Early-age Concrete Strength Research Articles

Comparing Machine Learning Regression Models for Early-Age Compressive Strength Prediction of Recycled Aggregate Concrete

A branch of artificial intelligence called machine learning is well-positioned as a prediction method that can take into consideration several influencing factors and complex inter-factor connections. Without being specifically trained to do so, these machine learning models have the ability to generalize, predict, and learn from data. Regression theory is a key topic in statistical modelling and machine learning. The main goal of this study is to compare the performance of several popular machine learning regression models for predicting the early-age compressive strength of concretes made from recycled concrete aggregates from a structure that demolished following the Sivrice-Elazig earthquake on January 24, 2020. Early-age concrete compressive strength is even more crucial due to factors like the fact that there are thousands of newly built structures in the aftermath of the earthquake, the quick manufacturing of these structures, and the completion of the project in the lowest amount of time. Determining the early-age concrete strength with high accuracy and in a useful manner is crucial for this reason. Seven different classical machine learning algorithms were employed in this study to achieve all of these goals. Early-age concrete compressive strength values were considered for 1 and 3 days. The relationship between the experimental results and the predicted outcomes of the employed algorithms was investigated, and a thorough comparison of these intelligent regression algorithms was conducted. Within the scope of sustainable development and circular economy goals, it is thought that this article will make significant contributions to the literature in terms of utilizing these waste materials and determining the early-age compressive strengths of the concretes produced with high accuracy.

Deep learning neural networks for monitoring early-age concrete strength through a surface-bonded PZT sensor configuration

Monitoring the immediate evolution of concrete’s strength is essential to ensure structural integrity and construction efficiency, requiring Forecasting to avoid unforeseen and severe failures during construction. The present investigation introduces an Equivalent structural parametric (ESP) study using a surface-bonded piezo sensor and electromechanical impedance (EMI) methodology to monitor and forecast the strength of concrete by implementing machine learning and deep learning methods. The concrete hydration processes are simulated using COMSOL™ 5.5. The concrete cube’s hydration is represented by altering Young’s modulus and damping ratio to show the rate of curing. Concrete strength development is examined in terms of conductance resonant frequency (CRF) and Conductance resonant peak (CRP). Continuous conductance signature monitoring and data analysis show that CRF and CRP increase with compressive strength. The system’s mechanical impedance is measured, and EMI signatures vs. frequency plots within a specific frequency range are compared to healthy impedance graphs. A mass-spring-damper system with identical properties is identified, and relevant structural parameters are computed. Modern ML algorithms include linear regression (LR), interaction LR, fine, medium, and coarse Gaussian SVM, etc. reliably predict strength with an error rate of less than 2%. Convolutional neural networks (CNN) have advanced image-based recognition, but their usage in EMI-based structural strength assessment is still being studied. A unique strategy using 2D CNN, 2D CNN– Long short-term memory (LSTM), and 2D CNN Bidirectional-LSTM to forecast concrete structure compressive strength shows the potential of deep learning. The proposed 2D CNN-Bi-LSTM model excels in compressive strength prediction, obtaining an R2 value of 0.99 and stabilizing loss error over a few epochs.

Performance of self-compacting concrete with treated rice husk ash at different curing temperatures

Self-compacting concrete (SCC) is currently gaining traction as a replacement to conventional vibrated concrete. Its distinct microstructure leads to varied mechanical behaviour under different curing temperatures. In the past various supplementary cementitious materials (SCMs) were used in SCC to investigate their respective effects on the performance. However, there has been no systematic studies conducted to determine the effect of different curing temperature on the sensitivity reaction of rice husk ash (RHA) in SCC. This research focuses on high-strength SCC with SCMs such as RHA, silica fume (SF), fly ash (FA), and ground granulated blast-furnace slag (GGBS), exploring their applicability for concrete structures under varying curing temperatures. Heat of hydration, compressive strength and open porosity of SCC specimens were assessed at various temperature. Results indicate high curing temperatures expedite the hydration and pozzolanic reaction, refining the microstructure and increasing the early-age concrete strength, but compromising the long-term performance, potentially mitigated by the use of SCMs. Conversely, lower curing temperature, impedes hydration leading to gradual strength gain, particularly with SCMs, yet yielding significant strength increases at later concrete age. SCMs presence and curing temperature significantly influence maturity function-based strength predictions, impacting strength trends in the samples studied.

