High-performance Concrete Mixtures Research Articles

Evaluation of the mechanical behavior of high-performance concrete (HPC) reinforced with 3D-Printed trusses

The present study aims to explore the feasibility of employing 3D printing technology in reinforcing High Performance Concrete (HPC). To this end, the mechanical characteristics of HPC reinforced with four types of 3D-printed trusses (Pratt, Howe, Warren and Warren with vertical members) made from Polylactic Acid (PLA) have been evaluated. The 3D-printed truss reinforcements were plotted with the aid of 3D Max software. Then, they were produced using the Fused Deposition Modeling (FDM) technique and were placed into the molds. After that, the HPC mixture was poured into the molds and the specimens were cured for 28 days. Finally, the four-point bending tests were conducted on the specimens. The results showed that the employment of different 3D-printed trusses reduced the weight of the control samples between 0.5 and 2.5 kg. In addition, the application of 3D-printed Warren truss had the best performance among other types of trusses in terms of the flexural strength so that it increased the flexural strength of the control sample from 24.4 to 27.9 kN. Finally, all types of 3D-printed trusses increased the energy absorption capacity and were able to alter the fracture mechanism of HPC from brittle to ductile.

Investigation of mechanical properties of high-performance concrete via optimized neural network approaches

In this paper, an artificial intelligence approach has been employed to analyze the slump and compressive strength (CS) of high-performance concrete (HPC), focusing on its mechanical properties. The importance of assessing these critical concrete characteristics has been widely acknowledged by experts in the field, leading to the development of innovative methods for estimating parameters that typically require laboratory testing. These intelligent techniques improve the accuracy of mechanical property predictions and reduce the resource-intensive and costly nature of experimental work. The radial basis function neural network (RBFNN) is the foundational model for predicting the mechanical attributes of various HPC mixtures. To fine-tune the RBFNN’s performance in replicating the mechanical properties of HPC samples, two optimization algorithms, namely the Golden Eagle Optimizer (GEO) and Dynamic Arithmetic Optimization Algorithm (DAOA), have been employed. In this manner, both RBGE and RBDA models were trained using a dataset comprising 181 HPC samples that included superplasticizers and fly ash. The results show that DAOA has significantly improved the base model’s predictive capability, achieving a higher correlation with a value R2 of 0.936 when estimating slump. Furthermore, RBDA exhibited a more favorable root mean square error (RMSE) in predicting compressive strength compared to RBGE, with a notable 16% difference. Ultimately, both integrated models demonstrated their effectiveness in accurately modeling the mechanical properties of HPC.

Modeling the compressive strength of binary and ternary blended high-performance concrete mixtures using ensemble machine learning models

AbstractIn the present study, the compressive strength of binary and ternary blended high-performance concrete mixtures was modeled using different machine learning tools, such as artificial neural network (ANN), gradient tree boosting (GTB), and multivariate adaptive regression splines (MARS). The compressive strength of binary and ternary blended concrete at 28 days of curing period was modeled using seven quantitative input parameters such as cement, blast furnace slag, fly ash, superplasticizer, water, coarse aggregate, and fine aggregate based on three different training and testing (Tr–Te) scenarios. The performance of the models developed was analyzed based on several statistical evaluation metrics, of error and efficiency. During the testing phase, the compressive strength estimates obtained via modeling using ANN, GTB, and MARS had Kling–Gupta efficiency (KGE) values of 0.8389, 0.8602, and 0.8423, respectively, for the first Tr–Te scenario; similarly, the KGE values were 0.8025/0.8830, 0.8541/0.8901, and 0.8434/0.8582, respectively, for the second/third Tr–Te scenarios. The estimation accuracy of the GTB model was relatively superior to that of the ANN and MARS models, taking into consideration both the error and efficiency indices. All three models perform relatively well for the first I/O combination compared to the other two combinations.

