This comprehensive review of 83 publications surveys over 30 years of research into automating HAZOP studies, covering knowledge-based systems, model-based approaches, data-driven methods, and integrated tools. It categorizes automation efforts across chemical, petrochemical, and oil and gas industries. For MOC in process safety, HAZOP revalidation is often triggered when significant process changes are proposed. Automating portions of the HAZOP workflow—from hazard identification using AI models to consequence assessment using data-driven classifiers—can dramatically reduce the time and cost of MOC-triggered safety reviews. This review provides practitioners and researchers with a comprehensive roadmap of available AI tools and techniques for streamlining the hazard analysis component of Management of Change processes.
