An artificial neural network model for predicting the behaviour of flexible end-plate bare-steel joints in fire

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper describes an artificial neural networking model developed to predict the behavior of flexible end-plate bare-steel joints in fire. The joint used in the study was typical to the ones used in multistory steel-framed buildings. The Applied moment and joint's temperatures were used as input parameters to model the rotational capacity of the joint with increasing temperatures. Data from experimental fire tests were used for training and testing the ANN model. Results showed that the R2 value for the training and testing sets were 0.9905 and 0.9932, respectively. This indicates that results from the ANN model compared very closely with the experimental results demonstrating the capability of the ANN simulation techniques in predicting the behaviour of flexible end-plate joints in fire with high accuracy. The described model can be modified to study other important parameters that can have considerable effect on the behaviour of joints at elevated temperatures.

Original languageEnglish
Title of host publicationProceedings of 8th Pacific Structural Steel Conference - Steel Structures in Natural Hazards, PSSC 2007
Pages213-218
Number of pages6
Volume2
Publication statusPublished - 2007
Event8th Pacific Structural Steel Conference - Steel Structures in Natural Hazards, PSSC 2007 - Wairakei, New Zealand
Duration: Mar 13 2007Mar 16 2007

Other

Other8th Pacific Structural Steel Conference - Steel Structures in Natural Hazards, PSSC 2007
CountryNew Zealand
CityWairakei
Period3/13/073/16/07

Fingerprint

Fires
Neural networks
Steel
Testing
Temperature

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Al-Jabri, K. S., Al-Alawi, S. M., Al-Saidy, A. H., & Alnuaimi, A. S. (2007). An artificial neural network model for predicting the behaviour of flexible end-plate bare-steel joints in fire. In Proceedings of 8th Pacific Structural Steel Conference - Steel Structures in Natural Hazards, PSSC 2007 (Vol. 2, pp. 213-218)

An artificial neural network model for predicting the behaviour of flexible end-plate bare-steel joints in fire. / Al-Jabri, K. S.; Al-Alawi, S. M.; Al-Saidy, A. H.; Alnuaimi, A. S.

Proceedings of 8th Pacific Structural Steel Conference - Steel Structures in Natural Hazards, PSSC 2007. Vol. 2 2007. p. 213-218.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Al-Jabri, KS, Al-Alawi, SM, Al-Saidy, AH & Alnuaimi, AS 2007, An artificial neural network model for predicting the behaviour of flexible end-plate bare-steel joints in fire. in Proceedings of 8th Pacific Structural Steel Conference - Steel Structures in Natural Hazards, PSSC 2007. vol. 2, pp. 213-218, 8th Pacific Structural Steel Conference - Steel Structures in Natural Hazards, PSSC 2007, Wairakei, New Zealand, 3/13/07.
Al-Jabri KS, Al-Alawi SM, Al-Saidy AH, Alnuaimi AS. An artificial neural network model for predicting the behaviour of flexible end-plate bare-steel joints in fire. In Proceedings of 8th Pacific Structural Steel Conference - Steel Structures in Natural Hazards, PSSC 2007. Vol. 2. 2007. p. 213-218
Al-Jabri, K. S. ; Al-Alawi, S. M. ; Al-Saidy, A. H. ; Alnuaimi, A. S. / An artificial neural network model for predicting the behaviour of flexible end-plate bare-steel joints in fire. Proceedings of 8th Pacific Structural Steel Conference - Steel Structures in Natural Hazards, PSSC 2007. Vol. 2 2007. pp. 213-218
@inproceedings{a3ac09a551db4708b4116c7a4aafb929,
title = "An artificial neural network model for predicting the behaviour of flexible end-plate bare-steel joints in fire",
abstract = "This paper describes an artificial neural networking model developed to predict the behavior of flexible end-plate bare-steel joints in fire. The joint used in the study was typical to the ones used in multistory steel-framed buildings. The Applied moment and joint's temperatures were used as input parameters to model the rotational capacity of the joint with increasing temperatures. Data from experimental fire tests were used for training and testing the ANN model. Results showed that the R2 value for the training and testing sets were 0.9905 and 0.9932, respectively. This indicates that results from the ANN model compared very closely with the experimental results demonstrating the capability of the ANN simulation techniques in predicting the behaviour of flexible end-plate joints in fire with high accuracy. The described model can be modified to study other important parameters that can have considerable effect on the behaviour of joints at elevated temperatures.",
author = "Al-Jabri, {K. S.} and Al-Alawi, {S. M.} and Al-Saidy, {A. H.} and Alnuaimi, {A. S.}",
year = "2007",
language = "English",
isbn = "0908694547",
volume = "2",
pages = "213--218",
booktitle = "Proceedings of 8th Pacific Structural Steel Conference - Steel Structures in Natural Hazards, PSSC 2007",

}

TY - GEN

T1 - An artificial neural network model for predicting the behaviour of flexible end-plate bare-steel joints in fire

AU - Al-Jabri, K. S.

AU - Al-Alawi, S. M.

AU - Al-Saidy, A. H.

AU - Alnuaimi, A. S.

PY - 2007

Y1 - 2007

N2 - This paper describes an artificial neural networking model developed to predict the behavior of flexible end-plate bare-steel joints in fire. The joint used in the study was typical to the ones used in multistory steel-framed buildings. The Applied moment and joint's temperatures were used as input parameters to model the rotational capacity of the joint with increasing temperatures. Data from experimental fire tests were used for training and testing the ANN model. Results showed that the R2 value for the training and testing sets were 0.9905 and 0.9932, respectively. This indicates that results from the ANN model compared very closely with the experimental results demonstrating the capability of the ANN simulation techniques in predicting the behaviour of flexible end-plate joints in fire with high accuracy. The described model can be modified to study other important parameters that can have considerable effect on the behaviour of joints at elevated temperatures.

AB - This paper describes an artificial neural networking model developed to predict the behavior of flexible end-plate bare-steel joints in fire. The joint used in the study was typical to the ones used in multistory steel-framed buildings. The Applied moment and joint's temperatures were used as input parameters to model the rotational capacity of the joint with increasing temperatures. Data from experimental fire tests were used for training and testing the ANN model. Results showed that the R2 value for the training and testing sets were 0.9905 and 0.9932, respectively. This indicates that results from the ANN model compared very closely with the experimental results demonstrating the capability of the ANN simulation techniques in predicting the behaviour of flexible end-plate joints in fire with high accuracy. The described model can be modified to study other important parameters that can have considerable effect on the behaviour of joints at elevated temperatures.

UR - http://www.scopus.com/inward/record.url?scp=55649111324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=55649111324&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0908694547

SN - 9780908694549

VL - 2

SP - 213

EP - 218

BT - Proceedings of 8th Pacific Structural Steel Conference - Steel Structures in Natural Hazards, PSSC 2007

ER -