High Performance Concrete Mix Research Articles

Performance evaluation of high-performance concrete mixes incorporating recycled steel scale waste as fine aggregates

In this study, steel-scale waste (SSW), a byproduct generated during the manufacturing of steel, was investigated as a potential alternative to natural fine aggregates (sand) for preparing high-performance concrete (HPC). Three grades of sand and SSW with different particle sizes were mixed in varying combinations. Three different compaction techniques (loose, tamped, vibration) were employed. The optimum packing density for both SSW and natural aggregates was achieved using the vibration compaction method. Since the combination of 50 % sand and 50 % SSW exhibited the best packing density for both materials, this bi-grade aggregate mixture was selected for the mix preparation. The mechanical tests (compressive strength, flexural strength) and durability assessment (bulk water sorptivity, rate of water absorption, chloride ion penetration) were performed to achieve the desired objectives. The specimens were exposed to two different curing regimes i.e., normal curing and heat curing at elevated temperature. A significant increase in compressive and flexural strength was observed with the increased content of SSW. A compressive strength as high as 140 MPa was obtained for the HPC mix containing SSW aggregates and steel fibers. The replacement ratio of SSW was optimized to achieve better strength and durability. Experimental results showed that heat curing was more effective than conventional curing methods in improving the performance of the concrete.

Optimizing nano-TiO2 and ZnO integration in silica-based high-performance concrete: Mechanical, durability, and photocatalysis insights for sustainable self-cleaning systems

This research presents novel findings by exploring the synergistic effects of incorporating nano-sized titanium dioxide (TiO₂) and zinc oxide (ZnO) nanoparticles into a high-performance concrete (HPC) matrix. The study utilized Response Surface Methodology (RSM) to determine the optimal combinations of TiO₂ and ZnO for achieving peak performance within the matrix. Various combinations of TiO₂ and ZnO, ranging from 0 % to 2 %, were incorporated into HPC mixes, focusing on evaluating their effects on compressive strength (CS), splitting tensile strength (STS), flexural strength (FS), durability, and photocatalytic properties. The results revealed that maintaining higher proportions of TiO₂ over ZnO led to superior mechanical properties, with the most effective combination determined to be 2 % TiO₂ and 1.33 % ZnO, which agrees with the prediction by the RSM model and verified through experimental testing. However, these combinations did not significantly enhance the durability properties of the HPC samples when exposed to acidic curing for three months.On the other hand, the photocatalytic properties of HPCs with different combinations of TiO₂ and ZnO were significantly improved. The combination with the maximum content of both nanoparticles had only 23.7 % of Rhodamine B remaining on its surface after 100 hours of UV radiation. Comparing the individual effects of TiO₂ with ZnO, it was observed that a higher TiO₂ dosage (2 %) caused earlier Rhodamine B discolouration compared to a higher ZnO dosage (2 %). Therefore, based on the photocatalytic degradation efficiency, it was concluded that the concrete can confer self-cleaning properties under UV radiation and serve as a precursor for developing self-cleaning concrete composites for more sustainable and resilient structures.

Interlayer Bond Strength of 3D Printed Concrete Members with Ultra High Performance Concrete (UHPC) Mix

Interlayer Bond Strength of 3D Printed Concrete Members with Ultra High Performance Concrete (UHPC) Mix

Enhancing compressive strength and sustainability: a machine learning approach to recycled brick and tile concrete mix design

Optimizing concrete mix designs, especially for recycled brick and tile (RBT) concrete, is critical in construction materials. The optimization of RBT concrete mix designs was investigated using machine learning (ML) methods and metaheuristic algorithms. Hyperparameter tuning of the XGBoost (XGB) model was conducted using SFO, HGS, and HBA algorithms. Critical hyperparameters, including population size and iterations, were identified to ensure model convergence and performance. The model's predictive accuracy for compressive strength (CS) was evaluated using the coefficient of determination (R2) metric, revealing its superiority in mitigating overfitting. SHAP analysis highlighted testing age, cement content, and total coarse aggregate as influential input variables. A practical approach to RBT concrete mix design optimization was introduced, enabling the achievement of specific CS targets while maximizing RBT usage. Pareto solutions provided actionable insights for engineers to create tailored high-performance concrete mixes. This research contributes significantly to sustainable concrete mix design by offering practical ML tools.

