Machine learning and response surface methods for predicting the compressive strength of high-strength concrete have not been adequately compared. Therefore, this research aimed to predict the compressive strength of high-strength concrete (HSC) using different methods. To achieve this purpose, neuro-fuzzy inference systems (ANFISs), artificial neural networks (ANNs), and response surface methodology (RSM) were used as ensemble methods. Using an ANN and ANFIS, high-strength concrete (HSC) output was modeled and optimized as a function of five independent variables. The RSM was designed with three input variables: cement, and fine and coarse aggregate. To facilitate data entry into Design Expert, the RSM model was divided into six groups, with p-values of responses 1 to 6 of 0.027, 0.010, 0.003, 0.023, 0.002, and 0.026. The following metrics were used to evaluate model compressive strength projection: R, R², and MSE for ANN and ANFIS modeling; R², Adj. R², and Pred. R² for RSM modeling. Based on the data, it can be concluded that the ANN model (R = 0.999, R² = 0.998, and MSE = 0.417), RSM model (R = 0.981 and R² = 0.963), and ANFIS model (R = 0.962, R² = 0.926, and MSE = 0.655) have a good chance of accurately predicting the compressive strength of high-strength concrete (HSC). Furthermore, there is a strong correlation between the ANN, RSM, and ANFIS models and the experimental data. Nevertheless, the artificial neural network model demonstrates exceptional accuracy. The sensitivity analysis of the ANN model shows that cement and fine aggregate have the most significant effect on predicting compressive strength (45.29% and 35.87%, respectively), while superplasticizer has the least effect (0.227%). RSME values for cement and fine aggregate in the ANFIS model were 0.313 and 0.453 during the test process and 0.733 and 0.563 during the training process. Thus, it was found that both ANN and RSM models presented better results with higher accuracy and can be used for predicting the compressive strength of construction materials.

In today’s digital age, innovative artificial intelligence (AI) methodologies, notably machine learning (ML) approaches, are increasingly favored for their superior accuracy in anticipating the characteristics of cementitious composites compared to typical regression models. The main focus of current research work is to improve knowledge regarding application of one of the new ML techniques, i.e., gene expression programming (GEP), to anticipate the ultra-high-performance concrete (UHPC) properties, such as flowability, flexural strength (FS), compressive strength (CS), and porosity. In addition, the process of training a model that predicts the intended outcome values when the associated inputs are provided generates the graphical user interface (GUI). Moreover, the reported ML models that have been created for the aforementioned UHPC characteristics are simple and have limited input parameters. Therefore, the purpose of this study is to predict the UHPC characteristics while taking into account a wide range of input factors (i.e., 21) and use a GUI to assess how these parameters affect the UHPC properties. This input parameters includes the diameter of steel and polystyrene fibers (µm and mm), the length of the fibers (mm), the maximum size of the aggregate particles (mm), the type of cement, its strength class, and its compressive strength (MPa) type, the contents of steel and polystyrene fibers (%), and the amount of water (kg/m³). In addition, it includes fly ash, silica fume, slag, nano-silica, quartz powder, limestone powder, sand, coarse aggregates, and super-plasticizers, with all measurements in kg/m³. The outcomes of the current research reveal that the GEP technique is successful in accurately predicting UHPC characteristics. The obtained R², i.e., determination coefficients, from the GEP model are 0.94, 0.95, 0.93, and 0.94 for UHPC flowability, CS, FS, and porosity, respectively. Thus, this research utilizes GEP and GUI to accurately forecast the characteristics of UHPC and to comprehend the influence of its input factors, simplifying the procedure and offering valuable instruments for the practical application of the model’s capabilities within the domain of civil engineering.

In view of the disadvantages of polycarboxylic acid grinding aids, such as poor reinforcement effect and cumbersome synthesis process, a new type of polycarboxylic acid grinding aid was prepared to meet the requirements of multifunctional admixture for cement concrete. The polycarboxylate grinding aid (PC) was prepared using acrylic acid, sodium allyl sulfonate, and isoprenol polyoxyethylene ether (TPEG) as raw materials, and ammonium persulfate as initiator in the nitrogen atmosphere. The effect of PC and its compound with triethanolamine (TEA) and triisopropanolamine (TIPA) on cement particle size and strength, and hydration process and structures of hydrated products were investigated. Moreover, the grinding mechanism of grinding aids was also proposed. The results indicate that the PC has good performance in both grinding and high-efficiency water-reducing. The average particle diameter of cement was reduced by 3.65 μm when 0.03 wt% of PC was added as grinding aid. Moreover, a high initial fluidity of the cement paste, 290 mm, could be reached when 0.08 wt% of PC was added. The fluidity loss of cement paste after 30 min and 60 min was 265 mm and 260 mm, respectively. After PC compounding with TEA and TIPA, 4.07 μm and 4.7 μm of the average particle size of the cement can be reduced, respectively. Based on the investigations on the hydration rate of cement hydration, the phases, and the microstructures of the hardened slurry, it could be concluded that grinding aids can change the hydration process of cement and improve the morphologies and structures of hydration products without influence on the type of hydrated products. Note that the compounded grinding aids, such as PC with TEA or PC with TIPA, can more effectively enhance the early and late strength of cement. This shows excellent comprehensive performance. In this study, a new type of polycarboxylic acid grinding aid was prepared to meet the requirements of the versatility of cement concrete additives, and to simplify the synthesis process, reduce production costs, improve the grinding effect, and improve the performance of cement concrete.

