Research on Deep-learning-based Flight Load Test and Estimation Method

Abstract

The flight load test technology is of great importance for load designing, strength flight test and life monitoring of the aircraft. In order to realize the real-time distributed aerodynamic load test on the complex wing surface, the data-driven load estimation method based on refine finite element simulation is proposed. The artificial neural network is established with deep-learning method. The data set of the structural response is constructed by the high-precision finite element method, which is used to train the model. The wing load estimation results based on deep learning method is compared and verified with the finite element calculation results. The results show that the average error of the total load is about 0.2%, and the position error of the pressure center is about 1%. The method using several strain test points can estimate and reconstruct the load distribution of the whole wing in real time.

Keywords

• flight load test
• complex airfoils
• load estimation
• deep learning
• digital twins