Predicting Compressive Strength of High-Performance Concrete Using Hybridization of Nature-Inspired Metaheuristic and Gradient Boosting Machine

This study proposes a novel integration of the Extreme Gradient Boosting Machine (XGBoost) and Differential Flower Pollination (DFP) for constructing an intelligent method to predict the compressive strength (CS) of high-performance concrete (HPC) mixes. The former is employed to generalize a mapping function between the mechanical property of concrete and its influencing factors. DFP, as a metaheuristic algorithm, is employed to optimize the learning phase of XGBoost and reach a fine balance between the two goals of model building: reducing the prediction error and maximizing the generalization capability. To construct the proposed method, a historical dataset consisting of 400 samples was collected from previous studies. The model’s performance is reliably assessed via multiple experiments and Wilcoxon signed-rank tests. The hybrid DFP-XGBoost is able to achieve good predictive outcomes with a root mean square error of 5.27, a mean absolute percentage error of 6.74%, and a coefficient of determination of 0.94. Additionally, quantile regression based on XGBoost is performed to construct interval predictions of the CS of HPC. Notably, an asymmetric error loss is used to diminish overestimations committed by the model. It was found that this loss function successfully reduced the percentage of overestimated CS values from 47.1% to 27.5%. Hence, DFP-XGBoost can be a promising approach for accurately and reliably estimating the CS of untested HPC mixes.

Auto‐regulated radial base function structure implementation in the hybrid and ensemble hybrid domains to assess the hardened properties of novel mixture high performance concrete

AbstractThe mechanical properties of concrete, such as compressive strength and slump flow rates, are very nonlinear. For academics, it is crucial to forecast these qualities while creating new building methods. Such capabilities should be developed to lower the cost of expensive tests and increase the precision of the measurements. The goal of this study is to create an radial basis function neural network to describe the characteristics of hardness in high‐performance concrete (HPC) mix. Metaheuristic techniques were used to enhance the RBFNN's functionality. A dataset of 181 HPC mixes comprising ecologically beneficial ingredients, such as fly ash and silica fume, was used for training and evaluating the capabilities of the proposed hybrid models. According to the modeling process based on sensitivity analysis of input parameters and the results of hybrid models, the model combined with the multiverse optimization algorithm (MVO) had a higher correlation between the predicted and observed CS and slump values than the model combined with three optimization algorithms in terms of the R2 index being the maximum value of 0.984 in the tasting phase of CS and SL estimation. While evaluating two mechanical aspects of HPC samples, the of the model coupled with the MVO algorithm reconfirmed its accuracy being 3.59.

An experimental study of the relationship between modulus of elasticity, Poisson's ratio, and the mechanical properties of high-performance concrete

This study investigated the mechanical properties of high-performance concrete (HPC) with the percentage of mineral admixtures. HPC is a good choice for multi-story buildings because it has many advantages. As HPC becomes more popular, it is important to research its properties. This study used the P.C. Aitcin method to design HPC mixes with compressive strengths of 60 to 80 MPa. Fly ash is used for M60 and M70 grade HPC and Silica Fume is used for M80 grade HPC is used as mineral admixture as a 20% replacement for cement. In this research paper, the study of properties of the different ingredients used to make HPC is carried out. The testing of three concrete mixes for mechanical properties such as compressive strength, split tensile strength, modulus of elasticity, and flexural strength, as well as other important properties is done. This study explores High-Performance Concrete (HPC) by precisely controlling the water-to-cement ratio and incorporating mineral and chemical admixtures, achieving strengths from 60 to 80 MPa. It investigates key mechanical properties, establishes empirical equations, and compares findings with codes and literature. The results showed that a lower water-to-binder ratio (w/b) led to better mechanical properties. The experimental program includes the casting of 39 cubes, 39 cylinders, 39 beams and 81 columns to test the physical properties of different concrete grades. The use of a compression testing machine with a load capacity of 3000 kN to test the HPC cubes and a loading frame with a load capacity of 2000 kN to test the columns. The average compressive strength for HPC M60 to M80 was 65.40 MPa, 73.45 MPa, and 82.64 MPa respectively. The modulus of elasticity values ranged from 40 to 50 GPa. The findings of the study showed that an increase in concrete strength correlated with a decrease in the average value of Poisson's ratio. Overall, the study suggests that HPC is a good choice for high-rise buildings because it has many advantages. As HPC becomes more popular, it is important to research its mechanical properties. This study provides valuable results about the mechanical properties of HPC in comparison with IS 456:2000. From the experimental results of tested columns, it was observed that as the load increased, the deflection decreased for both uniaxially and biaxially loaded columns, highlighting the novelty of this finding. Additionally, the columns subjected to biaxial loading displayed greater sensitivity compared to their axial and uniaxial loading.

