Neural network based hysteretic model for steel beam-column connection

Component-based approach

G. J. Yun, J. Ghaboussi, Amr S. Elnashai

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

Abstract

Beam-column connections exhibit complex behavior and often suffer damage during earthquakes. Beam-column connection failures in steel structures during the two major earthquakes of Northridge, 1994, and Hyogo-ken Nanbu, 1995 have underscored the importance of reliable modeling of these connections; models that include their main governing response modes under hysteretic loading. Many different modeling approaches have been applied to steel (and composite) beam-to-column connections over the past 3 decades. In this paper, a new neural network based inelastic hysteretic model for steel beam-column connections is proposed. The neural network (NN) model employs a component-based approach whereby the main components of the connection, and the interaction between them, are simulated separately. A welded beam-column connection (pre-Northridge type) is selected to demonstrate the proposed method. A self-learning simulation algorithm based on an auto-progressive methodology is employed so that the model can reproduce realistic hysteretic moment-rotational behavior. The proposed methodology is general and it has applications beyond the steel beam-column connection. The proposed framework can also be applied to other types of connections and many other structural systems.

Original languageEnglish (US)
Title of host publicationProceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006
Pages377-382
Number of pages6
StatePublished - Dec 1 2006
Event5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006 - Yokohama, Japan
Duration: Aug 14 2006Aug 17 2006

Publication series

NameProceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006

Other

Other5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006
CountryJapan
CityYokohama
Period8/14/068/17/06

Fingerprint

Neural networks
Steel
Earthquakes
Steel structures
Composite materials

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Building and Construction
  • Architecture

Cite this

Yun, G. J., Ghaboussi, J., & Elnashai, A. S. (2006). Neural network based hysteretic model for steel beam-column connection: Component-based approach. In Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006 (pp. 377-382). (Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006).
Yun, G. J. ; Ghaboussi, J. ; Elnashai, Amr S. / Neural network based hysteretic model for steel beam-column connection : Component-based approach. Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006. 2006. pp. 377-382 (Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006).
@inproceedings{47eb763e75564fdeb1c839473cccfd80,
title = "Neural network based hysteretic model for steel beam-column connection: Component-based approach",
abstract = "Beam-column connections exhibit complex behavior and often suffer damage during earthquakes. Beam-column connection failures in steel structures during the two major earthquakes of Northridge, 1994, and Hyogo-ken Nanbu, 1995 have underscored the importance of reliable modeling of these connections; models that include their main governing response modes under hysteretic loading. Many different modeling approaches have been applied to steel (and composite) beam-to-column connections over the past 3 decades. In this paper, a new neural network based inelastic hysteretic model for steel beam-column connections is proposed. The neural network (NN) model employs a component-based approach whereby the main components of the connection, and the interaction between them, are simulated separately. A welded beam-column connection (pre-Northridge type) is selected to demonstrate the proposed method. A self-learning simulation algorithm based on an auto-progressive methodology is employed so that the model can reproduce realistic hysteretic moment-rotational behavior. The proposed methodology is general and it has applications beyond the steel beam-column connection. The proposed framework can also be applied to other types of connections and many other structural systems.",
author = "Yun, {G. J.} and J. Ghaboussi and Elnashai, {Amr S.}",
year = "2006",
month = "12",
day = "1",
language = "English (US)",
isbn = "0415408245",
series = "Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006",
pages = "377--382",
booktitle = "Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006",

}

Yun, GJ, Ghaboussi, J & Elnashai, AS 2006, Neural network based hysteretic model for steel beam-column connection: Component-based approach. in Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006. Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006, pp. 377-382, 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006, Yokohama, Japan, 8/14/06.

Neural network based hysteretic model for steel beam-column connection : Component-based approach. / Yun, G. J.; Ghaboussi, J.; Elnashai, Amr S.

Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006. 2006. p. 377-382 (Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006).

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

TY - GEN

T1 - Neural network based hysteretic model for steel beam-column connection

T2 - Component-based approach

AU - Yun, G. J.

AU - Ghaboussi, J.

AU - Elnashai, Amr S.

PY - 2006/12/1

Y1 - 2006/12/1

N2 - Beam-column connections exhibit complex behavior and often suffer damage during earthquakes. Beam-column connection failures in steel structures during the two major earthquakes of Northridge, 1994, and Hyogo-ken Nanbu, 1995 have underscored the importance of reliable modeling of these connections; models that include their main governing response modes under hysteretic loading. Many different modeling approaches have been applied to steel (and composite) beam-to-column connections over the past 3 decades. In this paper, a new neural network based inelastic hysteretic model for steel beam-column connections is proposed. The neural network (NN) model employs a component-based approach whereby the main components of the connection, and the interaction between them, are simulated separately. A welded beam-column connection (pre-Northridge type) is selected to demonstrate the proposed method. A self-learning simulation algorithm based on an auto-progressive methodology is employed so that the model can reproduce realistic hysteretic moment-rotational behavior. The proposed methodology is general and it has applications beyond the steel beam-column connection. The proposed framework can also be applied to other types of connections and many other structural systems.

AB - Beam-column connections exhibit complex behavior and often suffer damage during earthquakes. Beam-column connection failures in steel structures during the two major earthquakes of Northridge, 1994, and Hyogo-ken Nanbu, 1995 have underscored the importance of reliable modeling of these connections; models that include their main governing response modes under hysteretic loading. Many different modeling approaches have been applied to steel (and composite) beam-to-column connections over the past 3 decades. In this paper, a new neural network based inelastic hysteretic model for steel beam-column connections is proposed. The neural network (NN) model employs a component-based approach whereby the main components of the connection, and the interaction between them, are simulated separately. A welded beam-column connection (pre-Northridge type) is selected to demonstrate the proposed method. A self-learning simulation algorithm based on an auto-progressive methodology is employed so that the model can reproduce realistic hysteretic moment-rotational behavior. The proposed methodology is general and it has applications beyond the steel beam-column connection. The proposed framework can also be applied to other types of connections and many other structural systems.

UR - http://www.scopus.com/inward/record.url?scp=56249142812&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=56249142812&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0415408245

SN - 9780415408240

T3 - Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006

SP - 377

EP - 382

BT - Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006

ER -

Yun GJ, Ghaboussi J, Elnashai AS. Neural network based hysteretic model for steel beam-column connection: Component-based approach. In Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006. 2006. p. 377-382. (Proceedings of the 5th International Conference on Behaviour of Steel Structures in Seismic Areas - Stessa 2006).