Predicting concrete strength early age using a combination of machine learning and electromechanical impedance with nano-enhanced sensors

To ensure the structural integrity of concrete and prevent unanticipated fracturing, real-time monitoring of early-age concrete's strength development is essential, mainly through advanced techniques such as nano-enhanced sensors. The piezoelectric-based electro-mechanical impedance (EMI) method with nano-enhanced sensors is emerging as a practical solution for such monitoring requirements. This study presents a strength estimation method based on Non-Destructive Testing (NDT) Techniques and Long Short-Term Memory (LSTM) and artificial neural networks (ANNs) as hybrid (NDT-LSTMs-ANN), including several types of concrete strength-related agents. Input data includes water-to-cement rate, temperature, curing time, and maturity based on interior temperature, allowing experimentally monitoring the development of concrete strength from the early steps of hydration and casting to the last stages of hardening 28 days after the casting. The study investigated the impact of various factors on concrete strength development, utilizing a cutting-edge approach that combines traditional models with nano-enhanced piezoelectric sensors and NDT—LSTMs-ANN enhanced with nanotechnology. The results demonstrate that the hybrid provides highly accurate concrete strength estimation for construction safety and efficiency. Adopting the piezoelectric-based EMI technique with these advanced sensors offers a viable and effective monitoring solution, presenting a significant leap forward for the construction industry's structural health monitoring practices.

Prediction of concrete strength considering thermal damage using a modified strength-maturity model

The maturity method is widely used to estimate early-age concrete strength. However, the traditional maturity models exhibit limited predictive capability for late concrete strength under thermal curing conditions due to the influence of the “crossover effect”. This study developed a curing scheme for Standard Portland cement concrete in the absence of supplementary cementitious materials at temperatures ranging from 5 °C to 50 °C and analyzed the temperature variations inside thermally cured concrete specimens. The findings reveal that an increase in curing temperature and time between 30 °C and 50 °C and 8 and 72 h respectively led to an increase in the early strength and a decrease in the late strength of concrete, due to the “crossover effect”. Additionally, a linear relationship was found between curing temperature and the late strength reduction coefficient. Utilizing this relationship, a modified maturity model that considers the “crossover effect” was proposed, improving the accuracy of predicting concrete strength under thermal curing conditions (with a prediction error of less than 10%). The research outcomes are of significant guiding significance for winter construction by ensuring the quality of concrete, reducing construction accidents, and improving construction efficiency.

Challenges for structural health monitoring of concrete curing using piezoelectric sensor and electromechanical impedance (EMI) technique: A critical review

Monitoring the strength of early-age concrete is crucial by assessing an accurate time of removing construction formwork and loads on the structural elements, as well as the high technology strength identifications. This high technology is based on electromechanical impedance (EMI). EMI technique might also be monitored for efficient and verifiable effects, such as the curing phenomenon in situ investigation level. The curing effect on concrete strength elements has been significantly detected using piezoelectric patches (PZT) as smart material devices in electromechanical impedance investigation. This EMI approach is also becoming a sustainable solution for diagnostic demands in order to determine the signature characteristics at earlier phases of the concrete strength growth. In 2005, the first investigation on the curing problem was published, then became increasingly well-known in many relevant studies. Consequently, this paper presents the most recent state-of the- art curing studies by EMI technology. The literature reviews categorized relevant information into vital concrete curing challenges to be highlighted in future research. State-of-art listed the critical outputs and findings as installation techniques, computing technology integration, modelling, analysis techniques, signal processing, and environmental factors. In conclusion, EMI technology might potentially be transformed into a self-contained monitoring device to detect early damage in concrete. Similarly, the appropriate research gaps might examine more experiments and simultaneously provides an explanation for more research problems in the field of structural health monitoring.

