Smart Structures and Systems

  • 제33권4호
  • /
  • Pages.313-323
  • /
  • 2024
  • /
  • 1738-1584(pISSN)
  • /
  • 1738-1991(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

A deep neural network to automatically calculate the safety grade of a deteriorating building

  • Seungho Kim (Department of Architecture, Yeungnam University College) ;
  • Jae-Min Lee (School of Architecture, Yeungnam University) ;
  • Moonyoung Choi (School of Architecture, Yeungnam University) ;
  • Sangyong Kim (School of Architecture, Yeungnam University)
  • 투고 : 2022.05.20
  • 심사 : 2024.04.26
  • 발행 : 2024.04.25
⟨ 이전 논문 다음 논문 ⟩

초록

Deterioration of buildings is one of the biggest problems in modern society, and the importance of a safety diagnosis for old buildings is increasing. Therefore, most countries have legal maintenance and safety diagnosis regulations. However, the reliability of the existing safety diagnostic processes is reduced because they involve subjective judgments in the data collection. In addition, unstructured tasks increase rework rates, which are time-consuming and not cost-effective. Therefore, This paper proposed the method that can calculate the safety grade of deterioration automatically. For this, a DNN structure is generated by using existing precision inspection data and precision safety diagnostic data, and an objective building safety grade is calculated by applying status evaluation data obtained with a UAV, a laser scanner, and reverse engineering 3D models. This automated process is applied to 20 old buildings, taking about 40% less time than needed for a safety diagnosis from the existing manual operation based on the same building area. Subsequently, this study compares the resulting value for the safety grade with the already existing value to verify the accuracy of the grade calculation process, constructing the DNN with high accuracy at about 90%. This is expected to improve the reliability of aging buildings in the future, saving money and time compared to existing technologies, improving economic efficiency.

키워드

과제정보

This work was supported by the 2022 Yeungnam University Research Grant.

