Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Predicting torsional strength of RC beams by using Evolutionary Polynomial Regression
Advances in Engineering Software
| Hi-index | 0.00 |
In this study, the efficiency of different artificial neural networks (ANNs) in predicting the torsional strength of reinforced concrete (RC) beams is firstly explored. Experimental data of 76 rectangular RC beams from an existing database in the literature were used to develop ANN model. The input parameters affecting the torsional strength were selected as cross-sectional area of beams, dimensions of closed stirrups, spacing of stirrups, cross-sectional area of one-leg of closed stirrup, yield strength of stirrup and longitudinal reinforcement, steel ratio of stirrups, steel ratio of longitudinal reinforcement and concrete compressive strength. Each parameter was arranged in an input vector and a corresponding output vector that includes the torsional strength of RC beam. For all outputs, the ANN models were trained and tested using three layered 11 back-propagation methods. The initial performance evaluation of 11 different back propagations was compared with each other. In addition to these, the paper presents a short review of the well-known building codes provisions for the design of RC beams under pure torsion. The accuracy of the codes in predicting the torsional strength of RC beams was also examined with comparable way by using same test data. The study shows that the ANN models give reasonable predictions of the ultimate torsional strength of RC beams (R^2~0.988). Moreover, the study concludes that all ANN models predict the torsional strength of RC beams better than existing building code equations for torsion.