Assessment of mechanical and durability performance of silica fume and metakaolin as cementitious materials in high-performance concrete

AbstractThe present study aims to determine the effects of blending cementitious materials on the mechanical and durability properties of high-performance concrete (HPC). Densified silica fume and fine-grounded metakaolin are used as supplementary cementitious materials (SCMs). A total of 16 mixes containing both binary and ternary blending of SCMs were chosen for w/b ratios of 0.4 and 0.3 respectively. The hardened properties tested for the HPC mixes were compressive strength at 7, 28, and 90 days, flexural strength at 28 days, and modulus of elasticity at 28 days. Maximum strength gains up to 15%, 38%, and 23% for compression, flexure, and elastic modulus were observed in ternary mixes compared to binary mixes. Stress-strain behaviour of ternary mixes indicates increased tolerance of stress for the least amount of strain in the specimens. Based on the experimental results, empirical relations were developed and checked with the existing codes and by earlier researchers. The durability properties tested for HPC were water absorption at 28 days, acid attack, and sulphate attack at 28, 56, and 90 days. Ternary mixes improved the pore structure of HPC, resulting in a 56% reduction in water absorption and a 34% reduction in compressive strength loss due to immersion in 5% H2SO4 at 90 days. The findings of the study endorse that ternary blending of SF and MK can improve the engineering properties of HPC, and a mix containing SF 10% and MK 10% is recommended for the best results.

Eco-efficient high performance white concrete incorporating waste glass powder

Portland cement and supplementary cementitious materials (SCM) are crucial components in the mixture design of High-Performance Concrete (HPC). In certain regions, the constrained ready market availability of SCM may limit the widespread adoption of HPC, namely when a long-term supply is envisaged. These circumstances demand research into sustainable and cost-effective HPC mix designs independent of expensive and imported SCM, such as silica fume. Using locally available SCM reduces costs and the carbon dioxide (CO2) emissions associated with HPC production, while also assigning value to abundant industrial waste or by-products, such as glass powder.This study presents a wide range of more environmentally friendly white HPC formulations suited for architectural applications. The proposed formulations incorporate significant proportions of limestone filler and waste glass powder with varying fineness, serving as substantial partial replacements for white cement. An integrated assessment of engineering properties was conducted, including flowability, electrical resistivity, mechanical strength, and ecological balance. Response surface models of the material behaviour reveal that the water-to-cement weight ratio (w/c) and the glass powder-to-cement weight ratio (GP/c) have a significant influence on both the engineering properties and the ecological footprint of HPC.Regression models were used to obtain the high-flowable HPC. Five optimal mixtures were selected featuring significant partial replacement of cement (c) by limestone filler (Lf) and glass power (GP), with Lf/c∈[0.38;0.78] and GP/c∈[0.269;0.394]. These mixtures reached cube compressive strengths ranging from 90 to 100 MPa, flexure strengths in the 13–15 MPa range, and resistivity levels between 90–180 ohm.m at 28 days.

Study on the optimisation of cement and binder content to develop a sustainable high-performance concrete

According to ACI concrete terminology, “High Performance concrete (HPC) is defined as a concrete meeting special combinations of performance and uniformity requirements that cannot always be achieved routinely using conventional constituents and normal mixing, placing, and curing practices”. It is a new generation of concrete that has been evolved recently and are well received for its exceptional performance of strength and durability. Due to these characteristics, HPC are utilized in the construction of bridges, hydropower structures, pavements, mass concrete projects etc. HPC is a cementitious composite material composed of an optimized gradation of granular constituents, a water-to-binder ratio of less than 0.3, a high percentage of discontinuous internal fiber reinforcement and HPC can hold compressive strength of more than 60 MPa. HPC considered in this study is made with high-strength steel fibers, fine sand, cement, mineral and chemical admixtures and water. The conventional mix design used for normal concrete cannot be adopted for HPC because of the high compressive strength to be achieved. The main objective is to develop a sustainable HPC mix with optimum particle packing density to achieve the desired strength with the lowest cement and binder content. As part of the investigation, the impact of different constituents of HPC such as cement content and binder content on the compressive strength were examined. Also, the optimum particle packing density of mixes with different amount of cement and binder content were studied using EMMA software. From the results it is observed that the increase in cement or binder content beyond a particular level will have minimal impact on the compressive strength.

