Regression algorithms-driven mechanical properties prediction of angle bracket connection on cross-laminated timber structures

Abstract

Abstract The construction of structures using cross-laminated timber (CLT) has grown in popularity as a result of its environmentally friendly and high-strength characteristics. The primary function of angle bracket connections is to resist the force of CLT structures under horizontal forces, which is essential to ensure the seismic resilience and ductility of CLT structures. A regression algorithms-driven method for predicting the mechanical performance of angle bracket connections is introduced in this study. As input parameters, the geometric dimensions of the angle bracket connector, the connection method of the connector with the wall and floor slabs, and the properties of the CLT panel are utilized to predict the yield load, the maximal load, the initial stiffness, and the ductility ratio of the angle bracket connection. Prediction models were developed using the collected data from 110 angle bracket experiments, and each prediction model's performance was discussed in depth. Lastly, the permutation importance and SHapley Additive exPlanations (SHAP) value analysis were used to interpret the prediction models. The results showed that the extreme gradient boosting (XGB) algorithm could accurately predict the maximum and yielding load of the angle bracket connection, with R2 reaching 0.968 and 0.939. Furthermore, in predicting the initial stiffness of the angle bracket, the XGB algorithm performed the best with an average ratio of predicted to actual values of 0.985. The results indicated that this study proposed an accurate and efficient method for angle bracket connection to predicting its mechanical properties and confirmed the trustworthiness and feasibility of the prediction models.

Keywords

• Machine learning
• Regression algorithm
• Cross-laminated timber structure
• Angle bracket connection
• Mechanical property