Research on Accident Diagnosis Method of Reactor System Based on XGBoost Using Bayesian Optimization

Abstract

Traditional machine learning algorithms have problems such as overfitting, low accuracy, and difficulty in hyperparameter optimization when performing fault diagnosis.In order to improve the accident diagnosis ability of nuclear power plant reactor system, this paper combines Bayesian optimization (BO) algorithm with eXtreme Gradient Boosting (XGBoost) algorithm to develop a reactor accident diagnosis model.First, data preprocessing and feature quantity analysis are performed on accident data samples.Then, the BO algorithm is used to optimize the hyperparameters of the XGBoost model. Finally, the BO-XGBoost model is used to diagnose the operating conditions of seven nuclear power plants, and the diagnostic effects of various traditional machine learning classification algorithms are compared and analyzed.The results show that the BO-XGBoost model can achieve more efficient and accurate identification of reactor accident types, and the model has better generalization ability.This research can help nuclear power plant operators to accurately identify the types of reactor accidents, assist decision-making, and ensure the safe operation of nuclear power plants.