Study Of High Performance Concrete Using Local Materials (Fly Ash Of Pltu Labuhan Angin, Mount Sinabung Volcanic Ash And Silica Sand) On The Mechanical Properties Of Concrete

Currently in Indonesia a lot of construction work and concrete is one that is widely used. In the development of concrete construction technology, especially in Indonesia, it is necessary to have concrete capable of carrying high loads using available materials. The development of high quality concrete has 3 levels, namely High Strength Concrete (HSC), High Performance Concrete (HPC) and Ultra High Performance Concrete (UHPC). Against the background of future needs, in this study experiments were carried out in a concrete laboratory to obtain high performance concrete mixes with local materials. At the experimental stage, testing of tools and materials, concrete mix, casting, slump test, manufacture of specimens, maintenance, checking of unit weight, compressive strength test, split tensile strength and modulus of elasticity was carried out. In that study there were 11 variations. Furthermore, the test results were analyzed by the data to draw conclusions. The results showed that the average compressive strength of concrete at 3 days of age was relatively high, namely 53.8 MPa which could be used for fast precision work. In variation 11 mixture (PCC Cement, Silica Fume, Sand Mesh 35-60, Silica Mesh 325, Water, Viscocrete Superplasticizer 8670 MN, Fly Ash 7% and Polypropylene Fiber 0.2%) tested for 28 days, the compressive strength reached 87.5 MPa, so it can be said as HPC concrete. In this study it was concluded that the use of local materials, Sinabung Volcanic Ash waste and fly ash can improve the quality of concrete and can also reduce environmental pollution.

Optimasi Mix Design Beton Melalui Teknologi Machine Learning

The concrete mix design is a crucial step in ensuring the quality of concrete used in construction projects. Traditional mix design methods rely on trial and error, which can be time-consuming and escalate construction costs. In recent years, machine learning technology has been developed to predict concrete properties and optimize mix designs for high-quality concrete. This study aims to explore the application of machine learning in high-quality concrete mix design, considering theoretical conditions, methods, and related research. The focus of this research is to test the use of machine learning techniques in predicting concrete properties and optimizing mix designs for high-quality concrete. The theory and concepts of machine learning will be applied to concrete mix design datasets and relevant properties. The methods employed will include data pre-processing, feature selection, and model training and evaluation. The performance of the machine learning model will be compared with traditional mix design methods to determine its effectiveness. Furthermore, the results and benefits of this study will demonstrate the potential advantages of using machine learning in determining high-performance concrete mix designs. By accurately predicting concrete properties and optimizing mix designs, construction projects can be completed more efficiently and with higher quality. This technology also has the potential to reduce costs associated with trial and error methods and minimize the environmental impact of concrete production. The success of this study will pave the way for further research and development in the field of machine learning for high-performance concrete mix designs.

Assessment of Water Transport and Chemical Attack of Meta-Illite Calcined Clay Blended Cement in High-Performance Concrete.

Rapid urbanisation causes a rise in the need for infrastructure, which in turn fuels the creation of additional concrete and further increases cement supplies. Activation of illite-based clay mineral and usage in concrete production is one of the sustainable ways to address the cement industry anthropogenic issues. This study evaluates the durability properties of water transport (water absorption, and capillary water absorption), and resistance to aggressive environments (5% solutions of hydrochloric acid, HCl; sodium sulphate, Na2SO4; and calcium chloride, CaCl2) of meta-illite calcined clay (MCC)-based high-performance concrete (HPC). For this purpose, concrete was produced with 5, 10, 15, 20, 25 and 30% MCC content in partial substitution of CEM II. Results from the water absorption tests indicate an average percentage value of 3.57%, 3.35% and 2.52% for all the observed mixes at 28, 56 and 90 days, respectively, with MCCC-10 HPC having an average best value of 2.23% across the curing ages. On all observed days, the 5 to 15% cement replacements had very close average water sorptivity value of 0.125 ± 0.001 mm/min0.5 with the control mix (0.113 ± 0.011 mm/min0.5). The aggressive environments exposure findings of the hardened MCC-based HPC specimens of 10 to 20% recorded an approximately 15% compressive strength loss in HCl, Na2SO4 and CaCl2 solutions over the 90 days of curing. In all, the HPC mixes of 5 to 15% MCC content obtained an average durability performance factor of 89%. As a result, these findings imply that MCC can replace cement in up to 15% of HPC production.