Three intelligent computational models to predict the high-performance concrete mixture

Three intelligent computational models to predict the high-performance concrete mixture

Effect of manufactured sand, micro silica, and GGBS on properties of high-performance concrete

The most often used building material for engineering constructions is concrete. The rapid urbanization has necessitated the need for High Strength (HS) and High -Performance Concrete (HPC) for specialized constructions, such as high rise/tall structure and other important structures. Greater cement content may be required for concrete with higher performance like strength and durability, but code does not permit it, because higher cement content increases the heat of hydration, which leads to the development of thermal cracks in concrete, reduces its structural performance and damage environment by producing CO2 during production of Ordinary Portland Cement (OPC). This study tries to replace OPC by Micro Silica (MS) and Ground Granulated Blast Furnace Slag (GGBS) by some percentage to find our effect of these materials on properties of concrete HPC.In this work, the influence of Manufactured Sand (M-Sand), Micro Silica (MS) and Ground Granulated Blast Furnace Slag (GGBS) on the mechanical and durability qualities of High - Performance Concrete (HPC) is examined experimentally. Ordinary Portland cement (OPC) is used to create the HPC mixtures and then 40%,45%, 50% by weight of OPC is replaced with GGBS and 2.5% and 5% by weight of OPC is replaced with MS respectively. Additionally, OPC is replaced by 40%GGBS+ 2.5% MS, 40% GGBS+5% MS, 45%GGBS+ 2.5% MS, 45% GGBS+5% MS, and 50%GGBS+ 2.5%MS, 50%GGBS+5% MS. For each percentage replacement workability test, compressive test at the age of 28,56 and 90 days, water permeability test at 28 days and 90 days, Scanning Elector Microscope (SEM) test after 90 days are carried out. The investigative study’s findings showed that partial replacement of OPC with GGBS, MS, and combinations of GGBS and MS produces more consistent outcomes for strength and durability when compared to control mix.

The effect of water absorption distribution of recycled coarse aggregate on the compressive strength distribution of high-performance concrete

High water absorption is a typical characteristic of recycled coarse aggregate and is often used to explain the loss of performance of concrete when replacing natural coarse aggregate with recycled coarse aggregate. Extensive attention has been paid to the mean value of the water absorption of recycled coarse aggregate, but not to the standard deviation. This paper aims to assess whether recycled coarse aggregates with the same mean water absorption but different standard deviations will perform equally in high-performance concrete (HPC). The resulting HPC mixtures exhibited very similar compressive strength. Even so, it was hypothesised that as the standard deviation of the water absorption of recycled coarse aggregate increases over a wide range, the compressive strength of HPC will first increase due to local variations in the water/cement ratio, then decrease due to the presence of weak particles, and finally remain constant due to the role of the surrounding new mortar.

Modified particle packing approach for optimizing waste marble powder as a cement substitute in high-performance concrete

This study explores the potential of utilizing waste marble powder (WMP) instead of cement to develop environmentally friendly high-performance concrete (Eco-HPC). It assesses Eco-HPC's particle packing density, workability, mechanical characteristics, and durability at various stages. High-performance concrete (HPC) mixtures were optimized using a Modified Andreasen and Andersen (MAA) particle packing model to minimize cement content from 550 to 385 kg/m3. The MAA particle packing model demonstrated its ability to enhance and refine mixture microstructures. Response Surface Methodology (RSM) and Artificial Neural Networks (ANN) were employed to optimize and predict the mechanical properties and water absorption of modified Eco-HPC blends at 7, 28, and 56 days. As the coefficient of determination indicates, ANN outperformed RSM in predicting Eco-HPC properties across various ages. Substituting cement with WMP, Silica Fume (SF), and Fly Ash (FA) results in a dense microstructure. The mortar containing 20 % WMP and 10 % SF achieves the highest wet packing density at 0.9749 and the lowest void ratio at 0.025, respectively. The formation of CSH in the 70C/20 M−10SF mixture led to a substantial reduction in calcium hydroxide content, indicating enhanced mechanical properties. SEM analysis at 56 days demonstrated significant pozzolanic reactions in the 70C/20 M−10SF mixture, resulting in substantial CSH formation. Furthermore, the embodied CO2 index for 70C/20 M−10SF was reduced to 5.07 kg/MPa/m3, compared to the 100C/0M with value of 8.17 kg/MPa/m3. Economic and environmental assessments reveal enhanced mechanical properties and microstructure when using WMP. This evaluation confirms the effectiveness of 70C/20 M−10SF utilization, paving the way for further advancements in Eco-HPC development.

