Prediction of the Silica Fume Concrete Corrosion in Sulfuric Acid by SVM-Based Method

DOI

10.2991/iccet-15.2015.143How to use a DOI?

Keywords

support vector machine; silica fume concrete; sulfuric acid; corrosion model

Abstract

A long time immersion test of silica fume concrete specimens in sulfuric acid is carried out.On the basis of experimentaldatum, a novel prediction model for sulfuric acid corrosion of concrete based on support vector machine (SVM) is proposed. The design steps and learning algorithm are also given. Five main influencing factors including the water and cement ratio, pH value of the soaking solution, cement and silica fume quantity, specimens fluidity are analyzed with the proposed model. By comparison with the measured results, the root mean square error (RMSE) and mean absolute percentage error (MAPE) of predicted result of the model is only 0.118 and 0.096. It implies that this new method of computation appears to be a useful tool for sulfuric acid corrosion of silica fume concrete research.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yue Zhan
AU  - Zhigang Song
AU  - Haiying Wang
PY  - 2015/11
DA  - 2015/11
TI  - Prediction of the Silica Fume Concrete Corrosion in Sulfuric Acid by SVM-Based Method
BT  - Proceedings of the 5th International Conference on Civil Engineering and Transportation 2015
PB  - Atlantis Press
SP  - 766
EP  - 770
SN  - 2352-5401
UR  - https://doi.org/10.2991/iccet-15.2015.143
DO  - 10.2991/iccet-15.2015.143
ID  - Zhan2015/11
ER  -