Probability analysis and prediction associated with nuclear meltdown accident risk evaluation

Journal Information

J. Hefei Univ. Tech. (Nat. Sci.), Feb.2024, Vol.47 No.2: 161-168

DOI: 10.3969/j.issn.1003-5060.2024.02.003

Authors

HE Bowen $ ^{1} $, GUAN Qun $ ^{2} $

(1. Department of Civil and Environmental Engineering, Vanderbilt University, Nashville 37212, USA; 2. School of Civil and Hydraulic Engineering, Hefei University of Technology, Hefei 230009, China)

Abstract and Keywords

Abstract: This paper uses logistic regression model(LRM), linear discriminant model(LDM) and support vector machine(SVM) to evaluate the safety performance of nuclear reactors in nuclear meltdown accidents from both internal and external factors. For each model, the relevant influencing factors of nuclear reactor and the probability of nuclear meltdown accident are investigated by mathematical statistics theory. It is found that the external factors tend to dominate the internal factors and play an important role in the nuclear meltdown accident risk. The model analysis and prediction results in this paper can provide reference for nuclear reactor engineers and related decision makers in the site selection, design, construction and operation of nuclear reactors.

Keywords: nuclear meltdown; risk evaluation; probability analysis; logistic regression model(LRM); linear discriminant model(LDM); support vector machine(SVM)

作者信息

何博文 $ ^{1} $，关群 $ ^{2} $

(1. 范德堡大学土木与环境工程系，田纳西纳什维尔 37212；2. 合肥工业大学土木与水利工程学院，安徽合肥 230009)

摘要和关键词

摘要: 文章利用逻辑回归模型（logistic regression model，LRM）、线性判别模型（linear discriminant model，LDM）和支持向量机（support vector machine，SVM）3种统计模型，从核反应堆的内部和外部因素2个方面评估其在核泄漏事故中所体现的相关安全性能。针对每种模型，利用数理统计理论探究核反应堆相关影响因素与其发生核泄漏事故的概率。研究发现核反应堆外部因素有主导内部因素的趋势并在整个核泄漏事故风险中占有举足轻重的地位。文章提供的模型分析与预测结果可为核反应堆工程师及其相关决策者在核反应堆的选址、设计及建设运营等方面提供参考。

关键词: 核泄漏；风险评估；概率分析；逻辑回归模型（LRM）；线性判别模型（LDM）；支持向量机（SVM）

Funding

国家自然科学基金资助项目（51878234）

合肥工业大学学报(自然科学版)

Navigation