Development of a static test platform for determining the loads on an Unmanned Aerial Vehicle (UAV)

Ensuring the structural integrity of unmanned aerial vehicles (UAVs) before flight requires reliable experimental procedures that can replicate operational loading scenarios. In this paper, a static testing platform was developed to reproduce conditions characteristic of vertical lift and cruise motor activation, providing detailed insight into the distribution of forces, moments, and dynamic effects acting on the structure. The experimental data were employed to verify finite element simulations and to support the creation of an artificial neural network model capable of rapid load prediction in structural components. Beyond fast estimation, the ANN approach was used to identify sensor placement strategies that improve measurement quality within the testing setup. The platform integrates a reinforced frame with load and displacement sensors, while a dedicated acquisition system ensures accurate monitoring of responses under controlled loads. By combining experimental validation with advanced modeling techniques, the proposed methodology reduces structural uncertainty and contributes to the design of UAVs with higher reliability and efficiency, suitable for demanding applications in defense, surveillance, transport, and agriculture.