Computers and Concrete

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Intelligent prediction of engineered cementitious composites with limestone calcined clay cement (LC3-ECC) compressive strength based on novel machine learning techniques

  • Enming Li (Universidad Politecnica de Madrid-ETSI Minasy Energia) ;
  • Ning Zhang (Leibniz Institute of Ecological Urban and Regional Development (IOER)) ;
  • Bin Xi (Department of Civil and Environmental Engineering, Politecnico Di Milano) ;
  • Vivian WY Tam (School of Engineering, Design and Built Environment, Western Sydney University) ;
  • Jiajia Wang (Department of Real Estate and Construction, The University of Hong Kong) ;
  • Jian Zhou (School of Resources and Safety Engineering, Central South University)
  • Received : 2020.12.10
  • Accepted : 2023.07.24
  • Published : 2023.12.25
⟨ Previous Next ⟩

Abstract

Engineered cementitious composites with calcined clay limestone cement (LC3-ECC) as a kind of green, low-carbon and high toughness concrete, has recently received significant investigation. However, the complicated relationship between potential influential factors and LC3-ECC compressive strength makes the prediction of LC3-ECC compressive strength difficult. Regarding this, the machine learning-based prediction models for the compressive strength of LC3-ECC concrete is firstly proposed and developed. Models combine three novel meta-heuristic algorithms (golden jackal optimization algorithm, butterfly optimization algorithm and whale optimization algorithm) with support vector regression (SVR) to improve the accuracy of prediction. A new dataset about LC3-ECC compressive strength was integrated based on 156 data from previous studies and used to develop the SVR-based models. Thirteen potential factors affecting the compressive strength of LC3-ECC were comprehensively considered in the model. The results show all hybrid SVR prediction models can reach the Coefficient of determination (R2) above 0.95 for the testing set and 0.97 for the training set. Radar and Taylor plots also show better overall prediction performance of the hybrid SVR models than several traditional machine learning techniques, which confirms the superiority of the three proposed methods. The successful development of this predictive model can provide scientific guidance for LC3-ECC materials and further apply to such low-carbon, sustainable cement-based materials.

Keywords

Acknowledgement

Bin Xi and Enming Li want to acknowledge the funding supported by China Scholarship Council under grant No. 202008440524 and 202006370006, respectively. This research is partially supported by the Distinguished Youth Science Foundation of Hunan Province of China (2022JJ10073) and the Innovation Driven Project of Central South University (2020CX040).

References

  1. Abdi, H. and Williams, L.J. (2010), "Principal component analysis", Wiley Interdiscip. Rev. Comput. Stat., 2(4), 433-459. https://doi.org/10.1002/wics.101.
  2. Achirul Nanda, M., Boro Seminar, K., Nandika, D. and Maddu, A. (2018), "A comparison study of kernel functions in the support vector machine and its application for termite detection", Information, 9(1), 5. https://doi.org/10.3390/info9010005.
  3. Adesina, A. and Das, S. (2021), "Evaluation of the durability properties of engineered cementitious composites incorporating recycled concrete as aggregate", J. Mater. Civil Eng., 33(2), 04020439. https://doi.org/10.1061/(ASCE)MT.1943-5533.0003563.
  4. Altwair, N.M., Megat Johari, M.A. and Saiyid Hashim, S.F. (2012), "Flexural performance of green engineered cementitious composites containing high volume of palm oil fuel ash", Constr. Build. Mater., 37, 518-525. https://doi.org/10.1016/j.conbuildmat.2012.08.003.
  5. Arora, S. and Singh, S. (2019), "Butterfly optimization algorithm: A novel approach for global optimization", Soft Comput., 23(3), 715-734. https://doi.org/10.1007/s00500-018-3102-4.
  6. Bansal, T., Talakokula, V. and Mathiyazhagan, K. (2022a), "Equivalent structural parameters based non-destructive prediction of sustainable concrete strength using machine learning models via piezo sensor", Measure., 187, 110202. https://doi.org/10.1016/j.measurement.2021.110202.
