vdgtuВестник Дагестанского государственного технического университета. Технические наукиHerald of Dagestan State Technical University. Technical Sciences2073-61852542-095XDaghestan State Technical University10.21822/2073-6185-2025-52-3-61-70vdgtu-1839Research ArticleИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ И ТЕЛЕКОММУНИКАЦИИINFORMATION TECHNOLOGY AND TELECOMMUNICATIONSАвтоматизация процесса оценки технического состояния наружных стен кирпичных зданий с использованием технологии машинного обученияAutomating the Process of Assessing the Technical Condition of Exterior Walls of Brick Buildings Using Machine LearningКрыловС. А.KrylovS. A.

Сергей Андреевич Крылов - аспирант, кафедра «Строительные конструкции и вычислительная механика».

614990, Пермь, Комсомольский проспект, д. 29

Sergey A. Krylov - Graduate Student, Department of Building Structures and Computational Mechanics.

29 Komsomolsky Ave., Perm 614990

serishca@yandex.ruКашевароваГ. Г.KashevarovaG. G.

Галина Геннадьевна Кашеварова - доктор технических наук, профессор, член-корреспондент РААСН, заведующий кафедрой «Строительные конструкции и вычислительная механика».

614990, Пермь, Комсомольский проспект, д. 29

Galina G. Kashevarova - Dr. Sci.(Eng.), Prof., Corresponding Member of the Russian Academy of Architecture and Construction Sciences, Head of the Department of Building Structures and Computational Mechanics.

29 Komsomolsky Ave., Perm 614990

ggkash@mail.ruПермский национальный исследовательский политехнический университетРоссияPerm National Research Polytechnic UniversityRussian Federation2025101120255236170Copyright © Крылов С.А., Кашеварова Г.Г., 20252025Крылов С.А., Кашеварова Г.Г.Krylov S.A., Kashevarova G.G.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.dgtu.ru/jour/article/view/1839Цель

Цель. Целью работы является разработка программы по определению категории технического состояния зданий с использованием машинного обучения. Задачи работы заключаются в анализе существующих методов машинного обучения, написании кода программы, сборе обучающего набора данных, определение оптимального соотношение параметров обучения, определение наиболее точного алгоритма машинного обучения при заданных параметрах и исходных данных.

Метод

Метод. Исследование основано на методах и алгоритмах диагностирования состояния технических систем с использованием технологии машинного обучения.

Результат

Результат. Результаты исследования показывают, что даже при ограниченном объеме данных программа способна корректно и с высокой точностью определять категории технического состояния, минимизируя риск пропуска аварийных ситуаций, а также подтверждает перспективность применения машинного обучения в строительной диагностике.

Вывод

Вывод. Значимость полученных результатов для строительной отрасли состоит в том, что применение созданной программы позволит увеличить точность и скорость обследования зданий, что в свою очередь повысит их безопасность.

Objective

Objective. The aim of this study is to develop a program for determining the technical condition of buildings using machine learning. The objectives of the study include analyzing existing machine learning methods, writing program code, collecting a training dataset, determining the optimal ratio of training parameters, and determining the most accurate machine learning algorithm for the given parameters and input data.

Method

Method. The study is based on methods and algorithms for diagnosing the condition of technical systems using machine learning technology.

Result

Result. The results demonstrate that even with a limited amount of data, the program is capable of correctly and accurately determining technical condition categories, minimizing the risk of missing emergency situations, and also confirms the potential of using machine learning in construction diagnostics.

Conclusion

Conclusion. The significance of the obtained results for the construction industry is that the use of the developed program will increase the accuracy and speed of building inspections, which in turn will improve their safety.

