Aircraft maintenance information system design and verification
Operational support is one of the most important aspects of aeronautical maintenance. It aims to provide a portfolio of services to implement maintenance with a high level of efficiency, reliability and accessibility. One of the main difficulties in operational support is that there is no platform that integrates all aircraft maintenance processes in order to reduce costs and improve the level of service. It is, therefore, necessary to build an autonomous aircraft maintenance system in which all maintenance information can be collected, organized, analyzed and managed in a way that facilitates decision-making. To do this, an innovative methodology has been proposed, which concerns modelling, simulation, formal verification and performance analysis of the autonomous system mentioned. Three axes were addressed in this thesis:
- The first axis concerns the design and simulation of an autonomous system for aeronautical maintenance. We offer an innovative design of an autonomous system that supports automatic decision making for maintenance planning.
- The second axis is the verification of models on simulation systems. We propose a more comprehensive approach to verifying global behaviours and operational behaviours of systems.
- The third axis focuses on the analysis of the performance of simulation systems. We propose an approach of combining an agent-based simulation system with a Fuzzy Rough Nearest Neighbor approach, in order to implement efficient classification and prediction of aircraft maintenance failures with missing data. Finally, simulation models and systems have been proposed.
Simulation experiments illustrate the feasibility of the proposed approach.