A Machine Learning Approach to Classify Hypersonic Vehicle Trajectories
| Autor: | Nhat X. Nguyen, Mary L. Comer, Moses W. Chan, Edward J. Delp, Emily R. Bartusiak |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
020301 aerospace & aeronautics
Hypersonic speed Training set Computer science business.industry Hypersonic vehicle 02 engineering and technology Aerodynamics Machine learning computer.software_genre symbols.namesake Aerospace testing 0203 mechanical engineering Mach number 0202 electrical engineering electronic engineering information engineering symbols Trajectory 020201 artificial intelligence & image processing Artificial intelligence business computer Mile |
| Zdroj: | 2021 IEEE Aerospace Conference (50100). |
| DOI: | 10.1109/aero50100.2021.9438274 |
| Popis: | Compared to conventional ballistic vehicles and cruise vehicles, hypersonic vehicles exhibit unprecedented and clearly superior abilities. Hypersonic glide vehicles (HGVs) travel at speeds faster than Mach 5, enabling them to fly at least one mile per second. Furthermore, they possess maneuvering capabilities that assist them in evading defense systems, increasing precision of their impact points, and hindering prediction of their final destinations. In this paper, we examine machine learning methods to automatically identify different hypersonic glide vehicles and a ballistic reentry vehicle (RV) based on trajectory segments. Trained on aerodynamic state estimates, our methods analyze key vehicle maneuvers to classify vehicles with high accuracy. We also identify vehicles with higher accuracy as time after liftoff (TALO) increases and more data becomes available for analysis. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|