Integrating PZT-enabled active sensing with deep learning techniques for automatic monitoring and assessment of early-age concrete strength

Compressive strength of concrete is one of the key indicators to evaluate the quality of concrete materials. Real-time monitoring of the compressive strength development during the concrete curing process can effectively guide the staged construction and ensure the safety and stability of engineering structures. In this paper, a novel method is proposed to monitor and evaluate the early-age concrete strength development by integrating PZT-enabled active sensing and deep learning (DL) techniques. First of all, the stress wave signals were continuously captured during the concrete curing process using PZT-enabled active sensing, and then the time-frequency diagrams were generated from the collected signals through the continuous wavelet transform (CWT). After that, an innovative DL-based framework named concrete early-age strength monitoring network (CESMonitorNet) was developed to automatically learn optimal features from the CWT spectrum and ultimately quantify the early-age concrete strength. Finally, experiments on laboratory-cast concrete specimens were conducted to verify the effectiveness of the proposed method. A comprehensive comparison analysis with the widely used machine learning-based methods and convolutional neural network (CNN) was also performed. The results show that the proposed method can accurately predict the concrete strength development and has superior performances over other methods, indicating its great potential for real-time monitoring and rapid evaluation of the strength development of early-age concrete.

Real-time monitoring of early-age compressive strength of concrete using an IoT-enabled monitoring system: an investigative study

Determination of the early-age compressive strength of concrete is essential for quality assurance, safety, and economy of construction projects. Due to manual operation on construction site, conventional maturity meters are not efficient for live monitoring of the early-age concrete strength. Higher levels of automated and computerised improvements have been made possible by recent developments in wireless communications, sensor technologies, and data processing methods across the construction industry. For real-time monitoring of the early-stage concrete strength, the current study presents an innovative Internet of Things (IoT)-enabled system developed by concrete data sensors (CDS), an Australian-owned private business. The CDS sensor system (the system) communicates with temperature sensors via long-range wide-area network and is linked to a cloud-based platform for data storage. The suggested system’s effectiveness was assessed using three concrete mixtures and developed maturity relationships. It was observed that the predicted early-age compressive strength of the mixes matches well with the actual compressive strength and that the system can effectively automate the characterisation of maturity.

Early-age concrete strength monitoring using smart aggregate based on electromechanical impedance and machine learning

It is crucial to monitor the real-time strength development of early-age concrete, which is related to the structure safety and construction efficiency of concrete. This paper proposed a new method to predict and monitor concrete strength development. The basic idea is using embedded smart aggregates (SAs), combining the electromechanical impedance (EMI) technology and machine learning to monitor the strength development of early-age concrete. An EMI model of the embedded SA was firstly established and the relationship between the conductance resonant frequency (CRF) and conductance resonant peak (CRP) of the SA and the development of concrete strength was investigated. The conductance signatures were continuously monitored and the compressive strength of the specimens at different ages was tested. Hence, the EMI model results that the CRF decreases but CRP increases as the compressive strength of concrete increases were verified by analyzing the collected data. The four different models of a linear regression model (LR), a convolutional neural network (CNN), a hybrid (LR-CNN) model, and an empirical equation were established. The conductance of SAs as the developed models inputs, the compressive strength of specimens as outputs. Finally, these four models were compared with each other. Meanwhile, the performance indicators of the LR-CNN model and other hybrid models were compared. The results show that the LR-CNN model has excellent performance and successfully achieves quantitative prediction of concrete strength development. The proposed method for evaluating and predicting the compressive strength of concrete is simple, accurate, quantitative and reliable, and has promising application.