A comprehensive investigation on the impacts of steel slag aggregate on characteristics of high-performance concrete incorporating industrial by-products

Steel slag (SS), an industrial by-product of the steel industry, has the potential to serve as a natural aggregate alternative in concrete production to not only mitigate the exploitation of natural resources but also minimize the environmental impact of its treatment and disposal. This study was designed to investigate comprehensively the impacts of using SS as a full replacement for coarse aggregate and of using fly ash (FA) and ground granulated blast-furnace slag (GGBFS) as partial replacements for Portland cement on the engineering properties (i.e., workability, fresh unit weight, porosity, compressive and flexural strengths, ultrasonic pulse velocity, and drying shrinkage), durability (i.e., water absorption, surface electrical resistivity, and rapid chloride ion penetration), and microstructure (i.e., scanning electron microscopy observation) of high-performance concrete (HPC). A comparative analysis of the economic and environmental benefits of SS concrete versus natural aggregate concrete was also performed. The test results revealed that SS, FA, and GGBFS all impacted the properties of HPC significantly. The HPC mixtures in which natural aggregate had been completely replaced with SS exhibited about 20.4–21.3% higher unit weight than the natural aggregate concrete. The HPC samples with added FA and GGBFS exhibited enhanced performance in terms of mechanical strength, durability, and microstructure. Moreover, total material cost, global warming potential (GWP), and ozone depletion potential (ODP) were all found to be significantly lower in the HPC samples produced using SS and either GGBFS or a combination of FA and GGBFS. As a result, after 210 days of normal curing, the 100% SS concrete containing 15% FA and 35% GGBFS as a Portland cement substitution (S100F15G35 specimen) exhibited compressive and flexural strength values of 110.3 and 11.1 MPa, which were approximately 9.0% higher than the corresponding values of the reference concrete. Also, the S100F15G35 specimen registered the respective ultrasonic pulse velocity, surface electrical resistivity, and rapid chloride ion penetration values of 5328 m/s, 113.3 kΩ.cm, and 203 Coulombs, indicating high-quality and durable concrete. Moreover, incorporating 15% FA and 35% GGBFS in SS concrete resulted in a reduction of 15.7% drying shrinkage and 24.4% total material cost, especially reduced environmental impacts with a significant reduction in GWP and ODP by 43.5% and 29.2%, respectively. These findings further demonstrate the potential of using SS in combination with FA and GGBFS to create high-quality HPC that is both more economical and significantly more sustainable than conventional HPC.

Estimation of compressive strength and slump of HPC concrete using neural network coupling with metaheuristic algorithms

The compressive strength and slump of concrete have highly nonlinear functions relative to given components. The importance of predicting these properties for researchers is greatly diagnosed in developing constructional technologies. Such capacities should be progressed to decrease the cost of expensive experiments and enhance the measurements’ accuracy. This study aims to develop a Radial Basis Function Neural Network (RBFNN) to model the hardness features of High-Performance Concrete (HPC) mixtures. In this function, optimizing the predicting process via RBFNN will be aimed to be accurate, as the aim of this research, conducted with metaheuristic approaches of Henry gas solubility optimization (HGSO) and Multiverse Optimizer (MVO). The training phase of models RBHG and RBMV was performed by the dataset of 181 HPC mixtures having fly ash and superplasticizer. Regarding the results of hybrid models, the MVO had more correlation between the predicted and observed compressive strength and slump values than HGSO in the R2 index. The RMSE of RBMV (3.7 mm) was obtained 43.2 percent lower than that of RBHG (5.3 mm) in the appraising slump of HPC samples, while, for compressive strength, RMSE was 3.66 MPa and 5 MPa for RBMV and RBHG respectively. Moreover, to appraise slump flow rates, the R2 correlation rate for RBHG was computed at 96.86 % while 98.25 % for RBMV in the training phase, with a 33.30% difference. Generally, both hybrid models prospered in doing assigned tasks of modeling the hardness properties of HPC samples.

Optimizing a Polycarboxylate Superplasticizer Molecular Structure to Reduce Apparent Viscosity of Cement Paste at Higher Environmental Temperatures

