Advances in concrete construction

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Estimating concrete chloride diffusion using an enhanced arithmetic optimization-based fuzzy system

  • Fangxiu Wang (School of Mathematics and Computer Science, Wuhan Polytechnic University) ;
  • Jiemei Zhao (School of Mathematics and Computer Science, Wuhan Polytechnic University)
  • Received : 2024.10.07
  • Accepted : 2025.01.11
  • Published : 2025.02.25
⟨ Previous Next ⟩

Abstract

The corrosion of steel reinforcement in concrete structures due to chloride exposure poses significant financial and environmental risks. An accurate assessment of chloride diffusion is essential for predicting the service life of steel-reinforced concrete. This article develops six models for estimating the chloride diffusion coefficient (CDC) in concrete, considering various exposure conditions like tidal, splash, atmospheric, and submerged environments. The models utilize a hybrid approach combining the adaptive neuro-fuzzy inference system (ANFIS) and least square support vector regression (LSSVR), enhanced by an improved arithmetic optimization algorithm (IAA). The IAA merges the arithmetic optimization algorithm (AOA) with the Aquila optimizer (AO) to address AOA's limitations. The models undergo sensitivity analysis using the Fourier Amplitude Sensitivity Test (FAST), revealing that the curing mechanism (CM) is the most influential factor, with a sensitivity value of 0.993. The study demonstrates that LSSVR and ANFIS-based methods are highly effective in predicting CDC. Among them, the ANFIS combined with IAA outperforms others regarding reliability and accuracy, making it a superior choice for CDC estimation. This robust model could lead to better management and longevity of concrete structures exposed to chloride, mitigating potential risks. The main application of this research is to enhance the durability management and service life prediction of steel-reinforced concrete structures exposed to chloride-laden environments. Engineers and infrastructure managers can better assess the risk and timing of corrosion onset by accurately estimating the CDC, which is crucial for preventive maintenance and cost-effective design.

