PREDICTING OF TORSIONAL STRENGTH OF PRESTRESSED CONCRETE BEAMS USING ARTIFICIAL NEURAL NETWORKS PDFAkram S. MahmoodIn this paper, the artificial neural networks (ANNs) model in predicting the torsional strength of prestressed concrete beams is done. Experimental data of eighty two rectangular prestressed concrete beams under pure torsion from an existing available literature were used to develop ANN torsion model. The input parameters affecting the torsional strength of prestressed concrete beams were selected as dimensions of beams, steel ratio of transverse reinforcements, spacing of stirrups, steel ratio of longitudinal (main) reinforcement, prestressing force, concrete compressive strength, also flexural and splitting strengths. An algorithm of back propagation neural network (BPNN) with the log-sigmoid activation function is adopted due to its accuracy and results enhancement of predictions the torsional model. In addition to the ANN model is compared with ACI- 318 building code provisions for the design of prestressed concrete beams under pure torsion. The study illustrates that the ANN models give a very good predictions of the ultimate torsional strength of prestressed concrete beams.
- lifeOne crack code activation
Download: https://tlniurl.com/2vFFDY
2ff7e9595c
Comments