Please use this identifier to cite or link to this item:
https://idr.l4.nitk.ac.in/jspui/handle/123456789/14807
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Edward C. | |
dc.contributor.author | Balu A.S. | |
dc.date.accessioned | 2021-05-05T10:15:48Z | - |
dc.date.available | 2021-05-05T10:15:48Z | - |
dc.date.issued | 2020 | |
dc.identifier.citation | IOP Conference Series: Materials Science and Engineering , Vol. 936 , 1 , p. - | en_US |
dc.identifier.uri | https://doi.org/10.1088/1757-899X/936/1/012044 | |
dc.identifier.uri | http://idr.nitk.ac.in/jspui/handle/123456789/14807 | - |
dc.description.abstract | Columns are one of the most vital segments in bridgessince its post-seismic behaviour is of much importance. The retrofitting methods and rehabilitation strategies of bridges mainly rely on the identification of the failure mode of columns. It has been witnessed in various studies on columns that the mode of failure highly depends on section and material properties and there is no specific boundary between the modes, which makes their identification more sophisticated. This paper uses an artificial neural network to predict the modes of failure by analysing the effects of such soft computing methods. In this study, machine- learning models were generated from the experimental data of 253 columns of rectangular cross-section and its accuracy of failure mode prediction was evaluated by considering failure modes mainly flexure, flexure-shear, and shear. The optimal input parameters have also been evaluated for the machine-learning algorithm that enhances the efficiency of failure mode prediction. © Published under licence by IOP Publishing Ltd. | en_US |
dc.title | Failure Mode Recognition of Columns Using Artificial Neural Network | en_US |
dc.type | Conference Paper | en_US |
Appears in Collections: | 2. Conference Papers |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.