алгоритмзданиекатегориямашинное обучениетехническое состояниеalgorithmbuildingcategorymachine learningtechnical conditionReferencesКашеварова Г.Г., Тонков Ю.Л., Фурсов М.Н. Нечеткая экспертная система диагностики повреждений строительных конструкций // Вестник Волжского регионального отделения Российской академии архитектуры и строительных наук (ВРО РААСН). 2014. №17. С. 167-173.Kashevarova G.G., Tonkov Y.L., Fursov M.N. Fuzzy expert system for diagnosing damage to building structures. Bulletin of the Volga Regional Branch of the Russian Academy of Architecture and Building Sciences (VRO RAASN). 2014;17: 167-173.Наумов А.Е., Юдин Д.А., Долженко А. В. Совершенствование технологии проведения строительно-технических экспертиз с использованием аппаратно-программного комплекса автоматизированной дефектоскопии // Вестник БГТУ им. В.Г. Шухова. 2019. № 4. С. 61–69. DOI:10.34031/article_5cb824d26344e7.45899508.Naumov A.E., Yudin D.A., Dolzhenko A.V. Improving the technology of conducting construction and technical expertise using a hardware and software complex of automated inspection. Bulletin of BSTU namedafter V.G. Shukhov, 2019;4, 61–69. https://doi.org/10.34031/article_5cb824d26344e7.45899508.Кашеварова Г.Г. «Искусственный интеллект», или «логические рассуждения и разумные решения» в технической диагностике объектов строительства // Academia. Архитектура и строительство. 2023. № 4. С. 166–180. – DOI: 10.22337/2077-9038-2023-4-166-180.Kashevarova G.G. «Artificial Intelligence» or «Logical Discussion and Reasonable Solutions» in Technical Diagnostics of Construction Projects. Academia. Architecture and Construction, 2023;4:166–180. https://doi.org/10.22337/2077-9038-2023-4-166-180.Крылов, С.А. Автоматизация диагностирования причин возникновения дефектов на фасадах кирпичных зданий с применением технологий искусственного интеллекта / С.А. Крылов, Г.Г. Кашеварова // Вестник Пермского национального исследовательского политехнического университета. Прикладная экология. Урбанистика. – 2023. – № 4. – С. 51–62. DOI: 10.15593/2409-5125/2023.04.05Krylov S.A., Kashevarova G.G. Automation of diagnosing the causes of defects on the facades of brick buildings using artificial intelligence technologies. PNRPU Bulletin. Applied ecology. Urban development, 2023; 4, 51-62. https://doi.org/10.15593/2409-5125/2023.04.05.Gbadegeshin, S.A., Al Natsheh, A., Ghafel, K., Tikkanen, J., Gray, A., Rimpiläinen, A., Hirvonen, N. (2021). What is an Artificial intelligence (ai): a simple buzzword or a worthwhile inevitability? In ICERI 2021 Proceeding, 1, 468–479. https://doi.org/10.21125/iceri.2021.0171.Gbadegeshin, S.A., Al Natsheh, A., Ghafel, K., Tikkanen, J., Gray, A., Rimpiläinen, A., Hirvonen, N. What is an artificial intelligence (ai): a simple buzzword or a worthwhile inevitability? In ICERI2021 Proceeding, 2021; 1: 468–479. https://doi.org/10.21125/iceri.2021.0171.Соколов, В.А. Вероятностный анализ технического состояния кирпичных стен зданий старой городской застройки / Соколов В.А. // Безопасность зданий и сооружений. – 2015. № 1(57). -С. 65-73.Sokolov V.A. Probabilistic analysis of the technical state of brick walls of the old city buildings. Safety of buildings and structures, 2015;1 (57): 65-73.Sokolov V.A. (2013). Diagnostics of the technical condition of buildings and structures using methods of fuzzy set theory. Magazine of Civil Engineering, 5, 31-37. https://doi.org/10.18720/MCE.15.4.Sokolov V.A. Diagnostics of the technical condition of buildings and structures using methods of fuzzy set theory. Magazine of Civil Engineering. 