Detecting faults in a nuclear power plant by using dynamic node architecture artificial neural networks
- Iowa State Univ., Ames, IA (United States). Dept. of Mechanical Engineering
An artificial neural network (ANN)-based diagnostic adviser capable of identifying the operating status of a nuclear power plant is described. A dynamic node architecture scheme is used to optimize the architectures of the two backpropagation ANNs that embody the advisor. The first or root network is used to determine whether or not the plant is in a normal operating condition. If the plant is not in a normal condition, the second or classifier network is used to recognize the particular off-normal condition or transient taking place. These networks are developed using simulated plant behavior during both normal and abnormal conditions. The adviser is effective at diagnosing 27 distinct transients based on 43 scenarios simulated at various severities that contain up to 3% noise.
- DOE Contract Number:
- FG02-92ER75700
- OSTI ID:
- 7201237
- Journal Information:
- Nuclear Science and Engineering; (United States), Vol. 116:4; ISSN 0029-5639
- Country of Publication:
- United States
- Language:
- English
Similar Records
Backpropagation architecture optimization and an application in nuclear power plant diagnostics
Nuclear power plant fault-diagnosis using artificial neural networks
Related Subjects
21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS
BWR TYPE REACTORS
REACTOR MONITORING SYSTEMS
REACTOR SAFETY
TRANSIENTS
NEURAL NETWORKS
DETECTION
DIAGNOSTIC TECHNIQUES
FAILURES
NUCLEAR POWER PLANTS
REACTOR OPERATION
ENRICHED URANIUM REACTORS
NUCLEAR FACILITIES
OPERATION
POWER PLANTS
POWER REACTORS
REACTORS
SAFETY
THERMAL POWER PLANTS
THERMAL REACTORS
WATER COOLED REACTORS
WATER MODERATED REACTORS
220900* - Nuclear Reactor Technology- Reactor Safety
220400 - Nuclear Reactor Technology- Control Systems
210100 - Power Reactors
Nonbreeding
Light-Water Moderated
Boiling Water Cooled