Application of multiple linear regression to trip setpoint analysis in a reactivity‐initiated accident of a molten salt reactor

Abstract

Summary The trip setpoint parameters of a molten salt reactor have been analyzed by performing multiple linear regression (MLR) method. In the analysis, a reactivity‐initiated accident with inadvertent control rod withdrawal accident under low power condition was considered as the initiating event. A total of 285 cases located from 20 235 thermal‐hydraulic simulation runs have been divided into identification dataset (70%) and test dataset (30%) for MLR. MLR models show that the maximum fuel salt temperature and corresponding control rod extraction rate follow a quite convincing linear hypotheses relationship with trip setpoint parameters. Sensitivity analysis gives the sensitivity rankings of trip setpoint parameters. And the predictive values of three significantly influential trip setpoint parameters with different margin considerations have been acquired quantitatively.

Machine Learning Algorithms Used in PSE Environments: A Didactic Approach and Critical Perspective

“…Manenti et al analyzes the similarity between a batch reactor dynamics and the spread of SARS-Covid-2 infection using a MLR algorithm. Jiao et al present an MLR strategy for modeling the reactivity-initiated accident in a molten salt reactor. Aryafar et al model pollutant adsorption using nonlinear regression strategies.…”