Deconvolution of main hydration kinetic peaks in properly sulfated Portland cements with boundary nucleation and growth models and relation to early-age concrete strength development

When the hydration kinetics of properly sulfated Portland cements is monitored by heat flow calorimetry, the initial dissolution peak and the dormant period is followed by the main hydration peak – formation of calcium-silicate-hydrates and portlandite, the so-called silicate peak. This main peak is superimposed by a peak associated to further tricalcium aluminate dissolution and a surge in precipitation of sulfoaluminates (the so-called sulfate depletion peak) right after sulfate added for setting control is depleted in the material system. In this paper strategies for the deconvolution of silicate peak and sulfate depletion peak are presented. Hereby, the boundary nucleation and growth model and the classical bulk nucleation and growth model serve as tools for deconvolution of calorimetric data. We discuss obtained kinetic parameters and their temperature dependency. The boundary nucleation and growth model for constant nucleation rate emerged as the most suitable model for the silicate reaction, the bulk nucleation and growth model with an order of three, indicating site saturation, as adequate for the sulfate depletion peak. The reaction enthalpy for tricalcium silicate hydration was obtained as 503 J/g, remarkably close to literature values. Calorimetric data related to the sulfate depletion peak is corroborated by X-ray diffraction analysis of formation history of crystalline hydration products. Furthermore, the history of the (silicate) degree of reaction as predicted by the boundary nucleation and growth model for different temperature histories is related to experimentally obtained early-age strength histories. • Investigation of hydration kinetics of commercial, well-sulfated Portland cement. • Main peak (C-S-H and portlandite formation) superimposed by sulfate depletion peak. • Strategies for deconvolution of peaks with Avrami–Cahn models as tools for analysis. • Degree of silicate reaction history is linked to early-age strength gain.

Maturity method to estimate early age concrete strength in cold weather: alternative activation energy calibration

ABSTRACT Many critical concreting activities require the determination of the in-place concrete strength. It can be costly to wait too long to execute these activities, but acting too early can have a negative impact on structural performance. Conventional moulded concrete cylinders and alternative strength assessment methods such as the maturity method are commonly used to assess concrete’s in-place strength. This study is focused on a special case when the maturity method is applied for evaluating concrete strength in cold weather at an early age. Specifically, the study proposes an alternative method for calibrating the activation energy, an input for the maturity method. Concretes cured at two different temperatures are used to calibrate the activation energy. The maturity method based on this activation energy predicted the cold weather concrete’s compressive strength satisfactorily. It was also found that for a successful application of the proposed activation energy calibration, the two temperatures should represent the expected minimum and maximum temperature at the site. Furthermore, the results showed that the maturity method based on the proposed activation energy calibration method performed better than the conventional cylinder method.

Early-age concrete strength development monitoring using piezoelectric self-emission and detection (SED) and coda wave energy (CWE)

The property of concrete is very significant to structural safety, and the early hydration process plays a critical role in the final concrete property. This paper develops a self-emission and detection (SED) principle with a single piezoelectric smart aggregate (SA) transducer, which is used as both an actuator and a sensor, to monitor the concrete early age strength development. The signal analysis is carried out by the coda wave energy (CWE). Experiments of concrete specimens with and without the SAs were conducted. Experimental results show a high correlation between the strength of early-age concrete and the CWE and non-linear fitting is used to establish the relationship between them. The proposed CWE features a simple analysis method, and the SED principle does not require consideration of the matching between the transmitting transducer and the receiving sensor, such as frequency range, sensitivity. Furthermore, the proposed method can be used as a reference for health monitoring of other structures and has good application prospects.

Effect of the Thermal Insulation Cover Curing on Temperature Rise and Early-Age Strength of Concrete.

