Deep learning model for estimating the mechanical properties of concrete containing silica fume exposed to high temperatures

doi:10.1007/s11709-020-0646-z

Front. Struct. Civ. Eng.

2020, Vol. 14

Issue (6) : 1316-1330 https://doi.org/10.1007/s11709-020-0646-z

TRANSDISCIPLINARY INSIGHT

Deep learning model for estimating the mechanical properties of concrete containing silica fume exposed to high temperatures

Harun TANYILDIZI¹(

), Abdulkadir ŞENGÜR², Yaman AKBULUT², Murat ŞAHİN¹

¹. Faculty of Technology, Department of Civil Engineering, Firat University, Elazig 23100, Turkey
². Faculty of Technology, Department of Electrical-Electronics Engineering, Firat University, Elazig 23100, Turkey

Download: PDF(2715 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

In this study, the deep learning models for estimating the mechanical properties of concrete containing silica fume subjected to high temperatures were devised. Silica fume was used at concentrations of 0%, 5%, 10%, and 20%. Cube specimens (100 mm × 100 mm × 100 mm) were prepared for testing the compressive strength and ultrasonic pulse velocity. They were cured at 20°C±2°C in a standard cure for 7, 28, and 90 d. After curing, they were subjected to temperatures of 20°C, 200°C, 400°C, 600°C, and 800°C. Two well-known deep learning approaches, i.e., stacked autoencoders and long short-term memory (LSTM) networks, were used for forecasting the compressive strength and ultrasonic pulse velocity of concrete containing silica fume subjected to high temperatures. The forecasting experiments were carried out using MATLAB deep learning and neural network tools, respectively. Various statistical measures were used to validate the prediction performances of both the approaches. This study found that the LSTM network achieved better results than the stacked autoencoders. In addition, this study found that deep learning, which has a very good prediction ability with little experimental data, was a convenient method for civil engineering.

Keywords concrete high temperature strength properties deep learning stacked auto-encoders LSTM network

Corresponding Author(s): Harun TANYILDIZI

Just Accepted Date: 16 October 2020 Online First Date: 03 December 2020 Issue Date: 12 January 2021

Cite this article:

Harun TANYILDIZI,Abdulkadir ŞENGÜR,Yaman AKBULUT, et al. Deep learning model for estimating the mechanical properties of concrete containing silica fume exposed to high temperatures[J]. Front. Struct. Civ. Eng., 2020, 14(6): 1316-1330.

URL:

https://academic.hep.com.cn/fsce/EN/10.1007/s11709-020-0646-z
https://academic.hep.com.cn/fsce/EN/Y2020/V14/I6/1316

Tab.1 The chemical properties of cement, olivine, and silica fume

Tab.2 Mixture proportion of concretes

Fig.1 An illustration for auto-encoder.

Fig.2 The illustration of the whole DNNs structure.

Fig.3 The structure of the LSTM unit.

Fig.4 CS results at 7 d.

Fig.5 CS results at 28 d.

Fig.6 CS results at 90 d.

Fig.7 UPV results at 7 d.

Fig.8 UPV results at 28 d.

Fig.9 UPV results at 90 d.

Fig.10 The DNNs model that was used in experiments.

Fig.11 Illustration of the DNN-based predicted and actual results for CS. (a) First experiment (60-40); (b) second experiment (70-30); (c) third experiment (80-20).

Fig.12 Illustration of the DNN-based predicted and actual results for UPV. (a) First experiment (60-40); (b) second experiment (70-30); (c) third experiment (80-20).

Fig.13 The regression plots for the DNN-based predicted and actual results of CS. (a) First experiment (60-40); (b) second experiment (70-30); (c) third experiment (80-20).

Fig.14 The regression plots for the DNN-based predicted and actual results of UPV. (a) First experiment (60-40); (b) second experiment (70-30); (c) third experiment (80-20).

Fig.15 The training and testing processes of the DNN model for CS.

Fig.16 The training and testing processes of the DNN model for UPV.