참고문헌

  1. Ani, A.I.C., Johar, S., Tawil, N.M., Abd Razak, M.Z. and Hamzah, N. (2015), "Building information modeling (BIM)-based building condition assessment: A survey of water ponding defect on a flat roof", J. Teknol., 75(9), 25-31. https://doi.org/10.11113/jt.v75.5222
  2. Anuar, M.Z.T., Sarbini, N.N., Ibrahim, I.S., Osman, M.H., Ismail, M. and Khun, M.C. (2019), "A comparative of building condition assessment method used in Asia countries: A review", IOP Conf Ser. Mater. Sci. Eng., 513(1), 012029. https://doi.org/10.1088/1757-899X/513/1/012029
  3. Cha, Y.J., Choi, W. and Buyukozturk, O. (2017), "Deep learning-based crack damage detection using convolutional neural networks", Comput.-Aided Civil Infrastr. Eng., 32(5), 361-378. https://doi.org/10.1111/mice.12263
  4. Chaiyasarn, K., Buatik, A., Mohamad, H., Zhou, M., Kongsilp, S., and Poovarodom, N. (2022), "Integrated pixel-level CNN-FCN crack detection via photogrammetric 3D texture mapping of concrete structures", Automat. Constr., 140, 104388. https://doi.org/10.1016/j.autcon.2022.104388
  5. Chen, Z., Zhang, W., Huang, R., Dong, Z., Chen, C., Jiang, L. and Wang, H. (2022), "3D model-based terrestrial laser scanning (TLS) observation network planning for large-scale building facades", Automat. Constr., 144, 104594. https://doi.org/10.1016/j.autcon.2022.104594
  6. Cheng, J.C., Chen, W., Chen, K. and Wang, Q. (2020), "Data-driven predictive maintenance planning framework for MEP components based on BIM and IoT using machine learning algorithms", Automat. Constr., 112, 103087. https://doi.org/10.1016/j.autcon.2020.103087
  7. Choi, J., Yeum, C.M., Dyke, S.J. and Jahanshahi, M.R. (2018), "Computer-aided approach for rapid post-event visual evaluation of a building facade", Sensors, 18(9), 3017. https://doi.org/10.3390/s18093017
  8. El-Abbasy, M.S., Senouci, A., Zayed, T., Mirahadi, F. and Parvizsedghy, L. (2014), "Artificial neural network models for predicting condition of offshore oil and gas pipelines" Automat. Constr., 45, 50-65. https://doi.org/10.1016/j.autcon.2014.05.003
  9. Ensafi, M. and Thabet, W. (2021), "Challenges and gaps in facility maintenance practices", EPiC Series Built Environ., 2, 237-245. https://doi.org/10.29007/1h2j
  10. Falorca, J.F. and Lanzinha, J.C.G. (2020), "Facade inspections with drones-theoretical analysis and exploratory tests", Int. J. Build. Pathol. Adapt. https://doi.org/10.1108/IJBPA-07-2019-0063
  11. Gopalakrishnan, K., Gholami, H., Vidyadharan, A., Choudhary, A. and Agrawal, A. (2018), "Crack damage detection in unmanned aerial vehicle images of civil infrastructure using pre-trained deep learning model", Int. J. Traffic Transport Eng., 8(1), 1-14. http://dx.doi.org/10.7708/ijtte.2018.8(1).01
  12. Guo, J. and Wang, Q. (2022), "Human-related uncertainty analysis for automation-enabled facade visual inspection: A Delphi study", J. Manag. Eng., 38(2), 04021088. https://doi.org/10.1061/(ASCE)ME.1943-5479.0001000
  13. Kang, D. and Cha, Y.J. (2018), "Autonomous UAVs for structural health monitoring using deep learning and an ultrasonic beacon system with geo-tagging", Comput.-Aided Civil Infrastr. Eng., 33(10), 885-902. https://doi.org/10.1111/mice.12375
  14. Kang, T.W., Kim, J.E. and Jung, T.S. (2016), "Study on 3D Reverse Engineering-based MEP Facility Management Improvement Method", Korea Inst. Constr. Technol., 17(8), 38-45. https://doi.org/10.5762/KAIS.2016.17.8.38
  15. Kim, Y.S. (2020), "Current Status of Old Buildings and Future Tasks", Nat. Assembly Res. Serv., 133, 1-13.
  16. Klapa, P. (2023), "Integration of terrestrial laser scanning and UAV-based photogrammetry for heritage Building Information Modeling", Geomatics, Landmanagement and Landscape. https://doi.org/10.15576/GLL/2023.1.23
  17. Kwan, A.K.H. and Ng, P.L. (2015), "Building diagnostic techniques and building diagnosis: The way forward", In: Engineering Asset Management-Systems, Professional Practices and Certification: Proceedings of the 8th World Congress on Engineering Asset Management (WCEAM 2013) & the 3rd International Conference on Utility Management & Safety (ICUMAS), pp. 849-862. https://doi.org/10.1007/978-3-319-09507-3_74
  18. Kwon, S.W. (2009), "Object Recognition and Modeling Technology Using Laser Scanning and BIM for Construction Industry", Rev. Architect. Build. Sci., 53(4), 31-38.
  19. Kwon, N.Y., Song, K.S., Ahn, Y.H., Park, M.S. and Jang, Y.J. (2020), "Maintenance cost prediction for aging residential buildings based on case-based reasoning and genetic algorithm", J. Build. Eng., 28, 101006. https://doi.org/10.1016/j.jobe.2019.101006
  20. Laefer, D.F., Truong-Hong, L., Carr, H. and Singh, M. (2014), "Crack detection limits in unit based masonry with terrestrial laser scanning", Ndt & E Int., 62, 66-76. https://doi.org/10.1016/j.ndteint.2013.11.001
  21. Lattanzi, D. and Miller, G.R. (2014), "3D scene reconstruction for robotic bridge inspection", J. Infrastr. Syst., 21(2). https://doi.org/10.1061/(ASCE)IS.1943-555X.0000229
