XGBoost Gradient-Boosted Tree Predictions Using Limited Data for Coaxial Rotor Helicopters
- 1 December 2021
- journal article
- research article
- Published by American Institute of Aeronautics and Astronautics (AIAA) in Journal of Aerospace Information Systems
- Vol. 18 (12), 881-889
- https://doi.org/10.2514/1.i010983
Abstract
The use of finite-state methods is critical to the development of accurate and efficient inflow models used in rotorcraft flight dynamics simulation and control. Recent work in the finite-state field has allowed for the application of these models to multirotor systems using the adjoint theorem, which involves time delays and adjoint variables. However, the addition of time delays and adjoint variables drives the necessity for the addition of further inflow states to achieve model accuracy. Computation with a higher numbers of inflow states requires greater computing power and therefore limits the ability of real-time analysis. To help mitigate these issues, this paper explores the use of a gradient booted trees in XGBoostTM, as well as the use of varied, lower state training data and limited higher state training data, to accurately predict the velocity on the lower rotor of a coaxial rotor helicopter. The investigation involves XGBoost hyperparameter searches to determine the best model, variation in training and testing subset splits, and use of validation subset comparisons for identifying the best performing model.Keywords
Funding Information
- U.S. Army Aviation Development Directorate (W911 W6-17-2-0002)
This publication has 8 references indexed in Scilit:
- Simple Inflow and Structural Dynamics of a Coaxial Rotor with Time Delays and Adjoint VariablesPublished by AHS International dba Vertical Flight Society ,2019
- Improved EEMD-based crude oil price forecasting using LSTM networksPhysica A: Statistical Mechanics and its Applications, 2018
- AN EFFICIENT HYBRID MACHINE LEARNING METHOD FOR TIME SERIES STOCK MARKET FORECASTINGNeural Network World, 2018
- XGBoostPublished by Association for Computing Machinery (ACM) ,2016
- Autonomous Helicopter Aerobatics through Apprenticeship LearningThe International Journal of Robotics Research, 2010
- Apprenticeship learning for helicopter controlCommunications of the ACM, 2009
- Support Vector Machine based Online Composite Helicopter Rotor Blade Damage Detection SystemJournal of Intelligent Material Systems and Structures, 2007
- Autonomous Inverted Helicopter Flight via Reinforcement LearningPublished by Springer Science and Business Media LLC ,2006