Explore the vast range of titles available.

This study aims to investigate the prediction of critical buckling load of steel columns using two hybrid Artificial Intelligence (AI) models such as Adaptive Neuro-Fuzzy Inference System optimized by Genetic Algorithm (ANFIS-GA) and Adaptive Neuro-Fuzzy Inference System optimized by Particle Swarm Optimization (ANFIS-PSO). For this purpose, a total number of 57 experimental buckling tests of novel high strength steel Y-section columns were collected from the available literature to generate the dataset for training and validating the two proposed AI models. Quality assessment criteria such as coefficient of determination (R2), Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) were used to validate and evaluate the performance of the prediction models. Results showed that both ANFIS-GA and ANFIS-PSO had a strong ability in predicting the buckling load of steel columns, but ANFIS-PSO (R2 = 0.929, RMSE = 60.522 and MAE = 44.044) was slightly better than ANFIS-GA (R2 = 0.916, RMSE = 65.371 and MAE = 48.588). The two models were also robust even with the presence of input variability, as investigated via Monte Carlo simulations. This study showed that the hybrid AI techniques could help constructing an efficient numerical tool for buckling analysis.

The type of materials used in designing and constructing structures significantly affects the way the structures behave. The performance of concrete and steel, which are used as a composite in columns, has a considerable effect upon the structure behavior under different loading conditions. In this paper, several advanced methods were applied and developed to predict the bearing capacity of the concrete-filled steel tube (CFST) columns in two phases of prediction and optimization. In the prediction phase, bearing capacity values of CFST columns were estimated through developing gene expression programming (GEP)-based tree equation; then, the results were compared with the results obtained from a hybrid model of artificial neural network (ANN) and particle swarm optimization (PSO). In the modeling process, the outer diameter, concrete compressive strength, tensile yield stress of the steel column, thickness of steel cover, and the length of the samples were considered as the model inputs. After a series of analyses, the best predictive models were selected based on the coefficient of determination (R2) results. R2 values of 0.928 and 0.939 for training and testing datasets of the selected GEP-based tree equation, respectively, demonstrated that GEP was able to provide higher performance capacity compared to PSO–ANN model with R2 values of 0.910 and 0.904 and ANN with R2 values of 0.895 and 0.881. In the optimization phase, whale optimization algorithm (WOA), which has not yet been applied in structural engineering, was selected and developed to maximize the results of the bearing capacity. Based on the obtained results, WOA, by increasing bearing capacity to 23436.63 kN, was able to maximize significantly the bearing capacity of CFST columns.

This paper presents a comprehensive investigation into the prediction of axial load capacity (P) for elliptical double steel columns (EDSCs) using a diverse set of machine learning models (MLMs). These include Artificial Neural Network (ANN), Gene Expression Programming (GEP), Support Vector Regression (SVR), Random Forest (RF), and AdaBoost. Among the models, AdaBoost demonstrated superior performance, achieving an R 2 of 0.996 and a MAPE of 0.013 during training, outperforming other models under identical conditions. Using a dataset of 119 finite element models derived from prior experimental research, the study validates the proposed solution through k-fold cross-validation, feature importance analysis, and detailed comparisons with experimental data. A Graphical User Interface (GUI) was developed specifically for the AdaBoost model due to its superior accuracy and efficiency, offering engineers a practical and accessible tool for axial load prediction in EDSC design. This research highlights the significance of using advanced machine learning techniques for structural engineering applications, providing valuable insights for the optimization of EDSC performance and design under varying conditions.