  7. Bansal, T., Talakokula, V. and Sathujoda, P. (2022b), "Machine learning-based monitoring and predicting the compressive strength of different blended cementitious systems using embedded piezo-sensor data", Measure., 205, 112204. https://doi.org/10.1016/j.measurement.2022.112204.
  8. Benesty, J., Chen, J., Huang, Y. and Cohen, I. (2009), "Pearson correlation coefficient", Noise Reduction in Speech Processing, Springer, Berlin, Heidelberg, Germany.
  9. Biswas, R., Bardhan, A., Samui, P., Rai, B., Nayak, S. and Armaghani, D.J. (2021), "Efficient soft computing techniques for the prediction of compressive strength of geopolymer concrete", Comput. Concrete, 28(2), 221-232. https://doi.org/10.12989/cac.2021.28.2.221.
  10. Cai, Z., Liu, F., Yu, J., Yu, K. and Tian, L. (2021), "Development of ultra-high ductility engineered cementitious composites as a novel and resilient fireproof coating", Constr. Build. Mater., 288, 123090. https://doi.org/10.1016/j.conbuildmat.2021.123090.
  11. Calis, G., Akpinar, M.E., Yildizel, S.A. and Cogurcu, M.T. (2021), "Evaluation and optimization of PVA reinforced cementitious composite containing metakaolin and fly ash", Rev. Rom. Mater. Rom. J. Mater., 51, 53-66.
  12. Chopra, N. and Mohsin Ansari, M. (2022), "Golden jackal optimization: A novel nature-inspired optimizer for engineering applications", Expert Syst. Appl., 198, 116924. https://doi.org/10.1016/j.eswa.2022.116924.
  13. Dao, D., Ly, H.B., Trinh, S., Le, T.T. and Pham, B. (2019), "Artificial intelligence approaches for prediction of compressive strength of geopolymer concrete", Mater., 12(6), 983. https://doi.org/10.3390/ma12060983.
  14. Dhandapani, Y., Sakthivel, T., Santhanam, M., Gettu, R. and Pillai, R.G. (2018), "Mechanical properties and durability performance of concretes with limestone calcined clay cement (LC3)", Cement Concrete Res., 107, 136-151. https://doi.org/10.1016/j.cemconres.2018.02.005.
  15. Ding, Y., Yu, K. and Li, M. (2022), "A review on high-strength engineered cementitious composites (HS-ECC): Design, mechanical property and structural application", Struct., 35, 903-921. https://doi.org/10.1016/j.istruc.2021.10.036.
  16. Ding, Y., Yu, K. and Mao, W. (2020), "Compressive performance of all-grade engineered cementitious composites: Experiment and theoretical model", Constr. Build. Mater., 244, 118357. https://doi.org/10.1016/j.conbuildmat.2020.118357.
  17. Du, H. and Pang, S.D. (2020), "High-performance concrete incorporating calcined kaolin clay and limestone as cement substitute", Constr. Build. Mater., 264, 120152. https://doi.org/10.1016/j.conbuildmat.2020.120152.
  18. 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.
  19. Erdal, H., Erdal, M., Simsek, O. and Erdal, H.I. (2018), "Prediction of concrete compressive strength using non-destructive test results", Comput. Concrete, 21(4), 407-417. https://doi.org/10.12989/cac.2018.21.4.407.
  20. Faramarzi, A., Heidarinejad, M., Mirjalili, S. and Gandomi, A.H. (2020), "Marine predators algorithm: A nature-inspired metaheuristic", Expert Syst. Appl., 152, 113377. https://doi.org/10.1016/j.eswa.2020.113377.
  21. Farooq, F., Nasir Amin, M., Khan, K., Rehan Sadiq, M., Faisal Javed, M.F., Aslam, F. and Alyousef, R. (2020), "A comparative study of random forest and genetic engineering programming for the prediction of compressive strength of high strength concrete (HSC)", Appl. Sci., 10(20), 7330. https://doi.org/10.3390/app10207330.