Tab.3 DNN-based prediction evaluation metrics for CS

Tab.4 DNN-based prediction evaluation metrics for UPV

Tab.5 LSTM-based prediction evaluation metrics for CS

Tab.6 LSTM-based prediction evaluation metrics for UPV

Tab.7 The comparison of computational times of DNN and LSTM

Fig.17 Illustration of the LSTM-based predicted and actual results of CS. (a) First experiment (60-40); (b) second experiment (70-30); (c) third experiment (80-20).

Fig.18 Illustration of the LSTM-based predicted and actual results of UPV. (a) First experiment (60-40); (b) second experiment (70-30); (c) third experiment (80-20).

Fig.19 The regression plots for the LSTM-based predicted and actual results for CS. (a) First experiment (60-40); (b) second experiment (70-30); (c) third experiment (80-20).

Fig.20 The regression plots for the LSTM-based predicted and actual results for UPV. (a) First experiment (60-40); (b) second experiment (70-30); (c) third experiment (80-20).

Fig.21 The training and testing processes of the LSTM network model (third experiment) for CS. (a) RMSE; (b) loss.

Fig.22 The training and testing processes of the LSTM network model (third experiment) for UPV. (a) RMSE; (b) loss.

1	U Schneider. Concrete at high temperatures—A general review. Fire Safety Journal, 1988, 13(1): 55–68 https://doi.org/10.1016/0379-7112(88)90033-1
2	L T Phan. Fire performance of high-strength concrete: A report of the state-of-the art, building and fire research laboratory. Nistir, 1996, 5934: 1–105
3	C S Poon, S Azhar, M Anson, Y L Wong. Performance of metakaolin concrete at elevated temperatures. Cement and Concrete Composites, 2003, 25(1): 83–89 https://doi.org/10.1016/S0958-9465(01)00061-0
4	H Tanyildizi, E Asilturk. Performance of phosphazene-containing polymer-strengthened concrete after exposure to high temperatures. Journal of Materials in Civil Engineering, 2018, 30(12): 04018329 https://doi.org/10.1061/(ASCE)MT.1943-5533.0002505
5	H Tanyildizi, M Şahin. Taguchi optimization approach for the polypropylene fiber reinforced concrete strengthening with polymer after high temperature. Structural and Multidisciplinary Optimization, 2017, 55(2): 529–534 https://doi.org/10.1007/s00158-016-1517-z
6	H Tanyildizi, E Asiltürk. High temperature resistance of polymer-phosphazene concrete for 365 days. Construction & Building Materials, 2018, 174: 741–748 https://doi.org/10.1016/j.conbuildmat.2018.04.078
7	F B Varona, F J Baeza, D Bru, S Ivorra. Influence of high temperature on the mechanical properties of hybrid fibre reinforced normal and high strength concrete. Construction & Building Materials, 2018, 159: 73–82 https://doi.org/10.1016/j.conbuildmat.2017.10.129
8	C S Poon, S Azhar, M Anson, Y L Wong. Strength and durability recovery of fire-damaged concrete after post-fire-curing. Cement and Concrete Research, 2001, 31(9): 1307–1318 https://doi.org/10.1016/S0008-8846(01)00582-8
9	A R de Oliveira Dias, F A Amancio, M F de Carvalho Rafael, A E Bezerra Cabral. Study of propagation of ultrasonic pulses in concrete exposed at high temperatures. Procedia Structural Integrity, 2018, 11: 84–90 https://doi.org/10.1016/j.prostr.2018.11.012
10	R H Haddad, L G Shannis. Post-fire behavior of bond between high strength pozzolanic concrete and reinforcing steel. Construction & Building Materials, 2004, 18(6): 425–435 https://doi.org/10.1016/j.conbuildmat.2004.03.006
11	M Husem. The effects of high temperature on compressive and flexural strengths of ordinary and high-performance concrete. Fire Safety Journal, 2006, 41(2): 155–163 https://doi.org/10.1016/j.firesaf.2005.12.002
12	B Wu, Y Yu, X Y Zhao. Residual mechanical properties of compound concrete containing demolished concrete lumps after exposure to high temperatures. Fire Safety Journal, 2019, 105: 62–78 https://doi.org/10.1016/j.firesaf.2019.02.008
