Machine-Learning-Based Real-Time Trajectory Prediction of Store Release from Cavity
TL;DR
A data-driven reduced-order model (ROM) capable of accurately predicting the real-time trajectory of a store released from an internal cavity is developed and shows significant promise for efficiently predicting store trajectories, making it a viable solution for real-time analysis in defense and aerospace applications.
Abstract
The release of stores from internal carriage configurations in modern aircraft requires precise modeling due to the highly unsteady flow dynamics involved. Traditional methods for predicting store trajectories are often computationally intensive, making real-time predictions challenging. In this study, we develop a data-driven reduced-order model (ROM) capable of accurately predicting the real-time trajectory of a store released from an internal cavity. Using data generated from two-dimensional inviscid computational fluid dynamics (CFD) simulations, we employ dynamic-time-warping-based clustering to group similar cases and proper orthogonal decomposition (POD) for mode reduction. A support-vector-machine-based regression model is then used to predict the POD components for new cases. The proposed ROM successfully predicts the [Formula: see text]-position, [Formula: see text]-position, and orientation of the store with moderate to satisfactory accuracy when compared to CFD simulations. However, limitations in predicting higher-order POD modes, particularly for the [Formula: see text]-position, indicate areas for future improvement. Despite these challenges, the proposed ROM shows significant promise for efficiently predicting store trajectories, making it a viable solution for real-time analysis in defense and aerospace applications.