concconcЖелезобетонные конструкцииReinforced concrete structures2949-16222949-1614Национальный исследовательский Московский государственный строительный университет10.22227/2949-1622.2026.3.78-99concconc-104Research ArticleКОМПЬЮТЕРНОЕ МОДЕЛИРОВАНИЕ В СТРОИТЕЛЬСТВЕCOMPUTER MODELLING IN CONSTRUCTIONВозможности использования искусственного интеллекта для расчета железобетонных конструкцийPotential of Artificial Intelligence in the Analysis and Design of Reinforced Concrete Structureshttps://orcid.org/0000-0001-6292-0759МацеевичТ. А.MatseevichT. A.

Татьяна Анатольевна Мацеевич, доктор физико-математических наук, доцент, профессор кафедры железобетонных и каменных конструкций

129337, г. Москва, Ярославское шоссе, д. 26

Scopus: 51461741900, ResearcherID: AAB-2742-2020

Tatyana A. Matseevich, Doctor of Physical and Mathematical Sciences, Associate Professor, Professor of the Department of Reinforced Concrete and Masonry Structures

26 Yaroslavskoe shosse, Moscow, 129337

Scopus: 51461741900, ResearcherID: AAB-2742-2020

MatseevichTA@mgsu.ruhttps://orcid.org/0000-0002-6697-3388СавинС. Ю.SavinS. Yu.

Сергей Юрьевич Савин, кандидат технических наук, доцент, доцент кафедры железобетонных и каменных конструкций

129337, г. Москва, Ярославское шоссе, д. 26

Scopus: 57052453700, ResearcherID: M-8375-2016

Sergei Yu. Savin, Candidate of Technical Sciences, Associate Professor, Associate Professor of the Department of Reinforced Concrete and Masonry Structures

26 Yaroslavskoe shosse, Moscow, 129337

Scopus: 57052453700, ResearcherID: M-8375-2016

suwin@yandex.ruhttps://orcid.org/0000-0001-7740-9400ШапошниковаЮ. А.ShaposhnikovaYu. A.

Юлия Александровна Шапошникова, кандидат технических наук, доцент, доцент кафедры железобетонных и каменных конструкций

129337, г. Москва, Ярославское шоссе, д. 26

Scopus: 57190858958, ResearcherID: P-8986-2018

Yulia A. Shaposhnikova, Candidate of Technical Sciences, Associate Professor, Associate Professor of the Department of Reinforced Concrete and Masonry Structures

26 Yaroslavskoe shosse, Moscow, 129337

Scopus: 57190858958, ResearcherID: P-8986-2018

yuliatalyzova@yandex.ruhttps://orcid.org/0000-0002-5260-8793МанаенковИ. К.ManaenkovI. K.

Иван Константинович Манаенков, кандидат технических наук, доцент, доцент кафедры железобетонных и каменных конструкций

129337, г. Москва, Ярославское шоссе, д. 26

Scopus: 57209888951, ResearcherID: AAE-1570-2022

Ivan K. Manaenkov, Candidate of Technical Sciences, Associate Professor, Associate Professor of the Department of Reinforced Concrete and Masonry Structures

26 Yaroslavskoe shosse, Moscow, 129337

Scopus: 57209888951, ResearcherID: AAE-1570-2022

manaenkov.i.k@gmail.comhttps://orcid.org/0000-0001-6240-9993ЧерникВ. И.ChernikV. I.

Владимир Игоревич Черник, кандидат технических наук, доцент кафедры железобетонных и каменных конструкций

129337, г. Москва, Ярославское шоссе, д. 26

РИНЦ AuthorID: 1091685, Scopus: 57218420224, ResearcherID: AAD-8260-2022

Vladimir I. Chernik, Candidate of Technical Sciences, Associate Professor of the Department of Reinforced Concrete and Stone Structures

26 Yaroslavskoe shosse, Moscow, 129337

RSCI AuthorID: 1091685, Scopus: 57218420224, ResearcherID: AAD-8260-2022

chernik_vi@mail.ruНациональный исследовательский Московский государственный строительный университет (НИУ МГСУ)РоссияMoscow State University of Civil Engineering (National Research University) (MGSU)Russian Federation2026280820261537899Copyright © Мацеевич Т.А., Савин С.Ю., Шапошникова Ю.А., Манаенков И.К., Черник В.И., 20262026Мацеевич Т.А., Савин С.Ю., Шапошникова Ю.А., Манаенков И.К., Черник В.И.Matseevich T.A., Savin S.Y., Shaposhnikova Y.A., Manaenkov I.K., Chernik V.I.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.g-b-k.ru/jour/article/view/104