13	W M Lin, T D Lin, L J Powers-Couche. Microstructures of fire-damaged concrete. ACI Materials Journal, 1996, 93: 199–205
14	O Arioz. Effects of elevated temperatures on properties of concrete. Fire Safety Journal, 2007, 42(8): 516–522 https://doi.org/10.1016/j.firesaf.2007.01.003
15	K M Anwar Hossain. High strength blended cement concrete incorporating volcanic ash: Performance at high temperatures. Cement and Concrete Composites, 2006, 28(6): 535–545 https://doi.org/10.1016/j.cemconcomp.2006.01.013
16	H Tanyıldızı. Post-fire behavior of structural lightweight concrete designed by Taguchi method. Construction & Building Materials, 2014, 68: 565–571 https://doi.org/10.1016/j.conbuildmat.2014.07.021
17	H Tanyildizi, A Coskun, I Somunkiran. An experimental investigation of bond and compressive strength of concrete with mineral admixtures at high temperatures. Arabian Journal for Science and Engineering, 2008, 33(2): 443–449
18	L Biolzi, S Cattaneo, G Rosati. Evaluating residual properties of thermally damaged concrete. Cement and Concrete Composites, 2008, 30(10): 907–916 https://doi.org/10.1016/j.cemconcomp.2008.09.005
19	U Schneider, U Diederichs, C Ehm. Effect of temperature on steel and concrete for PCRV’s. Nuclear Engineering and Design, 1982, 67(2): 245–258 https://doi.org/10.1016/0029-5493(82)90144-3
20	Q Ma, R Guo, Z Zhao, Z Lin, K He. Mechanical properties of concrete at high temperature—A review. Construction & Building Materials, 2015, 93: 371–383 https://doi.org/10.1016/j.conbuildmat.2015.05.131
21	C S Poon, S Azhar, M Anson, Y L Wong. Comparison of the strength and durability performance of normal- and high-strength pozzolanic concretes at elevated temperatures. Cement and Concrete Research, 2001, 31(9): 1291–1300 https://doi.org/10.1016/S0008-8846(01)00580-4
22	A Behnood, H Ziari. Effects of silica fume addition and water to cement ratio on the properties of high-strength concrete after exposure to high temperatures. Cement and Concrete Composites, 2008, 30(2): 106–112 https://doi.org/10.1016/j.cemconcomp.2007.06.003
23	H G Ni, J Z Wang. Prediction of compressive strength of concrete by neural networks. Cement and Concrete Research, 2000, 30(8): 1245–1250 https://doi.org/10.1016/S0008-8846(00)00345-8
24	C Bilim, C D Atiş, H Tanyildizi, O Karahan. Predicting the compressive strength of ground granulated blast furnace slag concrete using artificial neural network. Advances in Engineering Software, 2009, 40(5): 334–340 https://doi.org/10.1016/j.advengsoft.2008.05.005
25	I B Topçu, M Saridemir. Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic. Computational Materials Science, 2008, 41(3): 305–311 https://doi.org/10.1016/j.commatsci.2007.04.009
26	O Karahan, H Tanyildizi, C D Atis. An artificial neural network approach for prediction of long-term strength properties of steel fiber reinforced concrete containing fly ash. Journal of Zhejiang University. Science A, 2008, 9(11): 1514–1523 https://doi.org/10.1631/jzus.A0720136
27	Z H Duan, S C Kou, C S Poon. Prediction of compressive strength of recycled aggregate concrete using artificial neural networks. Construction & Building Materials, 2013, 40: 1200–1206 https://doi.org/10.1016/j.conbuildmat.2012.04.063
28	H Tanyildizi. Prediction of the strength properties of carbon fiber-reinforced lightweight concrete exposed to the high temperature using artificial neural network and support vector machine. Advances in Civil Engineering, 2018, 2018: 1–10 https://doi.org/10.1155/2018/5140610
29	M Sarıdemir. Prediction of compressive strength of concretes containing metakaolin and silica fume by artificial neural networks. Advances in Engineering Software, 2009, 40(5): 350–355 https://doi.org/10.1016/j.advengsoft.2008.05.002