2013; 5: 31-37. https://doi.org/10.18720/MCE.15.4.Shtovba S.D., Pankevych O. D. Fuzzy technology-based cause detection of structural cracks of stone buildings. CEUR workshop proceedings, 2108, 209–218Shtovba S.D., Pankevych O.D. 2018 Fuzzy technology-based cause detection of structural cracks of stone buildings. CEUR workshop proceedings, 2105; 209–218.Солдатенко, Т.Н. Модель идентификации и прогноза дефектов строительной конструкции на основе результатов ее обследования / Т. Н. Солдатенко // Инженерно-строительный журнал. – 2011. – № 7 (25). – С. 52–61.Soldatenko T.N. Model of Identification and Prediction of Building Design Defects on the Basis of Its Inspections Results. Magazine of Civil Engineering, 2011;7 (25), 52–61. https://doi.org/10.5862/MCE.25.8.Kashevarova G.G., Tonkov Y.L. (2018). Intelligent technologies in the examination of construction structures. Academia. Architecture and Construction, 1, 92-99. https://doi.org/10.22337/2077-9038-2018-1-92-99.Kashevarova G.G., Tonkov Y.L.Intelligent technologies in the examination of construction structures. Academia. Architecture and Construction, 2018;1:92-99.https://doi.org/10.22337/2077-9038-2018-1-92-99.Кашеварова Г.Г., Тонков Ю.Л. Экспертная система для практической диагностики строительных конструкций // Academia. Архитектура и строительство. – 2022. – № 2. – С. 85-91. https://doi.org/10.22337/2077-9038-2022-1-85-91.Kashevarova G.G., Tonkov Y.L. Expert system for practical diagnostics of building structures. Academia. Architecture and Construction, 2022; 2:85–91. https://doi.org/10.22337/2077-9038-2022-1-85-91.Тарарушкин Е.В.. Применение нечеткой логики для оценки физического износа несущих конструкций зданий // Вестник БГТУ им. В.Г. Шухова. – 2016. – № 10. – С. 77-82. doi.org/10.12737/22032.Tararushkin E.V. Use of fuzzy logic for assessment of damage structures of buildings. Bulletin of BSTU named after V.G. Shukhov, 2016;10:77-82. https://doi.org/10.12737/22032.Кашеварова Г.Г., Платунов В.Ю., Крылов С.А. Определение категории технического состояния строительных конструкций зданий перегрузочных узлов калийных солей на основе многолетнего мониторинга с использованием нейронных сетей. В сборнике. Вестник Приволжского территориального отделения Российской академии архитектуры и строительных наук. Сборник научных трудов. Нижний Новгород, 2024. С. 212-218. eLIBRARY ID: 75131299Kashevarova G.G., Platunov V.Y, Krylov S.A. Multi-task neural network model of classification based on multi-year database of monitoring of technical condition of building structures of transshipment hubs buildings. Bulletin of the Volga Regional Branch of the Russian Academy of Architecture and Building Sciences (VRO RAASN), 2024; 27: 212-218. https://doi.org/ 10.22337/2077-9038-2023-4-166-180.Hosseini, M.A., M. Ravanshadnia, M. Rahimzadegan, and S. Ramezani (2024). Next-generation building condition assessment: BIM and neuralnetwork integration. Journal of Performance of Constructed Facilities, 38 (6). https://doi.org/10.1061/JPCFEV.CFENG-4828.Hosseini, M.A., M. Ravanshadnia, M. Rahimzadegan, and S. Ramezani. Next-generation building condition assessment: BIM and neuralnetwork integration. Journal of Performance of Constructed Facilities, 2024;38(6). https://doi.org/10.1061/JPCFEV.CFENG-4828.Hosseini, M.A., M. Ravanshadnia, M. Rahimzadegan, and S. Ramezani (2024). A robustf model for evaluating defects in building elements. Numerical Methods in Civil Engineering, 9(1). https://doi.org/10.61186/NMCE.2406.1064.Hosseini, M.A., M. Ravanshadnia, M. Rahimzadegan, and S. Ramezani. A robustf model for evaluating defects in building elements. Numerical Methods in Civil Engineering, 2024;9(1). https://doi.org/10.61186/NMCE.2406.1064.Mangalathu, S., Sun, H., Nweke, C.C., Yi, Z., & Burton, H.V. Classifying earthquake damage to buildings using machine learning. Earthquake Spectra, 2020;. 