Hybrid MARS-, MEP-, and ANN-based prediction for modeling the compressive strength of cement mortar with various sand size and clay mineral metakaolin content

• Autorzy: Abdalla Aso , Mohammed Ahmed Salih

Identyfikatory

DOI

10.1007/s43452-022-00519-0

• Języki publikacji: EN

Abstrakty

EN

In this study, several mathematical, soft computing, and machine learning modeling tools are used to develop a dependable model for forecasting the compressive strength of cement mortar modified with metakaolin (MK) additive and predicting the effect of MK and a maximum diameter of the fine aggregate (MDA) on the compressive strength of the mortar. In this regard, 230 datasets were collected from literature with a wide-ranging mix of proportion and curing time. Water to binder ratio (w/b) ranged between 0.36 and 0.6 (by the weight of dry cement), sand to binder ratio 2 to 3, metakaolin content 0–30%, and curing time up to 90 days. Multivariate regression spline (MARS), multiexpression programming (MEP), nonlinear regression (NLR), and artificial neural network (ANN) models were used. Several assessment tools were utilized to quantify the performance of the proposed models, such as coefficient of determination (R2), root mean squared error (RMSE), mean absolute error (MAE), scatter index (SI), and Taylor diagram. Based on the modeling result, the performance of the MARS model is better than MEP, NLR, and ANN models with high R2 and low RMSE and MAE. The MARS, MEP, and ANN excellently predicted the compressive strength based on the scatter index. The parametric analysis of MK and MDA revealed that the ANN model successfully predicted the influence of the mentioned model inputs and optimum MK content for improving long- and short-term compressive strength.

Słowa kluczowe

EN

metakaolin; maximum size of aggregate; compressive strength; modeling

PL

kruszywo; ściskanie; modelowanie

• Wydawca: Springer ; Wrocław University of Science and Technology
• Czasopismo: Archives of Civil and Mechanical Engineering
• Rocznik: 2022
• Tom: Vol. 22, no. 4
• Strony: art. no. e194, 2022
• Opis fizyczny: Bibliogr. 41 poz., rys., wykr.

Twórcy

autor

Abdalla Aso

• Civil Engineering Department, College of Engineering, University of Sulaimani, Kurdistan, Iraq

autor

Mohammed Ahmed Salih

• Civil Engineering Department, College of Engineering, University of Sulaimani, Kurdistan, Iraq

