Predicting the Ultimate Axial Capacity of Uniaxially Loaded CFST Columns Using Multiphysics Artificial Intelligence

The object of this research is concrete-filled steel tubes (CFST). The article aimed to develop a prediction Multiphysics model for the circular CFST column by using the Artificial Neural Network (ANN), the Adaptive Neuro-Fuzzy Inference System (ANFIS) and the Gene Expression Program (GEP). The database for this study contains 1667 datapoints in which 702 are short CFST columns and 965 are long CFST columns. The input parameters are the geometric dimensions of the structural elements of the column and the mechanical properties of materials. The target parameters are the bearing capacity of columns, which determines their life cycle. A Multiphysics model was developed, and various statistical checks were applied using the three artificial intelligence techniques mentioned above. Parametric and sensitivity analyses were also performed on both short and long GEP models. The overall performance of the GEP model was better than the ANN and ANFIS models, and the prediction values of the GEP model were near actual values. The PI of the predicted Nst by GEP, ANN and ANFIS for training are 0.0416, 0.1423, and 0.1016, respectively, and for Nlg these values are 0.1169, 0.2990 and 0.1542, respectively. Corresponding OF values are 0.2300, 0.1200, and 0.090 for Nst, and 0.1000, 0.2700, and 0.1500 for Nlg. The superiority of the GEP method to the other techniques can be seen from the fact that the GEP technique provides suitable connections based on practical experimental work and does not rely on prior solutions. It is concluded that the GEP model can be used to predict the bearing capacity of circular CFST columns to avoid any laborious and time-consuming experimental work. It is also recommended that further research should be performed on the data to develop a prediction equation using other techniques such as Random Forest Regression and Multi Expression Program.

Behaviour of Lightweight Concrete Wall Panel under Axial Loading: Experimental and Numerical Investigation toward Sustainability in Construction Industry

Awareness of sustainability in construction has led to the utilization of waste material such as oil palm shell (OPS) in concrete production. The feasibility of OPS as alternative aggregates in concrete has been widely studied at the material level. Meanwhile, nonlinear concrete material properties are not taken into account in the conventional concrete wall design equations, resulting in underestimation of lightweight concrete’s wall axial capacity. Against these sustainability and technical contexts, this research investigated the buckling behavior of OPS-based lightweight self-compacting concrete (LWSCC) wall. Failure mode, load-deflection responses, and ultimate strength were assessed experimentally. Numerical models have been developed and validated against experimental results. Parametric studies were conducted to study the influence of parameters like slenderness ratio, eccentricity, compressive strength, and elastic modulus. The results showed that the axial strength of concrete wall was very much dependent on these parameters. A generalized semi-empirical design equation, based on equivalent concrete stress block and modified by mathematical regression, has been proposed. The ratio of average calculated results to test results of the proposed equation, when compared to ACI 318, AS 3600, and Eurocode 2 equations, are respectively improved from 0.36, 0.31, and 0.42 to 0.97. This research demonstrates that OPS-based LWSCC concrete can be used for structural axial components and that the equation developed can serve a good guideline for its design, which could encourage automation and promote sustainability in the construction industry.

Using discrete-element method hindcasting of screw pile performance for practical design

Screw piles have been used to support a variety of structures due to their ease of installation and high axial capacity. Recently, screw piles have been proposed as an alternative foundation solution for offshore renewable structures due to their quiet or silent installation. Due to their variable geometry, design and prediction of installation requirements and its effect on in-service capacity may be challenging. In this research study, the discrete-element method (DEM) is used to numerically recreate a series of onshore field tests. The aim of the study is to investigate the ability of DEM to be used as a practical design tool for the design and deployment of screw piles. In this case study, the effect of the geometric helix pitch on the installation torque and tensile capacity of screw piles installed into sand is investigated. DEM results show that the geometric pitch of a screw pile appears to have little effect on the installation torque. The results show that DEM has the potential to be used as a practical design procedure for complex foundation installation where the simulation needs to capture installation effects.

