Structural Mechanics of Engineering Constructions and BuildingsStructural Mechanics of Engineering Constructions and BuildingsСтроительная механика инженерных конструкций и сооружений1815-52352587-8700Peoples’ Friendship University of Russia named after Patrice Lumumba (RUDN University)5120110.22363/1815-5235-2026-22-2-93-104JZQSKWAnalytical and numerical methods of analysis of structuresАналитические и численные методы расчета конструкцийResearch ArticlePrediction of Thermal Stress in Hardening Mass Concrete Structures Using Temperature Monitoring DataПрогнозирование температурных напряжений в твердеющих массивных монолитных конструкциях по данным мониторинга температурhttps://orcid.org/0009-0001-6399-401X8808-2687TyurinaVasilina S.ТюринаВасилина Сергеевна

Candidate of Technical Sciences, Associate Professor of the Department of Structural Mechanics and Theory of Structures

кандидат технических наук, доцент кафедры строительной механики и теории сооружений

vasilina.93@mail.ruhttps://orcid.org/0000-0002-9133-85467149-7981ChepurnenkoAnton S.ЧепурненкоАнтон Сергеевич

Doctor of Technical Sciences, Professor of the Department of Structural Mechanics and Theory of Structures

доктор технических наук, профессор кафедры строительной механики и теории сооружений

anton_chepurnenk@mail.ruhttps://orcid.org/0000-0002-5205-14465970-5350YazyevBatyr M.ЯзыевБатыр Меретович

Doctor of Technical Sciences, Professor of the Department of Structural Mechanics and Theory of Structures

доктор технических наук, профессор кафедры строительной механики и теории сооружений

ps62@yandex.ruDon State Technical UniversityДонской государственный технический университет080720262229310410072026Copyright ©; 2026, Tyurina V.S., Chepurnenko A.S., Yazyev B.M.Copyright ©; 2026, Тюрина В.С., Чепурненко А.С., Языев Б.М.2026Tyurina V.S., Chepurnenko A.S., Yazyev B.M.Тюрина В.С., Чепурненко А.С., Языев Б.М.https://creativecommons.org/licenses/by-nc/4.0https://journals.rudn.ru/structural-mechanics/article/view/51201

Thermal stress during the hardening of mass concrete structures is a significant risk factor for early cracking, which directly impacts the durability and load-bearing capacity of buildings and structures. Simplified calculation methods based on hypotheses about the pattern of temperature and stress distributions often demonstrate low accuracy, necessitating the search for more advanced approaches to stress state prediction. This paper proposes a method for predicting the thermal stress in mass concrete foundation slabs based on artificial neural networks (ANNs) using real-time temperature monitoring data. Three ANN architectures were investigated: recurrent, feedforward, and cascade. A comprehensive dataset, including 499,800 records obtained from parametric finite element calculations, was compiled for training. The models demonstrated high prediction accuracy, with the feedforward neural network achieving the best result, with a mean-square error of 0.025 MPa². Verification using experimental data confirmed the practical applicability of the approach, including the ability to predict the timing of crack formation. The developed method enables efficient and less computationally expensive analysis of temperature monitoring data in real time compared to traditional modeling, thereby improving the reliability of building structures.

Температурные напряжения в процессе твердения массивных монолитных конструкций являются значимым фактором риска раннего трещинообразования, что напрямую влияет на долговечность и несущую способность зданий и сооружений. Упрощенные методы расчета, основанные на гипотезах о характере распределения температур и напряжений, часто демонстрируют невысокую точность, что актуализирует поиск более совершенных подходов к прогнозированию напряжённого состояния. Авторами предложен метод прогнозирования температурных напряжений в массивных монолитных фундаментных плитах на основе искусственных нейронных сетей (ИНС) с использованием данных мониторинга температур в режиме реального времени. Для этого были исследованы три архитектуры ИНС - рекуррентная, прямого распространения и каскадная. В целях обучения сформирован обширный датасет, включающий 499 800 записей, полученных на основе параметрических конечно-элементных расчётов. Модели продемонстрировали высокую точность предсказания, при этом наилучший результат показала нейросеть прямого распространения со среднеквадратической ошибкой 0,025 МПа². Верификация на экспериментальных данных подтвердила практическую применимость подхода, включая способность прогнозировать момент образования трещин. Разработанный метод позволяет эффективно и с меньшими вычислительными затратами, по сравнению с традиционным моделированием, анализировать данные мониторинга температур в реальном времени, что способствует повышению надёжности строительных конструкций.

