Abstract
The concrete compressive strength (CS) is an important parameter used for durability design and service life prediction of concrete structures in civil engineering projects. It usually has a high nonlinear relationship with the age and main components of concrete, which makes it difficult for traditional regression analysis methods to perform predictive modelling. This study presents a data-driven Kriging model for predicting concrete CS under standard curing period. Two popular machine learning algorithms, namely Artificial Neural Network (ANN) and Support Vector Regression (SVR), are used for comparisons to validate the predictive ability of Kriging model. In addition, a parameter correlation analysis is implemented to reveal the intrinsic association of the selected seven main components of concrete and concrete CS. This study led to the following conclusions: (1) compared with ANN and SVR, the data-driven Kriging model has the highest accuracy in predicting concrete CS, and (2) the results of the parameter correlation analysis coincide with the physical laws of concrete CS.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ncibi MC (2008) Applicability of some statistical tools to predict optimum adsorption isotherm after linear and non-linear regression analysis[J]. J Hazard Mater 153(1–2):207–212
LaValley MP (2008) Logistic regression[J]. Circulation 117(18):2395–2399
Su X, Yan X, Tsai CL (2012) Linear regression[J]. Wiley Interdiscip Rev: Comput Stat 4(3):275–294
Yeh IC (1998) Modeling of strength of high-performance concrete using artificial neural networks[J]. Cem Concr Res 28(12):1797–1808
Ni HG, Wang JZ (2000) Prediction of compressive strength of concrete by neural networks[J]. Cem Concr Res 30(8):1245–1250
Asteris PG, Skentou AD, Bardhan A et al (2021) Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models[J]. Cem Concr Res 145:106449
Öztaş A, Pala M, Özbay E et al (2006) Predicting the compressive strength and slump of high strength concrete using neural network[J]. Constr Build Mater 20(9):769–775
Kewalramani MA, Gupta R (2006) Concrete compressive strength prediction using ultrasonic pulse velocity through artificial neural networks[J]. Autom Constr 15(3):374–379
Mohammed A, Rafiq S, Sihag P et al (2021) Soft computing techniques: systematic multiscale models to predict the compressive strength of HVFA concrete based on mix proportions and curing times[J]. J Build Eng 33:101851
Krige DG (1951) A statistical approach to some mine valuation and allied problems on the Witwatersrand. Master’s thesis, University of the Witwatersrand, South Africa
Matheron G (1963) Principles of geostatistics. Econ Geol 58(2):1246–1266
Sacks J, Welch WJ, et al (1989) Design and analysis of computer experiments. Stat Sci 4:409–435
Santner T, Williams B, Notz W (2003) The design and analysis of computer experiments. Springer series in Statistics, Springer
Lataniotis C, Wicaksono D, et al (2019) UQLab user manual—Kriging (Gaussian process modeling). Report # UQLab-V1.3-105, Chair of Risk, Safety and Uncertainty Quantification, ETH Zurich, Switzerland
Hansen N, Ostermeier A (2001) Completely derandomized self-adaptation in evolution strategies. Evol Comput 9(2):159–195
Yaghoubi V, Vakilzadeh MK, Abrahamsson TJS (2018) Automated modal parameter estimation using correlation analysis and bootstrap sampling[J]. Mech Syst Signal Process 100:289–310
Sedgwick P (2014) Spearman’s rank correlation coefficient[J]. Bmj 2014:349.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
YiFei, L., MaoSen, C., Abdel Wahab, M. (2023). Data-Driven Kriging Model for Predicting Concrete Compressive Strength and Parameter Correlation Analysis. In: Abdel Wahab, M. (eds) Proceedings of the 5th International Conference on Numerical Modelling in Engineering. Lecture Notes in Civil Engineering, vol 311. Springer, Singapore. https://doi.org/10.1007/978-981-19-8429-7_11
Download citation
DOI: https://doi.org/10.1007/978-981-19-8429-7_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8428-0
Online ISBN: 978-981-19-8429-7
eBook Packages: EngineeringEngineering (R0)