Research on a Small Modular Reactor Fault Diagnosis System Based on the Attention Mechanism

Sicong Wan and Jichong Lei ()
Additional contact information
Sicong Wan: College of Safety Science and Engineering, Xi’an University of Science and Technology, Xi’an 710699, China
Jichong Lei: School of Safe and Management Engineering, Hunan Institute of Technology, Hengyang 421002, China

Energies, 2025, vol. 18, issue 14, 1-20

Abstract: Small modular reactors are progressing towards greater levels of automation and intelligence, with intelligent control emerging as a pivotal trend in SMR development. When contrasted with traditional commercial nuclear power plants, SMR display substantial disparities in design parameters and the designs of safety auxiliary systems. As a result, fault diagnosis systems tailored for commercial nuclear power plants are ill-equipped for SMRs. This study utilizes the PCTRAN-SMR V1.0 software to develop an intelligent fault diagnosis system for the SMART small modular reactor based on an attention mechanism. By comparing different network models, it is demonstrated that the CNN–LSTM–Attention model with an attention mechanism significantly outperforms CNN, LSTM, and CNN–LSTM models, achieving up to a 7% improvement in prediction accuracy. These results clearly indicate that incorporating an attention mechanism can effectively enhance the performance of deep learning models in nuclear power plant fault diagnosis.

Keywords: fault diagnosis; CNN; LSTM; CNN–LSTM; CNN–LSTM–Attention; PACTRAN-SMR; deep learning (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/14/3621/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/14/3621/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:14:p:3621-:d:1697873

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().