Experimental and numerical evaluation of rigid column to baseplate connection under cyclic loading

Abstract

Summary One of the most important connections in steel structures is column to the baseplate connection. This kind of connection has a complex nature, due to different behaviors of the constituents, including baseplate, grout, foundation, and anchor bolts. Studying the impact of this connection in general behavior of structure seems to be an essential issue, especially during earthquake, which is more likely to be associated with plastic hinge forming. The main goal of this work is to provide a hybrid modeling for describing hysteresis behavior of column to the baseplate connection. Within hybrid modeling, a mechanical model is accomplished by using neural network model components. Our findings reveal that hybrid models are able to show pinched hysteresis complex behavior of baseplate connections. Also, the proposed hybrid developed model is robust and reliable approaches for predicting behaviors of a recent designed connection.

Hybrid Krill Herd-ANN Model for Prediction Strength and Stiffness of Bolted Connections

“…where N H represents the number of neurons in the hidden layers and N I is the number of input variables. Since the number of influential input variables for the current study is equal to 6, the empirical Equation (20) shows that the number of neurons in hidden layers can be less than 13. Therefore, several networks with different topologies (with a maximum of 2 hidden layers and a maximum of 13 neurons) were trained and studied in this paper.…”

“…Over the past few years, a large number of studies have been performed in the area of modeling beam-to-column connections, from simplified global models to comprehensive finite element simulations [17][18][19][20][21][22]. Examples of simplified methods are analytical and empirical models where predictions will be made by determining key parameters (e.g., moment capacity, initial stiffness, etc.)…”