Proceedings of the 2nd International Conference on Electronic & Mechanical Engineering and Information Technology (EMEIT 2012)

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

Authors
Weihang Zhang, Zhigang Song
Corresponding Author
Weihang Zhang
Available Online September 2012.
DOI
10.2991/emeit.2012.80How to use a DOI?
Keywords
support vector machine, concrete, sulfuric acid, corrosion model
Abstract

A long time immersion test of fly ash concrete specimens in sulfuric acid is carried out. On the basis of the experimental datum, 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 fly ash quantity, specimens fluidity are analyzed with the proposed model. By comparison with the measured results, the mean square error (MSE) of predicted result of the model is 0.188. It implies that this new method of computation appears to be a useful tool for sulfuric acid corrosion of fly ash concrete research.

Copyright
© 2012, 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)

Volume Title
Proceedings of the 2nd International Conference on Electronic & Mechanical Engineering and Information Technology (EMEIT 2012)
Series
Advances in Intelligent Systems Research
Publication Date
September 2012
ISBN
10.2991/emeit.2012.80
ISSN
1951-6851
DOI
10.2991/emeit.2012.80How to use a DOI?
Copyright
© 2012, 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/).

Cite this article

TY  - CONF
AU  - Weihang Zhang
AU  - Zhigang Song
PY  - 2012/09
DA  - 2012/09
TI  - Prediction of Concrete Corrosion in Sulfuric Acid by SVM-Based Method
BT  - Proceedings of the 2nd International Conference on Electronic & Mechanical Engineering and Information Technology (EMEIT 2012)
PB  - Atlantis Press
SP  - 400
EP  - 404
SN  - 1951-6851
UR  - https://doi.org/10.2991/emeit.2012.80
DO  - 10.2991/emeit.2012.80
ID  - Zhang2012/09
ER  -