Since laboratory tests are usually costly, simulating methods using computers are always under the spotlight. This study performed a finite element analysis (FEA) using iterative solutions for simulating circular and square concrete-filled steel tube (CFST) columns infilled with high-strength concrete and reinforced with a cross-shaped plate (comprising two plates along the columns that divide the hollow columns into four equal sections) with and without opening. For this reason and for validation purposes, the columns had length of 900 mm, width/diameter of 150 mm and wall thickness of 3 mm. In this study, unlike in some other studies, the cross-shaped plate was assumed to be fixed at the top and the bottom of a column, and the columns were subjected to axial compression pointed in the center. The outcomes revealed that the cross-shaped plate could improve the axial strength of both circular and square CFST columns; however, the structural performance of the square CFST columns changed: local outward buckling was observed after inserting the cross-shaped plate. By inserting an opening on the cross-shaped plate, the bearing capacity of the circular CFST columns was further improved, while the square CFST columns experienced a decline in their ultimate bearing capacity compared with the corresponding models without the opening. The lateral deflection also improved for the circular CFST columns by adding the reinforcement. However, for the square CFST columns, while it initially improved, increasing the thickness of the cross-shaped plate inversely influenced the lateral deflection of the square CFST columns. The results were also compared with some available codes, and a good agreement was achieved with those outcomes.

PurposeThe capability of steel columns to support their design loads is highly affected by the time of exposure and temperature magnitude, which causes deterioration of mechanical properties of steel under fire conditions. It is known that structural steel loses strength and stiffness as temperature increases, particularly above 400 °C. The duration of time in which steel is exposed to high temperatures also has an impact on how much strength it loses. The time-dependent response of steel is critical when estimating load carrying capacity of steel columns exposed to fire. Thus, investigating the structural response of cold-formed steel (CFS) columns is gaining more interest due to the nature of such structural elements.Design/methodology/approachIn this study, experiments were conducted on two CFS configurations: back-to-back (B-B) channel and toe-to-toe (T-T) channel sections. All CFS column specimens were exposed to different temperatures following the standard fire curve and cooled by air or water. A total of 14 tests were conducted to evaluate the capacity of the CFS sections. The axial resistance and yield deformation were noted for both section types at elevated temperatures. The CFS column sections were modelled to simulate the section's behaviour under various temperature exposures using the general-purpose finite element (FE) program ABAQUS. The results from FE modelling agreed well with the experimental results. Ultimate load of experiment and finite element model (FEM) are compared with each other. The difference in percentage and ratio between both are presented.FindingsThe results showed that B-B configuration showed better performance for all the investigated parameters than T-T sections. A noticeable loss in the ultimate strength of 34.5 and 65.6% was observed at 90 min (986℃) for B-B specimens cooled using air and water, respectively. However, the reduction was 29.9 and 46% in the T-T configuration, respectively.Originality/valueThis research paper focusses on assessing the buckling strength of heated CFS sections to analyse the mode of failure of CFS sections with B-B and T-T design configurations under the effect of elevated temperature.

This work presents the design and application of a low-cycle reciprocating loading test on 23 recycled aggregate concrete-filled steel tube columns and 3 ordinary concrete-filled steel tube columns. Additionally, a systematic study on the influence of various parameters (e.g., slenderness ratio, axial compression ratio, etc.) was conducted on the seismic performance of the specimens. The results show that all the specimens have good hysteresis performance and a similar development trend of skeleton curve. The influence of slenderness ratio on the seismic index of the specimens is more significant than that of the axial compression ratio and the steel pipe wall thickness. Furthermore, artificial intelligence was applied to estimate the influence of parameter variation on the seismic performance of concrete columns. Specifically, Random Forest with hyperparameters tuned by Firefly Algorithm was chosen. The high correlation coefficients ( ) and low root mean square error values from the prediction results showed acceptable accuracy. In addition, sensitivity analysis was applied to rank the influence of the aforementioned input variables on the seismic performance of the specimens. The research results can provide experimental reference for the application of steel tube recycled concrete in earthquake areas.

