APPLICATION OF CONVOLUTIONAL NEURAL NETWORK IN STRESS CALCULATIONS OF REINFORCED CONCRETE SLABS OF ROAD PAVEMENTS
DOI:
https://doi.org/10.36773/1818-1112-2024-135-3-24-30Keywords:
reinforced concrete slab, computational model, convolutional neural network, U-Net architectureAbstract
The design of rigid reinforced concrete slabs of foundations, slabs, road surfaces is based on calculation models, which are developed on a relatively limited number of experimental studies, in most cases requiring quite large material and time costs. The complex stress-strain state occurring in stiff reinforced concrete base and pavement slabs under load, especially under cyclic dynamic loading, can often lead to cracking and failure of the slabs. In this paper, reinforced concrete slabs of a container yard pavement were investigated for load bearing from the wheels of a reach stacker (container loading vehicle) travelling on the surface. Existing models for the design of such slabs typically consider the slab loaded by a single local load applied to an edge or corner of the slab from the wheels of a moving vehicle. In fact, there may be two wheels on the slab, resulting in more unfavorable conditions. The application of the finite element method in such problems is quite laborious as it requires highly skilled design engineers and considerable time, making the design routine and of limited use. This paper investigates an alternative approach based on the application of an artificial convolutional neural network (CNN) with U-Net architecture, which provides a reasonably accurate prediction of stresses in the slab much faster and simpler compared to the finite element method. The paper presents the architecture of the neural network with an indication of the features and stages of its training. Statistical analysis of the calculation results is performed, which allowed us to assess the reliability of the neural network model for determining stresses in reinforced concrete slabs on an elastic base.
References
Tully, S. H. А neural network approach for predicting the structural behavior of concrete slabs : a thesis submitted for the degree of master of engineering : 06.1997 / S. H. Tully. – Newfoundlan, 1997. – 126 p.
Betonnye i zhelezobetonnye konstrukcii = Betonnyya і zhalezabetonnyya kanstrukcyі : SP 5.03.01-2020. – Vved. 16.09.2020. – Minsk : RUP «Strojtekhnorm» : Ministerstvo arhitektury i stroitel'stva Respubliki Belarus', 2020. – 236 s.
Design of concrete structures – Part 1-1: General rules, rules for buildings, bridges and civil engineering structures : prEN 1992-1-1:2018 Eurocode 2. – Final draft of April 2018 by the Project Team SC2.T1 working on Phase 1 of the CEN/TC 250 work programme under Mandate M/515. – 293 p.
fib Model Code for Concrete Structures 2010. – Lausanne : International Federation for Structural Concrete (fib), Switzerland, 2013. – 432 p.
ACI. Building Code Requirements for Structural Concrete (ACI 318-08) and Commentary. In Aci-318-08; American Concrete Institute: Farmington Hills, MI, USA, 2008. – P. 1–471.
JSCE. Standard Specifications for Concrete Structures-2007. In JSCE Guideline for Concrete No. 15; JSCE: Tokyo, Japan, 2007. – P. 1–503.
CSA. Design of Concrete Structures. In A23.3-04; CSA: Mississauga, ON, Canada, 2004. – P. 1–232.
NZS. Concrete Structures Standard Part-1. In NZS 3101; New Zealand Standard. – Wellington, New Zealand, 2006. – Part 1. – P. 1–309.
KBCS. Korean Building Code-Structural (KBCS); Architectural Institute of Korea: Kimoondang, Korea, 2005.
Ahmad, A. Neural Network-Based Prediction: The Case of Reinforced Concrete Members under Simple and Complex Loading / A. Ahmad, N. D. Lagaros, D. M. Cotsovos // Applied Sciences. – 2021. – Vol. 11. – P. 4975. – DOI: 10.3390/app11114975.
Bamiyo, S. P. Prediction of Load deflection Behaviour of two way Rc Slab using Neural Network Approach / S. P. Bamiyo, O. A. Uche, M. Adamu // International journal of optimization in civil engineering. – 2017. – Vol. 7 (4). – P. 633–644.
Papadrakakis, M. Reliability-based structural optimization using neural networks and Monte Carlo simulation / M. Papadrakakis, N. D. Lagaros // Computer Methods in Applied Mechanics and Engineering. – 2002. – Vol. 191. – P. 3491–3507. – DOI: 10.1016/S0045-7825(02)00287-6.
Lagaros, N. D. Learning improvement of neural networks used in structural optimization / N. D. Lagaros, M. Papadrakakis // Advances in Engineering Software. – 2004. – Vol. 35, Iss. 1. – Р. 9–25. – DOI: 10.1016/S0965-9978(03)00112-1.
Lagaros, N. D. An adaptive neural network strategy for improving the computational performance of evolutionary structural optimization / N. D. Lagaros, D. C. Charmpis, M. Papadrakakis // Computer Methods in Applied Mechanics and Engineering. – 2005. – Vol. 194, Iss. 33-33. – P. 3374–3393. – DOI: 10.1016/j.cma.2004.12.023.
Lagaros, N. D. Multi-objective design optimization using cascade evolutionary computations / N. D. Lagaros, V. Plevris, M. Papadrakakis // Computer Methods in Applied Mechanics and Engineering. – 2005. – Vol. 194. – P. 3496–3515.
Lagaros, N. D. Fragility assessment of steel frames using neural networks / N. D. Lagaros, M. Fragiadakis // Earthq. Spectra. – 2007. – Vol. 23. – P. 735–752. – DOI: 10.1193/1.2798241.
Ahmad, A. Prediction of Properties of FRP-Confined Concrete Cylinders Based on Artificial Neural Networks / A. Ahmad, V. Plevris, Q.-U.-Z. Khan // Crystals. – 2020. – Vol. 10. – 811 p. – DOI: 10.3390/cryst10090811.