Keywords

References

  1. Abualigah, L. and Diabat, A. (2023), "Improved multi-core arithmetic optimization algorithm-based ensemble mutation for multidisciplinary applications", J. Intell. Manuf., 34(4), 1833-1874. https://doi.org/10.1007/s10845-021-01877-x
  2. Abualigah, L., Yousri, D., Abd Elaziz, M., Ewees, A.A., Al-qaness, M.A.A. and Gandomi, A.H. (2021), "Aquila Optimizer: A novel meta-heuristic optimization algorithm", Comput. Indust. Eng., 157, 107250. https://doi.org/10.1016/j.cie.2021.107250
  3. Alizadeh, R., Ghods, P., Chini, M., Hoseini, M., Ghalibafian, M. and Shekarchi, M. (2008), "Effect of curing conditions on the service life design of RC structures in the Persian Gulf region", J. Mater. Civil Eng., 20(1), 2-8. https://doi.org/10.1061/(ASCE)0899-1561(2008)20:1(2)
  4. Ashrafian, A., Panahi, E., Salehi, S., Karoglou, M. and Asteris, P.G. (2023), "Mapping the strength of agro-ecological lightweight concrete containing oil palm by-product using artificial intelligence techniques", Structures, 48, 1209-1229. https://doi.org/10.1016/j.istruc.2022.12.108
  5. Aydemir, S.B. (2023), "A novel arithmetic optimization algorithm based on chaotic maps for global optimization", Evolut. Intell., 16(3), 981-996. https://doi.org/10.1007/s12065-022-00711-4
  6. Boğa, A.R., Öztürk, M. and Topcu, I.B. (2013), "Using ANN and ANFIS to predict the mechanical and chloride permeability properties of concrete containing GGBFS and CNI", Compos. Part B: Eng., 45(1), 688-696. https://doi.org/10.1016/j.compositesb.2012.05.054
  7. Costa, A. and Appleton, J. (1999), "Chloride penetration into concrete in marine environment—Part I: Main parameters affecting chloride penetration", Mater. Struct., 32, 252-259. https://doi.org/10.1007/BF02479594
  8. Delgado, J., Silva, F.A.N., Azevedo, A.C., Silva, D.F., Campello, R.L.B. and Santos, R.L. (2020), "Artificial neural networks to assess the useful life of reinforced concrete elements deteriorated by accelerated chloride tests", J. Build. Eng., 31, 101445. https://doi.org/10.1016/j.jobe.2020.101445
  9. Farahani, A., Taghaddos, H. and Shekarchi, M. (2015), "Prediction of long-term chloride diffusion in silica fume concrete in a marine environment", Cement Concrete Compos., 59, 10-17. https://doi.org/10.1016/j.cemconcomp.2015.03.006
  10. Farahani, A., Taghaddos, H. and Shekarchi, M. (2018), "Chloride diffusion modeling in pozzolanic concrete in marine site", ACI Mater. J., 115(4), 509-518. https://doi.org/10.14359/51702185
  11. Ghods, P., Chini, M., Alizadeh, R., Hoseini, M., Shekarchi, M. and Ramezanianpour, A.A. (2005), "The effect of different exposure conditions on the chloride diffusion into concrete in the Persian Gulf region", 3th ConMat, 5.
  12. Golafshani, E.M., Kashani, A., Kim, T. and Arashpour, M. (2022), "Concrete chloride diffusion modelling using marine creatures-based metaheuristic artificial intelligence", J. Cleaner Prod., 374, 134021. https://doi.org/10.1016/j.jclepro.2022.134021
  13. Golafshani, E.M., Kashani, A. and Arashpour, M. (2023a), "Chloride diffusion modeling of concrete using tree‐based forest models", Struct. Concrete, 24(4), 5614-5634. https://doi.org/10.1002/suco.202300245
  14. Golafshani, E.M., Kashani, A., Behnood, A. and Kim, T. (2023b), "Modeling the chloride migration of recycled aggregate concrete using ensemble learners for sustainable building construction", J. Cleaner Prod., 407, 136968. https://doi.org/10.1016/j.jclepro.2023.136968
  15. Gölcük, İ., Ozsoydan, F.B. and Durmaz, E.D. (2023), "An improved arithmetic optimization algorithm for training feedforward neural networks under dynamic environments", Knowl.-Based Syst., 263, 110274. https://doi.org/10.1016/j.knosys.2023.110274
  16. Gonzalez, J.R., Reichert, T.A., Balestra, C.E.T. and Medeiros-Junior, R.A. (2024), "Response Variability of Diffusion Models Applied to Chloride Concentration Profiles from Concrete Structures", J. Mater. Civil Eng., 36(1), 04023493. https://doi.org/10.1061/JMCEE7.MTENG-16262
  17. Hodhod, O.A. and Ahmed, H.I. (2013), "Developing an artificial neural network model to evaluate chloride diffusivity in high performance concrete", HBRC Journal, 9(1), 15-21. https://doi.org/10.1016/j.hbrcj.2013.04.001