  22. Garg, A., Aggarwal, P., Aggarwal, Y., Belarbi, M.O., Chalak, H.D., Tounsi, A. and Gulia, R. (2022), "Machine learning models for predicting the compressive strength of concrete containing nano silica", Comput. Concrete, 30(1), 33-42. https://doi.org/10.12989/cac.2022.30.1.033.
  23. Gong, G., Guo, M., Zhou, Y., Zheng, S., Hu, B., Zhu, Z. and Huang, Z. (2022), "Multiscale investigation on the performance of engineered cementitious composites incorporating PE fiber and limstone calcined clay cement (LC3)", Polym., 14(7), 1291. https://doi.org/10.3390/polym14071291.
  24. Ivanciuc, O. (2007), "Applications of support vector machines in chemistry", Rev. Comput. Chem., 23, 291-400. https://doi.org/10.1002/9780470116449.ch6.
  25. Joseph, S., Dhandapani, Y., Geddes, D.A., Zhao, Z., Bishnoi, S., Vieira, M., Martirena, F., Castel, A., Kanavaris, F., Bansal, T. and Riding, K.A. (2023), "Mechanical properties of concrete made with calcined clay: A review by RILEM TC-282 CCL", Mater. Struct. Constr., 56(4), 1-20. https://doi.org/10.1617/s11527-023-02118-8.
  26. Lepech, M.D., Li, V.C., Robertson, R.E. and Keoleian, G.A. (2008), "Design of green engineered cementitious composites for improved sustainability", ACI Mater. J., 105(6), 567-575. https://doi.org/10.14359/20198.
  27. Li, E., Yang, F., Ren, M., Zhang, X., Zhou, J. and Khandelwal, M. (2021a), "Prediction of blasting mean fragment size using support vector regression combined with five optimization algorithms", J. Rock Mech. Geotech. Eng., 13(6), 1380-1397. https://doi.org/10.1016/j.jrmge.2021.07.013.
  28. Li, E., Zhang, N., Xi, B., Zhou, J. and Gao, X. (2023), "Compressive strength prediction and optimization design of sustainable concrete based on squirrel search algorithm-extreme gradient boosting technique", Front. Struct. Civil Eng., Accpeted. https://doi.org/10.1007/s11709-023-0997-3.
  29. Li, E., Zhou, J., Shi, X., Jahed Armaghani, D., Yu, Z., Chen, X. and Huang, P. (2021b), "Developing a hybrid model of salp swarm algorithm-based support vector machine to predict the strength of fiber-reinforced cemented paste backfill", Eng. Comput., 37(4), 3519-3540. https://doi.org/10.1007/s00366-020-01014-x.
  30. Li, V.C. (2003), "On engineered cementitious composites (ECC) a review of the material and its applications", J. Adv. Concrete Technol., 1(3), 215-230. https://doi.org/10.3151/jact.1.215.
  31. Lin, R.S., Han, Y. and Wang, X.Y. (2021), "Macro-meso-micro experimental studies of calcined clay limestone cement (LC3) paste subjected to elevated temperature", Cement Concrete Compos., 116, 103871. https://doi.org/10.1016/j.cemconcomp.2020.103871.
  32. Lin, X., Yu, J., Li, H., Lam, J.Y.K., Shih, K., Sham, I.M.L. and Leung, C.K.Y. (2018), "Recycling polyethylene terephthalate wastes as short fibers in strain-hardening cementitious composites (SHCC)", J. Hazard. Mater., 357, 40-52. https://doi.org/10.1016/j.jhazmat.2018.05.046.
  33. Liu, H., Zhang, Q., Li, V., Su, H. and Gu, C. (2017), "Durability study on engineered cementitious composites (ECC) under sulfate and chloride environment", Constr. Build. Mater., 133, 171-181. https://doi.org/10.1016/j.conbuildmat.2016.12.074.
  34. Liu, J., Zhang, W., Li, Z., Jin, H., Liu, W. and Tang, L. (2021), "Investigation of using limestone calcined clay cement (LC3) in engineered cementitious composites: The effect of propylene fibers and the curing system", J. Mater. Res. Technol., 15, 2117-2144. https://doi.org/10.1016/j.jmrt.2021.09.023.
