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

Conference · Fri Jan 01 04:00:00 EST 1993 · Transactions of the American Nuclear Society; (United States)

OSTI ID:7128927

Chou, H P ^[1]; Prock, J; Bonfert, J P ^[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--
• Conference Information: Journal Name: Transactions of the American Nuclear Society; (United States) Journal Volume: 69
• Country of Publication: United States
• Language: English

Related Subjects

22 GENERAL STUDIES OF NUCLEAR REACTORS
220400 -- Nuclear Reactor Technology-- Control Systems
220900* -- Nuclear Reactor Technology-- Reactor Safety
ARTIFICIAL INTELLIGENCE
DIAGNOSTIC TECHNIQUES
EXPERT SYSTEMS
FUZZY LOGIC
MATHEMATICAL LOGIC
NEURAL NETWORKS
NUCLEAR FACILITIES
NUCLEAR POWER PLANTS
POWER PLANTS
SYSTEM FAILURE ANALYSIS
SYSTEMS ANALYSIS
THERMAL POWER PLANTS