Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Fault diagnosis in nuclear power plants using an artificial neural network technique

Conference · · Transactions of the American Nuclear Society; (United States)
OSTI ID:7128927
 [1]; ;  [2]
  1. National Tsing-Hua Univ., Hsinchu (Taiwan, Province of China)
  2. Institute of Safety Technology, Garching (Germany)

Application of artificial intelligence (AI) computational techniques, such as expert systems, fuzzy logic, and neural networks in diverse areas has taken place extensively. In the nuclear industry, the intended goal for these AI techniques is to improve power plant operational safety and reliability. As a computerized operator support tool, the artificial neural network (ANN) approach is an emerging technology that currently attracts a large amount of interest. The ability of ANNs to extract the input/output relation of a complicated process and the superior execution speed of a trained ANN motivated this study. The goal was to develop neural networks for sensor and process faults diagnosis with the potential of implementing as a component of a real-time operator support system LYDIA, early sensor and process fault detection and diagnosis.

OSTI ID:
7128927
Report Number(s):
CONF-931160--
Journal Information:
Transactions of the American Nuclear Society; (United States), Journal Name: Transactions of the American Nuclear Society; (United States) Vol. 69; ISSN 0003-018X; ISSN TANSAO
Country of Publication:
United States
Language:
English