Prediction of fire spalling behaviour of fibre-reinforced concrete

Fire spalling prediction of fibre-reinforced concrete containing polypropylene (PP) or steel fibre at elevated temperatures is challenging. It is difficult to use conventional methods, such as finite-element modelling and discrete-element modelling, to solve the problem, because of the complicate coupling mechanism of PP and steel fibres in concrete. To this end, two artificial neural network (ANN) models, one (ANN1) based on a concrete mix study and the other (ANN2) based on a compressive strength study, were introduced to assess the resistance of concrete to explosive spalling. Test data (321 and 318 items, respectively) gathered from the literature were utilised to train the proposed models. Twenty-four concrete mixes (96 groups), that is, seven plain concrete mixes, four high performance concrete mixes reinforced with PP fibre, three ultra-high-performance concrete (UHPC) mixes with reinforced PP fibre and ten UHPC mixes reinforced with PP and steel hybrid fibres were designed and tested to validate the accuracy of the models. The study demonstrates that ANN1 and ANN2 can achieve a predictive accuracy of 89.6% and 84.4% for the explosive spalling, respectively, indicating the feasibility of the proposed models for predicting explosive spalling threat of the hybrid fibre-reinforced concrete.

Intelligent multiobjective optimization for high-performance concrete mix proportion design: A hybrid machine learning approach

The concrete mix proportion design process is complex but important, especially in cold, ocean, underground and other complex engineering environments. In this study, a hybrid intelligent optimization method based on the random forest (RF), recursive feature elimination (RFE), Bayesian optimization (BO), least squares support vector machine (LSSVM) and nondominated sorting genetic algorithm (NGSA)-III was proposed to optimize the concrete mix proportion and rapidly and accurately predict the frost resistance, chloride ion penetration resistance and concrete strength (CS). Adopting a key project in Jilin Province as an example, the RF-RFE-BO-LSSVM-NSGA-III algorithm achieved a significant optimization effect in terms of the chloride ion permeability coefficient (CIPC), relative dynamic elastic modulus (RDEM) and 28-day CS. After optimization, the chloride ion penetration resistance, frost resistance and CS increased by 34.6%, 4.1% and 3.7%, respectively, over the average levels of the sample data. This study can provide basis for concrete mix proportion design in complex environment.

Chopped Basalt Fiber-Reinforced High-Performance Concrete: An Experimental and Analytical Study

Basalt fiber (BF) is an environmentally friendly type of fiber that has attracted the attention of researchers in recent years due to its excellent performance in concrete constructions. This current research was conducted to investigate the effect of chopped basalt fiber on the workability, compressive strength, and impact resistance of high-performance concrete (HPC). Three various lengths (3, 12, and 18 mm) and six volume fractions (0%, 0.075%, 0.15%, 0.3%, 0.45%, and 0.6% by concrete volume) of BF were used in producing sixteen HPC mixes. HPC compressive strength and impact resistance were measured for each mix. Scanning electron microscopy (SEM) analysis was also conducted on selected mixes to closely investigate the effects of the applied variables through the microstructural scale. An empirical model was developed to study the relationship between the impact energy and compressive strength of BF-reinforced HPC. The results show that adding BF improves the compressive strength and impact resistance. Compared with the control concrete, the compressive strength of the HPC reinforced with 3 mm, 12 mm, and 18 mm BF increased by 12.2%, 15.1%, and 17.5%, respectively. The impact resistance increased with a dosage of 8 kg/m3 for all lengths of BF. The SEM observations revealed that the BF accumulated in pores and on the surface of the attached cement which improved the microstructure of the interfacial transition zone (ITZ), which further enhanced the strength and ductility of the HPC.

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.

