Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Carbonation depth prediction of concrete bridges based on long short-term memory

  • Youn Sang Cho (Department of Architectural Engineering, Sejong University) ;
  • Man Sung Kang (Department of Architectural Engineering, Sejong University) ;
  • Hyun Jun Jung (Korea Authority of Land & Infrastructure Safety (KALIS)) ;
  • Yun-Kyu An (Department of Architectural Engineering, Sejong University)
  • Received : 2023.09.07
  • Accepted : 2024.05.09
  • Published : 2024.05.25
⟨ Previous Next ⟩

Abstract

This study proposes a novel long short-term memory (LSTM)-based approach for predicting carbonation depth, with the aim of enhancing the durability evaluation of concrete structures. Conventional carbonation depth prediction relies on statistical methodologies using carbonation influencing factors and in-situ carbonation depth data. However, applying in-situ data for predictive modeling faces challenges due to the lack of time-series data. To address this limitation, an LSTM-based carbonation depth prediction technique is proposed. First, training data are generated through random sampling from the distribution of carbonation velocity coefficients, which are calculated from in-situ carbonation depth data. Subsequently, a Bayesian theorem is applied to tailor the training data for each target bridge, which are depending on surrounding environmental conditions. Ultimately, the LSTM model predicts the time-dependent carbonation depth data for the target bridge. To examine the feasibility of this technique, a carbonation depth dataset from 3,960 in-situ bridges was used for training, and untrained time-series data from the Miho River bridge in the Republic of Korea were used for experimental validation. The results of the experimental validation demonstrate a significant reduction in prediction error from 8.19% to 1.75% compared with the conventional statistical method. Furthermore, the LSTM prediction result can be enhanced by sequentially updating the LSTM model using actual time-series measurement data.

Keywords

Acknowledgement

This study was supported by the BK21 FOUR (Fostering Outstanding Universities for Research, No. 412024115147) funded by the Ministry of Education (MOE, Korea) and National Research Foundation of Korea (NRF), and Ministry of the Interior and Safety as Human Resource Development Project in Earthquake Disaster Management.

References

  1. Chen, G., Lv, Y., Zhang, Y. and Yang, M. (2021), "Carbonation depth predictions in concrete structures under changing climate condition in China", Eng. Fail. Anal., 119, 104990. https://doi.org/10.1016/j.engfailanal.2020.104990
  2. Ghanooni-Bagha, M., YekeFallah, M.R. and Shayanfar, M.A. (2020), "Durability of RC structures against carbonation-induced corrosion under the impact of climate change", KSCE J. Civil Eng., 24(1), 131-142. https://doi.org/10.1007/s12205-020-0793-8
  3. Hochreiter, S. and Schmidhuber, J. (1997), "Long short-term memory", Neural Computat., 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  4. Forsdyke, J.C. and Lees, J.M. (2023), "Model fitting to concrete carbonation data with non-zero initial carbonation depth", Mater. Struct., 56(1), 22. https://doi.org/10.1617/s11527-023-02104-0
  5. Jung, H. (2010), "Durability analysis and development of probability-based carbonation prediction model in concrete structure", KSCE J. Civil Environ. Eng. Res., 30(4A), 343-352. https://doi.org/10.12652/Ksce.2010.30.4A.343
  6. Jung, H.J. and Kim, G.S. (2010), "A long-term durability prediction for RC structures exposed to carbonation using probabilistic approach", J. Korea Inst. Struct. Maint. Inspect. (KSMI), 14(5), 119-127. https://doi.org/10.11112/jksmi.2010.14.5.119
  7. Jung, H., Im, S.B. and An, Y.K. (2020), "Probability-based concrete carbonation prediction using on-site data", Appl. Sci., 10(12), 4330. https://doi.org/10.3390/app10124330
  8. Konecny, P., Lehner, P., Vorechovska, D., Somodikova, M., Hornakova, M. and Rovnanikova, P. (2020), "Extended evaluation of durability-related field inspection data from concrete bridges under service", Procedia Struct. Integr., 26, 430-438. https://doi.org/10.1016/j.prostr.2020.06.054
  9. KDS 21, 45 (2022), Hypothesis Bridge and Pavement Dual Design Standards, Korea Construction Standards Center, Republic of Korea. [In Korean]
  10. Lei, J.Q. (2012), "Research on durability of coastal concrete bridges", Adv. Mater. Res., 374-377, 2167-2170. https://doi.org/10.4028/www.scientific.net/AMR.374-377.2167
  11. Li, S. (2019), "Durability evaluation of concrete bridges considering multi-scale high-efficiency numerical models", In: 2019 International Conference on Smart Grid and Electrical Automation (ICSGEA), pp. 169-172. https://doi.org/10.1109/ICSGEA.2019.00046
  12. Li, G.Z. and Zhou, X.G. (2013), "The research of predicting the carbonation depth of concrete with time-series analysis", Appl. Mech. Mater., 351-352, 1694-1699. https://doi.org/10.4028/www.scientific.net/AMM.351-352.1694
  13. Liu, P., Yu, Z. and Chen, Y. (2020), "Carbonation depth model and carbonated acceleration rate of concrete under different environment", Cement Concrete Compos., 114, 103736. https://doi.org/10.1016/j.cemconcomp.2020.103736
  14. Loreto, G., Di Benedetti, M. and Nanni, A. (2012), "Evaluation of concrete structures in marine environment: Geiger key bridge", Nondestructive Characterization for Composite Materials, Aerospace Engineering, Civil Infrastructure, and Homeland Security, 8347, 555-562. https://doi.org/10.1117/12.914862
  15. Monteiro, I., Branco, F.A., de Brito, J. and Neves, R. (2012), "Statistical analysis of the carbonation coefficient in open air concrete structures", Constr. Build. Mater., 29, 263-269. https://doi.org/10.1016/j.conbuildmat.2011.10.028
  16. Na, U.J., Kwon, S.J., Chaudhuri, S.R. and Shinozuka, M. (2012), "Stochastic model for service life prediction of RC structures exposed to carbonation using random field simulation", KSCE J. Civil Eng., 16(1), 133-143. https://doi.org/10.1007/s12205-012-1248-7
  17. Silva, A., Neves, R. and De Brito, J. (2014), "Statistical modelling of carbonation in reinforced concrete", Cement Concrete Compos., 50, 73-81. https://doi.org/10.1016/j.cemconcomp.2013.12.001
  18. Tasaka, S., Shinozuka, M., Chaudhuri, S.R.A.Y. and Na, U.J. (2009), "Bayesian inference for prediction of carbonation depth of concrete using MCMC", Mem Akashi Tech Coll, 52, 45-50.
  19. Zambon, I., Vidovic, A., Strauss, A., Matos, J. and Friedl, N. (2018), "Prediction of the remaining service life of existing concrete bridges in infrastructural networks based on carbonation and chloride ingress", Smart Struct. Syst., Int. J., 21(3), 305-320. https://doi.org/10.12989/sss.2018.21.3.305
  20. Zheng, X.Z. and Lin, J.F. (2012), "Pre-evaluation of durability for concrete bridge", Adv. Mater. Res., 594-597, 1581-1585. https://doi.org/10.4028/www.scientific.net/AMR.594-597.1581