mass concrete structuresfoundation slabthermal stressesmachine learningmonitoringearly crack formationмассивные монолитные конструкциифундаментная плитатемпературные напряжениямашинное обучениемониторингранее трещинообразованиеИсследование выполнено за счет гранта Российского научного фонда № 25-19-00164, https://rscf.ru/project/25-19-00164/The study was supported by the grant of the Russian Science Foundation No. 25-19-00164, https://rscf.ru/project/25-19-00164/Safiuddin M, Kaish ABM, Woon C-O, Raman SN. Early-age cracking in concrete: causes, consequences, remedial measures, and recommendations. Applied Sciences. 2018;8(10):1730. https://doi.org/10.3390/app8101730.Safiuddin M., Kaish A.B.M., Woon C.-O., Raman S.N. Early-age cracking in concrete: causes, consequences, remedial measures, and recommendations // Applied Sciences. 2018. Vol. 8. No. 10. Article no. 1730. https://doi.org/10.3390/app8101730Klemczak B, Batog M, Pilch M, Żmij A. Analysis of cracking risk in early age mass concrete with different aggregate types. Procedia engineering. 2017;193:234–241. https://doi.org/10.1016/j.proeng.2017.06.209Klemczak B., Batog M., Pilch M., Żmij A. Analysis of cracking risk in early age mass concrete with different aggregate types // Procedia engineering. 2017. Vol. 193. P. 234-241. https://doi.org/10.1016/j.proeng.2017.06.209Mazzoli A, Monosi S, Plescia ES. Evaluation of the early-age-shrinkage of fiber reinforced concrete (FRC) using image analysis methods. Construction and Building Materials. 2015;101:596–601. https://doi.org/10.1016/j.conbuildmat.2015.10.090Mazzoli A., Monosi S., Plescia E.S. Evaluation of the early-age-shrinkage of fiber reinforced concrete (FRC) using image analysis methods // Construction and Building Materials. 2015. Vol. 101. P. 596-601. https://doi.org/10.1016/j.conbuildmat.2015.10.090Waller V, d’Aloı̈a L, Cussigh F, Lecrux S. Using the maturity method in concrete cracking control at early ages. Cement and Concrete Composites. 2004;26(5):589–599. https://doi.org/10.1016/S0958-9465(03)00080-5Waller V., d’Aloı̈a L., Cussigh F., Lecrux S. Using the maturity method in concrete cracking control at early ages // Cement and Concrete Composites. 2004. Vol. 26. No. 5. P. 589-599. https://doi.org/10.1016/S0958-9465(03)00080-5Alos Shepherd D, Dehn F. Experimental study into the mechanical properties of plastic concrete: Compressive strength development over time, tensile strength and elastic modulus. Case Studies in Construction Materials. 2023;19:e02521. https://doi.org/10.1016/j.cscm.2023.e02521 EDN: DAARVNAlos Shepherd D., Dehn F. Experimental study into the mechanical properties of plastic concrete: Compressive strength development over time, tensile strength and elastic modulus // Case Studies in Construction Materials. 2023. Vol. 19. Article no. e02521. https://doi.org/10.1016/j.cscm.2023.e02521 EDN: DAARVNXu J, Shen Z, Yang S, Xie X, Yang Z. Finite element simulation of prevention thermal cracking in mass concrete. International Journal of Computing Science and Mathematics. 2019;10(4):327–339. https://doi.org/10.1504/IJCSM.2019.102691Xu J., Shen Z., Yang S., Xie X., Yang Z. Finite element simulation of prevention thermal cracking in mass concrete // International Journal of Computing Science and Mathematics. 2019. Vol. 10. No. 4. P. 327-339. https://doi.org/10.1504/IJCSM.2019.102691Julia R, Agrela F, Rosales M, López-Alonso M, Cuenca-Moyano G. Execution of large-scale sustainable pavement with recycled materials and eco-hybrid additions to cement. Assessment of Mechanical Behaviour and Life Cycle. Construction and Building Materials. 2025;453:139558. https://doi.org/10.1016/j.conbuildmat.2025.139967 EDN: GOCOWJJulia R., Agrela F., Rosales M., López-Alonso M., Cuenca-Moyano G. Execution of large-scale sustainable pavement with recycled materials and eco-hybrid additions to cement. Assessment of Mechanical Behaviour and Life Cycle // Construction and Building Materials. 