A Data-Driven Global Load Case Analysis Method for Aircraft Structural Design

Aircraft encounter complex ground and air scenarios during service, necessitating a comprehensive analysis of extensive global load cases during the design phase to ensure structural reliability and safety. While high-fidelity finite element analysis enables precise assessment of load case criticality, its prohibitive human and computational costs constrain aircraft iterative development. To overcome this challenge, this study proposes a Global Load Case Analysis (GLCA) system for identifying critical load cases across structural sections. The method is driven by aerodynamic load data and structural response data from coarse-grid models. First, it achieves a quantitative ranking of global load case criticality, providing engineers with a standardized severity metric. Second, based on defined criticality relationships, it identifies coverage, coupling, and differentiation patterns among load cases to establish criticality hierarchies. Finally, a novel 1DCNN architecture with specialized training strategies learns the GLCA system’s behavioral patterns, enabling accurate prediction of criticality for newly added load cases without computationally intensive reanalysis. The results demonstrate strong agreement between GLCA and high-fidelity model analyses: quantitative ranking achieves 95.98% average accuracy with complete identification of critical load cases. Predictions for new load cases yield coefficients of determination (R2) > 0.98 and 97.91% average criticality classification accuracy. Furthermore, GLCA operates 335 times more efficiently than high-fidelity finite element analysis. This approach effectively substitutes high-fidelity modeling during load development, reducing human effort and shortening aircraft design iteration cycles.