В данной обзорно-аналитической статье выполнена систематизация и критический анализ современного состояния исследований по применению машинного обучения для расчета железобетонных конструкций. В работе рассмотрены основные разновидности используемых моделей машинного обучения, проанализированы количественные метрики для оценки качества их предсказаний, а также обсуждены проблемы, связанные с интерпретируемостью результатов, оценкой ошибок и выявлением нелинейных зависимостей. Отдельное внимание уделено существующим пробелам в научном знании в области расчета железобетонных конструкций с использованием моделей машинного обучения, нормативным коллизиям и ограничениям, препятствующим практическому внедрению технологий ИИ в проектирование. На основе проведенного анализа сформулированы перспективные направления дальнейших исследований.

In this review, the current state of research on the use of machine learning for the design of reinforced concrete structures has been systematized and critically analyzed. The paper examines the main types of machine learning models used, analyzes quantitative metrics for assessing the quality of their predictions, and discusses issues related to the interpretability of results, error estimation, and the identification of nonlinear relationships. Special attention is given to existing gaps in scientific knowledge, regulatory conflicts, and limitations that hinder the practical implementation of AI technologies in design. Based on the analysis, promising directions for future research have been identified.

железобетонконструкциярасчетискусственный интеллектмашинное обучениеreinforced concretestructural designstructural analysisartificial intelligencemachine learningReferencesЗахаров Ф.Н., Цзе Ц., И.С. Физически-информированные нейронные сети для задач строительной механики и конструкций: моделирование прогиба однопролетной балки // Железобетонные конструкции. 2025. № 9 (1). С. 35–48. DOI: 10.22227/2949-1622.2025.1.35-48Zakharov F.N., Jie Q., Yi X. Physics-Informed Neural Networks for Structural Mechanics and Construction: Modeling the Deflection of a Single-Span Beam Physics-Informed Neural Networks. Reinforced concrete structures. 2025; 9(1):35-48. DOI: 10.22227/2949-1622.2025.1.35-48 (in Russian).Breiman L. Random forests. Mach Learn. 2001. 45 p. DOI: 10.1023/A:1010933404324Breiman L. Random forests. Mach Learn. 2001; 45. DOI: 10.1023/A:1010933404324Natekin A., Knoll A. Gradient boosting machines : a tutorial // Front Neurorobot. 2013. P. 7. DOI: 10.3389/fnbot.2013.00021Natekin A., Knoll A. Gradient boosting machines : a tutorial. Front Neurorobot. 2013; 7. DOI: 10.3389/fnbot.2013.00021Cortes C., Vapnik V. Support-Vector Networks // Mach Learn. 1995. № 20. DOI: 10.1023/A:1022627411411Cortes C., Vapnik V. Support-Vector Networks. Mach Learn. 1995; 20. DOI: 10.1023/A:1022627411411Sayed Y.A.K., Alzhraa I.A., Tamrazyan A.G., Fahmy M.F.M. Machine-learning-based models versus design-oriented models for predicting the axial compressive load of FRP-confined rectangular RC columns // Engineering Structures. 2023. Vol. 285. Р. 116030. DOI: 10.1016/j.engstruct.2023.116030Sayed Y.A.K., Alzhraa I.A., Tamrazyan A.G., Fahmy M.F.M. Machine-learning-based models versus design-oriented models for predicting the axial compressive load of FRP-confined rectangular RC columns. Engineering Structures. 