2025. Vol. 453. Article no. 139558. https://doi.org/10.1016/j.conbuildmat.2025.139967 EDN: GOCOWJNamatēvs I, Gaigals G, Ozols K. ConMonity: An IoT-Enabled LoRa/LTE-M platform for multimodal, real-time monitoring of concrete curing in construction environments. Sensors. 2026;26:14. https://doi.org/10.3390/s26010014 EDN: CNKAJTNamatēvs I., Gaigals G., Ozols K. ConMonity: An IoT-Enabled LoRa/LTE-M platform for multimodal, real-time monitoring of concrete curing in construction environments // Sensors. 2026. Vol. 26. Article no. 14. https://doi.org/10.3390/s26010014 EDN: CNKAJTAniskin NA, Chuc NT, Khanh PK. The use of surface thermal insulation to regulate the temperature regime of a mass concrete during construction. Power Technology and Engineering. 2021;55(1):1–7. https://doi.org/10.1007/s10749-021-01310-6 EDN: TSLLPNAniskin N.A., Chuc N.T., Khanh P.K. The use of surface thermal insulation to regulate the temperature regime of a mass concrete during construction // Power Technology and Engineering. 2021. Vol. 55. No. 1. P. 1-7. https://doi.org/10.1007/s10749-021-01310-6 EDN: TSLLPNTyurina V, Chepurnenko A, Tkachev D. A simplified method for assessing thermal stresses during the construction of massive monolithic foundation slabs based on temperatures at three points. Buildings. 2026;16(1):188. https://doi.org/10.3390/buildings16010188Tyurina V., Chepurnenko A., Tkachev D. A simplified method for assessing thermal stresses during the construction of massive monolithic foundation slabs based on temperatures at three points // Buildings. 2026. Vol. 16. No. 1. Article no. 188. https://doi.org/10.3390/buildings16010188Liu L, Zhao S, Xin J, Wang Z. Simplified analysis of thermal cracks in low–heat Portland cement concrete. Advances in Civil Engineering. 2022;2022:7630568. https://doi.org/10.1155/2022/7630568 EDN: IQXPLSLiu L., Zhao S., Xin J., Wang Z. Simplified analysis of thermal cracks in low - heat Portland cement concrete // Advances in Civil Engineering. 2022. Vol. 2022. Article no. 7630568. https://doi.org/10.1155/2022/7630568 EDN: IQXPLSAniskin NA, Nguyen TC. Predictive model of temperature regimes of a concrete gravity dam during construction: Reducing cracking risks. Buildings. 2023;13(8):1954. https://doi.org/10.3390/buildings13081954 EDN: LFQTEGAniskin N.A., Nguyen T.C. Predictive model of temperature regimes of a concrete gravity dam during construction: Reducing cracking risks // Buildings. 2023. Vol. 13. No. 8. Article no. 1954. https://doi.org/10.3390/buildings13081954 EDN: LFQTEGNguyen CT, Luu X.B. Reducing temperature difference in mass concrete by surface insulation. Magazine of Civil Engineering. 2019;4(88):70–79. https://doi.org/10.18720/MCE.88.7 EDN: HHFAQQNguyen C.T., Luu X.B. Reducing temperature difference in mass concrete by surface insulation // Magazine of Civil Engineering. 2019. Vol. 4. No. 88. P. 70-79. https://doi.org/10.18720/MCE.88.7 EDN: HHFAQQVan Lam T, Nguen CC, Bulgakov BI, Anh PN. Composition calculation and cracking estimation of concrete at early ages. Magazine of Civil Engineering. 2018;82:13. https://doi.org/10.18720/MCE.82.13 EDN: YZNUZVVan Lam T., Nguen C.C., Bulgakov B.I., Anh P.N.Composition calculation and cracking estimation of concrete at early ages // Magazine of Civil Engineering. 2018. Vol. 82. Article no. 13. https://doi.org/10.18720/MCE.82.13 EDN: YZNUZVVan Tran M, La H, Nguyen T. Hybrid machine learning for predicting hydration heat in pipe-cooled mass concrete structures. Construction and Building Materials. 2025;481:141558. https://doi.org/10.1016/j.conbuildmat.2025.141558 EDN: OTLQKBVan Tran M., La H., Nguyen T. Hybrid machine learning for predicting hydration heat in pipe-cooled mass concrete structures // Construction and Building Materials. 2025. Vol. 481. Article no. 141558. https://doi.org/10.1016/j.conbuildmat. 