Automation of STPA Using Natural Language Processing and Machine Learning: Automatic Generation of Safety Requirements

• Grant number: 25/16287-4
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: October 01, 2025
• End date: March 31, 2028
• Field of knowledge: Engineering - Aerospace Engineering - Aerospace Systems
• Principal Investigator: Luiz Eduardo Galvão Martins
• Grantee: Gabriel Nogueira Pacheco
• Host Institution: Instituto de Ciência e Tecnologia (ICT). Universidade Federal de São Paulo (UNIFESP). Campus São José dos Campos. São José dos Campos , SP, Brazil
• Associated research grant: 23/03393-5 - STPA Automation Using Natural Language Processing and Machine Learning, AP.R

Abstract

This project focuses on utilizing STAMP (System Theoretic Accident Model and Processes) and STPA (System Theoretic Process Analysis), both processes proposed by Nancy Leveson and widely used in risk and hazard analysis in critical aviation and aerospace systems. The goal is to promote automation of the STPA technique for the aviation domain by developing classifier models that automate and integrate the identification of losses, hazards, and constraints (STPA step 1), control actions and feedbacks (STPA step 2), unsafe control actions (STPA step 3), and loss scenarios (STPA step 4). The STPA values will form the basis for the automatic generation of safety requirements, the main focus of this doctoral program. Among the expected results, we intend to provide a set of tools that enable the automation of the STPA and the generation of safety requirements, to help improve the quality and productivity of the teams responsible for analyzing risks and hazards in critical systems, with a reduction in cost and time in the process of their development and certification. (AU)