  18. Hosseinpour, M., Shojaei, M.J., Salimi, M. and Amidpour, M. (2023), "Machine learning in absorption-based post-combustion carbon capture systems: A state-of-the-art review", Fuel, 353, 129265. https://doi.org/10.1016/j.fuel.2023.129265
  19. Inthata, S., Kowtanapanich, W. and Cheerarot, R. (2013), "Prediction of chloride permeability of concretes containing ground pozzolans by artificial neural networks", Mater. Struct., 46(10), 1707-1721. https://doi.org/10.1617/s11527-012-0009-x
  20. Issa, M. (2023), "Enhanced arithmetic optimization algorithm for parameter estimation of PID controller", Arab. J. Sci. Eng., 48(2), 2191-2205. https://doi.org/10.1007/s13369-022-07136-2
  21. Iwanaga, T., Usher, W. and Herman, J. (2022), "Toward SALib 2.0: Advancing the accessibility and interpretability of global sensitivity analyses", Socio-Environ. Syst. Modell., 4, 18155. https://doi.org/10.18174/sesmo.18155
  22. Kayhomayoon, Z., Arya Azar, N., Ghordoyee Milan, S., Berndtsson, R. and Najafi Marghmaleki, S. (2023), "Application of soft computing and evolutionary algorithms to estimate hydropower potential in multi-purpose reservoirs", Appl. Water Sci., 13(9), 183. https://doi.org/10.1007/s13201-023-02001-5
  23. Khaghanpour, R., Dousti, A. and Shekarchi, M. (2017), "Prediction of cover thickness based on long-term chloride penetration in a marine environment", J. Perform. Constr. Facil., 31(1), 4016070. https://doi.org/10.1061/(ASCE)CF.1943-5509.0000931
  24. Khoshroo, M., Javid, A.A.S. and Katebi, A. (2018), "Effect of chloride treatment curing condition on the mechanical properties and durability of concrete containing zeolite and micro-nano-bubble water", Constr. Build. Mater., 177, 417-427. https://doi.org/10.1016/j.conbuildmat.2018.05.086
  25. Li, H., Liu, J., Yang, L., Liu, L. and Sun, H. (2023), "An improved arithmetic optimization algorithm for task offloading in mobile edge computing", Cluster Comput., 27, 1667-1682. https://doi.org/10.1007/s10586-023-04048-0
  26. Liang, L., Su, T., Gao, Y., Qin, F. and Pan, M. (2023), "FCDT-IWBOA-LSSVR: An innovative hybrid machine learning approach for efficient prediction of short-to-mid-term photovoltaic generation", J. Cleaner Prod., 385, 135716. https://doi.org/10.1016/j.jclepro.2022.135716
  27. Liu, Q., Iqbal, M.F., Yang, J., Lu, X., Zhang, P. and Rauf, M. (2021), "Prediction of chloride diffusivity in concrete using artificial neural network: Modelling and performance evaluation", Constr. Build. Mater., 268, 121082. https://doi.org/10.1016/j.conbuildmat.2020.121082
  28. Liu, H., Zhang, X., Zhang, H., Li, C. and Chen, Z. (2023), "A reinforcement learning-based hybrid Aquila Optimizer and improved Arithmetic Optimization Algorithm for global optimization", Expert Syst. Applicat., 224, 119898. https://doi.org/10.1016/j.eswa.2023.119898
  29. Liu, W., Liu, G. and Zhu, X. (2024), "Applicability of machine learning algorithms in predicting chloride diffusion in concrete: modeling, evaluation, and feature analysis", Case Stud. Constr. Mater., 21, e03573. https://doi.org/10.1016/j.cscm.2024.e03573
  30. Mikaeili, O. and Shourian, M. (2024), "Application of hybridized ANN–GARCH, ANN–SETAR, MARS–SPSO, and CANFIS–SPSO meta-models for improving accuracy of monthly streamflow prediction", Soft Comput., 28, 6725-6740. https://doi.org/10.1007/s00500-023-09551-5
  31. Milan, S.G., Kayhomayoon, Z., Azar, N.A., Berndtsson, R., Ramezani, M.R. and Moghaddam, H.K. (2023), "Using machine learning to determine acceptable levels of groundwater consumption in Iran", Sustain. Product. Consump., 35, 388-400. https://doi.org/10.1016/j.spc.2022.11.018
  32. Mohamed, O., Kewalramani, M., Ati, M. and Al Hawat, W. (2021), "Application of ANN for prediction of chloride penetration resistance and concrete compressive strength", Materialia, 17, 101123. https://doi.org/10.1016/j.mtla.2021.101123
  33. Moradllo, M.K., Sadati, S. and Shekarchi, M. (2018), "Quantifying maximum phenomenon in chloride ion profiles and its influence on service-life prediction of concrete structures exposed to seawater tidal zone–a field oriented study", Constr. Build. Mater., 180, 109-116. https://doi.org/10.1016/j.conbuildmat.2018.05.284