A high environmental temperature can increase the apparent viscosity of high-performance concrete mixtures, causing difficulties in mixing, transporting, pumping, and molding the mixtures. Although polycarboxylate ether–based superplasticizers (PCEs) have been proven effective in reducing the apparent viscosity of cement pastes, little work has focused on how PCEs with various molecular structures affect the apparent viscosity of high-performance concrete mixtures when environmental temperature increases. In this study, a PCE (T54C3.5), which was synthesized by reacting acrylic acid (AA) and isoprenyloxypoly (ethylene glycol) ether macromonomer (TPEG) (mw=2,400 g/mol) with a ratio equal to 3.5∶1, was used as the control group. Variations on the molecular structure of T54C3.5, including different carboxylate-to-macromonomer ratios, backbone lengths, backbone compositions, side-chain lengths, and side-chain compositions, were made to investigate the effectiveness of the various PCEs in changing the apparent viscosity of an ordinary portland cement paste with the water-to-cement ratio of 0.23 at different environmental temperatures. A rotational viscometer was used to measure the apparent viscosity of cement pastes containing different PCEs, and the working mechanisms for the effective PCEs were discussed. Results showed that reducing the backbone length was more effective than the other variations in improving the viscosity-reducing ability of PCEs at all tested temperatures. The PCEs containing ester bonds were able to retain or slightly decrease the viscosity of their cement pastes when the environment temperature increased from 20°C to 40°C. Reducing the backbone length and introducing ester groups are two effective ways of improving the viscosity-reducing ability of PCEs at a high environmental temperature. Using PCEs with these structures can significantly simplify the manufacturing processes of the cement mixtures with a low water-to-cement ratio when the environmental temperature increases from 20°C to 40°C, without any special mixing or casting method.

Mix design method of granular packing for high performance concrete with natural pozzolans

This study presents an enhanced mix design method for High performance concrete (HPC) with Natural Pozzolans (NP) content that considers material packing theory. Seven HPC mixes with different NP replacement levels of 0, 5, 10, 15, 20, 25, 30% by volume were conducted to investigate the effect of NP on the rheological and mechanical properties of HPC. A basic water demand experiment was designed to obtain the granular packing and packing density of mortar. Furthermore, the equivalent packing density was defined and calibrated to represent the effect of NP, And the bilinear interpolation method was used to analyses the HPC properties. The results show that the relative accuracies of the improved method are higher than 15% to the initial method. The HPC mixtures with NP was also assessed and shown to be within the optimum area.

Increasing the Reliability of Formation Factor-Based Transport Property Prediction for High Performance Concrete Mixtures Through Innovative Matching Pore Solution Curing

Recent specifications for concrete bulk resistivity tests (ASTM C 1876 and AASHTO TP 119) recommend a submerged standard (simulated) pore solution (SPS, solution conductivity = 78.74 mS/cm) for curing concrete specimens. The rationale for the bucket test is that immersing concrete specimens in a soak solution similar to their pore solution would eliminate the need to determine pore solution resistivity for calculating the formation factor (FF) of concrete mixtures. However, the thermodynamic modeling predictions of 91-day pore solution concentration (PSC) for eight high performance concrete (HPC) mixtures evaluated in the current study showed SPS to be a close representation only for reference ordinary Portland cement (OPC) and binary silica fume mixtures. In contrast, the average PSC of Class F and Class C fly ash mixtures was approximately 12% to 20% lower and 20% to 40% higher, respectively, than the SPS. Accordingly, an innovative matching pore solution (MPS) curing approach was developed in which mixtures are grouped based on the influence of supplementary cementitious materials (SCMs), that is, their type and replacement levels of the long-term PSC of concrete mixtures and, thereby, cured in a simulated solution matching the average PSC of a particular group. Based on experimental work in the current study, HPC mixtures under MPS demonstrated a lower coefficient of variation (COV) and more comparable (<10% difference) bulk resistivity (BR) and surface resistivity (SR) measurements compared with SPS. Moreover, the MPS improved the reliability in FF determination and FF-based transport property prediction for HPC mixtures, as verified by lower mean absolute error and improved R2 between FF-predicted diffusion coefficients and experimental measurements.

Implementation of nonlinear computing models and classical regression for predicting compressive strength of high-performance concrete

The construction sector would greatly benefit from a strategy for optimizing high-performance concrete mixtures. However, traditional proportioning techniques are insufficient because of their high prices, usage restrictions, and inability to account for nonlinear interactions between components and concrete qualities. High-performance concrete (HPC) is a complicated composite material with highly nonlinear mechanical behaviour. When strength can be accurately predicted, design costs, design time, and material waste caused by several mixing trials can all be reduced. In this research, feed-forward neural network (FFNN), Elman neural network (ENN), support vector machine (SVM) and multilinear regression (MLR) were employed for predicting the compressive strength of HPC. The input variables include cement (C), cement strength (CeS), superplasticizer (S), fly ash (F), air entraining agent (A), coarse aggregate (CA), Sand (Sd) and water/binder (W/B) and 28 days’ compressive strength as the output variables. Finally, the results indicate that the proposed model has predictive robustness for predicting the compressive strength of HPC. The results showed that FFNN-M4, ENN-M4, SVM-M4, and MLR-M4 combination have the highest performance evaluation criteria of R2=0.9950, R2=0.9853, R2=0.9736, R2= 0.9678 in the testing phase respectively. The outcomes also show that the proposed model has high accuracy and effectiveness in predicting the compressive strength of HPC.