  35. Ma, H., Qian, S., Zhang, Z., Lin, Z. and Li, V.C. (2015), "Tailoring engineered cementitious composites with local ingredients", Constr. Build. Mater., 101, 584-595. https://doi.org/10.1016/j.conbuildmat.2015.10.146.
  36. Ma, H., Yi, C. and Wu, C. (2021), "Review and outlook on durability of engineered cementitious composite (ECC)", Constr. Build. Mater., 287, 122719. https://doi.org/10.1016/j.conbuildmat.2021.122719.
  37. Mardani-Aghabaglou, A., Tuyan, M., Yilmaz, G., Arioz, O. and Ramyar, K. (2013), "Effect of different types of superplasticizer on fresh, rheological and strength properties of self-consolidating concrete", Constr. Build. Mater., 47, 1020-1025. https://doi.org/10.1016/j.conbuildmat.2013.05.105.
  38. Mirjalili, S. and Lewis, A. (2016), "The whale optimization algorithm", Adv. Eng. Softw., 95, 51-67. https://doi.org/10.1016/j.advengsoft.2016.01.008.
  39. Nguyen, H., Vu, T., Vo, T.P. and Thai, H.T. (2021), "Efficient machine learning models for prediction of concrete strengths", Constr. Build. Mater., 266, 120950. https://doi.org/10.1016/j.conbuildmat.2020.120950.
  40. Ozbay, E., Karahan, O., Lachemi, M., Hossain, K.M.A. and Duran Atis, C. (2012), "Investigation of Properties of engineered cementitious composites incorporating high volumes of fly ash and metakaolin", ACI Mater. J., 109(5), 565-572. https://doi.org/10.14359/51684088.
  41. Ozcan, G., Kocak, Y. and Gulbandilar, E. (2017), "Estimation of compressive strength of BFS and WTRP blended cement mortars with machine learning models", Comput. Concrete, 19(3), 275-282. https://doi.org/10.12989/cac.2017.19.3.275.
  42. Pesaralanka, V. and Khed, V.C. (2021), "Flowability and compressive strength of lime stone calcinated clay cement based ECC", IOP Conf. Ser. Mater. Sci. Eng., 1197(1), 012084. https://doi.org/10.1088/1757-899X/1197/1/012084.
  43. Popovics, S. and Ujhelyi, J. (2008), "Contribution to the concrete strength versus water-cement ratio relationship", J. Mater. Civil Eng., 20(7), 459-463. https://doi.org/10.1061/(ASCE)0899-1561(2008)20:7(459).
  44. Qi, C. and Tang, X. (2018), "A hybrid ensemble method for improved prediction of slope stability", Int. J. Numer. Anal. Methods Geomech., 42(15), 1823-1839. https://doi.org/10.1002/nag.2834.
  45. Qiu, Y., Zhou, J., Khandelwal, M., Yang, H., Yang, P. and Li, C. (2022), "Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration", Eng. Comput., 38(S5), 4145-4162. https://doi.org/10.1007/s00366-021-01393-9.
  46. Rossen, J.E. (2014), "Composition and morphology of C-A-S-H in pastes of alite and cement blended with supplementary cementitious materials", Ph.D. Dessertation, Ecole Polytechnique Federale de Lausanne, Lausanne, Switzerland.
  47. Sanchez Berriel, S., Favier, A., Rosa Dominguez, E., Sanchez Machado, I.R., Heierli, U., Scrivener, K., Martirena Hernandez, F. and Habert, G. (2016), "Assessing the environmental and economic potential of limestone calcined clay cement in Cuba", J. Clean. Prod., 124, 361-369. https://doi.org/10.1016/j.jclepro.2016.02.125.
  48. Scrivener, K., Martirena, F., Bishnoi, S. and Maity, S. (2018), "Calcined clay limestone cements (LC3)", Cement Concrete Res., 114, 49-56. https://doi.org/10.1016/j.cemconres.2017.08.017.
