Confirmation of artificial neural networks: Nuclear power plant fault diagnostics

Conference · Tue Dec 31 23:00:00 EST 1991 · Transactions of the American Nuclear Society; (United States)

OSTI ID:6672446

Kim, K; Aljundi, T L; Barlett, E B ^[1]

---

1. Iowa State Univ., Ames (United States)

A fault diagnostics adviser was developed by training a backpropagation artificial neural network (ANN) to diagnose the status of the San Onofre nuclear generating station using data obtained from the plant's training simulator. These data simulate the plant's conditions during ten distinct transients. Stacked generalization is then used to confirm the diagnosis of the ANN. The network is capable of diagnosing each of the ten transients in a timely manner.

• OSTI ID: 6672446
• Report Number(s): CONF-921102--
• Journal Information: Transactions of the American Nuclear Society; (United States), Journal Name: Transactions of the American Nuclear Society; (United States) Vol. 66; ISSN 0003-018X; ISSN TANSAO
• Country of Publication: United States
• Language: English

Related Subjects

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS
210200* -- Power Reactors
Nonbreeding
Light-Water Moderated
Nonboiling Water Cooled
99 GENERAL AND MISCELLANEOUS
990200 -- Mathematics & Computers
ARTIFICIAL INTELLIGENCE
DIAGNOSTIC TECHNIQUES
ENRICHED URANIUM REACTORS
NEURAL NETWORKS
NUCLEAR FACILITIES
NUCLEAR POWER PLANTS
POWER PLANTS
POWER REACTORS
PWR TYPE REACTORS
REACTORS
SAN ONOFRE-1 REACTOR
SAN ONOFRE-2 REACTOR
SAN ONOFRE-3 REACTOR
THERMAL POWER PLANTS
THERMAL REACTORS
TRANSIENTS
WATER COOLED REACTORS
WATER MODERATED REACTORS