Aerospace systems are enormous in numbers and diverse, from small to complex subsystems. They range from a component to a complete air system as well as space systems, etc. A complete and universal machine learning (ML) framework for aerospace systems is still unavailable to this date. This paper proposes and implements an ML-based Aerospace System (MAS) framework to understand and model data of the targeted aerospace systems. Any of the aerospace systems can be modeled using the MAS framework. For easy presentation and convenience, three chosen aerospace systems are considered to be modeled using the MAS framework. The results show that the MAS framework has negligible error, and high accuracy. The proposed MAS framework is equally applicable to other remaining aerospace systems minimum modification. The MAS framework can be thought of as a universal artificial intelligence tool to understand, model, and predict the real-time behavior of aerospace systems.
MAS: A Machine Learning Framework for Aerospace Systems
Lect. Notes Electrical Eng.
International Conference on Aerospace System Science and Engineering ; 2024 ; Shanghai, China July 17, 2024 - July 18, 2024
Proceedings of the International Conference on Aerospace System Science and Engineering 2024 ; Chapter : 28 ; 292-304
2025-03-09
13 pages
Article/Chapter (Book)
Electronic Resource
English
Systems Engineering as an Effective Educational Framework for Active Aerospace Design Learning
British Library Conference Proceedings | 2009
|Framework for measuring complexity of aerospace systems
Tema Archive | 2014
|Machine learning and data mining in aerospace technology
SLUB | 2020
|