All Issue

2019 Vol.10, Issue 4 Preview Page

General Article

An analytical study on the prediction of carbonation velocity coefficient using deep learning algorithm
Dohyun Jung1
,
Hanseung Lee2*
1Student, Department of Architectural Engineering, Hanyang University, Ansan, South Korea
2Professor, Department of Architecture & Architectural Engineering, Hanyang University, Ansan, South Korea
* Corresponding Author
31 December 2019. pp. 205-215
PDF XML Citation
Abstract

In present paper, we have studied the prediction method to determine the carbonation velocity coefficient of the concrete using deep neural network (DNN). The accelerated carbonation test data for 291 mixtures were used as training data with different experimental variable such as water to binder ratio, admixture (blast furnace slag and fly ash), fine aggregate and coarse aggregate as input data. Therefore, the carbonation velocity coefficient was calculated for 5% CO2, 60% relative humidity, and 20°C temperature. The model-based learning set was 5 hidden layers, 15% validation data ratio and 64 batch data size. Under this study condition, all model-based learnings were trained to the point where the learning was not overfitted. The performance of the DNN model exhibit 9.91% mean absolute percentage error. We compared the DNN model with linear prediction equations proposed by Kishitani, Hamada, and Shirayama equation. The carbonation velocity coefficient (mm/year) which were calculated using accelerated carbonation experiment and compared with DNN model and linear prediction equations. The mean absolute percentage error of DNN model was 12.00%, which was smaller than that of the linear prediction equations of Kishitani, Shirayama and Hamada.

