Machine Learning-Based Prediction of Elastic Buckling Coefficients on Diagonally Stiffened Plate Subjected to Shear, Bending, and Compression

The buckling mechanism of diagonally stiffened plates under the combined action shear, bending, and compression is a complex phenomenon that difficult to describe with simple clear explicit expressions. Predicting elastic coefficient accurately crucial for calculating load these plates. Several factors influence plates, including plate’s aspect ratio, stiffener’s flexural torsional rigidity, in-plane load. Traditional analysis methods rely on fitting large number finite element numerical simulations obtain an empirical formula single However, this cannot be applied loads. To address limitations, several machine learning (ML) models were developed using ML method SHAP predict Eight trained, decision tree (DT), k-nearest neighbor (K-NN), artificial neural network (ANN), random forest (RF), AdaBoost, LightGBM, XGBoost, CatBoost. performance was evaluated found highly accurate in predicting loading. Among eight models, XGBoost best. Further revealed ratio plate most important feature influencing coefficient. This followed by as well flexure rigidity stiffener. Based findings, it recommended stiffener-to-plate stiffness greater than 20 torsional-to-flexural 0.4. will improve enable them achieve higher capacity.