Titulo Estágio
Interaction Design and Prototyping of a CBM Decision Support Tool (ReMAP project)
Áreas de especialidade
Engenharia de Software
Sistemas Inteligentes
Local do Estágio
CISUC (ISG)
Enquadramento
Enquadramento
Aircraft maintenance is currently carried out following one of two strategies: reactive, (also known as ‘fix when it fails’) and preventive (also known as pre-scheduled or interval-maintenance). The fusion of the emerging concepts of IoT, Big Data and Machine Learning have introduced a new promising alternative based on the concept of Integrated Fleet Health Monitoring.
Integrated Fleet Health Monitoring concept will enable a strategy to only repair aircraft parts that are actually damaged or to preventively replace parts that are approaching failure. A reliable network of sensors already covers several aircraft systems and primary structural elements, monitoring their health on a permanent basis. Efficient Machine Learning data analytics algorithms and physics models will process the terabytes of data generated per day by these sensors, providing operators with situational awareness and status of the entire fleet.
In the enar future, on-board algorithms will be able to diagnose the existence of systems’ faults that can be immediately communicated to the maintenance control centre. On the ground, powerful algorithms will fuse the coming data generated by the aircraft with historical data to diagnose the existence, location, and severity of structural damages or systems’ faults. Other algorithms will use the same type of data to estimate the remaining useful life of systems and structures, anticipating the need for maintenance.
A new planning interface is needed to support human performance under this Condition Based Maintenance context, that integrates all these elements, enabling a new model of AI assisted performance of the fleet maintenance planner.
Objetivo
Main Goal will be to study the foreseable new operative conditions in the Condition Based Maintenance context and propose an initial design for the interface to satisfy these conditions. This will imply getting involved with the international EU ReMAP project team, elicit relevant information from the team to propose interface designs and make prototypes, to be used in conjunction with relevant machine learning and classification techniques, when they become available in the context of other project tasks.
This will be an excelent opportunity to work on the novel frontier of designing ways for human interacting with AI, namely interfaces for data science systems.
Results will include:
- participatory prototyping workshop with stakeholders,
- draft design for the interface model,
- a working prototype version of the proposed interface,
- report on evaluation with relevant stakeholders.
Plano de Trabalhos - Semestre 1
This project follows a Design Research approach.
A1. (M1-M3) State of the art research - research and document the relevant publications and software, study interaction design techniques for the study of the problem at hand;
Overview of project context and importance of Condition Based Maintenance for Fleet Health Management; Propose initial predictive model workflow including the ML/AI techniques being developed by partners and prepare first case study;
A2. (M2 - M3) Participatory Design - PD workshops/interviews with stakeholders, detailed characterization of the problem to be solved stating specific goals and requirements, assumptions and milestones for the rest of the project;
A3. (M4 - M5) Detailed Design - performing initial development and technology tests, identification of quality issues, user interface model
Plano de Trabalhos - Semestre 2
A4. (M6 - M10) Prototyping - implementation and testing of a working interface prototype, corrections based on evaluation results
;
A5. (M9) Evaluation - definition of evaluation criteria and method, performance or evaluation and analysis of results
A6. (M6 - M10) Statement of Learning - production of a research paper and dissertation with reflection on artifacts/ knowledge produced.
Condições
This work will be carried out at CISUC (Information Systems Group), where there will be a regular supervision.
Good knowledge and research interest in the area of Human-Computer Interaction is a requirement.
A priori familiarity with Machine Learning and software tools is preferable, but not needed.
Student will likely acquire valuable knowledge and experience with data science tools.
The candidate should have an interest in research and good English proficiency.
Observações
This proposal is supported by the funded H2020 project REMAP (Real-time Condition-based Maintenance for Adaptive Aircraft Maintenance Planning): https://www.cisuc.uc.pt/projects/show/257.
A scholarship of 745 euros per month is foreseen for the full time period of the work, in renewable periods of 3 months.
Orientador
Licínio Gomes Roque
lir@dei.uc.pt 📩