Bibliografia

• [1] John N. Strength properties of metakaolin admixed concrete. Int J Sci Res Publ. 2013;3(6):1–7.
• [2] Torres A, Bartlett L, Pilgrim C. Effect of foundry waste on the mechanical properties of Portland Cement Concrete. Constr Build Mater. 2017;135:674–81.
• [3] Damtoft JS, Lukasik J, Herfort D, Sorrentino D, Gartner EM. Sustainable development and climate change initiatives. Cem Concr Res. 2008;38(2):115–27.
• [4] Gustavsson L, Sathre R. Variability in energy and carbon dioxide balances of wood and concrete building materials. Build Environ. 2006;41(7):940–51.
• [5] Gartner E. Industrially interesting approaches to “low-CO2” cements. Cem Concr Res. 2004;34(9):1489–98.
• [6] Nehdi ML, Suleiman AR, Soliman AM. Investigation of concrete exposed to dual sulfate attack. Cem Concr Res. 2014;64:42–53.
• [7] Wianglor K, Sinthupinyo S, Piyaworapaiboon M, Chaipanich A. Effect of alkali-activated metakaolin cement on compressive strength of mortars. Appl Clay Sci. 2017;141:272–9.
• [8] Zhang YJ, Wang YC, Li S. Mechanical performance and hydration mechanism of geopolymer composite reinforced by resin. Mater Sci Eng, A. 2010;527(24–25):6574–80.
• [9] Abdalla AA, Salih Mohammed A. Theoretical models to evaluate the effect of SiO2 and CaO contents on the long-term compressive strength of cement mortar modified with cement kiln dust (CKD). Arch Civ Mech Eng. 2022;22(3):1–21.
• [10] Mahmood LJ, Rafiq SK, Mohammed AS. A review study of eggshell powder as cement replacement in concrete (2022) SJES. 2022;9(1).
• [11] Qian X, Wang J, Wang L, Fang Y. Enhancing the performance of metakaolin blended cement mortar through in-situ production of nano to sub-micro calcium carbonate particles. Constr Build Mater. 2019;196:681–91.
• [12] Mahmood W, Mohammed AS, Sihag P, Asteris PG, Ahmed H. Interpreting the experimental results of compressive strength of hand-mixed cement-grouted sands using various mathematical approaches. Arch Civ Mech Eng. 2022;22(1):1–25.
• [13] Ilić BR, Mitrović AA, Miličić LR. Thermal treatment of kaolin clay to obtain metakaolin. Hem Ind. 2010;64(4):351–6.
• [14] Biljana I, Aleksandra M, Ljiljana M. Thermal treatment of kaolin clay to obtain metakaolin. Hem Ind. 2010;64(4):351–6.
• [15] Shvarzman A, Kovler K, Grader GS, Shter GE. The effect of dehydroxylation/amorphization degree on pozzolanic activity of kaolinite. Cem Concr Res. 2003;33(3):405–16.
• [16] Badogiannis E, Kakali G, Tsivilis S. Metakaolin as supplementary cementitious material: optimization of kaolin to metakaolin conversion. J Therm Anal Calorim. 2005;81(2):457–62.
• [17] Mohammed A, Rafiq S, Sihag P, Kurda R, Mahmood W, Ghafor K, Sarwar W. ANN, M5P-tree and nonlinear regression approaches with statistical evaluations to predict the compressive strength of cement-based mortar modified with fly ash. J Market Res. 2020;9(6):12416–27.
• [18] Courard L, Darimont A, Schouterden M, Ferauche F, Willem X, Degeimbre R. Durability of mortars modified with metakaolin. Cem Concr Res. 2003;33(9):1473–9.
• [19] Parande AK, Babu BR, Karthik MA, Kumaar KKD, Palaniswamy N. Study on strength and corrosion performance for steel embedded in metakaolin blended concrete/mortar. Constr Build Mater. 2008;22(3):127–34.
• [20] Sumasree C, Sajja S. Effect of metakaolin and cerafibermix on mechanical and durability properties of mortars. Int J Sci Eng Technol. 2016;4(3):501–6.
• [21] Batis G, Pantazopoulou P, Tsivilis S, Badogiannis E. The effect of metakaolin on the corrosion behavior of cement mortars. Cement Concr Compos. 2005;27(1):125–30.
• [22] Armaghani DJ, Asteris PG. A comparative study of ANN and ANFIS models for the prediction of cement-based mortar materials compressive strength. Neural Comput Appl. 2021;33(9):4501–32.
• [23] Mahmood W, Mohammed A. New Vipulanandan pq model for particle size distribution and groutability limits for sandy soils. J Test Eval. 2019;48(5):3695–712. https://doi.org/10.1520/JTE20180606.
• [24] Qadir W, Ghafor K, Mohammed A. Evaluation the effect of lime on the plastic and hardened properties of cement mortar and quantified using Vipulanandan model. Open Eng. 2019;9(1):468–80. https://doi.org/10.1515/eng-2019-0055.
• [25] Sihag P, Jain P, Kumar M. Modelling of impact of water quality on recharging rate of storm water filter system using various kernel function based regression. MESE. 2018;4(1):61–8. https://doi.org/10.1007/s40808-017-0410-0.
• [26] Vipulanandan C, Mohammed A. Magnetic field strength and temperature effects on the behavior of oil well cement slurry modified with iron oxide nanoparticles and quantified with vipulanandan models. J Test Eval. 2019;48(6):4516–37. https://doi.org/10.1520/JTE20180107.
• [27] Shah MI, Amin MN, Khan K, Niazi MSK, Aslam F, Alyousef R, Javed MF, Mosavi A. Performance evaluation of soft computing for modeling the strength properties of waste substitute green concrete. Sustainability. 2021;13(5):2867. https://doi.org/10.3390/su13052867.
• [28] Abdalla AA, Mohammed AS, Rafiq S, Noaman R, Qadir WS, Ghafor K, Hind ALD, Fairs R. Microstructure, chemical compositions, and soft computing models to evaluate the influence of silicon dioxide and calcium oxide on the compressive strength of cement mortar modified with cement kiln dust. Constr Build Mater. 2022;341: 127668.
• [29] Abdalla A, Salih Mohammed A. Surrogate models to predict the long-term compressive strength of cement-based mortar modified with fly ash. Arch Comput Methods Eng. 2022. p. 1–26.
• [30] Zhiyuan G, Yongxian W, Lan N (2000) Genetic algorithms based on bintree structure encoding. J Tsinghua Univ. 2000;40(10):125-128.
• [31] Ferreira C. Function finding and the creation of numerical constants in gene expression programming. In: Advances in soft computing. Springer; 2003. p. 257–65.
• [32] Lopes HS, Weinert WR. A gene expression programming system for time series modeling. In: Proceedings of XXV Iberian Latin American Congress on Computational methods in Engineering (CILAMCE), vol 10. Recife: Brazil; 2004. pp. 1-13.
• [33] Oltean M, Dumitrescu D. Multi expression programming. J Genet Program Evolvable Mach. 2022. https://doi.org/10.21203/rs.3.rs-853086/v1.
• [34] Searson DP, Leahy DE, Willis MJ. GPTIPS: an open source genetic programming toolbox for multigene symbolic regression. In: Proceedings of the Internationalmulti conference of engineers and computer scientists, vol 1. Citeseer; 2010. pp. 77–80.
• [35] Mohamad ET, Hajihassani M, Armaghani DJ, Marto A. Simulation of blasting-induced air overpressure by means of artificial neural networks. Int Rev Model Simul. 2012;5(6):2501–6.
• [36] Despotovic M, Nedic V, Despotovic D, Cvetanovic S. Evaluation of empirical models for predicting monthly mean horizontal diffuse solar radiation. Renew Sustain Energy Rev. 2016;56:246–60. https://doi.org/10.1016/j.rser.2015.11.058.
• [37] En BS (2005) 196–1.(2005). Methods of testing cement. Determination of strength. British Standards Institute.
• [38] Meddah MS, Zitouni S, Belâabes S. Effect of content and particle size distribution of coarse aggregate on the compressive strength of concrete. Constr Build Mater. 2010;24(4):505–12.
• [39] Kadri E-H, Kenai S, Ezziane K, Siddique R, De Schutter G. Influence of metakaolin and silica fume on the heat of hydration and compressive strength development of mortar. Appl Clay Sci. 2011;53(4):704–8.
• [40] Mardani-Aghabaglou A, Sezer Gİ, Ramyar K. Comparison of fly ash, silica fume and metakaolin from mechanical properties and durability performance of mortar mixtures view point. Constr Build Mater. 2014;70:17–25.
• [41] Potgieter-Vermaak SS, Potgieter JH. Metakaolin as an extender in South African cement. J Mater Civ Eng. 2006;18(4):619–23.

Uwagi

PL

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023)