Computers and Concrete

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Deep learning method for compressive strength prediction for lightweight concrete

  • Yaser A. Nanehkaran (School of Information Engineering, Yancheng Teachers University) ;
  • Mohammad Azarafza (Department of Civil Engineering, University of Tabriz) ;
  • Tolga Pusatli (Department of Management Information Systems, Cankaya University) ;
  • Masoud Hajialilue Bonab (Department of Civil Engineering, University of Tabriz) ;
  • Arash Esmatkhah Irani (Department of Civil Engineering, Islamic Azad University) ;
  • Mehdi Kouhdarag (Department of Civil Engineering, Malekan Branch, Islamic Azad University) ;
  • Junde Chen (Department of Electronic Commerce, Xiangtan University) ;
  • Reza Derakhshani (Department of Earth Sciences, Utrecht University)
  • Received : 2023.02.25
  • Accepted : 2023.06.20
  • Published : 2023.09.25
⟨ Previous Next ⟩

Abstract

Concrete is the most widely used building material, with various types including high- and ultra-high-strength, reinforced, normal, and lightweight concretes. However, accurately predicting concrete properties is challenging due to the geotechnical design code's requirement for specific characteristics. To overcome this issue, researchers have turned to new technologies like machine learning to develop proper methodologies for concrete specification. In this study, we propose a highly accurate deep learning-based predictive model to investigate the compressive strength (UCS) of lightweight concrete with natural aggregates (pumice). Our model was implemented on a database containing 249 experimental records and revealed that water, cement, water-cement ratio, fine-coarse aggregate, aggregate substitution rate, fine aggregate replacement, and superplasticizer are the most influential covariates on UCS. To validate our model, we trained and tested it on random subsets of the database, and its performance was evaluated using a confusion matrix and receiver operating characteristic (ROC) overall accuracy. The proposed model was compared with widely known machine learning methods such as MLP, SVM, and DT classifiers to assess its capability. In addition, the model was tested on 25 laboratory UCS tests to evaluate its predictability. Our findings showed that the proposed model achieved the highest accuracy (accuracy=0.97, precision=0.97) and the lowest error rate with a high learning rate (R2=0.914), as confirmed by ROC (AUC=0.971), which is higher than other classifiers. Therefore, the proposed method demonstrates a high level of performance and capability for UCS predictions.

Keywords

Acknowledgement

The authors would like to thank the anonymous reviewers for providing invaluable review comments and recommendations for improving the scientific level of the article. This research was funded by the National Nature Science Foundation of China (Grant ID: 42250410321).