Keywords
concrete carbonation
deep learning
carbonation prediction
References
1
V. G. Papadakis and V. G. Costas, A reaction engineering approach to the problem of concrete carbonation. AIChE Journal 35(10) (1989), pp. 1639-1650.
10.1002/aic.690351008
2
V. G. Papadakis, V. G. Costas, and N. F. Michael, Experimental investigation and mathematical modeling of the concrete carbonation problem. Chemical Engineering Science 46(5-6) (1991), pp. 1333-1338.
10.1016/0009-2509(91)85060-B
3
Korea Meteorological Administration, Report of global atmosphere watch 2018. Korea Meteorological Administration. (2019).
4
N.R. Buenfeld, N.M. Hassanein, and A.J. Jones, An artificial neural network for predicting carbonation depth in concrete structures. Manuals and Reports on Engineering Practice. (1998), pp. 77-117.
5
W. Z. Taffese and E. Sistonen, Machine learning for durability and service-life assessment of reinforced concrete structures: Recent advances and future directions. Automation in Construction. 77 (2017), pp. 1-14.
10.1016/j.autcon.2017.01.016
6
R. Xiang, Prediction of concrete carbonation depth based on support vector regression. 2009 Third International Symposium on Intelligent Information Technology Application. IEEE. 3 (2009), pp. 172-175.
10.1109/IITA.2009.469
7
N. BU, G. YANG, and H. ZHAO, Prediction of concrete carbonization depth based on DE-BP neural network. 2009 Third International Symposium on Intelligent Information Technology Application. IEEE. 3 (2009), pp. 240-243.
10.1109/IITA.2009.252
8
Y. Liu, S. Zhao and C. Yi, The forecast of carbonation depth of concrete based on RBF neural network. 2008 Second International Symposium on Intelligent Information Technology Application. IEEE. 3 (2008), pp. 544-548.
10.1109/IITA.2008.402PMC2562431
9
W. Z. Taffese, E. Sistonen, and J. Puttonen, Prediction of Concrete Carbonation Depth using Decision Trees. Proc. 23rd Eur. Symp. Artif. Neural Networks, Comput. Intell. Mach. Learn. ESANN. (2015), pp. 415-420.
10
W. Z. Taffese, F. Al-Neshawy, E. Sistonen, and M. Ferreira, Optimized neural network based carbonation prediction model. In International Symposium Non-Destructive Testing in Civil Engineering, NDTCE 2015, (2015), pp. 1074-1083
11
C. Lu and R. Liu, Predicting carbonation depth of prestressed concrete under different stress states using artificial neural network. Advances in Artificial Neural Systems. 2009, (2009).
10.1155/2009/193139
12
S. J. Kwon, Service Life Evaluation of RC Column Exposed to Carbonation Considering Time-dependent Crack Pattern, Journal of the Korean Recycled Construction Resources Institute, 4(1) (2016), pp. 10-18.
10.14190/JRCR.2016.4.1.010
13
Korean Standards, KS F 2584 Standard test method for accelerated carbonation of Concrete. Korea Industrial Standards, Korean Standards & Certification Information Center. (2015), pp. 1-4.
14
阿部道彦, 桝田佳寛, 田中斉, 柳啓, 和泉意登志, and 友沢史紀, コンクリートの促進中性化試験法の評価に関する研究. 日本建築学会構造系論文報告集. 409 (1990), pp. 1-10.
15
Architectural Institute of Japan, Recommendations for durability design and construction practice of reinforced concrete buildings. 2nd ed. Tokyo(Japan): Architectural Institute of Japan. (2016), pp. 98-126.
16
Architectural Institute of Japan, 鐵筋コンクリート造構造物の 耐久性設計施工指針 (案)·同解說, (2004).
17
岸谷孝一, 樫野紀元, コンクリート中の鉄筋の腐食に関する研究: その1 コンクリーの中性化深さが鉄筋腐食に及ぼす影響について. 日本建築学会論文報告集. 283 (1979), pp. 11-16.
18
S. Haykin, Neural networks: a comprehensive foundation. Prentice Hall PTR, 1994.
19
R. Hecht-Nielsen, Theory of the backpropagation neural network. Neural networks for perception. Academic Press. (1992), pp. 65-93.
10.1016/B978-0-12-741252-8.50010-8
20
S. L. Hung and H. Adeli, A model of perceptron learning with a hidden layer for engineering design. Neurocomputing, 3(1) (1991), pp. 3-14.
10.1016/0925-2312(91)90016-5
21
L. Deng and Y. Dong Yu, Deep learning: methods and applications. Foundations and Trends® in Signal Processing 7.3-4 (2014), pp. 19-33.Y. Freund, and D. Haussler, Unsupervised learning of distributions on binary vectors using two layer networks. Advances in neural information processing systems. (1992), pp. 912-919.
10.1561/2000000039
22
Bengio, Yoshua. Learning deep architectures for AI. Foundations and trends® in Machine Learning 2.1 (2009), pp, 1-127.
10.1561/2200000006
23
N. Buduma and L. Nicholas, Fundamentals of deep learning: Designing next-generation machine intelligence algorithms, O'Reilly Media, Inc. (2017).
24
C. Nwankpa, W. Ijomah, A. Gachagan, and S. Marshall, Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811.03378, (2018)
25
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1) (2014), pp. 1929-1958.
26
D. P. Kingma and Ba. Jimmy, Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, (2014).
27
Nowlan, Steven J., and Geoffrey E. Hinton. Simplifying neural networks by soft weight-sharing. Neural computation 4.4 (1992), pp. 473-493.
10.1162/neco.1992.4.4.473
Information
  • Publisher :Sustainable Building Research Center (ERC) Innovative Durable Building and Infrastructure Research Center
  • Publisher(Ko) :건설구조물 내구성혁신 연구센터
  • Journal Title :International Journal of Sustainable Building Technology and Urban Development
  • Volume : 10
  • No :4
  • Pages :205-215
  • Received Date : 2019-12-11
  • Accepted Date : 2019-12-24
  • DOI :https://doi.org/10.22712/susb.20190022
Journal Informaiton International Journal of Sustainable Building Technology and Urban Development International Journal of Sustainable Building Technology and Urban Development
Online Submission
  • scopus
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close