High early strength-high performance concrete produced with combination of ultra-fine slag and ultra-fine silica: Influence on fresh, mechanical, shrinkage and durability properties with microstructural investigation

This study relates to High early strength- High Performance concrete (HPC) produced with incorporation of Ultra-fine Slag (UFS) and Ultra-fine Silica (UFSi). Compressive Strength development was studied from an early period of 14–15 h of casting up to 180 days. The variations in workability and its retention levels after 60 min of mix preparation were recorded. Elastic modulus, compressive strain behaviour, flexural parameters, early age shrinkage and few durability properties were measured for resulting optimal concrete mixes. Modifications induced at microstructural level were assessed by Scanning Electron Microscopy (SEM) and Nanoindentation tests. Incorporation of UFS and UFSi resulted in reduction of fresh properties beyond certain addition percentages. Usage of UFS as part replacement to GGBS in HPC mixes showed considerable improvement with regards to mechanical and durability aspects. Incorporation of UFSi was evaluated to prominently improve early age strength of concrete in combination with UFS at optimal quantities, while moderately improving other mechanical properties. Early age shrinkage induced stress levels and the brittleness of concrete were observed to increase with use of selected admixtures under multiple blend system. Improvement in the microstructure was observed with denser hydrated matrix offering enhanced homogeneity and better bonding with aggregates. Increase in strength governing hydration phases was evidenced for optimal addition of UFS and UFSi. Durability behaviour was significantly enhanced for combination of UFS and UFSi owing to microstructural improvement through pore refinement.

Spalling mitigation techniques for high-performance concrete at elevated temperature

High-performance concrete (HPC) is highly susceptible to temperature-induced spalling, which unveils severe damage of HPC structural members. Therefore, this research work is aimed at developing spalling mitigation techniques for HPC and experimentally assessing spalling behaviour at transient heating conditions up to 1000 °C for a 4-hour fire resistance rating. A total of four HPC mixes were comprised for spalling behaviour evaluation, in which Mix H1 was designed only using main binder ordinary Portland cement (OPC), whereas Mix-H2, Mix-H3, and Mix-H4 were designed by partial replacement of OPC with three different supplementary cementitious materials (SCMs), i.e., fly ash (FA), silica fume (SF), ground granulated blast furnace slag (GGBS) one at a time as a binary composite system. Polypropylene (PP) fibres and steel (ST) fibres one at a time from a range of 0.00, 0.62, 1.24, 1.86, and 2.48 kg/m3 and ST fibres range of 0.00,12.43, 24.87, 37.30, and 49.74 kg/m3 were incorporated into HPC mixes for evaluating spalling mitigation behaviour at elevated temperature. For each HPC mix, a total of three standard cylindrical specimens (100 mm diameter × 200 mm height) were exposed to transit temperature 1000 °C for up to 4 h to assess spalling behaviour. It is observed that Mix-H1 content only OPC does not reveal any severe damage and spalling behaviour, whereas Mix-H2, Mix-H3, and Mix-H4 comprising SCMs revealed very severe damage and spalling behaviour. This result indicates that the highly dense microstructure with a highly durable HPC matrix using SCMs does not allow any moisture movement/migration from the inherent concrete binding matrix to the outer exposed surface of cylinder specimens and resulting in explosive-type spalling of HPC. However, using 1.86 kg/m3 of PP fibres and 37.30 kg/m3 of ST fibres in HPC binary systems has a positive impact on mitigating spalling of HPC at elevated temperatures.

Optimization of high-performance concrete mix ratio design using machine learning

High-durability concrete is required in extremely cold or ocean environments, making the design of concrete mixes highly important and complicated. In this study, a hybrid intelligent framework for multi-objective optimization based on random forest (RF) and the non-dominated sorting genetic algorithm version II (NSGA-II) is developed to efficiently predict concrete durability and optimize the concrete mix ratio. The relative dynamic elastic modulus of concrete after 300 freeze–thaw cycles and the chloride ion permeability coefficient at 28 days are defined as the standard measures of durability. The concrete mix ratio is taken as the influencing parameter, and orthogonal test data and engineering practice data are collected as the datasets. The proposed framework is applied to a realistic expressway project in a cold region of China. The results demonstrate that (1) a hybrid intelligent framework based on RF-NSGA-II can effectively predict concrete durability and optimize the mix ratio. (2) The developed RF model has an excellent regression learning ability, while the goodness of fit (R2) of concrete durability reaches 0.9503 and 0.9551, respectively, with root mean square error (RMSE) values of only 0.096 and 0.043, the mean absolute percentage error (MAPE) values of 2.54% and 2.17%. (3) After optimization, the concrete durability reaches a high standard, with a frost resistance of >95% and a chloride ion permeability coefficient of <3*10−8 cm2/s, at a unit volume cost of only 376.77 yuan. Hence, the proposed framework can be used to effectively optimize the concrete mix design and provide guidance for similar projects.