The continuous improvement of machine learning (ML) methods could change the approaches for the design and development of electrical Vertical Take Off and Landing (eVTOL) vehicles and drones and therefore lead to possible changes in certification and aviation standards.
The main objective of this research is to assess the impact of the deployment of digital solutions in eVTOL and drone development, processes, and operations on the whole airworthiness certification approach. It includes the safety standards and regulatory materials and how they could change. The use of digital solutions for the certification of drones and/or their components and related equipment could be a new method of compliance demonstration. The potential of this method is increased efficiency and decreased risks in flight testing.
To analyse this topic practically and effectively, the idea is to develop a case study of a digital twin (DT) of an eVTOL. It is carried out by enhancing an initial physics-based mathematical model, exploiting data from high-fidelity numerical simulations, computational fluid dynamics (CFD), and structural dynamics, as well as from flight testing. The “enhancement” concerns both accuracy and scope and is carried out via conventional and ML techniques, each exploited at its best. The final digital twin is expected to be a hybrid surrogate model-based DT, in which the necessary accuracy is provided by the initial physics-based model coupled with several surrogate models.
The expected result is a living DT able to reliably explore the entire flight envelope as well as the design space by accounting for changes in mass, centre of gravity, and configuration. The DT as such is expected to not only support certification but also continued airworthiness and follow the drone through its operative life. Finally, a roadmap should be developed to implement the needed aviation regulation changes as well as training materials to share the knowledge.