In the present paper, the effects of thermal insulation cover curing on the rise in temperature of concrete, and further on the mechanical properties of the concrete are measured experimentally. In the experiments, polyurethane foam boards of 100 mm thickness were used for thermal insulation, and three concrete strength grades of C30, C50 and C80, were used as concrete samples. Conventional standard curing, and two heat curing methods with a constant temperature of 40 °C and 60 °C were used for comparison. The pore structure of the cement paste subject to the different curing procedures, including insulation cover curing, heat curing and standard curing, was experimentally measured using mercury intrusion porosimetry. The test results show that rate of increase in compressive strength compared with standard curing is 22–34%, 16–26%, and 23–67%, respectively, for C30, C50, C80 concrete after being subject to 1 to 3 days thermal insulation cover curing in the initial period after concrete casting. As expected, initial heat curing of concrete will result in a reduction in the long-term strength of the concrete. At 28 days, the strength reduction rate compared with standard curing due to the insulation cover curing is 3.1–5.9%, 0.6–3.0%, 0–3.2%, respectively, for C30, C50, C80 concrete. By contrast, the compressive strength reduction compared with standard curing at 28 days is 8.6–10.5%, 8.6–9.1%, 4.7–5.6%, respectively, for C30, C50, C80 concrete after being subject to a constant heat curing of 40 °C and 60 °C in the initial period after concrete casting. Measurement of the pore structure of the paste subject to different curing procedures initially after casting shows that rising curing temperature leads to coarser pores, especially an increase in capillary pore fraction. Among the four curing methods used in the present study, the effect of insulation cover curing and low temperature (40 °C) heat curing on the capillary pore content is small, while the effect of high temperature (60 °C) heat curing is significant.

Study on the Influence of Train Dynamic Load on underneath Tunnel Cast-in-Situ Concrete in Early Age

The cast-in-situ concrete lining is prone to structural damage, cracks, and other defects, due to the influence of dynamic load at an early age, which is necessary to study the dynamic response. In this study, the finite difference software FLAC3D is used to carry out the dynamic analysis. Firstly, the reliability of the numerical model is verified by the train vibration test on-site. On this basis, the control variable method is used to analyze the dynamic response of the dynamic train load in early-age concrete structures under the factors of tunnel buried depth, train speed, cross angle, and surrounding rock grade. Then, the safety of the structure is evaluated. The numerical simulation results show that the influence of buried depth and surrounding rock on the early age structure is more obvious. Peak acceleration decreases with the increase in tunnel buried depth and increases with the increase in surrounding rock grade and train speed. Peak acceleration changes a little in the range of 0°–67.5°, but when the cross angle is 90°, the dynamic response reaches the minimum value. Multiple factors fitted the dynamic tensile stress, and the dynamic tensile stress under adverse conditions was calculated, compared with the splitting tensile strength of early-age concrete. The results show that the splitting tensile failure does not occur when the concrete age is more than 0.5 days.

Deconvolution of Main Hydration Kinetic Peaks in Properly Sulfated Portland Cements with Boundary Nucleation and Growth Models and Relation to Early-Age Concrete Strength Development

Deconvolution of Main Hydration Kinetic Peaks in Properly Sulfated Portland Cements with Boundary Nucleation and Growth Models and Relation to Early-Age Concrete Strength Development

Integrating Pzt-Enabled Active Sensing with Deep Learning Techniques for Automatic Monitoring and Assessment of Early-Age Concrete Strength

Integrating Pzt-Enabled Active Sensing with Deep Learning Techniques for Automatic Monitoring and Assessment of Early-Age Concrete Strength

Effects of the sole or combined use of chemical admixtures on properties of self-compacting concrete

Chemical additives are very important in determining the behavioral characteristics of self-compacting concrete. For this reason, determining the building materials that make up the chemical structure of self-compacting concrete and the interactions of these materials is of great importance. The present study pertains to the effects of the use of different chemical admixtures (high-range water-reducing, i.e., superplasticizer, hydration accelerating, air-entraining, shrinkage reducing, and hydration heat reducing admixtures) on the fresh and hardened properties of self-compacting concrete. The influence of using a single one or a hybrid combination of the air-entraining, hydration-accelerating, heat-reducing, and shrinkage-reducing admixtures on the mechanical properties of fresh and hardened SCC was investigated through a set of tests. For this purpose, sixteen different SCC mixtures with different combinations of chemical additives were prepared and tested. The properties of fresh concrete were examined as well as the compressive and tensile strengths of the mixtures. SCC mixtures with shrinkage-reducing admixtures were evaluated in terms of shrinkage development. The effect of the use of admixtures was found to be more pronounced on the early-age concrete strength. The use of any type of additive in addition to the shrinkage-reducing admixture increased the speed of flow of fresh concrete.

