Data underlying the research of Innovative control model and strategy development and applications to MSFR

The dataset refers to the research activity performed in the framework of the EU project SAMOSAFER, Task 6.3 - Innovative control model and strategy developmentand applications to MSFR.<br>In this activity, an innovative incident detection method has been developed, aiming at improving the safety and reliability of the Molten Salt Fast Reactorpower plant, focusing on operational scenarios involving some deviations from normal operational conditions.<br>The data-driven incident detection and classification methodology (based on the kNN algorithm) aims at identifying abnormal plant conditions thanks to acontinuous monitoring of some measurable system parameters and variables (e.g., the molten salt temperatures in the secondary circuit).<br>In order to train the algorithm, a set of numerical, time-dependent simulation is carried out at the system-level (primary circuit, secondary circuit andbalance of plant) with the Modelica language.本数据集对应欧盟SAMOSAFER项目框架下第6.3任务——面向熔盐快堆（MSFR）的创新控制模型与策略开发及应用研究工作。 本次研究开发了一种创新的事故检测方法，旨在提升熔盐快堆电站的安全性与可靠性，重点聚焦于存在若干偏离正常运行工况的运行场景。 该基于k近邻（kNN）算法的数据驱动型事故检测与分类方法，通过对若干可测量的系统参数与变量（例如二次回路熔盐温度）开展持续监测，以识别电站的异常工况。 为训练该算法，研究团队采用Modelica语言完成了一套系统级（涵盖一回路、二回路及全厂辅助系统）的数值时变仿真实验。

搜集汇总

背景与挑战

背景概述

该数据集支持熔盐快堆（MSFR）创新型控制模型和策略的研究，属于欧盟SAMOSAFER项目的一部分。它包含基于kNN算法的事故检测方法开发数据，通过系统级模拟（使用Modelica语言）训练算法，以监测参数（如熔盐温度）并识别异常工况，旨在提升核电站的安全可靠性。数据覆盖2022-2023年，包括训练和测试文件，适用于工程和能源领域的研究。