M. Hakan Arslan

Predicting of torsional strength of RC beams by using different artificial neural network algorithms and building codes

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.

Design Force Estimation Using Artificial Neural Network for Groups of Four Cylindrical Silos

The computation of design forces for the reinforced concrete groups of four cylindrical silos (GFCS) is fairly difficult because of the continuity of the walls between the adjacent silos. In this study, the efficiency of the artificial neural network (ANN) in predicting the design forces and the design moments of the GFCS due to interstice and internal loadings was investigated. Previously obtained finite element (FE) analyses results in the literature were used to train and test the ANN models. Each parameter (silo wall thickness, intersection wall thickness and the central angle spanning the intersection walls of the GFCS) affecting design forces and moments was set to be an input vector. The outputs of the ANN models would be the bending moments, hoop forces and shear forces at the supports and crowns of the interstice walls due to interstice loadings; the maximum axial forces and maximum bending moments at the external walls due to internal loadings. All the outputs of the ANN models were trained and tested by three-layered 11 back-propagation methods widely used in the literature. The obtained results presented that these 11 different methods were capable of predicting the design forces and the design moments at the interstice and external walls of the GFCS used in the training and testing phases of the study.

Sudden Complete Collapse of Zumrut Apartment Building and the Causes

AbstractIn recent years, buildings and structures in Turkey have frequently failed or suddenly sustained damage because of their own weight or other loads. The most dramatic failure was the Zumrut Apartment Building disaster: a 9-story RC building in Konya that collapsed on February 2, 2004, leaving 92 people dead. This study will investigate the cause of the building damage and failure. The significant mistakes made during the design and construction of the building will also be considered. This study was divided into three sections: site investigation, analytical study, and experimental study. The evaluation of the building failure relating to the vertical load-bearing members will be presented using observations from the site investigations, the test results obtained from specimens taken from the failed building, and the findings of an analytical study involving modeling the building using the finite-element method.