PREDICTION OF ULTIMATE SHEAR-STRENGTH OF DEEP BEAMS USING NEURAL NETWORKS

This study investigates the feasibility of using neural networks to ev aluate the ultimate strength of deep reinforced concrete beams in shea r. A neural network is an information processing system whose architec ture essentially mimics the biological system of the brain. The neural network is particularly useful for evaluating systems with a multitud e of nonlinear variables as in this study, where the critical factors include the strength of the concrete, the beam geometry, and the steel reinforcement in the beam. No pre-defined mathematical relationship b etween the variables is assumed. Instead, the neural network ''learns' ' by example patterns obtained from published experimental data of con crete beams tested to failure. Details of the neural network methodolo gy and the experimental data are presented. The neural network predict ions were more reliable than predictions using other conventional meth ods.