We introduce a framework for Foundational Analysis of Safety Engineering Requirements (SAFER), a model-driven methodology supported by Generative AI to improve the generation and analysis of safety requirements for complex safety-critical systems. Safety requirements are often specified by multiple stakeholders with uncoordinated objectives, leading to gaps, duplications, and contradictions that jeopardize system safety and compliance. Existing approaches are largely informal and insufficient for addressing these challenges. SAFER enhances Model-Based Systems Engineering (MBSE) by consuming requirement specification models and generating the following results: (1) mapping requirements to system functions, (2) identifying functions with insufficient requirement specifications, (3) detecting duplicate requirements, and (4) identifying contradictions within requirement sets. SAFER provides structured analysis, reporting, and decision support for safety engineers. We demonstrate SAFER on an autonomous drone system, significantly improving the detection of requirement inconsistencies, enhancing both efficiency and reliability of the safety engineering process. We show that Generative AI must be augmented by formal models and queried systematically, to provide meaningful early-stage safety requirement specifications and robust safety architectures.

翻译：本文提出了一种安全工程需求基础分析框架，该框架采用模型驱动方法并依托生成式人工智能技术，旨在提升复杂安全关键系统的安全需求生成与分析能力。安全需求通常由多个目标不一致的利益相关方分别制定，容易导致需求缺口、重复和矛盾，从而危及系统安全性与合规性。现有方法大多属于非形式化方法，难以有效应对这些挑战。SAFER框架通过引入需求规约模型，对基于模型的系统工程方法进行增强，可生成以下分析结果：(1) 建立需求与系统功能的映射关系；(2) 识别需求规约不完整的功能模块；(3) 检测重复需求；(4) 发现需求集合中的矛盾项。该框架为安全工程师提供结构化分析、报告生成和决策支持功能。我们在自主无人机系统上验证了SAFER框架，结果表明其能显著提升需求不一致性检测能力，有效提高安全工程流程的效率和可靠性。研究证实：生成式人工智能必须结合形式化模型并通过系统化查询，才能为早期安全需求规约和鲁棒性安全架构提供实质性支持。