Axial Behavior of Concrete-Filled Double-Skin Tubular Stub Columns Incorporating PVC Pipes

This experimental study presents concrete-filled double-skin tubular columns and demonstrates their expected advantages. These columns consist of an outer steel tube, an inner steel tube, and concrete sandwiched between two tubes. The influence of the outer-to-inner tube dimension ratio, outer tube to thickness ratio, and type of inner tube material (steel, PVC pipe) on the ultimate axial capacity of concrete-filled double-skin tubular columns is studied. It is found that the yield strength of the inner tube does not significantly affect the ultimate axial capacity of concrete-filled double-skin tubular composites. With the replacement of the inner tube of steel with a PVC pipe, on average, less than 10% strength is reduced, irrespective of size and dimensions of the steel tube. Hence, the cost of a project can be reduced by replacing inner steel tubes with a PVC pipes. Finally, the experimental results are compared with the existing design methods presented in AISC 360-16 (2016), GB51367 (2019), and EC4 (2004). It is found from the comparison that GB51367 (2019) gives better results, followed by AISC (2016) and EC4 (2004).

Numerical Evaluation of the Upright Columns with Partial Reinforcement along with the Utilisation of Neural Networks with Combining Feature-Selection Method to Predict the Load and Displacement

This study evaluated the axial capacity of cold-formed racking upright sections strengthened with an innovative reinforcement method by finite element modelling and artificial intelligence techniques. At the first stage, several specimens with different lengths, thicknesses and reinforcement spacings were modelled in ABAQUS. The finite element method (FEM) was employed to increase the available datasets and evaluate the proposed reinforcement method in different geometrical types of sections. The most influential factors on the axial strength were investigated using a feature-selection (FS) method within a multi-layer perceptron (MLP) algorithm. The MLP algorithm was developed by particle swarm optimization (PSO) and FEM results as input. In terms of accuracy evaluation, some of the rolling criteria including results showed that geometrical parameters have almost the same contribution in compression capacity and displacement of the specimens. According to the performance evaluation indexes, the best model was detected and specified in the paper and optimised by tuning other parameters of the algorithm. As a result, the normalised ultimate load and displacement were predicted successfully.

Experimental and numerical evaluation of the axial capacity of cracked tubular members

This paper presents the experimental and numerical results for the axial capacity of cracked tubular steel members. Experimental tests of 11 columns in compression with simulated cracks of different sizes, defined as the percentage of the circumference (12%, 23.5% and 38.5%). The crack-tips were further treated by drilling a crack arresting hole. These specimens were then modelled by finite element analysis which were verified to match the experimental test. The DNVGL-RP-C208 standard was used as basis for performing the numerical finite element analysis. In addition, the capacity of the columns was calculated according to the 2004 revision of the NORSOK N-004 standard. The experimental tests indicated that the capacity in compression did not change significantly with the presence of cracks and crack arresting holes. The results from the numerical finite element analysis show a good agreement with the experimental work. However, the compressive capacity according to NORSOK N-004 shows a significant deviation to the safe side.

Compressive behavior of light–gauge steel tubes filled with concrete containing recycled aggregates

The axial capacity of light–gauge steel tube columns filled with concrete including recycled asphalt pavement (RAP) aggregates and recycled concrete aggregates (RCA) was investigated. A total of 51 specimens, including 6 bare steel tubes, 30 composite columns and 15 concrete-only columns were tested under uniaxial load. Fifteen concrete mixes were considered by replacing the weight of natural coarse aggregates (NA) with RCA and RAP at replacement levels of 0, 20, 40, 60, 80, and 100%. In addition, RAP and RCA were combined in the same mixes with replacement levels of (1) 20% RAP and 80% RCA; (2) 40% RAP and 60% RCA; (3) 60% RAP and 40% RCA; and (4) 80% RAP and 20% RCA. Experimental results were analyzed by reporting the ultimate capacities and the patterns of failure. Moreover, the predictions of EUROCODE 4 (EC4) and American Institute of Steel Construction (AISC) codes were checked. ABAQUS software was used to perform a finite element analysis (FEA) of the tested composite specimens. The results showed that using recycled aggregates decreased the carrying capacity of columns. Carrying capacity of light–gauge steel tubes filled with concrete including different combinations of RCA, NA and RAP aggregates can be conservatively predicted by the AISC and EC4 recommendations. Results of FEA showed a good agreement with the experimental results.