Currently, one of the topical areas of application of machine learning methods in the construction industry is the prediction of the mechanical properties of various building materials. In the future, algorithms with elements of artificial intelligence form the basis of systems for predicting the operational properties of products, structures, buildings and facilities, depending on the characteristics of the initial components and process parameters. Concrete production can be improved using artificial intelligence methods, in particular, the development, training and application of special algorithms to determine the characteristics of the resulting concrete. The aim of the study was to develop and compare three machine learning algorithms based on CatBoost gradient boosting, k-nearest neighbors and support vector regression to predict the compressive strength of concrete using our accumulated empirical database, and ultimately to improve the production processes in construction industry. It has been established that artificial intelligence methods can be applied to determine the compressive strength of self-compacting concrete. Of the three machine learning algorithms, the smallest errors and the highest coefficient of determination were observed in the KNN algorithm: MAE was 1.97; MSE, 6.85; RMSE, 2.62; MAPE, 6.15; and the coefficient of determination R², 0.99. The developed models showed an average absolute percentage error in the range 6.15−7.89% and can be successfully implemented in the production process and quality control of building materials, since they do not require serious computing resources.

The development of new and improvement of existing technologies based on the use of waste products from various industries or recyclable materials is a current trend in the construction industry. Including in the composition of binders and concrete by-products of industry, reducing the proportion of Portland cement, it is crucial to maintain and improve the resulting products’ mechanical characteristics and life cycle. The main aim of the study was to investigate the influence of biochar additive on the microstructure and properties of the concrete and obtain the composition with improved characteristics due to nanomodification of rice straw recycled biochar. An environmentally friendly technology for concrete manufacture was obtained, using agricultural waste, rice straw, as its components, developing a composition of concrete nanomodified with processed rice straw biochar, identifying the dependences of concrete properties on their nanomodification with processed rice straw coal. It has been established that the most effective dosage is the addition of rice straw biochar in the amount of 6% by weight of cement. The improvement in the properties of concrete was expressed in the increase in its physical and mechanical characteristics and changes in deformability according to the results of the analysis of the stress-strain diagrams. The increase in strength characteristics ranged from 17% to 25%. The modulus of elasticity increased to 14%. The deformation characteristics decreased from 12% to 24%. Introducing a finely dispersed additive of rice straw biochar modified by the electromagnetic method leads to a decrease in cement consumption by up to 10%.

Some of the primary problems of construction are brittleness and low the mechanical properties of good thermal insulation materials. Heat-insulating foam concrete has a low thermal conductivity. However, it is practically impossible to transport it over long distances since corners are cracked during transportation, the structure is broken, and, in principle, the fragility of this material is a big problem for modern buildings. The purpose of this study was to develop a heat-insulating foam concrete with improved characteristics by experimentally selecting the optimal dosage of polypropylene fiber and a nanomodifying microsilica additive. Standard methods for determining the characteristics of fiber foam concrete were used as well as the method of optical microscopy to study the structure of the composite. It has been established that the use of polypropylene fiber with the optimal reinforcement range from 1% to 3% allows us to achieve an improvement in the mechanical and physical characteristics of fiber foam concrete. The optimal dosage of the nanomodifier introduced instead of a part of the binder (10%) and polypropylene fiber (2%) by weight of the binder was determined. The maximum values of increments in mechanical characteristics were 44% for compressive strength and 73% for tensile strength in bending. The values of the thermal conductivity coefficient at optimal dosages of the nanomodifier and fiber decreased by 9%. The absence of microcracking at the phase boundary between the polypropylene fiber and the hardened cement–sand matrix due to nanomodification was noted.

One of the unifying factors for all countries is the large consumption of chicken, and other, eggs in food and other types of economic activity. After using various types of eggs for their intended purpose, a large amount of waste accumulates in the form of eggshells. Currently, this problem exists and needs a non-trivial, original solution. The aim of the work was to fill the scientific gap in the direction of studying the microstructure formation of improved nano-modified environmentally-friendly concrete based on eggshell powder and obtaining a concrete composition for the manufacture of an industrial sample of such a material. An environmentally-friendly concrete was obtained, the characteristics of which were improved relative to standard concrete by modifying it with eggshell powder, for which the optimal dosage was determined. The most effective was the replacement of part of the cement with eggshell powder in the amount of 10%. The maximum increase in strength characteristics ranged from 8% to 11%. The modulus of elasticity increased by 4% compared to the control samples without eggshell powder. The maximum reduction in deformations under axial compression and tension in comparison with the control values ranged from 5% to 10%. The study of the composite’s microstructure nano-modified with eggshell powder, and an analysis of the changes occurring in this microstructure due to nano-modification, confirmed the improvement in characteristics and the optimal dosage of eggshell powder.

The determination of mechanical properties for different building materials is a highly relevant and practical field of application for machine learning (ML) techniques within the construction sector. When working with vibrocentrifuged concrete products and structures, it is crucial to consider factors related to the impact of aggressive environments. Artificial intelligence methods can enhance the prediction of vibrocentrifuged concrete properties through the use of specialized machine learning algorithms for materials’ strength determination. The aim of this article is to establish and evaluate machine learning algorithms, specifically Linear Regression (LR), Support Vector Regression (SVR), Random Forest (RF), CatBoost (CB), for the prediction of compressive strength in vibrocentrifuged concrete under diverse aggressive operational conditions. This is achieved by utilizing a comprehensive database of experimental values obtained in laboratory settings. The following metrics were used to analyze the accuracy of the constructed regression models: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root-Mean-Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R²). The average MAPE in the range from 2% (RF, CB) to 7% (LR, SVR) allowed us to draw conclusions about the possibility of using “smart” algorithms in the development of compositions and quality control of vibrocentrifuged concrete, which ultimately entails the improvement and acceleration of the construction and building materials manufacture. The best model, CatBoost, showed MAE = 0.89, MSE = 4.37, RMSE = 2.09, MAPE = 2% and R² = 0.94.

Promising areas of concrete material science are maximum greening, reducing the carbon footprint, and, at the same time, solving the problems of increasing the cost of raw materials using industrial waste as modifiers for self-compacting concrete mixtures. This study aimed to review, investigate and test from the point of view of theory and practice the possibility of using various industrial types as a nano-modifier in self-compacting concrete with improved performance. The possibility of nano-modification of self-compacting concrete with a complex modifier based on industrial waste has been proved and substantiated theoretically and experimentally. The possibility of improving the technological properties of concrete mixtures using such nanomodifiers was confirmed. The recipe and technological parameters of the process were revealed and their influence on the characteristics of concrete mixes and concretes were expressed and determined. Experimental technological and mathematical dependencies between the characteristics of the technological process and raw materials and the characteristics of concrete mixtures and concretes were determined. The optimization of these parameters was carried out, a theoretical substantiation of the obtained results was proposed, and a quantitative picture was presented, expressed in the increment of the properties of self-compacting concrete mixtures using nano-modifiers from industrial waste concretes based on them. The mobility of the concrete mixture increased by 12%, and the fluidity of the mixture increased by 83%. In relation to the control composition, the concrete strength increased by 19%, and the water resistance of concrete increased by 22%. The ultimate strains decreased by 14%, and elastic modulus increased by 11%.