Predictive modeling of BLDC motor performance in UAV systems using ensemble learning

Abstract

Accurate prediction of thrust and torque is essential for optimizing the performance, energy efficiency, and control of brushless direct current (BLDC) motors in unmanned aerial vehicles (UAVs). Traditional physics-based models often struggle to capture the nonlinear relationships between motor input parameters and aerodynamic outputs, prompting the exploration of data-driven approaches. This study evaluates the predictive capabilities of six ensemble learning algorithms, including Bootstrap Aggregating (Bagging), Adaptive Boosting (AdaBoost), Gradient Boosting Machine (GBM), Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), and Stacked Generalization (Stacking), in modeling thrust and torque. Experimental data were obtained using a Tyto Robotics thrust stand designed for precise static performance testing of electric propulsion systems. Among the models, CatBoost exhibited the highest accuracy in thrust prediction with a coefficient of determination of 0.9873, a root mean square error (RMSE) of 7.0506, a mean absolute error (MAE) of 6.0610, and a mean absolute percentage error (MAPE) of 2.10%. In torque prediction, AdaBoost demonstrated superior performance, achieving an R² of 0.9713, RMSE of 0.0018, MAE of 0.0013, and MAPE of 2.60%, effectively capturing complex electromechanical dynamics. In contrast, XGBoost underperformed in thrust prediction due to hyperparameter sensitivity, while Stacking showed limited generalization in torque estimation. Bagging and GBM delivered moderate and consistent results across both outputs. The findings underscore the potential of CatBoost and AdaBoost for robust predictive modeling of UAV propulsion systems, contributing to enhanced control and system design in autonomous flight applications.