Computation of corrosion initiation time with HPC mixtures and high-quality rebars

The U.S. report card on bridges, conducted by the ASCE in 2021, found that 7.5% of all the nation's bridges are structurally deficient. Corrosion of the reinforcement is one of the main concerns of the service life of concrete bridges, as it can weaken the strength and durability of concrete. This research aimed to create a robust corrosion initiation model for concrete structures.This study's various factors of interest were rebar type, cover depth, and replacement of cement ranging from 15% to 50%. This research implemented the commonly used deterministic model, based on Fick's second law of diffusion while including various sustainable supplementary cementitious materials (SCM) and high-quality rebars namely carbon steel, austenitic stainless steel, and duplex stainless steel. Zeolite was used as the primary SCM in this study. In addition to zeolite, metakaolin, fly ash, GGBS, pumice, and silica fume were used to develop various binary and ternary-based High-Performance Concrete (HPC) mixtures.Three resistivity testing devices were utilized to measure the corrosion propensity of the HPC mixtures. They are surface resistivity for Wenner probe, and two for bulk resistivity testing devices: Merlin and RCON. This resistivity data was analyzed using fundamentals of electrochemistry to compute the diffusion coefficient of the chloride through the concrete. Finally, these diffusion coefficients and corrosion threshold of rebars were incorporated within the diffusion model to obtain the corrosion initiation time.The results showed that the binary and ternary-based HPC mixtures containing 25% zeolite, 20% zeolite, and 10% metakaolin or 10% silica fume yielded the highest initiation times. Respectively, they had a 320% and 240% increase in initiation time compared to the control mixture of 100% Portland cement. In summary, this study shows promise in aiding research in enhancing corrosion initiation models in the step toward probabilistic modeling and the inclusion of durable materials.

Modeling the hardness properties of high-performance concrete via developed RBFNN coupling matheuristic algorithms

Examining the properties of High-Performance Concrete (HPC) has been a big challenge due to the highly heterogeneous relationships and coherence among several constituents. The employment of silica fume and fly ash as eco-friendly components in mixtures benefits the concrete to improve its physical features. Although machine learning approaches are utilized broadly in many studies solitarily to estimate the mechanical features of concrete, causing to reduce accuracy and lift the cost and complexities of computational networks. Consequently, current research aims to develop a Radial Basis Function Neural Network (RBFNN) integrating with optimization algorithms in order to precisely model the mechanical characteristics of HPC mixtures including compressive strength (CS) and slump (SL). Feeding the dataset of HPC samples to hybrid models will result to reproduce the given CS and SL factors simultaneously. The results of the models showed that the maximum rate of correlation between estimated values and measured ones was obtained at 98.3% while the minimum rate of RMSE was calculated at 3.684 mm (and MPa) in the testing phase. Employing such soft-oriented approaches has been benefiting us to reduce costs and increase the result accuracy.

Experimental and Statistical Analysis of Repeated Impact Records of Hybrid Fiber-Reinforced High-Performance Concrete

The effect of fiber type and fiber hybridization on the repeated impact strength was investigated experimentally using six high-performance concrete mixtures reinforced with a 2.5% fiber volume fraction. The fiber types considered in this study included short steel fibers (SF) with 6 mm length, long SF with 15 mm length, and polypropylene (PP) fibers. The repeated impact test was conducted using a specially made automatic testing machine following the test setup recommendations of the ACI 544-2R test, where cracking (Ncr) and failure (Nf) impact numbers were recorded and the failure mode and crack pattern were observed. The results were statistically analyzed using the normality test and variations were discussed. The test results showed that specimens with pure long SF (S15) obtained the highest Ncr and Nf values, which were 20% and 327% higher than those of the mixture with pure short SF (S6) owing to the better bond between fibers and the cementitious matrix in S15. Replacing 0.5% of the mixture’s SF with PP decreased the cracking resistance by 7% to 15%, while its effect on Nf was dependent on the length of SF. In most cases, the Ncr and Nf records did not exhibit a significant departure from normal distribution, according to the Anderson-darling test.

