Data-driven prediction of load transfer function for high neck flexible flange bolts in lattice wind turbine towers

The load transfer function (LTF) of flange bolt connections is crucial for evaluating the fatigue life of lattice wind turbine towers. Traditional LTF methods face accuracy challenges due to larger flange sizes with increasing turbine hub heights. This study validates the Schmidt/Neuper method and introduces a machine learning (ML) approach to calculate bolt internal forces. After validating the finite element model (FEM) through static testing, the study compares the LTFs of integral flange connections and simplified models with the Schmidt/Neuper method, identifying its limitations. A parameter correlation analysis leads to the creation of a FEM database, from which various machine learning models: Linear Regression (LR), k-Nearest Neighbors (KNN), Support Vector Regression (SVR), Decision Tree (DT), Gaussian Process Regression (GPR), Random Forest (RF), CatBoost (CB), and XGBoost (XG) are developed and tested. A user-friendly graphical interface is provided. The finding reveals the limitations of Schmidt/Neuper method, mainly due to its assumption of a single bolt joint and neglecting load distribution, leading to inaccuracies. The ML approach improves LTF prediction accuracy, providing a more reliable method for fatigue life assessment in flange bolt connections.