36(1), 183–208. doi.org/10.1177/8755293019878137.Mangalathu, S., Sun, H., Nweke, C.C., Yi, Z., & Burton, H.V. Classifying earthquake damage to buildings using machine learning. Earthquake Spectra, 2020;36(1):183–208. doi.org/10.1177/8755293019878137.Amiri Shahmirani, M.R., Nikghalb Rashti, A.A., Adib Ramezani, M.R., & Golafshani, E.M. (2022). Buildings, Causalities, and Injuries Innovative Fuzzy Damage Model during Earthquakes. Shock and Vibration. https://doi.org/10.1155/2022/4746587.Amiri Shahmirani, M. R., Nikghalb Rashti, A.A., Adib Ramezani, M. R., & Golafshani, E. M. (2022). Buildings, Causalities, and Injuries Innovative Fuzzy Damage Model during Earthquakes. Shock and Vibration. https://doi.org/10.1155/2022/4746587.ГОСТ 31937-2024 (2024). Здания и сооружения. Правила обследования и мониторинга технического состояния [Текст]. – Введ. 2024-05-01. – М. Институт стандартизации, 2024. – 69 с.GOST 31937-2024. Buildings and Structures. Rules for Inspection and Monitoring of Technical Condition. Russian Standardization Institute. Moscow, 2024;69.Бурков А. Машинное обучение без лишних слов / А. Бурков. СПб.: Питер, 2020. — 192 с.Burkov A. The Hundred-Page Machine Learning Book. Piter. Saint Petersburg, 2020; 192.Romeiko, X.X., Zhang, X., Pang, Y., Gao, F., Xu, M., Lin, S., & Babbitt, C. (2024). A review of machine learning applications in life cycle assessment studies. Science of the Total Environment. https://doi.org/10.1016/j.scitotenv.2023.168969.Romeiko, X.X., Zhang, X., Pang, Y., Gao, F., Xu, M., Lin, S., & Babbitt, C. (2024). A review of machine learning applications in life cycle assessment studies. Science of the Total Environment. https://doi.org/10.1016/j.scitotenv.2023.168969.S. Hu, T. Guo., M.S. Alam., Y. Koetaka, E. Ghafoori., Th. L. Karavasilis (2025). Machine learning in earthquake engineering: A review on recent progress and future trends in seismic performance evaluation and design. Engineering Structures. https://doi.org/10.1016/j.engstruct.2025.120721.S. Hu, T. Guo., M.S. Alam., Y. Koetaka, E. Ghafoori., Th.L. Karavasilis (2025). Machine learning in earthquake engineering: A review on recent progress and future trends in seismic performance evaluation and design. Engineering Structures. https://doi.org/10.1016/j.engstruct.2025.120721.Málaga-Chuquitaype, C. (2022). Machine Learning in Structural Design: An Opinionated Review. Frontiers in Built Environment, 8. https://doi.org/10.3389/fbuil.2022.815717.Málaga-Chuquitaype, C. Machine Learning in Structural Design: An Opinionated Review. Frontiers in Built Environment, 2022; 8. https://doi.org/10.3389/fbuil.2022.815717.Kurian, B., & Liyanapathirana, R. (2020). Machine Learning Techniques for Structural Health Monitoring. Proceedings of the 13th International Conference on Damage Assessment of Structures. Lecture Notes in Mechanical Engineering, 3–24. https://doi.org/10.1007/978-981-13-8331-1_1.Kurian, B., & Liyanapathirana, R. Machine Learning Techniques for Structural Health Monitoring. Proceedings of the 13th International Conference on Damage Assessment of Structures. Lecture