References

  1. ACI 318 (2008), Building Code Requirements for Structural Concrete (ACI 318-08) and Commentary, American Concrete Institute, Farmington Hills, MI, USA.
  2. Aggrawal, C. (2018), Neural Networks and Deep Learning: A Textbook, Springer Berlin/Heidelberg, Berlin, Germany.
  3. Ahmad, A., Ahmad, W., Aslam, F. and Joyklad, P. (2022), "Compressive strength prediction of fly ash-based geopolymer concrete via advanced machine learning techniques", Case Stud. Constr. Mater., 16, e00840. https://doi.org/10.1016/j.cscm.2021.e00840.
  4. Aiyer, B.G., Kim, D., Karingattikkal, N., Samui, P. and Rao, P.R. (2014), "Prediction of compressive strength of self-compacting concrete using least square support vector machine and relevance vector machine", KSCE J. Civil Eng., 18, 1753-1758. https://doi.org/10.1007/s12205-014-0524-0.
  5. Akers, D.J., Gruber, R.D., Ramme, B.W., Boyle, M.J., Grygar, J.G., Rowe, S.K., Bremner, T.W., Kluckowski, E.S., Sheetz, S.R. and Burg, R.G. (2003), "Guide for structural lightweight-aggregate concrete", ACI 213R-03, American Concrete Institute (ACI), Farmington Hills, MI, USA.
  6. Al-Haidari, H.S.J. and Al-Haydari, I.S. (2022), "Artificial intelligence-based compressive strength prediction of medium to high strength concrete", Iran. J. Sci. Technol., Trans. Civil Eng., 46, 951-964. https://doi.org/10.1007/s40996-021-00717-5.
  7. Al-Shamiri, A.K., Kim, J.H., Yuan, T.F. and Yoon, Y.S. (2019), "Modeling the compressive strength of high-strength concrete: An extreme learning approach", Constr. Build. Mater., 208, 204-219. https://doi.org/10.1016/j.conbuildmat.2019.02.165.
  8. Alshihri, M.M., Azmy, A.M. and El-Bisy, M.S. (2009), "Neural networks for predicting compressive strength of structural light weight concrete", Constr. Build. Mater., 23, 2214-2219. https://doi.org/10.1016/j.conbuildmat.2008.12.003.
  9. Aslam, M., Shafigh, P., Jumaat, M.Z. and Lachemi, M. (2016), "Benefits of using blended waste coarse lightweight aggregates in structural lightweight aggregate concrete", J. Clean. Product., 119, 108-117. https://doi.org/10.1016/j.jclepro.2016.01.071.
  10. Asteris, P.G., Skentou, A.D., Bardhan, A., Samui, P. and Pilakoutas, K. (2021), "Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models", Cement Concrete Res., 145, 106449. https://doi.org/10.1016/j.cemconres.2021.106449.
  11. ASTM C109 (2013), Standard Test Method for Compressive Strength of Hydraulic Cement Mortars (Using 2-in. or [50-mm] Cube Specimens), ASTM International, West Conshohocken, PA, USA.
  12. ASTM C39 (2014), Standard Test Method for Compressive Strength of Cylindrical Concrete Specimens, ASTM International, West Conshohocken, PA, USA.
  13. ASTM C494 (2005), Standard Specification for Chemical Admixtures for Concrete, ASTM International, West Conshohocken, PA, USA.
  14. Azarafza, M., Feizi-Derakhshi, M.R. and Azarafza, M. (2017), "Computer modeling of crack propagation in concrete retaining walls: A case study", Comput. Concrete, 19, 509-514. https://doi.org/10.12989/cac.2017.19.5.509.
  15. Azarafza, M., Hajialilue Bonab, M. and Derakhshani, R. (2022), "A deep learning method for the prediction of the index mechanical properties and strength parameters of marlstone", Mater., 15, 6899. https://doi.org/10.3390/ma15196899.
  16. Basu, S., Thirumalaiselvi, A., Sasmal, S. and Kundu, T. (2021), "Nonlinear ultrasonics-based technique for monitoring damage progression in reinforced concrete structures", Ultrasonics, 115, 106472. https://doi.org/10.1016/j.ultras.2021.106472.
  17. Chaipanich, A. and Chindaprasirt, P. (2015), "The properties and durability of autoclaved aerated concrete masonry blocks", Eco-Efficient Masonry Bricks and Blocks, Elsevier, Cambridge, UK.
  18. Chen, H., Li, X., Wu, Y., Zuo, L., Lu, M. and Zhou, Y. (2022), "Compressive strength prediction of high-strength concrete using long short-term memory and machine learning algorithms", Build., 12, 302. https://doi.org/10.3390/buildings12030302.