Concrete-filled steel columns are increasingly recognised for their enhanced structural performance. This study investigates an innovative shear connector design with screw connectors as an alternative to conventional connection types. From push-out testing, the shear capacity of screw connectors in composite columns comprising cold-formed steel sigma sections and concrete infill was evaluated. Experimental push-out testing demonstrated the effectiveness of theoretical equations in estimating the shear strength of screw connections. The comparison indicates that established design methods provide reasonable predictions, supporting their applicability in practical scenarios. Theoretical equations in the literature for estimating shear strength were tested for suitability and gave comparable results. Disassembling of tested specimens showed that a concrete failure was the prominent mode of ultimate condition. Shear screws offer a novel design alternative to conventional shear connection methods. They demonstrate significant potential for structural applications when integrated with advanced composite column sections, such as the four-sigma built-up CFS sections. The study highlights screw connectors as a cost-effective, sustainable, and practical solution for innovative composite column designs, offering significant potential for construction and maintenance efficiency.

A new type of dual-steering prestressed plate column is introduced. Compared to the previous prestressed strut column, this proposed column considers both bending and constraints at ends. The calculation results indicated that the support plate significantly improves the stable bearing capacity and buckling performance of the core steel column. When compared to the proposed column, the bearing capacity of the three-transverse prestressed beam column is 1.51 times smaller, the single-transverse prestressed beam column is 2.43 times lower, and the non-prestressed column is 4.51 times smaller. Moreover, this study examines the influences of effective length, buckling mode, stress nephogram detail, and prestress value. It explores the possibility of implementing this new type of dual-steering prestressed plate column in practical engineering. In addition, the variety and mechanical models of prestressed columns are expanded and refined.

Concrete filled steel tube (CFST) columns are the main loaded elements in the structures as they provoke the superior mechanical properties of constituent materials. However, concrete filled double steel tube (CFDST) columns refer to a new type of composite elements which have very high level of fire resistance and the potential to be implemented in high-rise structures. Columns are exposed to high stresses due to the increasing loads of daily life. Therefore, unpredictable deformations may occur and affect the performance and safety of structures. This article first studies the effectiveness of a concrete filled circular steel tube (CFCST)-based technique for repairing buckled and stressed CFST columns, then it studies the advantages of CFDST columns in improving the capability of composite members. The CFCST-based repairing system is to place the deformed CFST column in a larger diameter steel tube, and then the concrete is poured in the gap between the deformed column and the larger tube. Buckled CFST specimens with different tube tkicknesses were repaired and tested to failure under axial compression. The performance of repaired CFST columns was comparedwith that of undamaged counterpart columns. Based on findings, it can be concluded that the repair technique restored the capacity of the deformed columns from 97% to 100% of the capacity of the undamaged counterpart columns which confirm the effectiveness of repairing using CFCST-based technique. Results of the study provide significant information to the available test data concerning repairing of CFST members. KCI Citation Count: 14

This study provides valuable insights into the axial resistance of two different configurations and identifies different failure modes in specimens subjected to various temperatures and cooling methods. Fire exposure tests were conducted on galvanized iron (GI) based CFS columns with different configurations: back-to-back (B.B) and toe-toe (T.T) channel sections to explore the residual buckling capacity of CFS columns. Both section types, B.B and T.T channels, were assessed for axial resistance and yield deformation at elevated temperatures. In addition, two B.B sections were insulated with fire protective coatings such as perlite and zinc and heated to assess their performance. A series of finite element models were developed using ABAQUS to simulate the behavior of the tested columns under different fire exposures. Further, the results indicate that the B.B configuration exhibited a higher load carrying capacity than the T.T configuration. Among unheated specimens, B.B section has a load of 257.6kN, which is 21.61% higher than the load obtained for T.T section, which is 201.9kN. Among the coated specimens, the section coated with perlite has a load of 250.2kN after heating for 60 min, which is virtually unchanged from the unheated specimen. The difference between coated and reference is just 2.87%. The section that was coated with zinc had a load of 225.6kN, which is 9.83% lower than the other coated specimen. In all instances, the B.B configuration sections demonstrated higher axial stiffness than the T.T configuration sections. This trend persists throughout the study, with axial stiffness decreasing as the duration of heating increases.