2023; 285:116030. DOI: 10.1016/j.engstruct.2023.116030Mustafa R., Ahmad M.T. Appraisal of numerous machine learning techniques for the prediction of axial load carrying capacity of rectangular concrete column // Asian J Civ Eng. 2024. Vol. 25. Рр. 4471–4486. DOI: 10.1007/s42107-024-01060-6Mustafa R., Ahmad M.T. Appraisal of numerous machine learning techniques for the prediction of axial load carrying capacity of rectangular concrete column. Asian J Civ Eng. 2024; 25:4471-4486. DOI: 10.1007/s42107-024-01060-6Couto C., Tong Q., Gernay T. Predicting the Capacity of Thin-Walled Beams at Elevated Temperature with Machine Learning // Fire Saf J. 2022. Vol. 130. DOI: 10.1016/j.firesaf.2022.103596Couto C., Tong Q., Gernay T. Predicting the Capacity of Thin-Walled Beams at Elevated Temperature with Machine Learning. Fire Saf J. 2022; 130. DOI: 10.1016/j.firesaf.2022.103596Fu F. Fire Induced Progressive Collapse Potential Assessment of Steel Framed Buildings Using Machine Learning // J Constr Steel Res. 2020. Vol. 166. DOI: 10.1016/j.jcsr.2019.105918Fu F. Fire Induced Progressive Collapse Potential Assessment of Steel Framed Buildings Using Machine Learning. J Constr Steel Res. 2020; 166. DOI: 10.1016/j.jcsr.2019.105918Zhu Y.F., Yao Y., Huang Y., Chen C.H., Zhang H.Y., Huang Z. Machine Learning Applications for Assessment of Dynamic Progressive Collapse of Steel Moment Frames // Structures. 2022. Р. 36. DOI: 10.1016/j.istruc.2021.12.067Zhu Y.F., Yao Y., Huang Y., Chen C.H., Zhang H.Y., Huang Z. Machine Learning Applications for Assessment of Dynamic Progressive Collapse of Steel Moment Frames. Structures. 2022; 36. DOI: 10.1016/j.istruc.2021.12.067Das O. Prediction of the Natural Frequencies of Various Beams Using Regression Machine Learning Models // Sigma Journal of Engineering and Natural Sciences. 2023. Vol. 41. DOI: 10.14744/sigma.2023.00040Das O. Prediction of the Natural Frequencies of Various Beams Using Regression Machine Learning Models. Sigma Journal of Engineering and Natural Sciences. 2023; 41. DOI: 10.14744/sigma.2023.00040Ншимиримана Ж.Д., Эльшейх А.М. Автоматизация армирования железобетонных конструкций с помощью технологии информационного моделирования и визуального программирования // Вестник евразийской науки. 2025. Т. 17. № 2. URL: https://esj.today/PDF/36SAVN225.pdfNshimirimana Zh.D., Elsheikh A.M. Automation of Reinforcement of Reinforced Concrete Structures Using Building Information Modeling and Visual Programming Technology. Bulletin of Eurasian Science. 2025; 17:2. URL: https://esj.today/PDF/36SAVN225.pdf (in Russian).Фомин Н.И., Исупов Н.С. Оценка качества компоновки несущих конструкций с применением технологии генеративного проектирования // Вестник евразийской науки. 2024. Т. 16. № 5. URL: https://esj.today/PDF/54SAVN524.pdfFomin N.I., Isupov N.S. Assessment of the Quality of Arrangement of Load-Bearing Structures Using Generative Design Technology. Bulletin of Eurasian Science. 2024; 16:5. URL: https://esj.today/PDF/54SAVN524.pdf (in Russian).Tahmassebi A., Motamedi M., Alavi A.H., Gandomi A.H. An explainable prediction framework for engineering problems: case studies in reinforced concrete members modeling // Journal of Engineering Computations. 2021. URL: https://opus.lib.uts.edu.au/bitstream/10453/167687/2/Engineering_Computations_RC_Failures_XGB_SHAP%20%281%29%20%281%29.pdfTahmassebi A., Motamedi M., Alavi A.H., Gandomi A.H. An explainable prediction framework for engineering problems: case studies in reinforced concrete members modeling. Journal of Engineering Computations. 2021. URL: https://opus.lib.uts.edu.au/bitstream/10453/167687/2/Engineering_Computations_RC_Failures_XGB_SHAP%20%281%29%20%281%29.pdfVarghese S., Anand R., Paliwal G. Physics-Informed Neural Network for Concrete Manufacturing Process Optimization // Computer Science. Machine Learning. 2024. DOI: 10.48550/arXiv.2408.14502Varghese S., Anand R., Paliwal G. Physics-Informed Neural Network for Concrete Manufacturing Process Optimization. Computer Science. Machine Learning. 