Notes in Mechanical Engineering, 2020: 3–24. https://doi.org/10.1007/978-981-13-8331-1_1.Soydaner, D. (2020). A Comparison of Optimization Algorithms for Deep Learning. International Journal of Pattern Recognition and Artificial Intelligence, 34 (13). https://doi.org/10.1142/S0218001420520138.Soydaner, D. A Comparison of Optimization Algorithms for Deep Learning. International Journal of Pattern Recognition and Artificial Intelligence, 2020;34(13). doi.org/10.1142/S0218001420520138.Kuzyakin A.P. (2023) Comparative analysis of modern AutoML solutions. Collection of scientific papers of the 26th Russian Scientific Conference, 1. 183-195.Kuzyakin A.P. Comparative analysis of modern AutoML solutions. Collection of scientific papers of the 26th Russian Scientific Conference, 2023; 1:183-195.Ferreira, L., Pilastri, A., Martins, C.M., Pires, P.M., & Cortez, P. (2021). A Comparison of AutoML Tools for Machine Learning, Deep Learning and XGBoost. International Joint Conference on Neural Networks (IJCNN). https://doi.org/10.1109/IJCNN52387.2021.9534091.Ferreira, L., Pilastri, A., Martins, C.M., Pires, P.M., & Cortez, P. A Comparison of AutoML Tools for Machine Learning, Deep Learning and XGBoost. International Joint Conference on Neural Networks (IJCNN). 2021. https://doi.org/10.1109/IJCNN52387.2021.9534091.Akinosho, T.D., Oyedele, L.O., Bilal, M., Ajayi, A.O., Delgado, M.D., Akinade, O.O.; Ahmed, A.A. (2020). Deep learning in the construction industry: A review of present status and future innovations. Journal of Building Engineering, 32. https://doi.org/10.1016/j.jobe.2020.101827.Akinosho, T.D., Oyedele, L.O., Bilal, M., Ajayi, A.O., Delgado, M.D., Akinade, O.O.; Ahmed, A.A. Deep learning in the construction industry: A review of present status and future innovations. Journal of Building Engineering, 2020: 32. https://doi.org/10.1016/j.jobe.2020.101827.Yang, C., Gunay, B., Shi, Z., & Shen, W. (2021). Machine Learning-Based Prognostics for Central Heating and Cooling Plant Equipment Health Monitoring. IEEE Transactions on Automation Science and Engineering, 18 (1), 346–355. https://doi.org/10.1109/TASE.2020.2998586.Yang, C., Gunay, B., Shi, Z., & Shen, W. Machine Learning-Based Prognostics for Central Heating and Cooling Plant Equipment Health Monitoring. IEEE Transactions on Automation Science and Engineering, 2021;18 (1), 346–355. https://doi.org/10.1109/TASE.2020.2998586.Sun, H., Burton, H.V., & Huang, H. (2021). Machine learning applications for building structural design and performance assessment: State-of-the-art review. Journal of Building Engineering. https://doi.org/10.1016/j.jobe.2020.101816.Sun, H., Burton, H.V., & Huang, H. Machine learning applications for building structural design and performance assessment: State-of-the-art review. Journal of Building Engineering. 2021. doi.org/10.1016/j.jobe.2020.101816.Amiri Shahmirani, M.R.; Nikghalb Rashti, A.A.; Adib Ramezani, M.R.; Golafshani, E.M. (2021). Application of fuzzy modelling to predict the earthquake damage degree of buildings based on field data. Journal of Intelligent and Fuzzy Systems, 41 (2), 2717–2730. https://doi.org/10.3233/JIFS-202424Amiri Shahmirani, M.R.; Nikghalb Rashti, A.A.; Adib Ramezani, M.R.; Golafshani, E.M. Application of fuzzy modelling to predict the earthquake damage degree of buildings based on field data. Journal of Intelligent and Fuzzy Systems, 2021; 41(2):2717–2730. https://doi.org/10.3233/JIFS-202424.

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