Impact Analysis of a Concrete Beam via Generative Adversarial Networks
 |
International Journal of Recent Engineering Science (IJRES) |  |
| © 2022 by IJRES Journal | ||
| Volume-9 Issue-1 |
||
| Year of Publication : 2022 | ||
| Authors : R. Tuğrul Erdem, Engin Gücüyen, Aybike Özyüksel Çiftçioğlu, Erkan Kantar |
||
| DOI : 10.14445/23497157/IJRES-V9I1P103 |
How to Cite?
R. Tuğrul Erdem, Engin Gücüyen, Aybike Özyüksel Çiftçioğlu, Erkan Kantar, "Impact Analysis of a Concrete Beam via Generative Adversarial Networks," International Journal of Recent Engineering Science, vol. 9, no. 1, pp. 16-21, 2022. Crossref, https://doi.org/10.14445/23497157/IJRES-V9I1P103
Abstract
This study investigates the behavior of a concrete beam under impact loading. For this purpose, the beam specimen is produced for this purpose, and impact experiments have been performed using a drop weight test setup. Besides, several measurement devices such as an accelerometer, dynamic load cell, optic photocells and data logger are also utilized in the experimental study. The constant input energy is implemented on the concrete beam specimen, and measurements are collected for each hammer drop. In the numerical part of the study, a novel deep learning model called Generative Adversarial Network (GAN) that has the ability to generate synthetic data without human intervention has been designed. GANs create an artificial intelligence agent to compete against another artificial intelligence agent in order to generate new samples with desired properties. GANs are used to produce synthetic data with the same statistical distribution as the experimental acceleration and impact load values acquired from the experiments. When experimental (real) and numerical (synthetic) values are compared, it is discovered that the suggested numerical model has produced consistent results in creating synthetic experimental values for the specimen. So, it is thought that the proposed numerical could be evaluated in the prediction of impact experiments.
Keywords
Concrete beam, Test setup, Impact loading, GANs, TVAE.
Reference
[1] Özgür Anıl, and Tolga Yımaz, “Low Velocity Impact Behavior of Shear Deficient RC Beam Strengthened with CFRP Strips,” Steel and Composite Structures, vol. 19, no. 2, pp. 417-439, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Gürkan Yıldırım et al., “Performance of Engineered Cementitious Composites Under Drop-Weight Impact: Effect of Different Mixture Parameters,” Structural Concrete Journal of the Fib, vol. 21, no. 3, pp. 1051-1070, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Hiroki Tamai, Yoshimi Sonoda, and John E. Bolander, “Impact Resistance of RC Beams with Reinforcement Corrosion: Experimental Observations,” Construction and Building Materials, vol. 263, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Wei-Jian Yi, De-Bo Zhao, and Sashi K. Kunnath, “Simplified Approach for Assessing Shear Resistance of Reinforced Concrete Beams Under Impact Loads,” ACI Structural Journal, vol. 113, no. 4, pp. 747-756, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Chayanon Hansapinyo et al., “Residual Strength of Reinforced Concrete Beams Under Sequential Small Impact Loads,” Buildings, vol. 11, no. 11, pp. 518-531, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Satadru Das Adhikary, Bing Li, and Kazunori Fujikake, “Residual Resistance of Impact-Damaged Reinforced Concrete Beams,” Magazine of Concrete Research, vol. 67, no. 7, pp. 364-378, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Huawei Li, Wensu Chen, and Hong Hao, “Influence of Drop Weight Geometry and Interlayer on Impact Behavior of RC Beams,” International Journal of Impact Engineering, vol. 131, pp. 222-237, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Wuchao Zhao, and Jiang Qian, “Dynamic Response and Shear Demand of Reinforced Concrete Beams Subjected to Impact Loading,” International Journal of Structural Stability and Dynamics, vol. 19, no. 8, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Özgür Anil et al., “Experimental and Numerical Investigation of Reinforced Concrete Beams with Variable Material Properties Under Impact Loading,” Construction and Building Materials, vol. 125, pp. 94-104, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[10] ASTM E23-00, Standard Test Methods for Notched Bar Impact Testing of Metallic Materials, ASTM International, West Conshohocken, PA, 2002.
[11] I.J. Goodfellow, J. Pouget-Abadie, M. Mirza et al., Generative Adversarial Networks, 2014.
[12] Berardino Barile et al., “Data Augmentation using Generative Adversarial Neural Networks on Brain Structural Connectivity in Multiple Sclerosis,” Computer Methods and Programs in Biomedicine, vol. 206, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Tongge Huang, Pranamesh Chakraborty, and Anuj Sharma, “Deep Convolutional Generative Adversarial Networks for Traffic Data Imputation Encoding Time Series as Images,” International Journal of Transportation Science and Technology, vol. 12, no. 1, pp. 1-18, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Luka Posilovic et al., “Generative Adversarial Network with Object Detector Discriminator for Enhanced Defect Detection on Ultrasonic B-Scans,” Neurocomputing, vol. 459, pp. 361-369, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Yongfei Yang et al., “Multi-Scale Reconstruction of Porous Media from Low-Resolution Core Images using Conditional Generative Adversarial Networks,” Journal of Natural Gas Science and Engineering, vol. 99, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Lei Xuet al., “Modeling Tabular Data Using Conditional Gan,” Advances in Neural Information Processing Systems, 2019.
[Google Scholar] [Publisher Link]
[17] Neha Patki, Roy Wedge, and Kalyan Veeramachaneni, “The Synthetic Data Vault,” IEEE International Conference on Data Science and Advanced Analytics, pp. 399-410, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Ban Li et al., “Improving GAN with Inverse Cumulative Distribution Function for Tabular Data Synthesis,” Neurocomputing, vol. 456, pp. 373-383, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Ekaterina Plesovskaya, and Sergey Ivanov, “An Empirical Analysis of KDE-Based Generative Models on Small Datasets,” Procedia Computer Science, vol. 193, pp. 442-452, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Justin Engelmann, and Stefan Lessmann, “Conditional Wasserstein Gan-Based Oversampling of Tabular Data for Imbalanced Learning,” Expert Systems with Applications, vol. 174, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Amirsina Torfi, Edward A. Fox, and Chandan K. Reddy, “Differentially Private Synthetic Medical Data Generation using Convolutional Gans,” Information Sciences, vol. 586, pp. 458-500, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Monjee K. Almustafa, and Moncef L. Nehdi, “Machine Learning Prediction of the Structural Response of Steel Fibre-Reinforced Concrete Beams Subjected to Far-Field Blast Loading,” Cement and Concrete Composites, vol. 126, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Fanny, and Tjeng Wawan Cenggoro, “Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network,” Procedia Computer Science, vol. 135, pp. 60-67, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Matthew Amodio et al., “Generating Hard-to-Obtain Information from Easy-to-Obtain Information Applications in Drug Discovery and Clinical Inference,” Patterns, vol. 2, no. 7, 2021.
[CrossRef] [Google Scholar] [Publisher Link]