基于ASRS报告的可追踪LLM生成航空系统运行安全分析危险场景
Traceable LLM-Generated Hazard Scenarios for Operational Safety Analysis of Aviation Systems Using ASRS Reports
浏览论文内容
中文总结 AI 辅助
该研究针对航空系统运行安全分析，提出AI辅助方法结合ASRS报告，用LLM生成可追踪危险场景，通过进化溯因优化混合变体，经评估验证了模型与提示对生成场景有效性的影响。
中文摘要 AI 辅助
航空系统运行的运行危险分析必须考虑天气、空中交通管制（ATC）行动、空域约束、航空器运行及人为因素之间的相互作用，这与航空器系统层面应用的功能危险评估不同。我们提出一种AI辅助方法，可从美国国家航空航天局（NASA）的航空安全报告系统（ASRS）中生成候选危险场景。给定目标不良结果，该方法会生成结构化假设（以分类因子形式呈现）及符合该结构的叙事场景，描述运行事件序列。每个场景包含基于历史共现证据的可信度评分，以及对最相似预留ASRS报告的可追溯性。我们随后提出一种混合变体，通过进化溯因法生成的结构化假设来条件化叙事生成，以提升正确性并降低变异性。我们评估了多种大型语言模型、零样本与少样本提示及可选微调，测量提示与模型选择如何影响生成的结构及叙事的有效性与真实性。
英文摘要
Operational hazard analysis of aviation system operations must consider interactions among weather, ATC actions, airspace constraints, aircraft operations, and human factors - distinct from the functional hazard assessment applied at the aircraft-system level. We present an AI-assisted approach that generates candidate hazard scenarios from NASA's Aviation Safety Reporting System (ASRS). Given a target adverse outcome, it produces a structured hypothesis as categorical factors and a narrative scenario describing an operational event sequence consistent with the structure. Each scenario includes by a plausibility score from historical co-occurrence evidence and traceability to the most similar held-out ASRS reports. We then propose a hybrid variant, conditioning narrative generation on a structured hypothesis produced via evolutionary abduction, improving correctness and reducing variability. We evaluate multiple large language models, zero-shot versus few-shot prompting, and optional fine-tuning, measuring how prompting and model choice affect the validity and realism of the generated structures and narratives.
