Modelling Concrete Strength Using Support Vector Machines

Hai Ying Yang; Yi Feng Dong

doi:10.4028/www.scientific.net/AMM.438-439.170

Paper Titles

A Simple Method of Coarse Aggregate Generation Based on PFC2d
p.149

The Influence by the Method of Aggregate Enveloped with Cement of Multi-Step Mixing to Durability of High Performance Concrete
p.153

The Effects of Ocean Salinity Variance due to Climate Change on Australian Seaport Infrastructure
p.157

Evaluation on Compressive Strength and Workability of Green High-Performance Concrete by Grey Relational Grade
p.166

Modelling Concrete Strength Using Support Vector Machines
p.170

Study on Effect of Different Fine Aggregates on Properties of Dam Concrete
p.174

Experimental Research on the Influence of Pebble Aggregate Gradation on Concrete Strength
p.179

Statistical Damage Constitutive Model for Concrete under Biaxial Tension
p.183

Analysis and Comparison of Different Confined Concrete Models
p.187

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 438-439Modelling Concrete Strength Using Support Vector...

Modelling Concrete Strength Using Support Vector Machines

Abstract:

Support vector machine (SVM) is a statistical learning theory based on a structural risk minimization principle that minimizes both error and weight terms. A SVM model is presented to predict compressive strength of concrete at 28 days in this paper. A total of 20 data sets were used to train, whereas the remaining 10 data sets were used to test the created model. Radial basis function based on support vector machines was used to model the compressive strength and results were compared with a generalized regression neural network approach. The results of this study showed that the SVM approach has the potential to be a practical tool for predicting compressive strength of concrete at 28 days.

You might also be interested in these eBooks

Civil Engineering, Architecture and Sustainable Infrastructure II

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 438-439)

Pages:

170-173

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.438-439.170

Citation:

Cite this paper

Online since:

October 2013

Authors:

Hai Ying Yang, Yi Feng Dong

Keywords:

Concrete, Model, Prediction, Strength, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] S. Tsivilis, G. A. Parissakis, Mathematical-model for the prediction of cement strength, Cement Concrete Res., 25 (1995) 9-14.

DOI: 10.1016/0008-8846(94)00106-9

Google Scholar

[2] C. E. S. Tango, An extrapolation method for compressive strength prediction of hydraulic cement products, Cement Concrete Res., 28 (1998) 969-983.

DOI: 10.1016/s0008-8846(98)00074-x

Google Scholar

[3] M. Sebastia, I. F. Olmo, A. Irabien, Neural network prediction of unconfined compressive strength of coal fly ash–cement mixtures, Cement Concrete Res., 33 (2003) 1137-1146.

DOI: 10.1016/s0008-8846(03)00019-x

Google Scholar

[4] Harun Tanyildizi, Fuzzy logic model for the prediction of bond strength of high-strength lightweight concrete, Advances in Engineering Software, 40 (2009) 161-169.

DOI: 10.1016/j.advengsoft.2007.05.013

Google Scholar

[5] J. Hong, W. Huang, Study on prediction of concrete strength using wavelet neural network, Industrial Architecture, 34 (2004) 47-49.

Google Scholar

[6] H. Huang, Y. Zhang, J. Qiu, The application of neural network to forecast the concrete strength, Huazhong Univ. of Sci. & Tech. (Nature Science Edition), 30 (2002) 65-67.

Google Scholar

[7] Z. Yang, Predict ion model of common concrete strength by BPNN, Journal of Chang'an University (Natural Science Edition), 23 (2003) 50-52.

Google Scholar

[8] V. Vapnik, The Nature of Statistical Learning Theory, Springer, NY, (1995).

Google Scholar