2024. DOI: 10.48550/arXiv.2408.14502Ke Y., Liu C.W., Zhang S.S. Physics-informed neural network (PINN)-based numerical simulation of concrete mechanical responses // Engineering Structures. 2026. Vol. 350. Р. 121982. DOI: 10.1016/j.engstruct.2025.121982Ke Y., Liu C.W., Zhang S.S. Physics-informed neural network (PINN)-based numerical simulation of concrete mechanical responses. Engineering Structures. 2026; 350:121982. DOI: 10.1016/j.engstruct.2025.121982Qi Y., Ding Z., Luo Y., Ma Z. A Three-Step Computer Vision-Based Framework for Concrete Crack Detection and Dimensions Identification // Buildings. 2024. No. 14. Р. 2360. DOI: 10.3390/buildings14082360Qi Y., Ding Z., Luo Y., Ma Z. A Three-Step Computer Vision-Based Framework for Concrete Crack Detection and Dimensions Identification. Buildings. 2024; 14:2360. DOI: 10.3390/buildings14082360Kong X., Smyl D. Investigation of the condominium building collapse in Surfside, Florida: A video feature tracking approach // Structures. 2022. Vol. 43. Рр. 533–545. DOI: 10.1016/j.istruc.2022.06.009Kong X., Smyl D. Investigation of the condominium building collapse in Surfside, Florida: A video feature tracking approach. Structures. 2022; 43:533-545. DOI: 10.1016/j.istruc.2022.06.009Savin S.Yu., Sharipov M.Z. Nonlinear visco-elastic behavior of concrete under static-dynamic loading: Experimental and numerical studies // Structures. 2025. Vol. 74. Р. 108496.Savin S.Yu., Sharipov M.Z. Nonlinear visco-elastic behavior of concrete under static-dynamic loading: Experimental and numerical studies. Structures. 2025; 74:108496.Reklaitis G.V., Ravindran A., Ragsdell K.M. Engineering Optimization: Methods and Applications. John Wiley & Sons, 2006.Reklaitis G.V., Ravindran A., Ragsdell K.M. Engineering Optimization: Methods and Applications. John Wiley & Sons, 2006.Pan X., Yang T.T.Y., Li J. et al. A review of recent advances in data-driven computer vision methods for structural damage evaluation: algorithms, applications, challenges, and future opportunities // Arch Computat Methods Eng. 2025. Vol. 32. Pp. 4587–4619. DOI: 10.1007/s11831-025-10279-8Pan X., Yang T.T.Y., Li J. et al. A review of recent advances in data-driven computer vision methods for structural damage evaluation: algorithms, applications, challenges, and future opportunities. Arch Computat Methods Eng. 2025; 32:4587-4619. DOI: 10.1007/s11831-025-10279-8Song Y., Zhang Q., Su Y., Zhang S., Wang R., Zhang W., Bi Z., Yu Y. Advances in crack dataset development and deep learning-based detection models // Journal of Building Engineering. 2025. Vol. 116. Р. 114734.Song Y., Zhang Q., Su Y., Zhang S., Wang R., Zhang W., Bi Z., Yu Y. Advances in crack dataset development and deep learning-based detection models. Journal of Building Engineering. 2025; 116:114734.Hassouna M., Marzouk M., Fathalla E. Automated low-cost framework for crack measurements in RC structures using deep learning approach. 2026. Р. 14678. DOI: 10.1038/s41598-026-50880-wHassouna M., Marzouk M., Fathalla E. Automated low-cost framework for crack measurements in RC structures using deep learning approach. 2026; 14678. DOI: 10.1038/s41598-026-50880-wKemal H., Serhat D. Deep Learning-Based Automated Crack Detection for Post-Earthquake Damage Assessment in Reinforced Concrete Structures // Advances in Civil Engineering. 2026. Р. 6845779. DOI: 10.1155/adce/6845779Kemal H., Serhat D. Deep Learning-Based Automated Crack Detection for Post-Earthquake Damage Assessment in Reinforced Concrete Structures. Advances in Civil Engineering. 2026; 6845779. DOI: 10.1155/adce/6845779Левин Р., Дранг Д., Эделсон Б. Практическое введение в технологию искусственного интеллекта и экспертных систем с иллюстрациями на Бейсике / пер. с англ.; предисл. М.