Predicting the Load-Bearing Capacity of Square-Section Pipe-Concrete Columns Using Machine Learning Methods

Elliptical concrete-filled steel tubes (CFST) are structural elements where concrete is embedded in an elliptical steel tube, offering significant advantages such as effective axial compression resistance. These structures are widely applied in civil engineering and critical infrastructure like airport terminals and bridges. While most CFST research focuses on circular and rectangular cross-sections, there is limited study on elliptical CFST. The emergence of neural networks offers a novel approach to calculate the compressive capacity of elliptical CFST. Neural networks can learn from sample data without predefined assumptions, uncovering nonlinear relationships between the data and results. Furthermore, they can predict new variables, overcoming the constraints of traditional experimental and finite element methods. This paper proposes an advanced calculation method to quickly and accurately assess the axial compressive bearing capacity of elliptical CFST short columns. The model integrates neural network capabilities with unified strength theory, simulating the bearing capacity of elliptical CFST stub columns. Through simulation training, the method is validated for calculating the compressive performance of elliptical CFST. The findings demonstrate that this approach not only enhances computational efficiency but also provides a reliable and optimized tool for structural evaluation. The calculation efficiency of the compressive capacity of elliptical CFST based on a neural network is increased by about 23.7%.

Seismic response and failure mechanism of ordinary concrete and UHTCC short columns reinforced with negative Poisson's ratio steel bars

Oil and gas pipeline failure and leakage can seriously damage people's lives and the ecosystem. The prediction of failure pressure for pipelines with damage is one of the most important and challenging tasks faced by industry, which affects the assessment of pipeline safety. Previous studies widely used industrial models or the finite element (FE) method to predict the failure pressure. However, the industrial models may give limited information, and the FE method has much heavy computation burden. In this work, three machine learning models - artificial neural network (ANN), XGBoost (XGB) and CatBoost (CAT) are developed for forecasting the failure pressure of pipelines with defects. Firstly, the simulation results of the FE method are validated by real failure pressure and compared with the calculation results of industrial models (ASME-B31G and DNV). Then 180 pipeline samples including pipeline attributes and defect sizes collected from real in-line inspection data in a pipeline company and the corresponding FE simulation results of failure pressure of these 180 defective pipelines are used for the training and testing of the machine learning models. The results show that the simulation accuracy of the FE method is higher than the calculation accuracy of the industrial models, and the FE simulation results are suitable to be the outputs of machine learning models. The three machine learning methods all provide satisfactory prediction accuracy in failure pressure. Specifically, CAT is the best machine learning method in this study for its lowest relative error (3.11% on average), mean absolute error (0.53), root mean square error (0.78) and highest coefficient of determination (R2) up to 98% in testing. Moreover, the machine learning models present better performance on average relative errors compared to the industrial models. CAT shows higher accuracy than the industrial models and FE simulation on minimum and average relative errors. Finally, the prediction result of CAT is used to discuss the effect of input features on failure pressure of pipelines, which demonstrates that the importance of features follows the order of pipeline thickness > pipeline outside diameter > defect depth > defect length > defect width. Once the above machine learning methods are used in industry, more and more real data will be collected to train a model and make it more accurate. In this way, these methods will provide an efficient way to evaluate the safety of defective pipelines. In addition, the failure pressure of pipeline could be estimated to help operators figure out a pipeline condition and further prioritize the pipelines for maintenance.

To explore new avenues for solid waste utilization and energy conservation and emission reduction, waste glass was crushed, ground, and sieved to obtain waste glass sand, which was then used to replace fine aggregate and cement in concrete, respectively. Steel tube glass sand concrete short columns were fabricated, and subjected to axial compression tests, finite element simulation analysis, and theoretical calculations of bearing capacity. The study investigated the effects of waste glass sand replacement rates of 0%, 5%, 15%, 30%, and 60% on the mechanical performance of these axially loaded steel tube glass sand concrete short columns. The results show that: the failure mode of all fabricated steel tube glass sand concrete short columns was a bulging shape, and their ductility was higher than that of concrete-filled steel tube short columns without waste glass sand. When the waste glass sand replacement rate did not exceed 30%, the energy dissipation capacity of the steel tube glass sand concrete short columns was higher than that of those without waste glass sand. The axial bearing capacity calculated using the CECS28-2012 formula for steel tube glass sand concrete short columns had an error within 4%, while calculations using the Zhong Shantong formula provided higher accuracy and conservative prediction results for the axial bearing capacity of these columns.