  22. Law, D.W., Holden, L. and Silcock, D. (2015), "The assessment of crack development in concrete using a terrestrial laser scanner (TLS)", Austral. J. Civil Eng., 13(1), 22-31. https://doi.org/10.1080/14488353.2015.1092635
  23. Liu, D., Chen, J., Hu, D. and Zhang, Z. (2019), "Dynamic BIM-augmented UAV safety inspection for water diversion project", Comput. Indust., 108, 163-177. https://doi.org/10.1016/j.compind.2019.03.004
  24. Marcus, G. (2018), "Deep learning: A critical appraisal", Technical Report; Departments of Psychology and Neural Science, New York University, New York, USA. https://doi.org/10.48550/arXiv.1801.00631
  25. Mukupa, W., Roberts, G.W., Hancock, C.M. and Al-Manasir, K. (2016), "A review of the use of terrestrial laser scanning application for change detection and deformation monitoring of structures", Survey Review, 49(353), 99-116. https://doi.org/10.1080/00396265.2015.1133039
  26. Nex, F., Duarte, D., Tonolo, F.G. and Kerle, N. (2019), "Structural building damage detection with deep learning: Assessment of a state-of-the-art CNN in operational conditions", Remote Sensing, 11(23), 2765. https://doi.org/10.3390/rs11232765
  27. Pan, N.H., Tsai, C.H., Chen, K.Y. and Sung, J. (2020), "Enhancement of external wall decoration material for the building in safety inspection method", J. Civil Eng. Manag., 26(3), 216-226. https://doi.org/10.3846/jcem.2020.11925
  28. Park, J. and Kim, S.G. (2020), "Structural Safety Management for Small-scale Buildings", The Seoul Institute, 1-115.
  29. Park, H.J., Ryu, J.R., Woo, S.H. and Choo, S.Y. (2016), "An improvement of the building safety inspection survey method using laser scanner and BIM-based reverse engineering", J. Architect. Inst. Korea Plann. Des., 32(12), 79-90. https://doi.org/10.5659/JAIK_PD.2016.32.12.79
  30. Park, H.J., Lee, S.H., Kim, E.J. and Choo, S.Y. (2017), "A proposal for building safety diagnosis processes using bim-based reverse engineering technology", Proceeding of the 22nd International conference of the Association for Computer-Aided Architectural Design Research in Asia, pp. 673-683.
  31. Perez, H., Tah, J.H. and Mosavi, A. (2019), "Deep learning for detecting building defects using convolutional neural networks", Sensors, 19(16), 3556. https://doi.org/10.3390/s19163556
  32. Luo, Q., Ge, B. and Tian, Q. (2019), "A fast adaptive crack detection algorithm based on a double-edge extraction operator of FSM", Constr. Build. Mater., 204, 244-254. https://doi.org/10.1016/j.conbuildmat.2019.01.150
  33. Rachmawati, T.S.N. and Kim, S. (2022), "Unmanned Aerial Vehicles (UAV) integration with digital technologies toward construction 4.0: A systematic literature review", Sustainability, 14(9), 5708. https://doi.org/10.3390/su14095708
  34. Sarker, M.M., Ali, T.A., Abdelfatah, A., Yehia, S. and Elaksher, A. (2017), "A cost-effective method for crack detection and measurement on concrete surface", Int. Arch. Photogramm. Remote Sens. Spatial Inform. Sci., 42, 237. https://doi.org/10.5194/isprs-archives-XLII-2-W8-237-2017
  35. Shi, Z. and Ergan, S. (2018), "Leveraging Point Cloud Data Detecting Building Facade Deterioration Caused by Neighboring Consturction", Tamap J. Eng. https://doi.org/10.29371/2018.3.66
  36. Shi, Z. and Ergan, S. (2020), "Towards Point Cloud and Model-Based Urban Facade Inspection: Challenges in the Urban Facade Inspection Process", In: Constuction Research Congress 2020 : Safety, Workforce, and Education, pp. 385-394.
  37. Silva, A., Dias, J.L., Gaspar, P.L. and de Brito, J. (2013), "Statistical models applied to service life prediction of rendered facades", Automat. Constr., 30, 151-160. https://doi.org/10.1016/j.autcon.2012.11.028
  38. Sousa, V., Matos, J.P. and Matias, N. (2014), "Evaluation of artificial intelligence tool performance and uncertainty for predicting sewer structural condition", Automat. Constr., 44, 84-91. https://doi.org/10.1016/j.autcon.2014.04.004
  39. Tsai, Y.C.J. and Li, F. (2012), "Critical assessment of detecting asphalt pavement cracks under different lighting and low intensity contrast conditions using emerging 3D laser technology", J. Transport. Eng., 138(5), 649-656. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000353
  40. Turkan, Y., Hong, J., Laflamme, S. and Puri, N. (2018), "Adaptive wavelet neural network for terrestrial laser scanner-based crack detection", Automat. Constr., 94, 191-202. https://doi.org/10.1016/j.autcon.2018.06.017
  41. Vasic, D., Ninkov, T., Bulatovic, V., Susic, Z. and Markovic, M. (2014), "Terrain mapping by applying unmanned aerial vehicle and lidar system for the purpose of designing in Serbia", FIG, Ingeo, pp. 217-222.
  42. Wu, J., Shi, Y., Wang, H., Wen, Y. and Du, Y. (2023), "Surface Defect Detection of Nanjing City Wall Based on UAV Oblique Photogrammetry and TLS", Remote Sens., 15(8), 2089. https://doi.org/10.3390/rs15082089
  43. Zhang, J., Qian, S. and Tan, C. (2023), "Automated bridge crack detection method based on lightweight vision models", Complex Intell. Syst., 9(2), 1639-1652. https://doi.org/10.1007/s40747-022-00876-6