Evaluating the Impacts of Pumping on Aquifer Depletion in Arid Regions Using MODFLOW, ANFIS and ANN / M. R. Almuhaylan, A. R. Ghumman, I. S. Al-Salamah [et al.] // Water. – 2020. – Vol. 12. – P. 2297. – DOI: 10.3390/w12082297.
Relating groundwater levels with meteorological parameters using ANN technique / M. Iqbal, U. A. Naeem, A. Ahmad [et al.] // Measurement. – 2020. – Vol. 166. – DOI: 10.1016/j.measurement.2020.108163.
Raza, A. Prediction of axial compressive strength for FRP-confined concrete compression members / A. Raza, Q. U. Z. Khan, A. Ahmad // KSCE Journal of Civil Engineering. – 2020. – Vol. 24. – P. 2099–2109. – DOI: 10.1007/s12205-020-1682-x.
The Role of Damage Extent in the Estimation of Direct Economic Losses of Existing RC Buildings / V. Manfredi, A. Masi, G. Nicodemo [et al.]. – Pisa, Italy : Pisa University Press, 2019. – Р. 36–45.
Development of Integrated Techniques to Improve Seismic Performance and Energy Efficiency of Buildings: Preliminary Results of the Experimental Campaign on RC Portal Frames / D. Nigro, A. Digrisolo, G. Ventura [et al.]. – Pisa, Italy : Pisa University Press, 2019. – Р. 128–137.
Structural health monitoring based on the hybrid ant colony algorithm by using Hooke–Jeeves pattern search / A. Shakya, M. Mishra, D. Maity, G. Santarsiero // SN Applied Sciences. – 2019. – Vol. 1. – Р. 1–14. – DOI: 10.1007/s42452-019-0808-6.
Volna, E. Introduction to Soft Computing / E. Volna // 1st ed. ; Department of Computer Science. – Ostrava, Czechia : University of Ostrava, 2013. – Р. 137.
Garrett, J. H. Neural Networks and their Applicability within Civil Engineering / J. H. Garrett // Proceedings, 8th Congress of Computing in Civil Engineering. ASCE. – New York, 1992.
Caudill, M. Naturally Intelligent Systems / M. Caudill, C. Butler. – Cambridge, Ma : MIT Press, 1990. – 314 p.
Moselhi, O. Neural networks for cost estimating of structural steel buildings / O. Moselhi, I. Siqueira // AACE Int. Transact. – 1998. – IT22.
Moselhi, O. Potential applications of neural networks in construction / O. Moselhi, T. Hegazy, P. Fazio // Canadian Journal of Civil Engineering. – 2002. – Vol. 19(3). – P. 521-529. – DOI: 10.1139/l92-061.
Betonnye i zhelezobetonnye konstrukcii = Betonnyya i zhalezabetonnyya kanstrukcyi : SP 5.03.01-2020. – Vved. 16.09.2020. – Minsk : RUP «Strojtekhnorm» : Min. arh. i str. Respubliki Belarus', 2020. – 244 s.
Golovko, V. A. Nejrosetevye tekhnologii obrabotki dannyh / V. A. Golovko, V. V. Krasnoproshin. – Minsk : Belorusskij gosudarstvennyj universitet, 2017. – 264 s.
Ronneberger, O. U-Net: Convolutional Networks for Biomedical Image Segmentation / O. Ronneberger, P. Fischer, T. Brox // University of Freiburg, Germany. – 2015. – arXiv: 1505.04597v1 [cs.CV]. – Р. 8.
Ioffe, S. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift / S. Ioffe, Ch. Szegedy // International Conference on Machine Learning, Lille, France. – 2015. – Vol. 37. – DOI: 10.48550/arXiv.1502.03167.
Dropout i Batch normalization. Blog kompanii M. Video-El'dorado. – URL: https://habr.com/ru/companies/mvideo/articles/782360 (data obrashcheniya: 22.05.2024).
Long, J. Fully Convolutional Networks for Semantic Segmentation / J. Long, E. Shelhamer, T. Darrell // IEEE Conference on Computer Vision and Pattern Recognition (CVPR). – 2015. – DOI: 10.1109/CVPR.2015.7298965.
Barrodale, I. L1 Approximation and the Analysis of Data / I. Barrodale // Journal of the Royal Statistical Society Series C: Applied Statistics. – 1968. – Vol. 17, Iss. 1. – P. 51–57. – DOI: 10.2307/2985267.
Mean absolute error with L1 norm. – URL: https://montjoile.medium.com/l0-norm-l1-norm-l2-norm-l-infinity-norm-7a7d18a4f40c (date of access: 20.12.2023).
Python programming language and the Tensorflow framework. – URL: https://www.tensorflow.org/about/bib (date of access: 22.10.2023).
Osnovy proektirovaniya stroitel'nyh konstrukcij = Asnovy praektavannya budaunichyh kanstrukcyj : SN 2.01.01. – Vved. 16.19.2019. – Minsk : RUP «Strojtekhnorm»: Ministerstvo arhitektury i stroitel'stva Respubliki Belarus', 2020. – 89 s.
Koefficient variacii (Variation coefficient). – URL: https://wiki.loginom.ru/articles/variation-coefficient.html (data obrashcheniya: 28.02.2024).
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The work is provided under the terms of Creative Commons public license Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). This license allows an unlimited number of persons to reproduce and share the Licensed Material in all media and formats. Any use of the Licensed Material shall contain an identification of its Creator(s) and must be for non-commercial purposes only. Users may not prevent other individuals from taking any actions allowed by the license.
