Open Access

AI-Augmented Functional Safety Evidence Validation for ISO 26262 Automotive Systems

4 Independent Researcher Hyderabad, Telangana, India

Abstract

This manuscript presents a comprehensive Artificial Intelligence (AI)-driven framework for validating functional safety evidence in ISO 26262 automotive development programs. The proposed approach integrates advanced technologies, including machine learning, knowledge graphs, natural language processing (NLP), engineering analytics, and continuous compliance monitoring, to automate the assessment of safety-related artifacts throughout the entire product lifecycle. The framework systematically analyzes safety requirements, traceability links, verification results, safety cases, and supporting documentation to identify inconsistencies, missing evidence, and potential compliance risks. By leveraging AI-based analytics, organizations can improve the accuracy, efficiency, and scalability of functional safety assessments while reducing manual review effort. The framework was evaluated using a representative Software Defined Vehicle (SDV) development program and demonstrated substantial improvements in traceability coverage, evidence completeness, assessment readiness, and overall review efficiency, thereby enabling a more proactive and data-driven approach to functional safety assurance.

Keywords

References

ISO 26262: Road Vehicles – Functional Safety.
ASPICE Process Assessment Model Version 4.0.
N. Leveson, Engineering a Safer World.
R. Bloomfield and P. Bishop, Safety Case Development.
Recent AI-assisted software assurance literature.
Machine learning applications in automotive quality engineering.
Knowledge graph analytics for systems engineering.
AI-based compliance monitoring frameworks.
Functional safety assurance in software-defined vehicles.
Explainable AI for safety-critical systems.

Most read articles by the same author(s)

1 2 3 4 5 6 7 8 > >> 

Similar Articles

1-10 of 32

You may also start an advanced similarity search for this article.