Neural Network Modeling of Confined Compressive Strength and Strain of Circular Concrete Columns

Abstract

The application of artificial neural networks (ANN) to predict the confined compressive strength and corresponding strain of circular concrete columns is explored. Using available data from past experiments, an ANN model with input parameters consisting of the unconfined compressive strength, core diameter, column height, yield strength of lateral reinforcement, volumetric ratio of lateral reinforcement, tie spacing, and longitudinal steel ratio was found to be acceptable in predicting the confined compressive strength and corresponding strain of circular concrete columns subject to limitations in the training data. The study shows the importance of validating the ANN models in simulating physical processes especially when data are limited. The ANN model was also compared to some analytical models and was found to perform well.