Evaluation of Shear Strength of Deep Beams using Artificial Neural Networks
Mohammad Tasleema1, M. Anil Kumar2, J. Leon Raj3

1Mohammad Tasleema, Department of Civil Engineering, Koneru Lakshmaiah Education Foundation, Guntur (A.P), India.
2M. Anil Kumar, Department of Civil Engineering, Koneru Lakshmaiah Education Foundation, Guntur (A.P), India.
3J. Leon Raj, Scientist Applied, Department of Civil Engineering Group, CSIR-North East Institute of Science and Technology, Jorhat (Assam), India.
Manuscript received on 02 May 2019 | Revised Manuscript received on 14 May 2019 | Manuscript Published on 28 May 2019 | PP: 341-345 | Volume-7 Issue-6C2 April 2019 | Retrieval Number: F10620476C219/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: In reinforced concrete deep beams, the customary standards of stress analysis are neither appropriate to define failure mechanism nor sufficient to forecast the shear capacity of deep beams. This paper reports the prediction of shear strength of deep beams using Artificial Neural Networks (ANNs), and the results are compared with experimentally measured shear strength as well as expressions suggested by codes of practice. Test data is collected from the past research works and the artificial neural network is trained using this test data. MATLAB is used for training and analyzing the collected experimental data. The comparison of results show that ANN has predicted the shear strength of concrete deep beams more precisely when compared with the other existing models with coefficient of variation 5 %, whereas other models COV varied in between 37 and 47 %.
Keywords: Artificial Neural Networks (ANN), Reinforced Concrete Deep Beams, Shear Strength, Shear Span-to-depth Ratio.
Scope of the Article: Nondestructive Testing and Evaluation