  19. Chollet, F. (2017), Deep learning with Python, Manning Publications Company, New York, NY, USA.
  20. Cree, D., Green, M. and Noumowe, A. (2013), "Residual strength of concrete containing recycled materials after exposure to fire: A review", Constr. Build. Mater., 45, 208-223. https://doi.org/10.1016/j.conbuildmat.2013.04.005.
  21. Deng, F., He, Y., Zhou, S., Yu, Y., Cheng, H. and Wu, X. (2018), "Compressive strength prediction of recycled concrete based on deep learning", Constr. Build. Mater., 175, 562-569. https://doi.org/10.1016/j.conbuildmat.2018.04.169.
  22. Dutta, S., Murthy, A.R., Kim, D. and Samui, P. (2017), "Prediction of compressive strength of self-compacting concrete using intelligent computational modeling", Comput. Mater. Contin., 53, 167-185. https://doi.org/10.3970/cmc.2017.053.167.
  23. Dutta, S., Samui, P. and Kim, D. (2018), "Comparison of machine learning techniques to predict compressive strength of concrete", Comput. Concrete, 21(4), 463-470. https://doi.org/10.12989/cac.2018.21.4.463.
  24. Elango, K., Sanfeer, J., Gopi, R., Shalini, A., Saravanakumar, R. and Prabhu, L. (2021), "Properties of light weight concrete-a state of the art review", Mater. Today: Proc., 46, 4059-4062. https://doi.org/10.1016/j.matpr.2021.02.571.
  25. Farooq, F., Ahmed, W., Akbar, A., Aslam, F. and Alyousef, R. (2021), "Predictive modeling for sustainable high-performance concrete from industrial wastes: A comparison and optimization of models using ensemble learners", J. Clean. Product., 292, 126032. https://doi.org/10.1016/j.jclepro.2021.126032.
  26. Ferreira, T.R., Archilha, N.L. and Pires, L.F. (2022), "An analysis of three XCT-based methods to determine the intrinsic permeability of soil aggregates", J. Hydrol., 612, 128024. https://doi.org/10.1016/j.jhydrol.2022.128024.
  27. Hearty, J. (2016), Advanced Machine Learning with Python, Packt Publishing Ltd, Birmingham, UK.
  28. Hu, T., Zhao, J., Zheng, R., Wang, P., Li, X. and Zhang, Q. (2021), "Ultrasonic based concrete defects identification via wavelet packet transform and GA-BP neural network", Peer J. Comput. Sci., 7, e635. https://doi.org/10.7717/peerj-cs.635.
  29. Kaloop, M.R., Kumar, D., Samui, P., Hu, J.W. and Kim, D. (2020), "Compressive strength prediction of high-performance concrete using gradient tree boosting machine", Constr. Build. Mater., 264, 120198. https://doi.org/10.1016/j.conbuildmat.2020.120198.
  30. Kaloop, M.R., Samui, P., Iqbal, M. and Hu, J.W. (2022), "Soft computing approaches towards tensile strength estimation of GFRP rebars subjected to alkaline-concrete environment", Case Stud. Constr. Mater., 16, e00955. https://doi.org/10.1016/j.cscm.2022.e00955.
  31. Kandiri, A., Sartipi, F. and Kioumarsi, M. (2021), "Predicting compressive strength of concrete containing recycled aggregate using modified ANN with different optimization algorithms", Appl. Sci., 11, 485. https://doi.org/10.3390/app11020485.
  32. Kim, Y.J., Choi, Y.W. and Lachemi, M. (2010), "Characteristics of self-consolidating concrete using two types of lightweight coarse aggregates", Constr. Build. Mater., 24, 11-16. https://doi.org/10.1016/j.conbuildmat.2009.08.004.
  33. Kumar, A., Arora, H.C., Kapoor, N.R., Mohammed, M.A., Kumar, K., Majumdar, A. and Thinnukool, O. (2022), "Compressive strength prediction of lightweight concrete: Machine learning models", Sustainab., 14, 2404. https://doi.org/10.3390/su14042404.
  34. Kumar, V.K., Priya, A., Manikandan, G., Naveen, A., Nitishkumar, B. and Pradeep, P. (2021), "Review of materials used in light weight concrete", Mater. Today: Proc., 37, 3538-3539. https://doi.org/10.1016/j.matpr.2020.09.425.
  35. LeCun, Y., Bengio, Y. and Hinton, G. (2015), "Deep learning", Nat., 521, 436-444. https://doi.org/10.1038/nature14539.
  36. Li, Q.F. and Song, Z.M. (2022), "High-performance concrete strength prediction based on ensemble learning", Constr. Build. Mater., 324, 126694. https://doi.org/10.1016/j.conbuildmat.2022.126694.
