A Formalisation and Reasoning Proposal based on QRH Analysis for Failure Mitigation in Aircraft Systems Emergencies

• Grant number: 25/02886-3
• Support Opportunities: Regular Research Grants
• Start date: August 01, 2025
• End date: July 31, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Mobility Program: SPRINT - Projetos de pesquisa - Mobilidade
• Principal Investigator: Carlos Henrique Costa Ribeiro
• Grantee: Carlos Henrique Costa Ribeiro
• Principal researcher abroad: Odinaldo Rodrigues
• Institution abroad: King's College London, England
• Host Institution: Divisão de Ciência da Computação (IEC). Instituto Tecnológico de Aeronáutica (ITA). Ministério da Defesa (Brasil). São José dos Campos , SP, Brazil
• Associated research grant: 21/11258-5 - Engineering Research Center for the Aerial Mobility of the Future (ERC-AMF), AP.PCPE

Abstract

In aircraft operation, irregular flight situations usually trigger failure signals which are displayed on dashboards on the flight deck. A failure is associated with one or more irregular scenarios, each requiring some type of intervention from pilots. The Quick Reference Handbook (QRH) contains a series of checklists - sequences of corrective actions to be taken when specific failure signals occur. However, in complex situations multiple checklists may need to be considered and employed, and at each step of a sequence, the execution of one action may impair the effectiveness of the corrective procedure of an alternative checklist. Multiple failure signals can also occur at once, making it arduous for pilots to determine the actual scenario an aircraft is in, and to decide which actions need to be taken to correct the aircraft's operation. Our proposal is to set the foundation for a long-term project to investigate and devise novel alternative representations and decision-making supporting schemes for the issues outlined above. The work will not be limited to one specific type of aircraft or manufacturer, as international standards dictating the operation of all modern aircraft systems. Moreover, the investigation will have a direct positive impact for the aeronautical industry and for the research carried out at the Decision Making for Autonomous Systems Group at the FlyMov Research Center, a joint effort by Embraer, ITA and FAPESP, upon which this proposal is defined. As additional motivation, we highlight that the Artificial Intelligence Roadmap of the European Union Aviation Safety Agency defines safety risk management as one of the aspects that can have an impact from AI-based solutions, defining it as a key enabler for emerging risks detection, risk classification of occurrences, and Safety Risk Portfolio design and prioritisation of safety issues. The problem to be tackled is how to define a knowledge representation scheme compatible with aircraft emergency procedures satisfying two objectives: a) It must provide useful information for the aircraft operator (the pilot) in the case of multiple failures that trigger distinct and possibly conflicting procedures; and b) It must be suitable for autonomous learning mechanisms for supporting decision-making in multiple failure scenarios. (AU)