한국공간구조학회논문집 (Journal of Korean Association for Spatial Structures)

  • 제23권3호
  • /
  • Pages.87-94
  • /
  • 2023
  • /
  • 1598-4095(pISSN)
  • /
  • 2287-7401(eISSN)
한국공간구조학회 (Korean Association for Spatial Structures)
권호 표지
DOI QR코드

DOI QR Code

기계학습을 이용한 염화물 확산계수 예측모델 개발

Development of Prediction Model of Chloride Diffusion Coefficient using Machine Learning

  • Kim, Hyun-Su (Division of Architecture, Sunmoon University)
  • 투고 : 2023.08.01
  • 심사 : 2023.08.11
  • 발행 : 2023.09.15
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Chloride is one of the most common threats to reinforced concrete (RC) durability. Alkaline environment of concrete makes a passive layer on the surface of reinforcement bars that prevents the bar from corrosion. However, when the chloride concentration amount at the reinforcement bar reaches a certain level, deterioration of the passive protection layer occurs, causing corrosion and ultimately reducing the structure's safety and durability. Therefore, understanding the chloride diffusion and its prediction are important to evaluate the safety and durability of RC structure. In this study, the chloride diffusion coefficient is predicted by machine learning techniques. Various machine learning techniques such as multiple linear regression, decision tree, random forest, support vector machine, artificial neural networks, extreme gradient boosting annd k-nearest neighbor were used and accuracy of there models were compared. In order to evaluate the accuracy, root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE) and coefficient of determination (R2) were used as prediction performance indices. The k-fold cross-validation procedure was used to estimate the performance of machine learning models when making predictions on data not used during training. Grid search was applied to hyperparameter optimization. It has been shown from numerical simulation that ensemble learning methods such as random forest and extreme gradient boosting successfully predicted the chloride diffusion coefficient and artificial neural networks also provided accurate result.

키워드

과제정보

본 논문은 2022년도 가동원전 안전성향상 핵심기술개발사업의 지원으로 수행되고 있는 과제(과제번호: 20224B10200080) 내용의 일부입니다. 산업통상자원부와 한국에너지기술평가원의 연구비 지원에 깊은 감사를 드립니다.

참고문헌

  1. Pontes, J., Bogas, J.A., Real, S. and Silva A., "The rapid chloride migration test in assessing the chloride penetration resistance of normal and lightweight concrete", Applied Science, Vol. 11, 7251, 2021. DOI:https://doi.org/10.3390/app11167251 
  2. Nguyen, T.S., Lorente, S. and Carcasses, M., "Effect of the environment temperature on the chloride diffusion through CEM-I and CEM-V mortars: An experimental study", Construction and Building Materials, Vol. 23, pp. 795-803, 2009. DOI:https://doi.org/10.1016/j.conbuildmat.2008.03.004 
  3. Ye, H., Jin, X., Fu, C., Jin, N., Xu, Y. and Huang, T., "Chloride penetration in concrete exposed to cyclic drying-wetting and carbonation", Construction and Building Materials, Vo. 112, pp. 457-463, 2016. DOI:https://doi.org/10.1016/j.conbuildmat.2016.02.194 
  4. Torres-Luque, M., Bastidas-Arteaga, E., Schoefs, F., Sanchez-Silva, M. and Osma, J.F., "Nondestructive methods for measuring chloride ingress into concrete: State-of-the- art and future challenges", Construction and Building Materials, Vol. 68, pp. 68-81, 2014. DOI:https://doi.org/10.1016/j.conbuildmat.2014.06.009 
  5. Choi, Y.C., Park, B., Pang, G.S., Lee, K.M. and Choi, S., "Modelling of chloride diffusivity in concrete considering effect of aggregates", Construction and Building Materials, Vol. 136, pp. 81-87, 2017. DOI:https://doi.org/10.1016/j.conbuildmat.2017.01.041 
  6. Elfmarkova, V., Spiesz, P. and Brouwers, H.J.H., "Determination of the chloride diffusion coefficient in blended cement mortars", Cement and Concrete Research, Vol. 78, pp. 190-199, 2015. DOI:https://doi.org/10.1016/j.cemconres.2015.06.014 
  7. Homayoonmehr, R., Rahai, A. and Ramezanianpour, A.A., "Predicting the chloride diffusion coefficient and surface electrical resistivity of concrete using statistical regression-based models and its application in chloride-induced corrosion service life prediction of RC structures", Construction and Building Materials, Vol. 357, 129351, 2022. DOI:https://doi.org/10.1016/j.conbuildmat.2022.129351 
  8. Taffese, W.Z. and Espinosa-Leal, L., "Multitarget regression models for predicting compressive strength and chloride resistance of concrete", Journal of Building Engineering, Vol. 72, 106523, 2023. DOI:https://doi.org/10.1016/j.jobe.2023.106523 
  9. Thai, H.T., "Machine learning for structural engineering: A state-of-the-art review", Structures, Vol. 38, pp. 448-491, 2022. DOI:https://doi.org/10.1016/j.istruc.2022.02.003 
  10. Kim, H.S., "Development of seismic response simulation model for building structures with semi-active control devices using recurrent neural network", Applied Sciences, Vol. 10, 3915, 2020. DOI:https://doi.org/10.3390/app10113915 
  11. Wen, W., Zhang, C. and Zhai, C., "Rapid seismic response prediction of RC frames based on deep learning and limited building information", Engineering Structures, Vol. 267, 114638, 2022. DOI:https://doi.org/10.1016/j.engstruct.2022.114638 
  12. Taffese, W.Z. and Espinosa-Leal, L., "A machine learning method for predicting the chloride migration coefficient of concrete", Construction and Building Materials, Vol. 348, 128566, 2022. DOI:https://doi.org/10.1016/j.conbuildmat.2022.128566 
  13. Al Fuhaid AF and Alanazi H. "Prediction of chloride diffusion coefficient in concrete modified with supplementary cementitious materials using machine learning algorithms", Materials, Vol. 23, 1277, 2023. DOI:https://doi.org/10.3390/ma16031277 
  14. Hasholt, M.T. and Jensen, O.M., "Chloride migration in concrete with superabsorbent polymers", Cement and Concrete Composites, Vol. 55, pp. 290-297, 2015. DOI:https://doi.org/10.1016/j.cemconcomp.2014.09.023