Model-based Estimator Design for the Curing Process of a Concrete Structure

Concrete is one of the most important building materials and is used as a collective term for different dispersions of cement and aggregates. High performance concrete (HPC) is a rather new type of concrete mixture. A topic of current research is the behavior of fresh concrete during heat treatment. It is known that the heat treatment of fresh concrete accelerates the reaction of the cement and thus the chemically complex process of hydration. The mathematical representation of the curing concrete is a further step towards the systematic investigation. The objective of this work is the development of a state estimator to determine the temperature behavior of the fresh HPC mixture under heat treatment. Using a continuum representation describing the spatial-temporal evolution of temperature, moisture, and maturity of fresh HPC during heat treatment a finite-dimensional approximation is derived using a high order finite difference scheme. Experimental data is included for model parameterization by optimization. Based on this, three different nonlinear extensions of the Kalman filter (KF) techniques are realized and compared combining simulated and experimental data.

Variation of Electrical Resistivity and Charge Passed in High-Performance Concrete

This study investigated the variation of bulk resistivity (BR) and charge passed for various high-performance concrete (HPC) mixtures based on significant factors (i.e., geometric size, operation frequency, and mixture constituents and proportions) using three testing instruments. These instruments were a surface resistivity (SR) meter and two bulk conductivity meters: one for using the BR data at a constant frequency, and the other at a wide range of frequencies. These HPC mixtures were categorized into several groups based on various supplementary cementitious materials (SCMs). The variation and distribution of BR and the charge passed were investigated and statistical analysis results showed that the addition of SCMs and their varying replacement level remarkably influenced the reduction of charge passed in each group over an extended period. The results revealed that, for fly ash-based ternary mixtures, the addition of 3% metakaolin or 12% silica fume resulted in the highest reduction of charge passed over time (82% and 90%, respectively). For cost purposes, 5% silica fume replacement in ternary mixtures was chosen as an optimal solution. Finally, this study offered promising options for charge passed computation to assess corrosion in light of simple, rapid, and reliable SR/BR measurement.

Evaluation of mechanical properties and environmental impact of using limestone powder in high-performance concrete

In this study, various dosages of limestone (LS) powder (10, 15 and 20%) of varying fineness were used as a replacement for cement to investigate its influence on the selected properties of high-performance concrete (HPC). The efficiency factor and carbon dioxide (CO2) equivalent emissions were evaluated for life cycle assessment of HPC mixtures containing LS powder. The workability, compressive, split tensile and flexural strength, semi-adiabatic temperature rise and autogenous shrinkage of HPC were investigated. The results indicated that workability and density were enhanced by replacing cement with fine and intermediate LS powder in comparison with coarse LS powder. The compressive, split tensile and flexural strengths were all reduced by increasing the replacement level of fine, intermediate and coarse LS powder at all curing ages. Furthermore, higher temperature peaks and high autogenous shrinkage were observed in fine LS mixtures due to the nucleation effect and the accelerating hydration reaction of fine LS particles. The highest efficiency factor and highest reduction in carbon dioxide equivalent emissions was observed in the mixtures containing 20% coarse LS powder followed by the intermediate LS powder. This research work may help in understanding the role of varying finenesses of LS powder as a viable material in high-performance-based composites.

Investigation on factors affecting early strength of high-performance concrete by Gaussian Process Regression.

This study aims to investigate the influence of all the mixture components of high-performance concrete (HPC) on its early compressive strength, ranging from 1 to 14 days. To this purpose, a Gaussian Process Regression (GPR) algorithm was first constructed using a database gathered from the available literature. The database included the contents of cement, blast furnace slag (BFS), fly ash (FA), water, superplasticizer, coarse, fine aggregates, and testing age as input variables to predict the output of the problem, which was the early compressive strength. Several standard statistical criteria, such as the Pearson correlation coefficient, root mean square error and mean absolute error, were used to quantify the performance of the GPR model. To analyze the sensitivity and influence of the HPC mixture components, partial dependence plots analysis was conducted with both one-dimensional and two-dimensional. Firstly, the results showed that the GPR performed well in predicting the early strength of HPC. Second, it was determined that the cement content and testing age of HPC were the most sensitive and significant elements affecting the early strength of HPC, followed by the BFS, water, superplasticizer, FA, fine aggregate, and coarse aggregate contents. To put it simply, this research might assist engineers select the appropriate amount of mixture components in the HPC production process to obtain the necessary early compressive strength.