• Steel and Composite Structures
• /
• v.47 no.6
• /
• pp.759-779
• /
• 2023

The paper proposes two hybrid metaheuristic optimization and artificial neural network (ANN) methods for the close prediction of the ultimate axial compressive capacity of concentrically loaded concrete filled double skin steel tube (CFDST) columns. Two metaheuristic optimization, namely genetic algorithm (GA) and particle swarm optimization (PSO), approaches enable the dynamic training architecture underlying an ANN model by optimizing the number and sizes of hidden layers as well as the weights and biases of the neurons, simultaneously. The former is termed as GA-ANN, and the latter as PSO-ANN. These techniques utilize the gradient-based optimization with Bayesian regularization that enhances the optimization process. The proposed GA-ANN and PSO-ANN methods construct the predictive ANNs from 125 available experimental datasets and present the superior performance over standard ANNs. Both the hybrid GA-ANN and PSO-ANN methods are encoded within a user-friendly graphical interface that can reliably map out the accurate ultimate axial compressive capacity of CFDST columns with various geometry and material parameters.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.04a
• /
• pp.81-84
• /
• 2008

The equation, specified in current bridge design code, for calculating the confining transverse reinforcement amount of RC bridge columns has been made to provide additional load-carrying strength for concentrically loaded columns equal to or slightly greater than the strength lost when the cover concrete spalls off. However, this equation does not directly consider ductile behavior, which is an important factor for the seismic behavior of bridge columns. Consequently, if the section area is relatively small or if the section area ratio becomes excessively large due to the concrete cover thickness increased for durability, too large an amount of transverse reinforcement, which could deteriorate the constructability and economy of piers, will be required. This study intends to analyze what effects the concrete cover thickness has on the equation for determining the confining transverse reinforcement amount.

• Journal of the Korea Concrete Institute
• /
• v.21 no.2
• /
• pp.169-178
• /
• 2009

An equation for calculating confining reinforcement amount of RC bridge columns, specified in the current bridge design codes, has been made to provide additional load-carrying strength for concentrically loaded columns. The additional load-carrying strength will be equal to or slightly greater than the resistant strength of a column against axial load, which is lost because the cover concrete spalls off. The equation considers concrete compressive strength, yield strength of transverse reinforcement, and the section area ratio as major variables. Among those variables, the section area ratio between the gross section and the core section, varying by cover thickness, is a variable which considers the strength in the compression-controlled region. Therefore, the cross section ratio does not have a large effect in the aspect of ductile behavior of the tension-controlled region, which is governed by bending moment rather than axial force. However, the equation of the design codes for calculating confining reinforcement amount does not directly consider ductile behavior, which is an important factor for the seismic behavior of bridge columns. Consequently, if the size of section is relatively small or if the section area ratio becomes excessively large due to the cover thickness increased for durability, too large an amount of confining reinforcement will be required possibly deteriorating the constructability and economy. Against this backdrop, in this study, comparison and analysis were performed to understand how the cover thickness influences the equation for calculating the amount of confining reinforcement. An equation for calculating the amount of confining reinforcement was also modified for reasonable seismic design and the safety. In addition, appropriateness of the modified equation was examined based on the results of various test results performed at home and abroad.