Search results

This paper aims to clarify the efficient process of the machine learning algorithms implemented in the ready-mix concrete (RMC) onsite. It proposes innovative machine learning algorithms in terms of preciseness and computation time for the RMC strength prediction.

This paper presents an investigation of five different machine learning algorithms, namely, multilinear regression, support vector regression, k-nearest neighbors, extreme gradient boosting (XGBOOST) and deep neural network (DNN), that can be used to predict the 28- and 56-day compressive strengths of nine mix designs and four mixing conditions. Two algorithms were designated for fitting the actual and predicted 28- and 56-day compressive strength data. Moreover, the 28-day compressive strength data were implemented to predict 56-day compressive strength.

The efficacy of the compressive strength data was predicted by DNN and XGBOOST algorithms. The computation time of the XGBOOST algorithm was apparently faster than the DNN, offering it to be the most suitable strength prediction tool for RMC.

Since none has been practically adopted the machine learning for strength prediction for RMC, the scope of this work focuses on the commercially available algorithms. The adoption of the modified methods to fit with the RMC data should be determined thereafter.

The selected algorithms offer efficient prediction for promoting sustainability to the RMC industries. The standard adopting such algorithms can be established, excluding the traditional labor testing. The manufacturers can implement research to introduce machine learning in the quality controcl process of their plants.

Regarding literature review, machine learning has been assessed regarding the laboratory concrete mix design and concrete performance. A study conducted based on the on-site production and prolonged mixing parameters is lacking.

Engineering composite laminates/structures are usually subjected to complex and variable loads, which result in interlayer delamination damage. However, damaged laminate may cause the whole structure to fail before reaching the design level. Therefore, the purpose of this paper is to develop an equivalent model to effectively evaluate compressive residual strength.

In this paper, taking carbon fiber reinforced composite T300/69 specimens as the study object, first, the compressive residual strength under different impact energy is obtained. Then, zero-thickness cohesive elements, Hashin failure criteria and Camanho nonlinear degradation scheme are used to simulate the full-process simulation for compression after edge impact (CAEI). Lastly, based on an improved Whitney–Nuismer criterion, the equation of edge hole stress distribution, characteristic length and compressive residual strength is used to verify the correctness of the equivalent model.

An equivalent relationship between the compressive residual strength of damaged laminates and laminates with edge hole is established. For T300/69 laminates with a thickness of 2.4 mm, the compressive residual strength after damage under an impact energy of 3 J is equivalent to that when the hole aperture R = 2.25 mm and the hole aperture R = 9.18 mm when impact energy is 6 J. Besides, the relationship under the same size and different thickness is obtained.

The value of this study is to provide a reference for the equivalent behavior of damaged laminates. An equivalent model proposed in this paper will contribute to the research of compressive residual strength and provide a theoretical basis for practical engineering application.

Since columns are critical structural elements, they shall withstand hazards without any considerable damage. In the case of a fire, although concrete has low thermal conductivity compared to other construction materials, its properties are changed at elevated temperatures. Most critically, the residual compressive strengths of reinforced concrete columns are significantly reduced after fire exposure. Validation of the worthiness of rehabilitating concrete structures after fire exposure is highly dependent on accurately determining the residual strengths of fire-damaged essential structural elements such as columns.

In this study, eight reinforced-concrete columns (200 × 200 × 1,500 mm) that were experimentally examined in a prior related study have been numerically modelled using ABAQUS software to investigate their residual compressive strengths after exposure to different durations of standard fire (i.e. one and two hours) while subjected to different applied load ratios (i.e. 20 and 40% of the compressive resistance of the column). Outcomes of the numerical simulations were verified against the prior study's experimental results.

In a subsequent phase, the results of a parametric study that has been completed as part of the current study to investigate the effects of the applied load ratios show that the application of axial load up to 80% of the compressive resistance of the column did not considerably influence the residual compressive strength of the shorter columns (i.e. 1,500 and 2,000-mm high). However, increasing the height of the column to 2,500 or 3,000 mm considerably reduced the residual compressive strength when the load ratio applied on the columns exceeded 60 and 40%, respectively. Also, when the different columns were simulated under two-hour standard fire exposure, the dominant failure was buckling rather than concrete crushing which was the typical failure mode in most columns.

