Buy article PDF
The purchased file will be sent to you
via email after the payment is completed.
US$ 35
|
Computers and Concrete Volume 24, Number 5, November 2019 , pages 399-412 DOI: https://doi.org/10.12989/cac.2019.24.5.399 |
|
|
|
Elman ANNs along with two different sets of inputs for predicting the properties of SCCs |
||
Atefeh Gholamzadeh-Chitgar and Javad Berenjian
|
||
| Abstract | ||
| In this investigation, Elman neural networks were utilized for predicting the mechanical properties of Self- Compacting Concretes (SCCs). Elman models were designed by using experimental data of many different concrete mixdesigns of various types of SCC that were collected from the literature. In order to investigate the effectiveness of the selected input variables on the network performance in predicting intended properties, utilized data in artificial neural networks were considered in two sets of 8 and 140 input variables. The obtained outcomes showed that not only can the developed Elman ANNs predict the mechanical properties of SCCs with high accuracy, but also for all of the desired outputs, networks with 140 inputs, compared to ones with 8, have a remarkable percent improvement in the obtained prediction results. The prediction accuracy can significantly be improved by using a more complete and accurate set of key factors affecting the desired outputs, as input variables, in the networks, which is leading to more similarity of the predicted results gained from networks to experimental results. | ||
| Key Words | ||
| self-compacting concrete; Elman artificial neural networks; mechanical properties; input variables | ||
| Address | ||
| Atefeh Gholamzadeh-Chitgar: Department of Civil Engineering, Construction Management and Engineering, Tabari University of Babol, Babol, Iran Javad Berenjian: Department of Civil Engineering, Tabari University of Babol, Babol, Iran | ||