Skip to main content

Advertisement

Log in

Period estimate of wood buildings employing soft modelling techniques

  • Application of soft computing
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

This study explores the applicability of the metaheuristic algorithm for calculating the building period. Firefly algorithm (FA) employing the feed-forward (FF) model is applied to an existing period dataset of several wood buildings, whose motions were recorded at ambient conditions. The composition of the considered artificial neural network (ANN) is optimized employing the firefly algorithm, and the fixed weights are determined with the least error for the model. The model's precision is evaluated by comparing the results with the multiple linear regression (MLR) model, the ANN model combined with the genetic algorithm (GA-ANN), particle swarm optimization algorithm (PSO-ANN), and the models existing in building code. The results are also compared with the models presented in the literature for the period estimate required for the seismic design of wood buildings. The paper concludes that the proposed informational model can predict the fundamental period of light-frame wood buildings more accurately than the other available models.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

Data availability

The data of this study will be available upon request.

Abbreviations

ANN:

Artificial neural network

FA:

Firefly algorithm

FF:

Feed forward

FA-ANN:

Artificial neural network model combined with firefly algorithm

NBCC:

The National Building Code of Canada

T :

The fundamental period of vibration (T)

h :

Height

ATC 1978:

Applied technology council-1978

NEHRP 94:

National Earthquake Hazards Reduction Program

\({A}_{\mathrm{e}}\) :

The equal shear area

I :

The second moments per wall in the considered direction

I 0 :

Maximum brightness

β :

The attractiveness of the fireflies

β 0 :

Maximum attractiveness

ϵ i :

A Gaussian-distributed random number

P-P :

Probability plot

\({R}^{2}\) :

Coefficient of determination

\({N}_{\mathrm{H}}\) :

Number of hidden layer nodes

SLR:

Simple linear regression

ANNs:

Artificial neural networks

GA:

Genetic algorithm

MLR:

Multiple linear regression

GA-ANN:

Artificial neural network model combined with genetic algorithm

UBC-97:

The uniform building code-1997

USH:

Uniform hazards spectra

N :

Number of stories

OSB:

Oriented strand board

SEAOC 96 :

Structural engineers association of California

L w :

Total wall width per section plan area

LMA:

Levenberg–Marquardt algorithm

γ :

Light absorption coefficient

I(r) :

Light intensities

r :

Distance between two fireflies

α :

A randomization parameter

AAE:

Average absolute error

VAF:

Variance account factor

\({N}_{\mathrm{I}}\) :

Number of inputs

PSO:

Particle swarm optimization

References

Download references

Acknowledgements

This research received no specific support from public, commercial, or not-for-profit funding organizations. The authors would like to thank Dr. Ghasan Doudak, Professor at the University of Ottawa and Dr. Gyhslaine McClure, Professor at McGill University, for their help and guidance in the data collection of wood buildings.

Funding

This research study did not receive any financial funding.

Author information

Authors and Affiliations

Authors

Contributions

MN contributed to conceptualization, methodology, investigation, formal analysis, validation, writing—original draft preparation, review and editing. GH contributed to supervision, data collection, conceptualization, methodology, investigation, visualization, writing, review and editing.

Corresponding author

Correspondence to Ghazanfarah Hafeez.

Ethics declarations

Conflict of interest

The authors declare that they have no conflicting interests concerning the publication of this article.

Ethical approval

This manuscript has not been published and is not under consideration for publication elsewhere.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Nikoo, M., Hafeez, G. Period estimate of wood buildings employing soft modelling techniques. Soft Comput 27, 16251–16264 (2023). https://doi.org/10.1007/s00500-023-08040-z

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-023-08040-z

Keywords

Navigation