Advances in concrete construction

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

AI-driven seismic durability of concrete structures using reinforcement learning

  • M. Rajesh (Department of Computer Science and Engineering, School of Computing, Aarupadai Veedu Institute of Technology)
  • Received : 2024.03.29
  • Accepted : 2024.06.22
  • Published : 2024.08.25
⟨ Previous Next ⟩

Abstract

In order to improve the oversight, security, and upkeep of smart city infrastructures, this article investigates the potential for combining IoT with structural health monitoring (SHM) systems and cutting-edge ML methods. The suggested solution overcomes the shortcomings of conventional monitoring methods by enhancing the real-time gathering and analysis of data on structural integrity through the use of sensors powered by the Internet of Things (IoT) and deep learning (DL) algorithms. The approach achieves over 90% accuracy in forecasting structural health post-seismic events, demonstrating high prediction accuracy with up to 93,500 data points analysed for seismic response models of reinforced concrete (RC) structures. Moreover, cloud computing allows for effective data storage and remote access, guaranteeing that steps are taken promptly to ensure the safety of urban infrastructure. These advancements lay the groundwork for smart city solutions that are scalable, efficient, and dependable; they improve sustainability and resilience by using cutting-edge SHM and IoT technology.

Keywords

References

  1. Abduljaleel, Y., Usman, F., Syamsir, A., Albaker, B., Najeeb, M. and Khattab, M. A Systematic Review on Utilizing Artificial Intelligence in Lateral Resisting Systems of Buildings. Available at SSRN 4696205.
  2. Arslan, M.H. (2010), "An evaluation of effective design parameters on earthquake performance of RC buildings using neural networks", Eng. Struct., 32(7), 1888-1898. https://doi.org/10.1016/j.engstruct.2010.03.010
  3. Audretsch, J. (2020), "Earthquake detection using deep learning based approaches", Doctoral dissertation.
  4. Chen, C.S. (2020), "Seismic performance assessments of school buildings in Taiwan using artificial intelligence theories", Eng. Computat., 37(9), 3321-3343. https://doi.org/10.1108/EC-09-2019-0400
  5. Falcone, R., Ciaramella, A., Carrabs, F., Strisciuglio, N. and Martinelli, E. (2022), "Artificial neural network for technical feasibility prediction of seismic retrofitting in existing RC structures", Structures, 41, 1220-1234. https://doi.org/10.1016/j.istruc.2022.05.008
  6. Hossain, K.A. (2013), Structural optimization and life-cycle sustainability assessment of reinforced concrete buildings in seismic regions.
  7. Hu, A. (2024), Seismic Design for Buildings. In Structural Design of Buildings: Holistic Design, pp. 237-262.
  8. Kaliappan, V. and Lakshmanan, T. (2024), "Reinforcement Learning for Enhancing Earthquake Resistance in Concrete Structures Using Artificial Intelligence", Nanotechnol. Percept., 20, 179-190. https://doi.org/10.62441/nano-ntp.v20iS5.15
  9. Lazaridis, P.C., Kavvadias, I.E., Demertzis, K., Iliadis, L. and Vasiliadis, L.K. (2022), "Structural damage prediction of a reinforced concrete frame under single and multiple seismic events using machine learning algorithms", Appl. Sci., 12(8), p.3845. https://doi.org/10.3390/app12083845
  10. Li, S., Liew, J.R. and Xiong, M.X. (2021), "Prediction of fire resistance of concrete encased steel composite columns using artificial neural network", Eng. Struct., 245, 112877. https://doi.org/10.1016/j.engstruct.2021.112877
  11. Noureldin, M., Ali, A., Sim, S. and Kim, J. (2022), "A machine learning procedure for seismic qualitative assessment and design of structures considering safety and serviceability", J. Build. Eng., 50, 104190. https://doi.org/10.1016/j.jobe.2022.104190
  12. Pan, Y. and Zhang, L. (2021), "Roles of artificial intelligence in construction engineering and management: A critical review and future trends", Automat. Constr., 122, 103517. https://doi.org/10.1016/j.autcon.2020.103517
  13. Shadabfar, M., Mahsuli, M., Zhang, Y., Xue, Y., Ayyub, B.M., Huang, H. and Medina, R.A. (2022), "Resilience-based design of infrastructure: Review of models, methodologies, and computational tools", ASCE-ASME J. Risk Uncertain. Eng. Syst. Part A: Civil Eng., 8(1), 03121004. https://doi.org/10.1061/AJRUA6.0001184
  14. Souza, L. and Savoikar, P. (2022), "Need for artificial intelligence in geotechnical earthquake engineering", Earthquake Geotechnics: Select Proceedings of 7th ICRAGEE 2021, pp. 425-434.
  15. Tseranidis, S., Brown, N.C. and Mueller, C.T. (2016), "Data-driven approximation algorithms for rapid performance evaluation and optimization of civil structures", Automat. Constr., 72, 279-293. https://doi.org/10.1016/j.autcon.2016.02.002
  16. Wang, G.G. and Shan, S. (2006), "Review of metamodeling techniques in support of engineering design optimization", In: International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Vol. 4255, pp. 415-426, Philadelphia, PA, USA, September. https://doi.org/10.1115/DETC2006-99412
  17. Yazdani, H., Khatibinia, M., Gharehbaghi, S. and Hatami, K. (2017), "Probabilistic performance-based optimum seismic design of RC structures considering soil–structure interaction effects", ASCE-ASME J. Risk Uncertain. Eng. Syst., Part A: Civil Eng., 3(2), G4016004. https://doi.org/10.1061/AJRUA6.0000880