2025.141558 EDN: OTLQKBSargam Y, Wang K, Cho I.H. Machine learning based prediction model for thermal conductivity of concrete. Journal of Building Engineering. 2021;34:101956. https://doi.org/10.1016/j.jobe.2020.101956 EDN: RIIOZESargam Y., Wang K., Cho I.H. Machine learning based prediction model for thermal conductivity of concrete // Journal of Building Engineering. 2021. Vol. 34. Article no. 101956. https://doi.org/10.1016/j.jobe.2020.101956 EDN: RIIOZETuvayanond W, Kamchoom V, Prasittisopin L. Efficient machine learning for strength prediction of ready-mix concrete production (prolonged mixing). Construction innovation. 2026;26(2):369–394. https://doi.org/10.1108/CI-09-2023-0240 EDN: TEFJHHTuvayanond W., Kamchoom V., Prasittisopin L. Efficient machine learning for strength prediction of ready-mix concrete production (prolonged mixing) // Construction innovation. 2026. Vol. 26. No. 2. P. 369-394. https://doi.org/10.1108/CI-09-2023-0240 EDN: TEFJHHChou JS, Tsai CF, Pham AD, Lu YH. Machine learning in concrete strength simulations: Multi-nation data analytics. Construction and Building materials. 2014;73:771–780. https://doi.org/10.1016/j.conbuildmat.2014.09.054Chou J.S., Tsai C.F., Pham A.D., Lu Y.H. Machine learning in concrete strength simulations: Multi-nation data analytics // Construction and Building materials. 2014. Vol. 73. P. 771-780. https://doi.org/10.1016/j.conbuildmat.2014.09.054Klemczak B, Bąba D, Siddique R. Machine Learning-Based Prediction of Heat Transfer and Hydration-Induced Temperature Rise in Mass Concrete. Energies. 2025;18(17):4673. https://doi.org/10.3390/en18174673 EDN: ZVWFTYKlemczak B., Bąba D., Siddique R. Machine learning-based prediction of heat transfer and hydration-induced temperature rise in mass concrete // Energies. 2025. Vol. 18. No. 17. Article no. 4673. https://doi.org/10.3390/en18174673 EDN: ZVWFTYDo TA, Le BA. Machine learning approach for predicting early-age thermal cracking potential in concrete bridge piers. Forces in Mechanics. 2024;17:100297. https://doi.org/10.1016/j.finmec.2024.100297 EDN: STXYTPDo T.A., Le B.A. Machine learning approach for predicting early-age thermal cracking potential in concrete bridge piers // Forces in Mechanics. 2024. Vol. 17. Article no. 100297. https://doi.org/10.1016/j.finmec.2024.100297 EDN: STXYTPShahrokhishahraki M, Malekpour M, Mirvalad S, Faraone G. Machine learning predictions for optimal cement content in sustainable concrete constructions. Journal of Building Engineering. 2024;82:108160. https://doi.org/10.1016/j.jobe.2023.108160 EDN: THDUVMShahrokhishahraki M., Malekpour M., Mirvalad S., Faraone G. Machine learning predictions for optimal cement content in sustainable concrete constructions // Journal of Building Engineering. 2024. Vol. 82. Article no. 108160. https://doi.org/10.1016/j.jobe.2023.108160 EDN: THDUVMSun G, Du M, Shan B, Shi J, Qu Y. Ultra-high performance concrete design method based on machine learning model and steel slag powder. Case Studies in Construction Materials. 2022;17:e01682. https://doi.org/10.1016/j.cscm.2022.e01682 EDN: PNYATBSun G., Du M., Shan B., Shi J., Qu Y. Ultra-high performance concrete design method based on machine learning model and steel slag powder // Case Studies in Construction Materials. 2022. Vol. 17. Article no. e01682. https://doi.org/10.1016/j.cscm.2022.e01682 EDN: PNYATBForsdyke JC, Zviazhynski B, Lees JM, Conduit GJ. Probabilistic selection and design of concrete using machine learning. Data-Centric Engineering. 2023;4:e9. https://doi.org/10.1017/dce.2023.5 EDN: VLTCTAForsdyke J.C., Zviazhynski B., Lees J.M., Conduit G.J. Probabilistic selection and design of concrete using machine learning // Data-Centric Engineering. 2023. Vol. 4. Article no. e9. https://doi.org/10.1017/dce.2023.5 EDN: VLTCTALi Z, Yoon J, Zhang R, Rajabipour F, Srubar III WV, Dabo I, Radlińska A. Machine learning in concrete science: applications, challenges, and best practices. npj Computational Materials. 