  49. Sharma, M., Bishnoi, S., Martirena, F. and Scrivener, K. (2021), "Limestone calcined clay cement and concrete: A state-of-the-art review", Cement Concrete Res., 149, 106564. https://doi.org/10.1016/j.cemconres.2021.106564.
  50. Smola, A.J. and Scholkopf, B. (2004), "A tutorial on support vector regression", Stat. Comput., 14(3), 199-222. https://doi.org/10.1023/B:STCO.0000035301.49549.88.
  51. Taylor, K.E. (2001), "Summarizing multiple aspects of model performance in a single diagram", J. Geophys. Res. Atmos., 106(D7), 7183-7192. https://doi.org/10.1029/2000JD900719.
  52. Tien Bui, D., Abdullahi, M.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(1), 701-712. https://doi.org/10.1007/s00366-019-00850-w.
  53. Wang, L., Rehman, N.U., Curosu, I., Zhu, Z., Beigh, M.A.B., Liebscher, M. and Mechtcherine, V. (2021), "On the use of limestone calcined clay cement (LC3) in high-strength strain-hardening cement-based composites (HS-SHCC)," Cement Concrete Res., 144, 106421. https://doi.org/10.1016/j.cemconres.2021.106421.
  54. Xi, B., Li, E., Fissha, Y., Zhou, J. and Segarra, P. (2023), "LGBM-based modeling scenarios to compressive strength of recycled aggregate concrete with SHAP analysis", Mech. Adv. Mater. Struct., 2023, 1-16. https://doi.org/10.1080/15376494.2023.2224782.
  55. Xi, B., Zhou, Y., Yu, K., Hu, B., Huang, X., Sui, L. and Xing, F. (2020), "Use of nano-SiO2 to develop a high performance green lightweight engineered cementitious composites containing fly ash cenospheres", J. Clean. Prod., 262, 121274. https://doi.org/10.1016/j.jclepro.2020.121274.
  56. Yu, J. and Leung, C.K.Y. (2020a), "Sustainable PVA fiber-reinforced strain-hardening cementitious composites (SHCC) with ultrahigh-volume limestone calcined clay", Proceedings of the 3rd International Conference on Calcined Clays for Sustainable Concrete, New Delhi, India, October.
  57. Yu, J. and Leung, C.K.Y. (2020b), "Using limestone calcined clay to improve tensile performance and greenness of high-tensile strength strain-hardening cementitious composites (SHCC)", Proceedings of the 3rd International Conference on Calcined Clays for Sustainable Concrete, New Delhi, India, October.
  58. Yu, J., Wu, H.L. and Leung, C.K.Y. (2020c), "Feasibility of using ultrahigh-volume limestone-calcined clay blend to develop sustainable medium-strength Engineered Cementitious Composites (ECC)", J. Clean. Prod., 262, 121343. https://doi.org/10.1016/j.jclepro.2020.121343.
  59. Yu, J., Yao, J., Lin, X., Li, H., Lam, J.Y.K., Leung, C.K.Y., Sham, I.M.L. and Shih, K. (2018), "Tensile performance of sustainable strain-hardening cementitious composites with hybrid PVA and recycled PET fibers", Cement Concrete Res., 107, 110-123. https://doi.org/10.1016/j.cemconres.2018.02.013.
  60. Yu, K., Li, L., Yu, J., Xiao, J., Ye, J. and Wang, Y. (2018), "Feasibility of using ultra-high ductility cementitious composites for concrete structures without steel rebar", Eng. Struct., 170, 11-20. https://doi.org/10.1016/j.engstruct.2018.05.037.
  61. Zhang, D., Jaworska, B., Zhu, H., Dahlquist, K. and Li, V.C. (2020), "Engineered cementitious composites (ECC) with limestone calcined clay cement (LC3)", Cement Concrete Compos., 114, 103766. https://doi.org/10.1016/j.cemconcomp.2020.103766.
