Nuclear power plant fault-diagnosis using neural networks with error estimation
The assurance of the diagnosis obtained from a nuclear power plant (NPP) fault-diagnostic advisor based on artificial neural networks (ANNs) is essential for the practical implementation of the advisor to fault detection and identification. The objectives of this study are to develop an error estimation technique (EET) for diagnosis validation and apply it to the NPP fault-diagnostic advisor. Diagnosis validation is realized by estimating error bounds on the advisor`s diagnoses. The 22 transients obtained from the Duane Arnold Energy Center (DAEC) training simulator are used for this research. The results show that the NPP fault-diagnostic advisor are effective at producing proper diagnoses on which errors are assessed for validation and verification purposes.
- OSTI ID:
- 89046
- Report Number(s):
- CONF-941102--
- Journal Information:
- Transactions of the American Nuclear Society, Journal Name: Transactions of the American Nuclear Society Vol. 71; ISSN 0003-018X; ISSN TANSAO
- Country of Publication:
- United States
- Language:
- English
Similar Records
Error bounds on the outputs of artificial neural networks
Error prediction for a nuclear power plant fault-diagnostic advisor using neural networks