  34. Najimi, M., Ghafoori, N. and Nikoo, M. (2019), "Modeling chloride penetration in self-consolidating concrete using artificial neural network combined with artificial bee colony algorithm", J. Build. Eng., 22, 216-226. https://doi.org/10.1016/j.jobe.2018.12.013
  35. Nguyen, T.-H., Tran, D.-H., Nguyen, N.-M., Vuong, H.-T., Chien-Cheng, C. and Cao, M.-T. (2023), "Accurately predicting the mechanical behavior of deteriorated reinforced concrete components using natural intelligence-integrated Machine learners", Constr. Build. Mater., 408, 133753. https://doi.org/10.1016/j.conbuildmat.2023.133753
  36. Nielsen, C.V. (2019), "Service Life Modeling of Chloride Ingress", ACI Mater. J., 116(5). https://doi.org/10.14359/51716823
  37. Parichatprecha, R. and Nimityongskul, P. (2009), "Analysis of durability of high performance concrete using artificial neural networks", Constr. Build. Mater., 23(2), 910-917. https://doi.org/10.1016/j.conbuildmat.2008.04.015
  38. Piri, J., Abdolahipour, M. and Keshtegar, B. (2023), "Advanced machine learning model for prediction of drought indices using hybrid SVR-RSM", Water Resour. Manag., 37(2), 683-712. https://doi.org/10.1007/s11269-022-03395-8
  39. Reichert, T.A., Balestra, C.E.T. and de Medeiros-Junior, R.A. (2024), "Coupled model on the variation of diffusion coefficient and surface chloride concentration in reinforced concrete structures over time", Constr. Build. Mater., 411, 134715. https://doi.org/10.1016/j.conbuildmat.2023.134715
  40. Roach, L., Rignanese, G.-M., Erriguible, A. and Aymonier, C. (2023), "Applications of machine learning in supercritical fluids research", J. Supercrit. Fluids, 202, 106051. https://doi.org/10.1016/j.supflu.2023.106051
  41. Sharafi, S., Ghaleni, M.M. and Scholz, M. (2023), "Comparison of predictions of daily evapotranspiration based on climate variables using different data mining and empirical methods in various climates of Iran", Heliyon, 9(2). https://doi.org/10.1016/j.heliyon.2023.e13245
  42. Shekarchi, M., Rafiee, A. and Layssi, H. (2009), "Long-term chloride diffusion in silica fume concrete in harsh marine climates", Cement Concrete Compos., 31(10), 769-775. https://doi.org/10.1016/j.cemconcomp.2009.08.005
  43. Song, H.-W. and Kwon, S.-J. (2009), "Evaluation of chloride penetration in high performance concrete using neural network algorithm and micro pore structure", Cement Concrete Res., 39(9), 814-824. https://doi.org/10.1016/j.cemconres.2009.05.013
  44. Suykens, J.A.K. and Vandewalle, J. (1999), "Least Squares Support Vector Machine Classifiers", Neural Process. Lett., 9(3), 293-300. https://doi.org/10.1023/A:1018628609742
  45. Tadayon, M.H., Shekarchi, M. and Tadayon, M. (2016), "Long-term field study of chloride ingress in concretes containing pozzolans exposed to severe marine tidal zone", Constr. Build. Mater., 123, 611-616. https://doi.org/10.1016/j.conbuildmat.2016.07.074
  46. Taylor, K.E. (2001), "Summarizing multiple aspects of model performance in a single diagram", J. Geophys. Res.: Atmosph., 106(D7), 7183-7192. https://doi.org/10.1029/2000JD900719
  47. Tran, V.Q., Mai, H.T., To, Q.T. and Nguyen, M.H. (2023), "Machine learning approach in investigating carbonation depth of concrete containing Fly ash", Struct. Concrete, 24(2), 2145-2169. https://doi.org/10.1002/suco.202200269
  48. Valipour, M., Pargar, F., Shekarchi, M., Khani, S. and Moradian, M. (2013), "In situ study of chloride ingress in concretes containing natural zeolite, metakaolin and silica fume exposed to various exposure conditions in a harsh marine environment", Constr. Build. Mater., 46, 63-70. https://doi.org/10.1016/j.conbuildmat.2013.03.026
  49. Valipour, M., Shekarchi, M. and Arezoumandi, M. (2017), "Chlorine diffusion resistivity of sustainable green concrete in harsh marine environments", J. Cleaner Prod., 142, 4092-4100. https://doi.org/10.1016/j.jclepro.2016.10.015
  50. Yıldız, B.S., Kumar, S., Panagant, N., Mehta, P., Sait, S.M., Yildiz, A.R., Pholdee, N., Bureerat, S. and Mirjalili, S. (2023), "A novel hybrid arithmetic optimization algorithm for solving constrained optimization problems", Knowl.-Based Syst., 271, 110554. https://doi.org/10.1016/j.knosys.2023.110554