The outcomes of the numerical study presented in this paper reflect the residual compressive strength of RC columns subjected to various applied load ratios and standard fire durations. Also, the parametric study conducted as part of this research on the effects of higher load ratios and greater column heights on the residual compressive strength of the fire-damaged columns is practical and efficient. The developed computer models can be beneficial to assist engineers in assessing the validity of rehabilitating concrete structures after being exposed to fire.

The purpose of this paper is to develop new predictive models using gene expression programming in order to estimate the compressive strength of green concrete, as accurate models that can predict the compressive strength of green concrete are still lacking.

To estimate the compressive strength of plain concrete, fly ash concrete, silica fume concrete and concrete with silica fume and fly ash, four predictive GEP models are developed. The GEP models are developed using a large and reliable database that is collected from the literature. The GEP models are validated using the collected experimental database.

The R² is used to statistically evaluate the performance of the GEP models wherein the R² values for the GEP models including all data are 85, 95, 80 and 95.3 percent for the models that predict the compressive strength of plain concrete, fly ash concrete, silica fume concrete and concrete with silica fume and fly ash, respectively.

The GEP models have high R² values and low RMSE and MAE, which indicates that they are capable of predicting the compressive strength of green concrete with a reasonable accuracy.

Utilization of sustainable materials is a global demand in the construction industry. Hence, this study aims to integrate waste management and artificial intelligence by developing an artificial neural network (ANN) model to predict the compressive strength of green concrete. The proposed model allows the use of recycled coarse aggregate (RCA), recycled fine aggregate (RFA) and fly ash (FA) as partial replacements of concrete constituents.

The model is constructed, trained and validated using python through a set of experimental data collected from the literature. The model’s architecture comprises an input layer containing seven neurons representing concrete constituents and two neurons as the output layer to represent the 7- and 28-days compressive strength. The model showed high performance through multiple metrics, including mean squared error (MSE) of 2.41 and 2.00 for training and testing data sets, respectively.

Results showed that cement replacement with 10% FA causes a slight reduction up to 9% in the compressive strength, especially at early ages. Moreover, a decrease of nearly 40% in the 28-days compressive strength was noticed when replacing fine aggregate with 25% RFA.

The research is limited to normal compressive strength of green concrete with a range of 25 to 40 MPa.

The developed model is designed in a flexible and user-friendly manner to be able to contribute to the sustainable development of the construction industry by saving time, effort and cost consumed in the experimental testing of materials.

Green concrete containing wastes can solve several environmental problems, such as waste disposal problems, depletion of natural resources and energy consumption.

This research proposes a machine learning prediction model using the Python programming language to estimate the compressive strength of a green concrete mix that includes construction and demolition waste and FA. The ANN model is used to create three guidance charts through a parametric study to obtain the compressive strength of green concrete using RCA, RFA and FA replacements.

Modern construction methods have been developed with the goal of reducing construction time as much as possible, which results in some situations during construction and within the first few days after it, when concrete is subjected to exceptionally high loads. The precast concrete, which is the concrete in very early ages, may result in severe cracks or damages. In conventional construction projects, sometimes working with concrete, which had not reached its ultimate strength, is an unavoidable matter of fact. This paper aims to discuss these issues.

Researchers in the field of construction materials have done their best to make some changes in the different parts of the concrete in order to bring about reforms, based on the existing needs, and achieve new quality and primacy from concrete. One kind of concrete, the emergence of which dates back to many years ago, is self-compacting concrete. Thanks to its high efficiency for the parts with complex forms of high-density steel, this kind of concrete suggests new prospects.

This study aims at evaluating the effect of early loads on the 28-day compressive strength of concretes with zeolite and limestone powder under different curing conditions (wet or dry). In this regard, two self-compacting concrete mix designs with the same ratio of water to cementations materials and 0.4 percent and 10 percent zeolite have been considered; therefore, concrete cube samples with zeolite and limestone powder in different curing conditions at ages of three, one and seven days under preloading with 80–90 percent of compressive strength are damaged, and after curing in different conditions, their 28-day compressive strength is measured. According to the results, the recovery of the 28-day compressive strength of damaged samples, compared to that of intact samples, is possible in all curing conditions. The experiments that have been performed on concrete samples under dry and wet curing conditions show that the full recovery of compressive strength of damaged samples compared to that of intact ones happened only in preloaded samples at the age of one days, and in other ages (three and seven days) the 28-day strength reduction has occurred in damaged samples compared to the that in intact samples. The results of concrete samples with zeolite and without limestone powder at the age of one day indicate the greatest impact on other samples on the 28-day compressive strength of damaged samples compared to that of intact ones, occurring under dry condition.