2022;8(1):127. https://doi.org/10.1038/s41524-022-00810-x EDN: BSEOLVLi Z., Yoon J., Zhang R., Rajabipour F., Srubar III W.V., Dabo I., Radlińska A. Machine learning in concrete science: applications, challenges, and best practices // npj Computational Materials. 2022. Vol. 8. No. 1. Article no.127. https://doi.org/10.1038/s41524-022-00810-x EDN: BSEOLVNesvetaev GV, Koryanova YuI. Forecasting the strength gaining kinetics of the concrete hardening in the abnormal conditions. Modern Trends in Construction, Urban and Territorial Planning. 2023;2(4):59–68. (In Russ.) https://doi.org/10.23947/2949-1835-2023-2-4-59-68 EDN: UAIZPO Несветаев Г.В., Корянова Ю.И. Прогноз кинетики прочности бетона при твердении в условиях, отличных от нормальных // Современные тенденции в строительстве, градостроительстве и планировке территорий. 2023. Т. 2. № 4. С. 59–68. https://doi.org/10.23947/2949-1835-2023-2-4-59-68 EDN: UAIZPOНесветаев Г.В., Корянова Ю.И. Прогноз кинетики прочности бетона при твердении в условиях, отличных от нормальных // Современные тенденции в строительстве, градостроительстве и планировке территорий. 2023. Т. 2. № 4. С. 59-68. https://doi.org/10.23947/2949-1835-2023-2-4-59-68 EDN: UAIZPOChepurnenko A, Nesvetaev G, Koryanova Y. Modeling non-stationary temperature fields when constructing mass cast-in-situ reinforced-concrete foundation slabs. Architecture and Engineering. 2022;7(2):66–78. https://doi.org/10.23968/2500-0055-2022-7-2-66-78 EDN: AKGXYNChepurnenko A., Nesvetaev G., Koryanova Y. Modeling non-stationary temperature fields when constructing mass cast-in-situ reinforced-concrete foundation slabs // Architecture and Engineering. 2022. Vol. 7. No. 2. P. 66-78. https://doi.org/10.23968/2500-0055-2022-7-2-66-78 EDN: AKGXYNChepurnenko AS, Nesvetaev GV, Koryanova YI, Yazyev BM. Simplified model for determining the stressstrain state in massive monolithic foundation slabs during construction. International Journal for Computational Civil and Structural Engineering. 2022;18(3):126–136. https://doi.org/10.22337/2587-9618-2022-18-3-126-136 EDN: RQQYSKChepurnenko A.S., Nesvetaev G.V., Koryanova Y.I., Yazyev B.M. Simplified model for determining the stressstrain state in massive monolithic foundation slabs during construction // International Journal for Computational Civil and Structural Engineering. 2022. Vol. 18. No. 3. P. 126-136. https://doi.org/10.22337/2587-9618-2022-18-3-126-136 EDN: RQQYSKChepurnenko AS, Nesvetaev GV, Koryanova YuI, Shut VV, Tyurina VS. Experience of concreting a massive monolithic foundation slab. Construction Materials and Products. 2025;8(5):2. https://doi.org/10.58224/2618-7183-2025-8-5-2 EDN: ECAUPOChepurnenko A.S., Nesvetaev G.V., Koryanova Yu.I., Shut V.V., Tyurina V.S. Experience of concreting a massive monolithic foundation slab // Construction Materials and Products. 2025. Vol. 8. No. 5. P. 2. https://doi.org/10.58224/2618-7183-2025-8-5-2 EDN: ECAUPOChepurnenko A, Turina V. Simplified Method for Determining Thermal Stresses during the Construction of Massive Monolithic Foundation Slabs. CivilEng. 2023;4(3):740–752. https://doi.org/10.3390/civileng4030042 EDN: PBHJUBChepurnenko A., Turina V. Simplified method for determining thermal stresses during the construction of massive monolithic foundation slabs // CivilEng. 2023. Vol. 4. No. 3. P. 740-752. https://doi.org/10.3390/civileng4030042 EDN: PBHJUBSmolana A, Klemczak B, Azenha M, Schlicke D. Thermo-mechanical analysis of mass concrete foundation slabs at early age — essential aspects and experiences from the FE modelling. Materials. 2022;15(5):1815. https://doi.org/10.3390/ma15051815 EDN: SNFMFCSmolana A., Klemczak B., Azenha M., Schlicke D. Thermo-mechanical analysis of mass concrete foundation slabs at early age - essential aspects and experiences from the FE modeling // Materials. 2022. Vol. 15. No. 5. Article no.1815. https://doi.org/10.3390/ma15051815 EDN: SNFMFC