. of Science and Technology, Ames, IA (United States). Dept. of Mechanical Engineering
  2. Tennessee Univ., Knoxville, TN (United States). Dept. of Nuclear Engineering
Publication Date:
OSTI Identifier:
10104399
Report Number(s):
CONF-9109110--15
ON: DE93003560
DOE Contract Number:
FG07-88ER12824
Resource Type:
Conference
Resource Relation:
Conference: International conference on frontiers in innovative computing for the nuclear industry,Jackson, WY (United States),15-18 Sep 1991; Other Information: PBD: [1991]
Research Org:
Tennessee Univ., Knoxville, TN (United States). Dept. of Nuclear Engineering
Sponsoring Org:
USDOE, Washington, DC (United States)
Country of Publication:
United States
Language:
English
Subject:
22 GENERAL STUDIES OF NUCLEAR REACTORS; 99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; NEURAL NETWORKS; REACTOR ACCIDENTS; REACTOR MONITORING SYSTEMS; NUCLEAR POWER PLANTS; TRAINING; DIAGNOSTIC TECHNIQUES 220900; 990200; REACTOR SAFETY; MATHEMATICS AND COMPUTERS