This research analyzed and studied the influence under wet and dry curing conditions and the presence of limestone powder and zeolite fillers in recovering of the 28-day compressive strength of preloaded concrete samples at early stages (one, three and seven days) after the construction of the concrete.

Recycled waste glasses have been widely used in Portland cement and concrete as aggregate or supplementary cementitious material. Compressive strength is one of the most important properties of concrete containing waste glasses, providing information about the loading capacity, pozzolanic reaction and porosity of the mixture. This study aims to propose highly nonlinear models to predict the compressive strength of concrete containing finely ground glass particles.

A robust machine leaning method called genetic programming is used the build the compressive strength prediction models. The models are developed using a number of test results on 50-mm mortar cubes containing glass powder according to ASTM C109. Parametric and sensitivity analyses are conducted to evaluate the effect of the predictor variables on the compressive strength. Furthermore, a comparative study is performed to benchmark the proposed models against classical regression models.

The derived design equations accurately characterize the compressive strength of concrete with ground glass fillers and remarkably outperform the regression models. A key feature of the proposed models as compared to the previous studies is that they include the simultaneous effect of various parameters such as glass compositions, size distributions, curing age and isothermal temperatures. Parametric and sensitivity analyses indicate that compressive strength is very sensitive to the curing age, curing temperature and particle surface area.

This study presents accurate machine learning models for the prediction of one of the most important mechanical properties of cementitious mixtures modified by waste glass, i.e. compressive strength. In addition, it provides an insight into the effect of several parameters influencing the compressive strength. From a computing perspective, a robust machine learning technique that overcomes the shortcomings of existing soft computing methods is introduced.

This work aims to investigate the interaction effects of printing process parameters of acrylonitrile butadiene styrene (ABS) parts fabricated by fused deposition modeling (FDM) technology on both the dimensional accuracy and the compressive yield stress. Another purpose is to determine the optimum process parameters to achieve the maximum compressive yield stress and dimensional accuracy at the same time.

The standard cylindrical specimens which produced from ABS by using an FDM 3D printer were measured dimensions and tested compressive yield stresses. The effects of six process parameters on the dimensional accuracy and compressive yield stress were investigated by separating the printing orientations into horizontal and vertical orientations before controlling five factors: nozzle temperature, bed temperature, number of shells, layer height and printing speed. After that, the optimum process parameters were determined to accomplish the maximum compressive yield stress and dimensional accuracy simultaneously.

The maximum compressive properties were achieved when layer height, printing speed and number of shells were maintained at the lowest possible values. The bed temperature should be maintained 109°C and 120°C above the glass transition temperature for horizontal and vertical orientations, respectively.

The optimum process parameters should result in better FDM parts with the higher dimensional accuracy and compressive yield stress, as well as minimal post-processing and finishing techniques.

The important process parameters were prioritized as follows: printing orientation, layer height, printing speed, nozzle temperature and bed temperature. However, the number of shells was insignificant to the compressive property and dimensional accuracy. Nozzle temperature, bed temperature and number of shells were three significant process parameters effects on the dimensional accuracy, while layer height, printing speed and nozzle temperature were three important process parameters influencing compressive yield stress. The specimen fabricated in horizontal orientation supported higher compressive yield stress with wide processing ranges of nozzle and bed temperatures comparing to the vertical orientation with limited ranges.

The purpose of this paper is to provide a method to predict the situation of a loaded element in the compressive stress curve to prevent failure of crucial elements in load-bearing masonry walls and to propose a material model to simulate a compressive element successfully in Abaqus software to study the structural safety by using non-linear finite element analysis.

