Foundational Analysis of Safety Engineering Requirements (SAFER)

TL;DR

SAFER is a model-driven framework utilizing Generative AI to improve safety requirement analysis in complex systems, addressing inconsistencies, gaps, and contradictions to enhance safety and compliance.

Contribution

This paper introduces SAFER, a novel formal, AI-supported methodology that enhances MBSE for safety requirements analysis in safety-critical systems.

Findings

Improved detection of requirement inconsistencies in autonomous drone system

Enhanced efficiency and reliability in safety engineering processes

Demonstrated the importance of formal models combined with Generative AI

Abstract

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.