Coupled bending-shear-torsion bearing capacity of concrete filled steel tube short columns

Predicting students’ academic performance is a crucial initiative in the field of education, as it allows educators and administrators to spot students who may require extra assistance, customize educational resources to meet individual requirements, and improve overall educational results. Conventional approaches to forecasting academic achievement, such as statistical analysis and expert evaluation, have certain drawbacks in terms of precision and scalability. The emergence of machine learning (ML) methods provides a possible alternative by utilizing extensive datasets and advanced algorithms to reveal patterns and generate more precise predictions. This investigation’s primary goal is to explore the predictive modelling of student academic performance by improving the accuracy of predictions through the utilization of machine learning techniques. The study was conducted utilizing the Python programming environment. The prediction of student academic performance was carried out utilising the Bidirectional long short-term memory (Bi-LSTM) based Weighted Cost Effective Random Forest algorithm. The study utilized the Deep Encoder CNN-Bi-LSTM for optimal feature extraction to foresee student academic performance. The extracted features were then classified using the Weighted Cost Effective Random Forest (WECRF) classifier, and the classification was evaluated in terms of accuracy, precision, specificity, sensitivity, and recall. The issues addressed include the class imbalance, computational complexity, cost, and huge dimensional issue, among others. The random forest method achieved Precision Score - 0.72, Recall Score - 0.68, F1 Score - 0.69, and Accuracy - 0.77 in this study. Moreover, the suggested technique facilitates the automated forecasting and enhancement of students' future academic performance. Keywords: Predictive Modelling; Students; Academic Performance; Machine Learning; Bi-LSTM; CNN-Bi-LSTM; Deep Learning.

This paper presents the results of cyclic loading tests on new high-strength concrete (HC) short columns. The seismic performance and deformation capacity of three reinforced high-strength concrete filled Polyvinyl Chloride tube (RHCPVCT) short columns and one reinforced high-strength concrete (RHC), under pseudo-static tests (PSTs) with vertical axial force was evaluated. The main design parameters of the columns in the tests were the axial compression ratio, confinement type, concrete strength, height-diameter ratio of PVCT. The failure modes, hysteretic curves, skeleton curves of short columns were presented and analyzed. Placing PVCT in the RHC column could be remarkably improved the ultimate strength and energy dissipation of columns. However, no fiber element models have been formulated for computing the seismic responses of RHCPVCT columns with PVT tubes filled with high-strength concrete. Nonlinear finite element method (FEM) was conducted to predict seismic behaviors. Finite element models were verified through a comparison of FEM results with experimental results. A parametric study was then performed using validated FEM models to investigate the effect of several parameters on the mechanical properties of RHC-PVCT short columns. The parameters study indicated that the concrete strength and the ratio of diameter to height affected the seismic performance of RHC-PVCT short column significantly.

The study aimed to simulate the behavior of the concrete-filled double skin steel tubular (CFDST) composite columns having a circular hollow section using the finite element method (FEM). To indicate the accuracy and the reliability of the model, the proposed FEM model was verified by the experimental test results available in the literature. Moreover, the code-based formulas (ACI, AISC, and Eurocode 4) and some empirical models suggested by the previous researchers for predicting the axial capacity of CFDST columns were used in this study to compare their results with the proposed FEM model. Furthermore, to visualize the effectiveness of sectional properties and infilled concrete compressive strength on the ultimate axial strength of double skin composite columns, a parametric study was conducted. For this, 72 test specimens were modeled considering two outer and inner steel tube diameters, three outer and inner steel tube thicknesses, and two different concrete cylinder strengths. All results were statistically evaluated. It was observed that the proposed FEM model had a good prediction performance. As well, the FEM model results indicated that the sectional properties, in particular, the diameter of the outer steel tube and concrete compressive strength, had remarkable effects on the load-carrying capacity of CFDST columns.

This paper investigates the damage and residual bearing capacity of corroded reinforced concrete (RC) short columns after impact and presents a method for evaluating the residual bearing capacity of RC short columns by nondestructive testing. Firstly, accelerated corrosion test and drop hammer impact test were carried out to obtain specimens under different impact loads and corrosion rates. Then, the damage caused by corrosion and impact loads was evaluated by supersonic wave aided nondestructive test. Through the damage factor, the influence of corrosion rate and impact loads on the specimen was revealed, and the calculation method of corrosion rate and impact velocity was proposed. Finally, according to the bearing capacity test results, the influence factors of reinforcement, concrete, and impact were introduced into the bearing capacity calculation equation. Considering the relationship between the residual bearing capacity of RC short columns and the damage factor, an improved formula for calculating the residual bearing capacity of corroded RC short columns under impact loads was proposed. This work lays the foundation for further research on mechanical properties of corroded RC structures under impact loads.

