|
NISCAIR ONLINE PERIODICALS REPOSITORY (NOPR) >
NISCAIR PUBLICATIONS >
Research Journals >
Indian Journal of Engineering and Materials Sciences (IJEMS) >
IJEMS Vol.19 [2012] >
IJEMS Vol.19(2) [April 2012] >
| Title: | Predicting the flexural behaviour of reinforced concrete and lightweight concrete beams by ANN |
| Authors: | Kamanli, Mehmet
Kaltakci, M Yasar
Bahadir, Fatih
Balik, Fatih S
Korkmaz, H Husnu
Donduren, M Sami
Cogurcu, M Tolga |
| Keywords: | Mechanical properties
Aggregates
Concrete
Modelling
Reinforced concrete
ANN |
| Issue Date: | Apr-2012 |
| Publisher: | NISCAIR-CSIR, India |
| Abstract: | In
this study, artificial neural network (ANN) method is used to predict the
deflection values of beams and compared with the experimental results of a
testing series. For this purpose six reinforced concrete beams with constant
rectangular cross-section are prepared and tested under pure bending. The
concrete of the test specimens is casted using the lightweight aggregates
obtained from volcanic sediments. The lightweight concrete has some advantages
comparing the traditional concrete, such as less self weight, less earthquake
forces due to decreased mass, good sound and thermal insulation. The use of lightweight
concrete in the construction industry is popular due to various advantages. The
neural network procedure is applied to determine or predict the deflection
values of 1/1 scaled model beams. The analytical results are compared with the
test results and further predictions, including different mix designs can be
possible at the end of the study. As a result, while the statistical values
RMSE, R2 and MAE from
training in ANN model are found as 0.266, 99.2% and 0.216, respectively, these
values are found in testing as 0.370, 96.47% and 0.419, respectively. |
| Page(s): | 87-94 |
| CC License: |  CC Attribution-Noncommercial-No Derivative Works 2.5 India |
| ISSN: | 0975-1017 (Online); 0971-4588 (Print) |
| Source: | IJEMS Vol.19(2) [April 2012]
|
|
