Title:
Reinforced Concrete Beam-Column Design: An Artificial Neural Network Approach
Author(s):
M. E. Haque
Publication:
Symposium Paper
Volume:
209
Issue:
Appears on pages(s):
757-770
Keywords:
artificial neural network; axial load; beam-column; interaction curve; moment; reinforced concrete
DOI:
10.14359/12531
Date:
9/26/2002
Abstract:
The basic problem in beam-column design is to establish the proportions of a reinforced concrete cross-section whose design strength is just adequate enough to support the factored axial load and moments. Since the stress distribution due to the axial load and moment depends on the cross-section’s proportions, which are initially unknown, column design cannot be carried out directly. Instead, the proportions of a cross-section must be estimated and then investigated to determine whether its design capacity is adequate for the factored loads and moments. The dimensions of a beam-column cross-section and the area of reinforcing steel required to support a specific combination of axial load and moment can be established by using the column design interaction curves, where an interaction curve represents all possible combinations of axial load and moment that produce failure of the cross-section. The bending resistance of an axially loaded column about a particular skewed axis due to biaxial moments can be determined through itera- tions and lengthy calculations. These extensive calculations are multiplied when optimization of the reinforcing steel or column cross-section is required. This pa- per investigated the suitability of an Artificial Neural Network (ANN) for model- ing a preliminary design of reinforced concrete beam-column. An ANN back- propagation model has been developed to design a beam-column which predicts column cross-section and reinforcing steel requirements for a given set of inputs which are concrete compressive strength, reinforcing steel strength, factored axial load and moment. The trained ANN back-propagation model has been tested with several actual design data, and a comparative evaluation between the ANN model predictions and the actual design has been presented.