A Weibull distribution function was rewritten to relate between failure probability function and axial strain during uniaxial compressive loading. Weibull distribution parameters (shape and scale parameters) were defined by detected acoustic emission (AE) events with a linear regression. It was shown that the shape parameter of Weibull distribution was able to illustrate the effects of the added fibers on increasing or decreasing the specimens’ brittleness. Since both Weibull function and compressive stress are functions of compressive strain, a relation between compressive stress and normalized cumulative AE hits was calculated when the compressive strain was available. By suggested procedures, it was possible to monitor pretested plain or random distributed short fibers reinforced adobe elements (with AE sensor and strain detector) in a masonry building under uniaxial compression loading to predict the situation of element in the compressive stress‒strain curve, hence predicting the time to element collapse by an AE sensor and a strain detector. In the predicted compressive stress‒strain curve, the peak stress and its corresponding strain, the stress and strain point with maximum elastic modulus and the maximum elastic modulus were predicted successfully. With a proposed material model, it was illustrated that the needed parameters for simulating a specimen in Abaqus software with concrete damage plasticity were peak stress and its corresponding strain, the stress and strain point with maximum elastic modulus and the maximum elastic modulus.

The AE cumulative hits versus strain plots corresponding to the stress‒strain curves can be divided into four stages: inactivity period, discontinuous growth period, continuous growth period and constant period, which can predict the densifying, linear, non-linear and residual stress part of the stress‒strain relationship. By supposing that the relation between cumulative AE hits and compressive strain complies with a Weibull distribution function, a linear analysis was conducted to calibrate the parameters of Weibull distribution by AE cumulative hits for predicting the failure probability as a function of compressive strain. Parameters of m and θ were able to predict the brittleness of the plain and tire fibers reinforced adobe elements successfully. The calibrated failure probability function showed sufficient representation of the cumulative AE hit curve. A mathematical model for the stress–strain relationship prediction of the specimens after detecting the first AE hit was developed by the relationship between compressive stress versus the Weibull failure probability function, which was validated against the experimental data and gave good predictions for both plain and short fibers reinforced adobe specimens. Then, the authors were able to monitor and predict the situation of an element in the compressive stress‒strain curve, hence predicting the time to its collapse for pretested plain or random distributed short fibers reinforced adobe (with AE sensor and strain detector) in a masonry building under uniaxial compression loading by an AE sensor and a strain detector. The proposed model was successfully able to predict the main mechanical properties of different adobe specimens which are necessary for material modeling with concrete damage plasticity in Abaqus. These properties include peak compressive strength and its corresponding axial strain, the compressive strength and its corresponding axial strain at the point with maximum compressive Young’s modulus and the maximum compressive Young’s modulus.

The authors were not able to decide about the effects of the specimens’ shape, as only cubic specimens were chosen; by testing different shape and different size specimens, the authors would be able to generalize the results.

The paper includes implications for monitoring techniques and predicting the time to the collapse of pretested elements (with AE sensor and strain detector) in a masonry structure.

This paper proposes a new method to monitor and predict the situation of a loaded element in the compressive stress‒strain curve, hence predicting the time to its collapse for pretested plain or random distributed short fibers reinforced adobe (with AE sensor and strain detector) in a masonry building under uniaxial compression load by an AE sensor and a strain detector.

In order to reduce the impact of bridge construction on traffic under the bridge, the construction of bridges for some important traffic nodes usually adopts the swivel construction method. The spherical hinge is a rotating mechanism located between the bottom of the pier and the bridge cap, and is subjected to tremendous vertical pressure. According to the mechanical characteristics of the spherical hinges, this paper applies the ultra-high performance concrete (UHPC) material to the spherical hinge. The spherical hinge is subjected to a compression test to test its mechanical behavior. This paper aims to discuss this issue.

In order to test the mechanical behavior of the UHPC spherical hinge, multiple sets of 100 mm UHPC spherical hinge specimens were prefabricated. Through the universal testing machine to measure the compressive strength of specimens, draw the force-displacement curve to analyze the failure mechanism and establish the stress calculation formula of the spherical hinge at each point along the radial direction.

Through the test, the compressive strength of UHPC spherical hinge is obtained, and the influencing factors of UHPC spherical hinge strength are found: reducing water–cement ratio, increasing steel fiber content and length and changing steel fiber arrangement direction can effectively improve the compression strength of UHPC spherical hinge.

For the first time, UHPC materials were applied to the spherical hinge structure, the UHPC spherical hinge diameter is 1/3 of the diameter of the reinforced concrete spherical hinge, which is equivalent to the diameter of the steel spherical hinge. By applying the UHPC spherical hinge, the manufacturing cost is reduced, the process is simple, and the construction difficulty is reduced.