What question did this study set out to answer?

The aim is to create a reliable model for diagnosing faults in CPR1000 reactor systems using AI techniques.

February 28, 2026Open Access

A transformer–XGBoost based model to fault diagnosis for CPR1000

Key Points

The aim is to create a reliable model for diagnosing faults in CPR1000 reactor systems using AI techniques.
Developed a hybrid model combining Transformer and XGBoost for analysis.
Utilized a 10-fold cross-validation with recursive feature elimination for feature selection.
Collected fault-related data automatically using AutoSave-PCTRAN software from the PCTRAN simulator.
Employed self-attention mechanism in the Transformer for feature extraction.
Used RWOA for tuning XGBoost hyperparameters.
Achieved a fault classification accuracy of 99.46%.
Successfully identified specific faults including Loss of Coolant Accident (LOCA), Steam Line Break Inside Containment (SLBLC), and steam generator B-tube rupture (SGTR-B).
Demonstrated the model's reliability and practicality in nuclear systems.

Abstract

With the rapid advancement of artificial intelligence (AI), intelligent diagnostics have seen broad application across industries. To address the limitations of traditional data-driven methods in accurately identifying faults in nuclear power reactor systems, this study proposes a hybrid model combining Transformer and XGBoost for diagnosing faults in CPR1000 pressurized water reactors. Fault-related data were automatically collected using the self-developed AutoSave-PCTRAN software from the PCTRAN simulator, with key nuclear parameters selected as features. A 10-fold cross-validation with recursive feature elimination was used for feature selection. The Transformer model extracted temporal features via its self-attention mechanism, and an RWOA was employed to tune XGBoost hyperparameters for fault classification. The model effectively identified faults such as Loss of Coolant Accident(LOCA), Steam Line Break Inside Containment(SLBLC), and steam generator B-tube rupture(SGTR-B), achieving 99.46% accuracy, confirming its reliability and practicality.

A transformer–XGBoost based model to fault diagnosis for CPR1000

Key Points

Abstract

Cite This Study