Based on the unified strength theory, according to the characteristics of axial bearing capacity of round-ended concrete-filled steel tubular stub short columns with binding bars, the cross shaped section was divided into a rectangular section which has bars and two round-ended sections which have no bars. Considering intermediate principal stress, the ration of width to thickness of pipe to the bearing capacity of steel tube was in consideration too, the paper analyzed force mechanism. In the end, the mathematical formulation of bearing capacity for the round-ended concrete filled steel tube stub column with binding bars was obtained. The formula calculation values were in good agreement with the value of the relevant literature. Theoretical formulas are expected to be helpful for engineering applications.

Temperatures in unprotected joints between steel beams and concrete-filled tubular columns in fire

Curing residual stress (CRS) is common in polymer‐matrix composites due to the anisotropic properties of materials. Finite element method (FEM), the most extensively used approach for curing behavior prediction, is usually complicated and time‐consuming. To achieve a fast prediction of process‐induced stresses, a convolutional neural network (CNN) is established based on the FEM. Firstly, a fully coupled methodology is built and validated through distortions of experimentally manufactured laminates. Then, it is applied to generate models with different stacking layers, and the residual stress is computed and serves as the dataset of the deep learning model. Finally, the construction and hyperparameters are determined, and the good generalization performance proves the high accuracy of the current model. Besides, the CNN method (<1 s) greatly reduces the computational time compared with the FEM (>14 min). The supervised machine learning method shows great potential in promoting efficiency in stacking sequence designing and optimization of composites.Highlights A fully coupled model was built to predict the curing behavior of composites. The numerical model was validated by the deformation of unsymmetrical composites. A FEM‐CNN method was proposed for the fast prediction of curing residual stress. Compared with FEM, this machine learning method is accurate and efficient.

The focus of this study is to apply finite element method (FEM) and machine learning methods to investigate the interfacial bonding strength of continuous fiber reinforced thermoset composite (TSC)‐thermoplastic structures manufactured through co‐curing and overmolding processes, with polyamide 6 (PA 6) as the thermoplastic material. A model for interfacial healing degree in TSC‐PA 6 structures was developed. Then, FEM was employed to study the influence of various injection overmolding process parameters on the interfacial bonding strength of TSC‐PA 6 structures. The results show that there is a strong correlation between the degree of interface healing and the bonding strength. Subsequently, six machine learning methods were employed to correlate interfacial healing degree with diverse injection molding process parameters. Simulation data were utilized for training, calibration, and validation of the six machine learning models. Based on the results of simulation and machine learning predictions, a quantitative analysis of the significance of injection molding process parameters on healing degree was conducted. These parameters are ranked in descending order of importance as follows: insert temperature, melt temperature, and injection rate.Highlights The interfacial healing degree model of PA 6 was established and validated through the integration FEM and experiment. Six machine learning models were built to predict the interfacial healing degree. Grad boosting performed best in predicting the interfacial healing degree. Insert temperature had the greatest impact on the interface healing degree.

Research on the Concrete-Filled Double Skin steel Tubular (CFDST) columns subjected to axial force after fire

A reliability analysis of the axial compressive load bearing capacity of postfire reinforced concrete (RC) columns strengthened with carbon fiber reinforced polymer (CFRP) sheets was presented. A 3D finite element (FE) model was built for heat transfer analysis using software ABAQUS. Based on the temperature distribution obtained from the FE analysis, the residual axial compressive load bearing capacity of RC columns was worked out using the section method. Formulas for calculating the residual axial compressive load bearing capacity of the columns after fire exposure and the axial compressive load bearing capacity of postfire columns retrofitted with CFRP sheets were developed. Then the Monte Carlo method was used to analyze the reliability of the axial compressive load bearing capacity of the RC columns retrofitted with CFRP sheets using a code developed in MATLAB. The effects of fire exposure time, load ratio, number of CFRP layers, concrete cover thickness, and longitudinal reinforcement ratio on the reliability of the axial compressive load bearing capacity of the columns after fire were investigated. The results show that within 60 minutes of fire exposure time, the reliability index of the RC columns after retrofitting with two layers of CFRPs can meet the requirements of Chinese code GB 50068 (GB 2001) for safety level II. This method is effective and accurate for the reliability analysis of the axial load bearing capacity of postfire reinforced concrete columns retrofitted with CFRP.