  37. Lin, H.J., Liao, C.I., Yang, C. (2006), "A numerical analysis of compressive strength ofrnrectangular concrete columns confined by FRP", Comput. Concrete, 3(4), 235-248. https://doi.org/10.12989/cac.2006.3.4.235.
  38. Mo, K.H., Alengaram, U.J. and Jumaat, M.Z. (2016), "Bond properties of lightweight concrete-a review", Constr. Build. Mater., 112, 478-496. https://doi.org/10.1016/j.conbuildmat.2016.02.125.
  39. Mohammed, J.H. and Hamad, A.J. (2014), "Materials, properties and application review of lightweight concrete", Tech. Rev. Fac. Eng. Univ. Zulia, 37(2), 10-15.
  40. Muliauwan, H., Prayogo, D., Gaby, G. and Harsono, K. (2020), "Prediction of concrete compressive strength using artificial intelligence methods", J. Phys. Conf. Seri., 1625, 012018. https://doi.org/10.1088/1742-6596/1625/1/012018.
  41. Muller, A.C. and Guido, S. (2016), Introduction to Machine Learning with Python: A Guide for Data Scientists, O'Reilly Media, Inc., Sebastopol, CA, USA.
  42. Ofuyatan, O.M., Olutoge, F., Omole, D. and Babafemi, A. (2021), "Influence of palm ash on properties of light weight self-compacting concrete", Clean. Eng. Technol., 4, 100233. https://doi.org/10.1016/j.clet.2021.100233.
  43. Ramadoss, P. and Nagamani, K. (2012), "Statistical methods of investigation on the compressive strength of high-performance steel fiber reinforced concrete", Comput. Concrete, 9(2), 53-169. https://doi.org/10.12989/cac.2012.9.2.153.
  44. Rumsys, D., Spudulis, E., Bacinskas, D. and Kaklauskas, G. (2018), "Compressive strength and durability properties of structural lightweight concrete with fine expanded glass and/or clay aggregates", Mater., 11, 2434. https://doi.org/10.3390/ma11122434.
  45. Tabsh, S.W. (2006), "Elimination of the effect of strain gradient from concrete compressive strength test results", Comput. Concrete, 3(6), 375-388. https://doi.org/10.12989/cac.2006.3.6.375.
  46. Tanyildizi, H. (2021), "Predicting the geopolymerization process of fly ash-based geopolymer using deep long short-term memory and machine learning", Cement Concrete Compos., 123, 104177. https://doi.org/10.1016/j.cemconcomp.2021.104177.
  47. Tanyildizi, H., Sengur, A., Akbulut, Y. and Sahin, M. (2020), "Deep learning model for estimating the mechanical properties of concrete containing silica fume exposed to high temperatures", Front. Struct. Civil Eng., 14, 1316-1330. https://doi.org/10.1007/s11709-020-0646-z.
  48. Thienel, K.C., Haller, T. and Beuntner, N. (2020), "Lightweight concrete-From basics to innovations", Mater., 13, 1120. https://doi.org/10.3390/ma13051120.
  49. Tien Bui, D., Abdullahi, M.A.M., Ghareh, S., Moayedi, H. and Nguyen, H. (2021), "Fine-tuning of neural computing using whale optimization algorithm for predicting compressive strength of concrete", Eng. Comput., 37, 701-712. https://doi.org/10.1007/s00366-019-00850-w.
  50. Vakhshouri, B. and Nejadi, S. (2018), "Review on the mixture design and mechanical properties of the lightweight concrete containing expanded polystyrene beads", Australian J. Struct. Eng., 19, 1-23. https://doi.org/10.1080/13287982.2017.1353330.
  51. Wongkeo, W., Thongsanitgarn, P., Pimraksa, K. and Chaipanich, A. (2012), "Compressive strength, flexural strength and thermal conductivity of autoclaved concrete block made using bottom ash as cement replacement materials", Mater. Des., 35, 434-439. https://doi.org/10.1016/j.matdes.2011.08.046.
  52. Yuzer, N., Akbas, B. and Kizilkanat, A.B. (2011), "Predicting the high temperature effect on mortar compressive strength by neural network", Comput. Concrete, 8(5), 491-510. https://doi.org/10.12989/cac.2011.8.5.491.
  53. Zhu, W., Huang, L., Mao, L. and Esmaeili-Falak, M. (2022), "Predicting the uniaxial compressive strength of oil palm shell lightweight aggregate concrete using artificial intelligence-based algorithms", Struct. Concrete, 23, 3631-3650. https://doi.org/10.1002/suco.202100656.