Predicting Effective Parameters in Cyclic Behavior of Reinforced Masonry Walls with Shotcrete Using Artificial Neural Networks

Abstract:

In Masonry buildings, walls are the main structural elements resistant to lateral loads. Reinforcing masonry walls by shotcreting one- or two-sides is one of the most common reinforcement methods. Considering the economic losses and casualties caused by damage to these elements in previous earthquakes, it is necessary to investigate the seismic behavior of these walls. The existing data can train artificial neural networks, and the behaviors could be generalized for future cases. In this study, the prediction of cyclic behavior parameters of reinforced masonry walls with one- and two-way shotcrete is investigated using different artificial neural network methods. Input parameters of the neural network include length, thickness, height, mortar shear strength, mortar compressive strength, mesh type, spring dimensions, rebar diameter, average thickness of shotcrete, and concrete compressive strength. Output parameters were the relative displacement of yield, relative displacement corresponding to maximum resistance, final relative displacement, yield strength, displacement resistance corresponding to maximum resistance, ultimate resistance, and initial stiffness. The results showed that the feed-forward back-propagation neural network could accurately predict the examined output parameters compared to other models, which can be considered as an alternative to some time-consuming and costly laboratory and analytical investigations.

• Periodical: Solid State Phenomena (Volume 329)
• Pages: 71-78
• DOI: https://doi.org/10.4028/p-qx75o7
• Online since: March 2022
• Authors: Mohammad Hajmohammadian Baghban*, Seyed Amirhossein Hashemi, Elahe Sadat Hashemi, M.H Aghaei
• Keywords: Feed-Forward Back-Propagation Neural Network, Masonry Walls, Relative Displacement, Shotcrete

References

[1] B. Ghiassi, M Soltani Mohamadi, A.A Tasnimi, Linear Homogenization and Mechanical Characterization of Strengthened Masonry Elements with Concrete Overlay, Journal of civil and surveying engineering. Volume 45 (Issue 4) (2011) 455-466. (in Persian).

[2] Improvement Network brick walls with steel and concrete lining. (2011) Tehran: (Poly Copy) (in Persian).

[3] A. Kalali, M.Z. Kabir, Out-of-Plane Performance Based on Homogenization & Micromechanics Approach, Journal of civil and surveying engineering. Volume 45(Issue 2) (2011) 203-217. (in Persian).

[4] E.S Hashemi, Numerical investigation of the behaviour of masonry walls reinforced with shotcrete, Master's degree in earthquake engineering. Road, Housing & Urban Development Research Center, Institute of Building and Housing. (2013).

[5] A. Larbi, H. G. Harris, Seismic Performance of Low Aspect Ratio Reinforced Block Masonry Shear Walls.Proceeding of Fourth U.S, National Conference on Earthquake Engineering. Vol. 2 (2013).

[6] B. Ghiass, M.M Soltani, A.A Tasnimi, A Simplified Model for Analysis of Unreinforced Masonry ShearWalls under Axial, Shear and Flexural Loading, Engineering Structure, Science Direct. Vol.42 (2012) 396-409.

DOI: 10.1016/j.engstruct.2012.05.002

[7] E.S Hashemi, A S. Moghadam, N. K.A Attari, S.A. Hashemi, Study the relative contribution of materials, reinforcement and concrete layers at different levels of cyclic deformation of masonry walls reinforced with shotcrete, Journal of structural and construction engineering.vol5 no 2 (2017) 22-39.

[8] A.Cascardi, F.Micelli, M.A. Aiello, Analytical model based on artificial neural network for masonry shear walls strengthened with FRM systems, Composites Part B: Engineering Volume 95 (2016) 252-263.

DOI: 10.1016/j.compositesb.2016.03.066

[9] P.G., Asteris, V.Plevris, Anisotropic masonry failure criterion using artificial neural networks, Neural Comput & Applic.28 (2017) 2207–2229.

DOI: 10.1007/s00521-016-2181-3

[10] Q. Zhou, F. Zhu, X. Yang, F. Wang, B. Chi, Z. Zhang, Shear capacity estimation of fully grouted reinforced concrete masonry walls using neural network and adaptive neuro-fuzzy inference system models, Construction and Building Materials. Volume 153 (2017) Pages 937-947.

DOI: 10.1016/j.conbuildmat.2017.07.171

[11] R. Hung, Artificial Neural Network Model for Analysis of In-Plane Shear Strength of Partially Grouted Masonry Shear Walls. University of Alberta.

[12] O. Onat, M. Gul, Application of Artificial Neural Networks to the prediction of out-of-plane response of infill walls subjected to shake table, Smart Structures Systems. Vol. 21, No. 4 (2018) 521-535.

[13] P.G Asteris. et al. Masonry Compressive Strength Prediction Using Artificial Neural Networks. In: Transdisciplinary Multispectral Modeling and Cooperation for the Preservation of Cultural Heritage. TMM_CH, Communications in Computer and Information Science. vol 962 (2018).

DOI: 10.1007/978-3-030-12960-6_14

[14] N. Pitchaipillai, S.K Paramasivam, Deep neural network‐based mechanical behavior analysis for various masonry infill walls with hybrid fiber mortar, Journal of the fib. Volume20, Issue6 (2019) 1974-1985.

DOI: 10.1002/suco.201900064

[15] K. Suzuki, Artificial Neural Networks: Methodological Advances and Biomedical Applications. Rijeka: (2011) InTech, 1-362.

[16] Z.H Tang, R. Li, An Improved Neural Network Model and Its Applications. Journal of Information & Computational Science. 10 (2011) 1881–1888.

[17] Goodfellow, Bengio & Courville 2016, p.200, The back-propagation algorithm (Rumelhart et al., 1986a), often simply called backprop.

[18] Goodfellow, Bengio & Courville 2016, p.200, Furthermore, back-propagation is often misunderstood as being specific to multi-layer neural networks, but in principle it can compute derivatives of any function,.

[19] Goodfellow, Bengio & Courville 2016, p.214, This table-filling strategy is sometimes called dynamic programming.,.