Steel Moment Frames with RWS Connections: Bilin Parameter Prediction with Machine Learning

This paper investigates the seismic performance of Reduced Web Section (RWS) connections in steel moment frames. To be able to evaluate the performance of RWS, a well-established concept involving strategic weakening of beam sections. This paper employs advanced machine learning and deep learning techniques to predict the Ibarra-Medina-Krawinkler (IMK) Bilin parameters for RWS connections across various configurations. A database of 154 specimens from experimental and finite element studies was analysed, focusing on non-composite RWS connections. The study develops and compares multiple predictive models, including Random Forest, Neural Networks, Support Vector Regression, Gradient Boosting, XGBoost, and Deep Learning, to predict IMK Bilin parameters with high accuracy. XGBoost consistently demonstrated superior performance across various metrics. Feature importance analysis revealed complex interactions between geometric properties and connection behaviour, with web slenderness and span-to-depth ratio playing critical roles. Moreover, pushover analyses were conducted on 2-, 4-, 8-, 12-, and 20-story benchmark frames to associate the global seismic behaviour of frames with RWS and RBS connections. Results indicate that RWS connections often provide higher strength and comparable or superior ductility to RBS connections, especially in low to mid-rise structures. All RWS configurations achieved interstory drifts exceeding 4%, meeting ANSI/AISC and EC8 performance targets. This research further contributes to the adoption of RWS connections for retrofitting purposes and provides a robust tool for structural engineers to incorporate these connections into performance-based seismic design.