Shotcrete is widely used in civil engineering as a supporting structure. In this paper, the compressive behavior of ultra-high-performance shotcrete (UHPSC) with different steel fiber content by volume (0, 0.5%, 0.75%, 1%, 1.25%, 1.5%) was investigated. The results showed that the failure pattern of UHPSC was changed from brittle failure to ductile failure with the increase in steel fiber content. The compressive strength, peak strain and compressive toughness of UHPSC increased with the increase in steel fiber content, but the elastic modulus and Poisson’s ratio did not change significantly. With content of 1.5% steel fibers, its axial compressive strength, peak strain and compressive strain energy were 122.7 MPa, 3749 με and 0.269 MPa, respectively, increased by 14%, 23.5% and 55.5% compared with those without steel fiber. The peak strain and compressive toughness were higher than that of ultra-high-performance concrete (UHPC), while the elastic modulus of UHPSC was lower than that of UHPC. Based on the experimental data, the relationship between compressive strength, peak strain, compressive toughness and the change in the characteristic value of steel fiber content (λ_f) were revealed. The uniaxial compressive constitutive model of UHPSC with different steel fiber content was established and reflected the change rule of the shape parameter of α (constitutive model ascending section) and β (constitutive model descending section) with λ_f. The experimental results were in good agreement with the model calculation results, which can provide theoretical support for the structural design of UHPSC.

The construction of subways, hydroelectric stations and water substations is exposed to stray currents, which can accelerate concrete corrosion. The influence of stray currents on reinforced concrete structures is unclear. In this paper, the influence of concrete strength grade, reinforcement diameter and stray current intensity on the extent of reinforcement corrosion and calcium ion dissolution were investigated, and the damage of reinforcement and calcium ion corrosion to concrete strength was investigated by simulating a stray current environment and conducting an electrified acceleration test. The test results show that the higher the strength grade of concrete, the lower the stray current intensity and the smaller the corrosion rate and calcium ion dissolution rate of reinforcement; with the increase in the diameter of reinforcement the corrosion rate decreases, but the calcium ion dissolution rate is not affected by reinforcement diameter. The damage effect of reinforcement corrosion on concrete compressive strength is more obvious than that of calcium ion corrosion.

The huge demand for sand and gravel resources in road engineering construction leads to excessive consumption of resources and environmental damage. Recycling waste concrete and industrial solid waste as a road material is a promising alternative. In order to explore the application of these solid wastes in the road base, this paper studies the effect of adding lithium slag activated by an alkaline activator, fly ash (FA) and a combination of the two on the compressive strength, splitting strength and shrinkage performance of recycled cement-stabilized macadam mixture (RCSM). The optimum content of recycled aggregate (RA), alkali-activated lithium slag (AALS) and FA in composite-improved RCSM was optimized using a response surface method (Box–Behnken), and the microscopic characteristics of the mixture were analyzed using X-ray diffraction (XRD) and scanning electron microscopy (SEM). The results show that the optimum dosage of AALS, FA and RA determined by the response surface method is 15%, 10% and 40%, respectively. Compared with the cement-stabilized macadam mixture (CSM) with 40% RA, the 28 d compressive strength and 28 d splitting strength of the composite-improved RCSM are increased by 26.8% and 22.9%, respectively, and the dry shrinkage coefficient and average temperature shrinkage coefficient are decreased by 25.8% and 14.8%, respectively. Microscopic tests show that AALS and FA participate in the hydration reaction, generate more hydrated silicate (C-S-H) and ettringite (AFt), refine pores, effectively improve the performance of the internal interface transition zone of the mixture, make the microstructure of the mixture denser, and improve the strength and shrinkage performance of RCSM. This study provides technical support for the reuse of resources and the sustainable development of road construction.