30	H Tanyildizi. Prediction of compressive strength of lightweight mortar exposed to sulfate attack. Computers and Concrete, 2017, 19(2): 217–226 https://doi.org/10.12989/cac.2017.19.2.217
31	Y J Cha, W Choi, O Büyüköztürk. Deep learning-based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(5): 361–378 https://doi.org/10.1111/mice.12263
32	A Zhang, K C P Wang, B Li, E Yang, X Dai, Y Peng, Y Fei, Y Liu, J Q Li, C Chen. Automated pixel-level pavement crack detection on 3d asphalt surfaces using a deep-learning network. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(10): 805–819 https://doi.org/10.1111/mice.12297
33	Y Z Lin, Z H Nie, H W Ma. Structural damage detection with automatic feature-extraction through deep learning. Computer-Aided Civil and Infrastructure Engineering, 2017, 32(12): 1025–1046 https://doi.org/10.1111/mice.12313
34	F Deng, Y He, S Zhou, Y Yu, H Cheng, X Wu. Compressive strength prediction of recycled concrete based on deep learning. Construction & Building Materials, 2018, 175: 562–569 https://doi.org/10.1016/j.conbuildmat.2018.04.169
35	C Anitescu, E Atroshchenko, N Alajlan, T Rabczuk. Artificial neural network methods for the solution of second order boundary value problems. Computers. Materials & Continua, 2019, 59(1): 345–359 https://doi.org/10.32604/cmc.2019.06641
36	H Guo, X Zhuang, T Rabczuk. A deep collocation method for the bending analysis of Kirchhoff plate. Computers, Materials & Continua, 2019, 59(2): 433–456 https://doi.org/10.32604/cmc.2019.06660
37	T Rabczuk, H Ren, X Zhuang. A Nonlocal operator method for partial differential equations with application to electromagnetic waveguide problem. Computers, Materials & Continua, 2019, 59(1): 31–55 https://doi.org/10.32604/cmc.2019.04567
38	G T G Mohamedbhai. Effect of exposure time and rates of heating and cooling on residual strength of heated concrete. Magazine of Concrete Research, 1986, 38(136): 151–158 https://doi.org/10.1680/macr.1986.38.136.151
39	Y N Chan, G F Peng, M Anson. Residual strength and pore structure of high-strength concrete and normal strength concrete after exposure to high temperatures. Cement and Concrete Composites, 1999, 21(1): 23–27 https://doi.org/10.1016/S0958-9465(98)00034-1
40	A Krizhevsky, I Sutskever, G E Hinton. ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 2012, 25(2): 1097–1105
41	S Hochreiter, J Schmidhuber. Long short-term memory. Neural Computation, 1997, 9(8): 1735–1780 https://doi.org/10.1162/neco.1997.9.8.1735
42	Y Liu, Y Qin, J Guo, C Cai, Y Wang, L Jia. Short-term forecasting of rail transit passenger flow based on long short-term memory neural network. In: 2018 International Conference on Intelligent Rail Transportation. Singapore, 2018, 1–5 https://doi.org/10.1109/ICIRT.2018.8641683
43	F A Gers, N N Schraudolph, J Schmidhuber. Learning precise timing with LSTM recurrent networks. Journal of Machine Learning Research, 2003, 3: 115–143
44	G Liu, H Bao, B Han. A stacked autoencoder-based deep neural network for achieving gearbox fault diagnosis. Mathematical Problems in Engineering, 2018, 2018: 1–10 https://doi.org/10.1155/2018/5105709
45	J Xie, Z Zhang, Z Lu, M Sun. Coupling effects of silica fume and steel-fiber on the compressive behaviour of recycled aggregate concrete after exposure to elevated temperature. Construction & Building Materials, 2018, 184: 752–764 https://doi.org/10.1016/j.conbuildmat.2018.07.035
46	H Esen, F Ozgen, M Esen, A Sengur. Artificial neural network and wavelet neural network approaches for modelling of a solar air heater. Expert Systems with Applications, 2009, 36(8): 11240–11248 https://doi.org/10.1016/j.eswa.2009.02.073
47	H Esen, M Inalli, A Sengur, M Esen. Artificial neural networks and adaptive neuro-fuzzy assessments for ground-coupled heat pump system. Energy and Building, 2008, 40(6): 1074–1083 https://doi.org/10.1016/j.enbuild.2007.10.002