Concrete mix design modelling based on variation of hidden layer and neuron of ANN for virtual learning development

Artificial Neural Network (ANN) is a Machine Learning (ML) algorithm which learn by itself and organize its thinking to solve problems. Although the learning process involves many hidden layers (Deep Learning) this algorithm still has weaknesses when faced with a high noise data. Concrete mixture design data has a high enough noise caused by many unidentified / unmeasurable aspects. Information needs about the compressive strength of early age concrete (under 28 days) are often needed while the construction process is still ongoing. H2O’s Deep Learning type of ANN has been tried to predict the compressive strength of early age concrete, but the results are less than optimal. This study aims to improve the H2O’s-ANN prediction model using Bagging to reduce the influence of noise and overfitting. The lowest RMSE that are able to be achieved in this research with Bagging is 6.385 while it is 6,674 without Bagging. This result proves that Bagging is significant to reduce the Deep Learning error rate for predicting the compressive strength of early age concrete. Future work this model, as a new innovation in machine learning in civil engineering vocational education subject, can be used to various concrete mixture design and learning about concrete. Because this concrete mix design model is digital, it can be used for virtual learning. Currently the author is conducting research to create a virtual concrete mix design learning model.

Novel C-A-S-H/PCE nanocomposites: Design, characterization and the effect on cement hydration

Concrete is the most widely used building material in the world. With the development of the modern civil engineering construction, the rapid development of early-age strength of concrete is becoming more and more crucial. Nowadays, the early-age strength of concrete is generally enhanced by thermal curing at high temperature. However, the drawbacks of thermal curing include the high energy consumption and the adverse effect on the long-term strength of concrete, which promotes the development of green and highly-efficient accelerator. During the past decade, it has been found that C-S-H (calcium-silicate-hydrates) nanoparticles could act as the seeds for cement hydration and thus effectively enhance the early-age strength of concrete, which has drawn many research interests due to their economic and environmental benefits. This study proposes novel C-A-S-H (calcium-alumina-silicate-hydrates) nanocomposites by incorporating moderate Al into C-S-H in the presence of PCE (polycarboxylate superplasticizer), and find the formed C-A-S-H/PCE nanocomposites could remarkably promote the dispersion retention ability and the effect on early-age strength development of concrete comparing to traditional C-S-H nanoparticles. Moreover, this study also provides a basis for the production of green and cheap nano-seeding materials based on Al-rich wastes.

Development of a Novel Concrete Curing Method Using Induction Heating System

This study aimed to develop an accelerated concrete curing method based on induction heating (IH) technology. The proposed curing method provides improved heating efficiency and safety since it directly heats only the metallic forms in a non-contacting manner. It also has the advantage of being capable of heating the concrete according to a desirable heating scenario. The effects of several parameters on its performance were evaluated using a finite element method (FEM)-based thermal analysis and heating performance tests. The FEM analysis revealed the steel form to be appropriate for the IH system. The analysis also revealed that equally spaced three-turn coils yielded increased temperature uniformity in the steel form, which was verified by results of the steel form heating experiments. Furthermore, the minimum temperature generated in the form was sufficient for concrete curing. The efficiency of the use of IH for concrete curing and the effects of curing parameters were further investigated through compression tests after applications of various curing methods and by examining the temperature distributions during curing. The test results revealed early strength development even under water freezing conditions. This demonstrated the effectiveness of IH for concrete curing in cold weather. However, the efficiency decreased when the cross-sectional dimension of the specimen increased. The test results also verified that the maximum temperature and duration of induction heat curing affect the early age strength of concrete.