What question did this study set out to answer?

This study aims to predict key operational parameters of nuclear reactors using machine learning techniques.

February 28, 2026Journal of Nuclear Engineering and Radiation Science0 citations

Comparative Study of Three Machine Learning Algorithms for Reactor Operation Parameter Inference

ZCZiyuan ChenZhejiang University RZRuizhi ZhangEast China Normal University YWYanhao WangShanghai Jiao Tong University

Key Points

This study aims to predict key operational parameters of nuclear reactors using machine learning techniques.
Developed a Multi-Input Single-Output framework for modeling reactor parameters.
Evaluated K-Nearest Neighbors, Random Forest, and Extreme Gradient Boosting algorithms on reactor data.
Used extensive datasets from nuclear reactor Unit 5/6 for performance assessment.
Random Forest and XGBoost outperformed K-Nearest Neighbors in predictive accuracy.
Models showed effective generalization on a separate dataset.
Parameter tuning and evaluation metrics enhanced model performance.

Abstract

Abstract This study presents a data-driven approach for predicting nuclear reactor operation state parameters using machine learning algorithms. We developed a Multi-Input Single-Output (MISO) framework to model key parameters such as temperature, boron concentration, R-rod position, burnup, and power level, monitored by the Digital Control System (DCS). Using extensive datasets from a certain nuclear reactor's Unit 5/6, we evaluated the performance of K-Nearest Neighbors (KNN), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) algorithms. The predictive accuracy was significantly improved through meticulous parameter tuning and the introduction of a comprehensive set of evaluation metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), and Mean Relative Error (MRE). RF and XGBoost outperformed KNN, indicating the superiority of ensemble models. The models also showed strong generalization capabilities when tested on a separate dataset. The resulting regression model offers an effective tool for accurate prediction of reactor state parameters, enhancing the safety and efficiency of nuclear power plant operations.

Demander à l'IA

Bookmark

View Full Paper