[1]	Subhasis PRADHAN, Shailendra KUMAR, Sudhirkumar V. BARAI. Understanding the behavior of recycled aggregate concrete by using thermogravimetric analysis[J]. Front. Struct. Civ. Eng., 2020, 14(6): 1561-1572.
[2]	Fulin Qu, Wengui Li, Xiaohui Zeng, Zhiyu Luo, Kejin Wang, Daichao Sheng. Effect of microlimestone on properties of self-consolidating concrete with manufactured sand and mineral admixture[J]. Front. Struct. Civ. Eng., 2020, 14(6): 1545-1560.
[3]	Mohammad Reza AZADI KAKAVAND, Ertugrul TACIROGLU. An enhanced damage plasticity model for predicting the cyclic behavior of plain concrete under multiaxial loading conditions[J]. Front. Struct. Civ. Eng., 2020, 14(6): 1531-1544.
[4]	Fangyu LIU, Wenqi DING, Yafei QIAO, Linbing WANG. An artificial neural network model on tensile behavior of hybrid steel-PVA fiber reinforced concrete containing fly ash and slag power[J]. Front. Struct. Civ. Eng., 2020, 14(6): 1299-1315.
[5]	Luisa PANI, Flavio STOCHINO. Punching of reinforced concrete slab without shear reinforcement: Standard models and new proposal[J]. Front. Struct. Civ. Eng., 2020, 14(5): 1196-1214.
[6]	Masoud RANJBARNIA, Milad ZAHERI, Daniel DIAS. Three-dimensional finite difference analysis of shallow sprayed concrete tunnels crossing a reverse fault or a normal fault: A parametric study[J]. Front. Struct. Civ. Eng., 2020, 14(4): 998-1011.
[7]	Chunfeng ZHAO, Xin YE, Avinash GAUTAM, Xin LU, Y. L. MO. Simplified theoretical analysis and numerical study on the dynamic behavior of FCP under blast loads[J]. Front. Struct. Civ. Eng., 2020, 14(4): 983-997.
[8]	Divahar RAVI, Aravind Raj PONSUBBIAH, Sangeetha Sreekumar PRABHA, Joanna Philip SARATHA. Experimental, analytical and numerical studies on concrete encased trapezoidally web profiled cold-formed steel beams by varying depth-thickness ratio[J]. Front. Struct. Civ. Eng., 2020, 14(4): 930-946.
[9]	Luthfi Muhammad MAULUDIN, Chahmi OUCIF, Timon RABCZUK. The effects of mismatch fracture properties in encapsulation-based self-healing concrete using cohesive-zone model[J]. Front. Struct. Civ. Eng., 2020, 14(3): 792-801.
[10]	Feng YU, Cheng QIN, Shilong WANG, Junjie JIANG, Yuan FANG. Stress-strain relationship of recycled self-compacting concrete filled steel tubular column subjected to eccentric compression[J]. Front. Struct. Civ. Eng., 2020, 14(3): 760-772.
[11]	Rwayda Kh. S. AL-HAMD, Martin GILLIE, Safaa Adnan MOHAMAD, Lee S. CUNNINGHAM. Influence of loading ratio on flat slab connections at elevated temperature: A numerical study[J]. Front. Struct. Civ. Eng., 2020, 14(3): 664-674.
[12]	Luthﬁ Muhammad MAULUDIN, Chahmi OUCIF. Computational modeling of fracture in concrete: A review[J]. Front. Struct. Civ. Eng., 2020, 14(3): 586-598.
[13]	Yasmin MURAD, Wassel AL BODOUR, Ahmed ASHTEYAT. Seismic retrofitting of severely damaged RC connections made with recycled concrete using CFRP sheets[J]. Front. Struct. Civ. Eng., 2020, 14(2): 554-568.
[14]	Xiao-Yong WANG. Impacts of climate change on optimal mixture design of blended concrete considering carbonation and chloride ingress[J]. Front. Struct. Civ. Eng., 2020, 14(2): 473-486.
[15]	Dan V. BOMPA, Ahmed Y. ELGHAZOULI. Nonlinear numerical simulation of punching shear behavior of reinforced concrete flat slabs with shear-heads[J]. Front. Struct. Civ. Eng., 2020, 14(2): 331-356.

Viewed

Full text

Abstract

Cited

Shared

Discussed