Modern approaches to assessing the technical condition of building structures at the operational stage

Introduction. The paper is devoted to the development of approaches to the construction of an automated assessment system for the technical condition of building structures using defect detection mechanisms and preliminary assessment of the physical deterioration of buildings based on artificial intelligence methods. Modern construction objects are characterized by high complexity and scale, which requires special attention to the quality and reliability of structures. Traditional methods of technical maintenance do not always show their effectiveness due to the influence of human factors. Currently, the primary method of defects detention remains visual inspection, which, although it allows to assess the condition of objects, depends on the level of qualification and attentiveness of the evaluator. This creates risks of error, which can threaten the safety of buildings and lead to incorrect decisions regarding repairs and maintenance. The aim of the research is to analyze the required functionality and modelling of an automated system capable of quickly and accurately identifying potential defects in building structures and assessing likely physical deterioration.

Materials and methods. The comprehensive approach includes two main components: a system for analyzing accumulated data on the physical deterioration of residential properties and a defect detection mechanism based on image analysis using artificial intelligence. The main input data for analysis are the results of photographic documentation of the building condition, as well as the volume of accumulated observations and data on the physical deterioration of the housing stock over a long period of observation.

Results. The libraries and tools necessary for the implementation of this system are described in detail, including popular frameworks for machine learning and image processing.

Conclusions. Modern approaches based on the application of artificial intelligence and machine learning methods open new horizons in the detection of defects and forecasting the technical condition of buildings. They significantly increase the speed and accuracy of analysis.

1. Adewale B.A., Ene V.O., Ogunbayo B.F., Aigbavboa C.O. A Systematic Review of the Applications of AI in a Sustainable Building’s Lifecycle. Buildings. 2024; 14(7):2137. DOI: 10.3390/buildings14072137

2. Mishra A., Pareek R.K., Kumar S., Varalakshmi S. A review of the current and future developments of artificial intelligence in the management and building sectors. Multidisciplinary Reviews. 2024; 6:2023ss068. DOI: 10.31893/multirev.2023ss068

3. Suleymanova L., Obaydi A. Building life cycle management at the operation stage using artificial neural network models and machine learning. Bulletin of Belgorod State Technological University named after. V.G. Shukhov. 2024; 3:38-46. DOI: 10.34031/2071-7318-2024-9-3-38-46. EDN DHJYVT. (rus.).

4. Jaufer L., Kader S., Spalevic V., Škatarić G., Dudić B. Machine learning practices during the operational phase of buildings : a critical review. Applied Engineering Letters. 2024; 9(1):37-45. DOI: 10.46793/aeletters.2024.9.1.4

5. Burgos D.A.T., Vargas R.C.G., Pedraza C., Agis D., Pozo F. Damage Identification in Structural Health Monitoring: A Brief Review from its Implementation to the Use of Data-Driven Applications. Sensors. 2020; 20(3):733. DOI: 10.3390/s20030733

6. Entezami A., Sarmadi H., Behkamal B., Mariani S. Health Monitoring of Large-Scale Civil Structures : аn Approach Based on Data Partitioning and Classical Multidimensional Scaling. Sensors. 2021; 21(5):1646. DOI: 10.3390/s21051646

7. Thohari A.N.A., Karima A., Santoso K., Rahmawati R. Crack Detection in Building Through Deep Learning Feature Extraction and Machine Learning Approch. Journal of Applied Informatics and Computing. 2024; 8(1):1-6. DOI: 10.30871/jaic.v8i1.7431

8. Hamishebahar Y., Guan H., So S., Jo J. A Comprehensive Review of Deep Learning-Based Crack Detection Approaches. Applied Sciences. 2022; 12(3):1374. DOI: 10.3390/app12031374

9. Hsieh Y.-A., Tsai Y.J. Machine learning for crack detection: review and model performance comparison. Journal of Computing in Civil Engineering. 2020; 34(5). DOI: 10.1061/(asce)cp.1943-5487.0000918

10. Sikorskij O.S. Review of convolutional neural networks for the problem of image classification. New Information Technologies in Automated System. 2017; 20:37-42. EDN YNADUJ. (rus.).

11. Sosnin A.S., Suslova I.A. Functions of neural net activation: sigmoid, linear, step, ReLu, tan. Science. Informatization. Technologies. Education. 2019; 237-246. (rus.).

12. Dorafshan S., Tomas R.Dzh., Maguajr M. Comparison of deep convolutional neural networks and edge detectors for detecting cracks in concrete based on images. Construction and Building Materials. 2018; 186:1031-1045. (rus.).

13. Knyazeva N., Nazojkin E., Orekhov A. The use of artificial intelligence to detect defects in building structures. Construction and Architecture. 2023; 11(3):18. DOI: 10.29039/2308-0191-2023-11-3-18-18. EDN SVXCZV. (rus.).

14. Naumov A., Yudin D., Dolzhenko A. Improving the technology of construction and technical expertise using a hardware and software complex of automated inspection. Bulletin of Belgorod state technological university named after V.G. Shukhov. 2019; 4:61-69. DOI: 10.34031/article_5cb824d26344e7.45899508. EDN FHPDTK. (rus.).

15. Knyazeva N., Levina D. Using BIM scenarios in operation services. Bulletin of Belgorod state technological university named after V.G. Shukhov. 2019; 5:99-105. DOI: 10.34031/article_5cd6df471c80b0.92422061. EDN IBNDHU. (rus.).

16. Kurochkina E.V. New information systems in construction: Technologies of information systems in the design, construction, and operation of buildings. Scientific Leader. 2022; 25(70):27-30. EDN DVSRFK. (rus.).

17. Knyazeva N.V., Medyntsev A.A. An algorithm for creating a building monitoring system based on the integration of building information modeling and radio frequency identification technologies. Engineering journal of Don. 2022; 12(96):646-659. EDN NSKKNZ. (rus.).

18. Gerc V., Knyazeva N. Regulatory documentation for the operation of buildings with TIM. Construction and Architecture. 2023; 11(3):9. DOI: 10.29039/2308-0191-2023-11-3-9-9. EDN BCGLSC. (rus.).

19. Knyazeva N., Medincev A., Orekhov A. Configuring parameters of information model elements for integration with RFID tags. E3S Web of Conferences. 2023; 458:09010. DOI: 10.1051/e3sconf/202345809010

20. Munir M., Kiviniemi A., Jones S.W., Fin-negan S. BIM-based operational information requirements for asset owners. Architectural Engineering and Design Management. 2020; 16(2):100-114. DOI: 10.1080/17452007.2019.1706439

21. Zhou X., Qi Y., Tang H. Application of Artificial Intelligence Technology in Big Data Nining. Lecture Notes in Electrical Engineering. 2023; 737-744. DOI: 10.1007/978-981-99-2092-1_92

22. Dale D.C., Crawford J., Klippel Z., Reiner M., Osslund T., Fan E. et al. A systematic literature review of the efficacy, effectiveness, and safety of filgrastim. Supportive Care in Cancer. 2018; 26(1):7-20. DOI: 10.1007/s00520-017-3854-x

23. Elkabalawy M., Al-Sakkaf A., Abdelkader E.M., Alfalah G. CRISP-DM-Based Data-Driven Approach for Building Energy Prediction Utilizing Indoor and Environmental Factors. Sustainability. 2024; 16(17):7249. DOI: 10.3390/su16177249