Worker Centric Aircraft Maintenance Training

Stakeholders' Roles

TAP will provide domain knowledge, context definition, as well as maintenance, training, technical orders, and technicians data and will evaluate the pilot’s results. IML will extend its XR platform (SLB) to support human-robot training in the maintenance of the WAIV. SUPSI will be responsible for the development of the Human DT.

Motivation & Description

Proper maintenance of airplanes is critical to ensure the safety of passengers and crew members. One of the essential components that must be in working order is the Wing Anti-Ice Valve (WAIV), which is a part of the Minimum Equipment List (MEL). If this component fails, the aircraft cannot take off, and maintenance technicians must quickly repair it to minimise the grounding time. The process of repairing the WAIV is not only time-sensitive but also subject to maloperation, which can lead to costly consequences. All certified Aircraft Maintenance Technicians (AMTs) are required to perform this maintenance procedure, and they face harsh stress conditions during the process. XR5.0 technologies can be used to improve the efficiency and safety of such training processes. The pilot aims to enhance WAIV maintenance efficiency and precision, reducing maloperation risks by developing AI tools and XR environments. It involves expanding IML's VR platform with AI and human Decision Trees solutions, offering immersive simulations based on skilled AMT's. Successful implementation will integrate human-cenric XR applications in aviation, improving aircraft safety and reliability for passengers and airlines.


Stress index: The less stress the human faces increase the probability of the successful operation, it will be measured with physiological sensors, the baseline will be the resting person and will be compared with the skilled worker’s performance; Performance: Precision and faults of the execution by comparing with the learning digital twin taking as baseline the skilled worker operation. It will use time and adherence to the digital twin measurements.

Use Cases

This Use Case will leverage the project's AI tools in an XR environment to support and train AMTs in this critical maintenance procedure. Specifically, IML’s Systemic Lisbon Battery (SLB) platform will be expanded to provide XR environments for human-robot training in the maintenance of the WAIV. Using AI in a properly designed XR environment (including XAI explanations) the UC will improve the efficiency and accuracy of the maintenance procedure while reducing the risk of maloperation. This will result in a safer and more reliable fleet of airplanes, which will benefit both passengers and airlines.

This Use Case will develop a Human DT simulating the most skilled Aircraft Maintenance Technicians (AMTs) and continuously improve its skills and knowledge. By learning from failures and avoiding them in the future, the DT will be a valuable asset in training new maintenance technicians. The DT will use the XR5.0 visualisation and AI-generated voice instructions to guide the technician through the maintenance process. It will also provide feedback about the movements to execute and warn if the execution deviates from the plan proposed by the AI through the DT.