Strength prediction of rotary brace damper using MLR and MARS

I. Mansouri, M. Safa, Z. Ibrahim, O. Kisi, M. M. Tahir, Shahrizan Baharom, M. Azimi

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

This study predicts the strength of rotary brace damper by analyzing a new set of probabilistic models using the usual method of multiple linear regressions (MLR) and advanced machine-learning methods of multivariate adaptive regression splines (MARS), Rotary brace damper can be easily assembled with high energy-dissipation capability. To investigate the behavior of this damper in structures, a steel frame is modeled with this device subjected to monotonic and cyclic loading. Several response parameters are considered, and the performance of damper in reducing each response is evaluated. MLR and MARS methods were used to predict the strength of this damper. Displacement was determined to be the most effective parameter of damper strength, whereas the thickness did not exhibit any effect. Adding thickness parameter as inputs to MARS and MLR models did not increase the accuracies of the models in predicting the strength of this damper. The MARS model with a root mean square error (RMSE) of 0.127 and mean absolute error (MAE) of 0.090 performed better than the MLR model with an RMSE of 0.221 and MAE of 0.181.

Original languageEnglish
Pages (from-to)471-488
Number of pages18
JournalStructural Engineering and Mechanics
Volume60
Issue number3
DOIs
Publication statusPublished - 10 Nov 2016

Fingerprint

Linear regression
Splines
Mean square error
Learning systems
Energy dissipation
Steel

Keywords

  • Damper strength
  • MARS
  • MLR
  • Nonlinear response
  • Passive energy dissipation
  • Rotary brace damper

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Building and Construction
  • Mechanics of Materials
  • Mechanical Engineering

Cite this

Strength prediction of rotary brace damper using MLR and MARS. / Mansouri, I.; Safa, M.; Ibrahim, Z.; Kisi, O.; Tahir, M. M.; Baharom, Shahrizan; Azimi, M.

In: Structural Engineering and Mechanics, Vol. 60, No. 3, 10.11.2016, p. 471-488.

Research output: Contribution to journalArticle

Mansouri, I, Safa, M, Ibrahim, Z, Kisi, O, Tahir, MM, Baharom, S & Azimi, M 2016, 'Strength prediction of rotary brace damper using MLR and MARS', Structural Engineering and Mechanics, vol. 60, no. 3, pp. 471-488. https://doi.org/10.12989/sem.2016.60.3.471
Mansouri, I. ; Safa, M. ; Ibrahim, Z. ; Kisi, O. ; Tahir, M. M. ; Baharom, Shahrizan ; Azimi, M. / Strength prediction of rotary brace damper using MLR and MARS. In: Structural Engineering and Mechanics. 2016 ; Vol. 60, No. 3. pp. 471-488.
@article{57042bfba8a44ce0b30f968981198b99,
title = "Strength prediction of rotary brace damper using MLR and MARS",
abstract = "This study predicts the strength of rotary brace damper by analyzing a new set of probabilistic models using the usual method of multiple linear regressions (MLR) and advanced machine-learning methods of multivariate adaptive regression splines (MARS), Rotary brace damper can be easily assembled with high energy-dissipation capability. To investigate the behavior of this damper in structures, a steel frame is modeled with this device subjected to monotonic and cyclic loading. Several response parameters are considered, and the performance of damper in reducing each response is evaluated. MLR and MARS methods were used to predict the strength of this damper. Displacement was determined to be the most effective parameter of damper strength, whereas the thickness did not exhibit any effect. Adding thickness parameter as inputs to MARS and MLR models did not increase the accuracies of the models in predicting the strength of this damper. The MARS model with a root mean square error (RMSE) of 0.127 and mean absolute error (MAE) of 0.090 performed better than the MLR model with an RMSE of 0.221 and MAE of 0.181.",
keywords = "Damper strength, MARS, MLR, Nonlinear response, Passive energy dissipation, Rotary brace damper",
author = "I. Mansouri and M. Safa and Z. Ibrahim and O. Kisi and Tahir, {M. M.} and Shahrizan Baharom and M. Azimi",
year = "2016",
month = "11",
day = "10",
doi = "10.12989/sem.2016.60.3.471",
language = "English",
volume = "60",
pages = "471--488",
journal = "Structural Engineering and Mechanics",
issn = "1225-4568",
publisher = "Techno Press",
number = "3",

}

TY - JOUR

T1 - Strength prediction of rotary brace damper using MLR and MARS

AU - Mansouri, I.

AU - Safa, M.

AU - Ibrahim, Z.

AU - Kisi, O.

AU - Tahir, M. M.

AU - Baharom, Shahrizan

AU - Azimi, M.

PY - 2016/11/10

Y1 - 2016/11/10

N2 - This study predicts the strength of rotary brace damper by analyzing a new set of probabilistic models using the usual method of multiple linear regressions (MLR) and advanced machine-learning methods of multivariate adaptive regression splines (MARS), Rotary brace damper can be easily assembled with high energy-dissipation capability. To investigate the behavior of this damper in structures, a steel frame is modeled with this device subjected to monotonic and cyclic loading. Several response parameters are considered, and the performance of damper in reducing each response is evaluated. MLR and MARS methods were used to predict the strength of this damper. Displacement was determined to be the most effective parameter of damper strength, whereas the thickness did not exhibit any effect. Adding thickness parameter as inputs to MARS and MLR models did not increase the accuracies of the models in predicting the strength of this damper. The MARS model with a root mean square error (RMSE) of 0.127 and mean absolute error (MAE) of 0.090 performed better than the MLR model with an RMSE of 0.221 and MAE of 0.181.

AB - This study predicts the strength of rotary brace damper by analyzing a new set of probabilistic models using the usual method of multiple linear regressions (MLR) and advanced machine-learning methods of multivariate adaptive regression splines (MARS), Rotary brace damper can be easily assembled with high energy-dissipation capability. To investigate the behavior of this damper in structures, a steel frame is modeled with this device subjected to monotonic and cyclic loading. Several response parameters are considered, and the performance of damper in reducing each response is evaluated. MLR and MARS methods were used to predict the strength of this damper. Displacement was determined to be the most effective parameter of damper strength, whereas the thickness did not exhibit any effect. Adding thickness parameter as inputs to MARS and MLR models did not increase the accuracies of the models in predicting the strength of this damper. The MARS model with a root mean square error (RMSE) of 0.127 and mean absolute error (MAE) of 0.090 performed better than the MLR model with an RMSE of 0.221 and MAE of 0.181.

KW - Damper strength

KW - MARS

KW - MLR

KW - Nonlinear response

KW - Passive energy dissipation

KW - Rotary brace damper

UR - http://www.scopus.com/inward/record.url?scp=84991435097&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991435097&partnerID=8YFLogxK

U2 - 10.12989/sem.2016.60.3.471

DO - 10.12989/sem.2016.60.3.471

M3 - Article

AN - SCOPUS:84991435097

VL - 60

SP - 471

EP - 488

JO - Structural Engineering and Mechanics

JF - Structural Engineering and Mechanics

SN - 1225-4568

IS - 3

ER -