arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.23927cs.MA
收藏

TEAM-SimHRA:基于团队的人因可靠性分析仿真框架——使用多智能体大语言模型

TEAM-SimHRA: A Team-Based Simulation Framework for Human Reliability Analysis Using Multi-Agent Large Language Models

Institute of Nuclear and New Energy Technology, Tsinghua University(清华大学核能与新能源技术研究院);National Key Laboratory of Human Factors Engineering(人类工效学国家重点实验室)

Xingyu Xiao, Jiejuan Tong, Jingang Liang, Haitao Wang

AI总结:

提出TEAM-SimHRA框架,利用多智能体大语言模型模拟核控制室团队交互,将人因可靠性视为涌现属性,在三哩岛和切尔诺贝利事故验证中实现历史决策延迟复现和通信抑制再现。

摘要:

核控制室中的团队级故障并非源于孤立的操作员错误,而是来自涌现的交互动态、延迟诊断、压制异议以及权威驱动的错误传播,传统人因可靠性分析方法在结构上无法建模这些现象。本研究引入TEAM-SimHRA,一个多智能体大语言模型仿真框架,将人因可靠性重新概念化为控制室团队中交互驱动的涌现属性,而非静态的个体属性。与现有方法为预定义任务分配固定错误概率不同,TEAM-SimHRA在时间演变的事故进程中再现集体认知、角色条件化的权威动态以及实时通信抑制。通过对三哩岛(1979年)和切尔诺贝利(1986年)事故(两个记录最详尽的核团队故障案例)进行验证,该框架分别达到43.5%和52.6%的表面效度通过率,再现了接近历史的决策延迟(134.8分钟对138分钟)、完美的通信抑制稳定性以及以历史准确传播深度发生的完整权威压力级联。这些结果表明,多智能体仿真能够提取传统方法无法获得的定量团队级可靠性指标,为安全关键的社会技术系统开辟了一条基于仿真的动态概率安全评估可行路径。

英文摘要:

Team-level failure in nuclear control rooms arises not from isolated operator error, but from emergent interaction dynamics, delayed diagnosis, suppressed dissent, and authority-driven error propagation, that conventional human reliability analysis methods are structurally unable to model. This study introduces TEAM-SimHRA, a multi-agent large language model simulation framework that reconceptualizes human reliability as an interaction-driven emergent property of control room teams rather than a static individual attribute. Unlike existing approaches that assign fixed error probabilities to predefined tasks, TEAM-SimHRA reproduces collective cognition, role-conditioned authority dynamics, and real-time communication suppression across temporally evolving accident progressions. Validated against the Three Mile Island (1979) and Chernobyl (1986) accidents, the two most extensively documented nuclear team failures , the framework achieves face-validity pass rates of 43.5% and 52.6% respectively, reproducing near-historical decision delay (134.8 vs. 138 min), perfect communication suppression stability, and full authority pressure cascade at historically accurate propagation depth. These results demonstrate that multi-agent simulation can extract quantitative team-level reliability indicators that are inaccessible to traditional methods, opening a viable path toward simulation-based dynamic probabilistic risk assessment for safety-critical sociotechnical systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