  62. Zhang, N., Xi, B., Li, J., Liu, L. and Song, G. (2022a), "Utilization of CO2 into recycled construction materials: A systematic literature review", J. Mater. Cycl. Waste Manag., 24(6), 2108-2125. https://doi.org/10.1007/s10163-022-01489-4.
  63. Zhang, N., Zhang, D., Zuo, J., Miller, T.R., Duan, H. and Schiller, G. (2022b), "Potential for CO2 mitigation and economic benefits from accelerated carbonation of construction and demolition waste", Renew. Sustain. Energy Rev., 169, 112920. https://doi.org/10.1016/j.rser.2022.112920.
  64. Zheng, G., Zhang, W., Zhang, W., Zhou, H. and Yang, P. (2021), "Neural network and support vector machine models for the prediction of the liquefaction-induced uplift displacement of tunnels", Undergr. Sp., 6(2), 126-133. https://doi.org/10.1016/j.undsp.2019.12.002.
  65. Zhou, J., Zhang, R., Qiu, Y. and Khandelwal, M. (2023), "A true triaxial strength criterion for rocks by gene expression programming", J. Rock Mech. Geotech. Eng., 15(10), 2508-2520. https://doi.org/10.1016/j.jrmge.2023.03.004.
  66. Zhou, M., Chen, J., Huang, H., Zhang, D., Zhao, S. and Shadabfar, M. (2021), "Multi-source data driven method for assessing the rock mass quality of a NATM tunnel face via hybrid ensemble learning models", Int. J. Rock Mech. Min. Sci., 147, 104914. https://doi.org/10.1016/j.ijrmms.2021.104914.
  67. Zhou, Y., Gong, G., Xi, B., Guo, M., Xing, F. and Chen, C. (2022), "Sustainable lightweight engineered cementitious composites using limestone calcined clay cement (LC3)", Compos. Part B: Eng., 243, 110183. https://doi.org/10.1016/j.compositesb.2022.110183.
  68. Zhou, Y., Xi, B., Yu, K., Sui, L. and Xing, F. (2018), "Mechanical properties of hybrid ultra-high performance engineered cementitous composites incorporating steel and polyethylene fibers", Mater., 11(8), 1448. https://doi.org/10.3390/ma11081448.
  69. Zhu, H., Yu, K. and Li, V.C. (2021a), "Sprayable engineered cementitious composites (ECC) using calcined clay limestone cement (LC3) and PP fiber", Cement Concrete Compos., 115, 103868. https://doi.org/10.1016/j.cemconcomp.2020.103868.
  70. Zhu, H., Yu, K., McGee, W., Ng, T.Y. and Li, V.C. (2021), "Limestone calcined clay cement for three-dimensional- printed engineered cementitious composites", ACI Mater. J., 118(6), 111-122. https://doi.org/10.14359/51733109.
  71. Zhu, H., Zhang, D., Wang, T., McBain, M. and Li, V.C. (2021), "Intrinsic self-stressing and low carbon engineered cementitious composites (ECC) for improved sustainability", Cement Concrete Res., 149, 106580. https://doi.org/10.1016/j.cemconres.2021.106580.
  72. Zhu, H., Zhang, D., Wang, T., Wu, H. and Li, V.C. (2020), "Mechanical and self-healing behavior of low carbon engineered cementitious composites reinforced with PP-fibers", Constr. Build. Mater., 259, 119805. https://doi.org/10.1016/j.conbuildmat.2020.119805.
  73. Zhu, M., Chen, B., Wu, M. and Han, J. (2022), "Effects of different mixing ratio parameters on mechanical properties of cost-effective green engineered cementitious composites (ECC)", Constr. Build. Mater., 328, 127093. https://doi.org/10.1016/j.conbuildmat.2022.127093.
  74. Zorlu, K., Gokceoglu, C., Ocakoglu, F., Nefeslioglu, H.A. and Acikalin, S. (2008), "Prediction of uniaxial compressive strength of sandstones using petrography-based models", Eng. Geol., 96(3-4), 141-158. https://doi.org/10.1016/j.enggeo.2007.10.009.