EXP-Transformer time series prediction model for accident scenarios in high-reliability energy systems: Nuclear power plants case

Xuan Zhang, Meiqi Song, Xiao Xiao and Xiaojing Liu

Energy, 2025, vol. 322, issue C

Abstract: As typical High-Reliability energy system, the safety of nuclear power plants (NPPs) has always been a hot topic. With the development of deep learning, it has emerged as a feasible approach to enhance safety by monitoring and forecasting of critical time series operation data. However, to meet the strict safety requirements, there are external interventions based on human action during accident conditions, resulting in sudden changes in operation sensor data, which affect the effectiveness of predictions. In this paper, a time-series data prediction model, EXP-Transformer, is proposed based on Transformer architecture and human–machine collaboration principle. By modifying the existing architecture and enhancing datasets with quantified human intervention, a specific time series data prediction model for NPPs accident conditions is obtained. The model demonstrates significant performance improvement on real datasets and exhibits generalization ability under different accident conditions. This method can accurately predict various important parameters during the accident conditions of NPPs, thereby enhancing the safety level in NPPs and providing reference for similar High-Reliability energy system.

Keywords: Time series data prediction; Accident conditions; NPPs; Human–machine collaboration (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544225011235
Full text for ScienceDirect subscribers only

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:eee:energy:v:322:y:2025:i:c:s0360544225011235

DOI: 10.1016/j.energy.2025.135481

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().