Л. Сальникова, Ю.В. Сальниковой. М. : Финансы и статистика, 1990. 239 с.Levin R., Drang D., Edelson B. Practical Introduction to Artificial Intelligence and Expert Systems Technology with Illustrations in BASIC. Translated from English. Preface by M.L. Salnikov, Yu.V. Salnikova. Moscow, Finansy i statistika, 1990; 239. (in Russian).Римшин В.И., Трунтов П.С., Молчанова А.Е. Методы применения искусственного интеллекта при моделировании напряженно-деформированного состояния усиленных конструкций // Вестник Поволжского государственного технологического университета. Серия «Материалы. Конструкции. Технологии». 2023. № 3 (27). С. 45–54. DOI: 10.25686/2542-114X.2023.3.45Rimshin V.I., Truntov P.S., Molchanova A.E. Methods of Applying Artificial Intelligence in Modeling the Stress-Strain State of Strengthened Structures. Bulletin of the Volga State Technological University. Series "Materials. Structures. Technologies". 2023; 3(27):45-54. DOI: 10.25686/2542-114X.2023.3.45 (in Russian).Li C. et al. Physics-Informed Gaussian Process Regression for the Constitutive Modeling of Concrete: A Data-Driven Improvement to Phenomenological Models // arXiv. Preprint, 2026. URL: https://arxiv.org/abs/2601.03367Li C. et al. Physics-Informed Gaussian Process Regression for the Constitutive Modeling of Concrete: A Data-Driven Improvement to Phenomenological Models. arXiv. Preprint, 2026. URL: https://arxiv.org/abs/2601.03367Guo X., Song Zh. Review on crack monitoring technology based on physics-informed neural networks // Jixie Qiangdu (Mechanical Strength). 2025. Vol. 47. Рр. 18–30. DOI: 10.16579/j.issn.1001.9669.2025.12.002Guo X., Song Zh. Review on crack monitoring technology based on physics-informed neural networks. Jixie Qiangdu (Mechanical Strength). 2025; 47:18-30. DOI: 10.16579/j.issn.1001.9669.2025.12.002Saeed H.M. et al. Recent Advances of Machine Learning in Fracture Mechanics of Quasi-Brittle Materials : a Review // Jurnal Kejuruteraan. 2025. No. 37 (7). Pp. 3151–3172. DOI: 10.17576/jkukm-2025-37(7)-06Saeed H.M. et al. Recent Advances of Machine Learning in Fracture Mechanics of Quasi-Brittle Materials : a Review. Jurnal Kejuruteraan. 2025; 37(7):3151-3172. DOI: 10.17576/jkukm-2025-37(7)-06Baniya S., Maity D. A comprehensive review of theoretical concepts and advancements in physics-informed neural networks with applications in structural engineering // Artificial Intelligence Review. 2025. Vol. 59. No. 49. DOI: 10.1007/s10462-025-11444-yBaniya S., Maity D. A comprehensive review of theoretical concepts and advancements in physics-informed neural networks with applications in structural engineering. Artificial Intelligence Review. 2025; 59:49. DOI: 10.1007/s10462-025-11444-yVarghese S., Anand R., Paliwal G. Physics-Informed Neural Network for Concrete Manufacturing Process Optimization // arXiv. 2025. Vol. 2408. Р. 14502. DOI: 10.48550/arXiv.2408.14502Varghese S., Anand R., Paliwal G. Physics-Informed Neural Network for Concrete Manufacturing Process Optimization. arXiv. 2025; 2408:14502. DOI: 10.48550/arXiv.2408.14502Sahin T., Wolff D., von Danwitz M., Popp A. Towards a Hybrid Digital Twin: Fusing Sensor Information and Physics in Surrogate Modeling of a Reinforced Concrete Beam // Proceedings of the 2024 Sensor Data Fusion: Trends, Solutions, Applications (SDF 2024). 2024. DOI: 10.1109/SDF63218.2024.10773885Sahin T., Wolff D., von Danwitz M., Popp A. Towards a Hybrid Digital Twin: Fusing Sensor Information and Physics in Surrogate Modeling of a Reinforced Concrete Beam. Proceedings of the 2024 Sensor Data Fusion: Trends, Solutions, Applications (SDF 2024). 2024. DOI: 10.1109/SDF63218.2024.10773885

The authors declare that there are no conflicts of interest present.