Buy article PDF
The purchased file will be sent to you
via email after the payment is completed.
US$ 35
|
Computers and Concrete Volume 13, Number 6, June 2014 , pages 765-780 DOI: https://doi.org/10.12989/cac.2014.13.6.765 |
|
|
|
Application of artificial neural networks for dynamic analysis of building frames |
||
Shardul G. Joshi, Shreenivas N. Londhe and Naveen Kwatra
|
||
| Abstract | ||
| Many building codes use the empirical equation to determine fundamental period of vibration where in effect of length, width and the stiffness of the building is not explicitly accounted for. In the present study, ANN models are developed in three categories, varying the number of input parameters in each category. Input parameters are chosen to represent mass, stiffness and geometry of the buildings indirectly. Total numbers of 206 buildings are analyzed out of which, data set of 142 buildings is used to develop these models. It is demonstrated through developed ANN models that geometry of the building and the sizes of the columns are significant parameters in the dynamic analysis of building frames. The testing dataset of these three models is used to obtain the empirical relationship between the height of the building and fundamental period of vibration and compared with the similar equations proposed by other researchers. Experiments are conducted on Mild Steel frames using uniaxial shake table. It is seen that the values obtained through the ANN models are close to the experimental values. The validity of ANN technique is verified by experimental values. | ||
| Key Words | ||
| dynamic analysis; artificial neural network; data driven tools | ||
| Address | ||
| Shardul G. Joshi and Shreenivas N. Londhe: Department of Civil Engineering, Vishwakarma Institute of Information Technology, Pune. MH 411048. India Naveen Kwatra: Department of Civil Engineering, Thapar University, Patiala, Punjab, 147004. India | ||