Aircraft Structural Stress Prediction Based on Multilayer Perceptron Neural Network

In the field of aeronautics, aircraft, as a critical aviation tool, exert a decisive influence on the structural integrity and safety of the entire system. Accurate prediction of the stress field distribution and variations within the aircraft structure is of great importance to ensuring its safety performance. To facilitate such predictions, a rapid assessment method for stress fields based on a multilayer perceptron (MLP) neural network is proposed. Compared to the traditional machine learning algorithm, the random forest algorithm, MLP demonstrates superior accuracy and computational efficiency in stress field prediction, particularly exhibiting enhanced adaptability when handling high-dimensional input data. This method is applied to predict stresses in the wing rib structure. By performing finite element meshing on the wing ribs, the angle of attack, inflow velocity, and node coordinates are utilized as input tensors for the model, enabling it to learn the stress distribution in the wing ribs. Additionally, a peak stress prediction model is separately established for regions experiencing peak stresses. The results indicate that the MAPE of the stress field prediction model is within 5%, with a coefficient of determination R2 exceeding 0.994. For the peak stress model, the MAPE is within 2%, with an R2 exceeding 0.995. This method offers faster computation and greater flexibility, presenting a novel approach for structural strength assessment.