Investigation of Stress-Strain Relationship of Confined Concrete in Hollow Bridge Columns Using Neural Networks

    Volume 30, Issue 4 (July 2002)

    ISSN: 0090-3973

    CODEN: JTEOAD

    Page Count: 10


    Mo, YL
    Professor, University of Houston, Houston, TX

    Hung, HY
    Structural Engineer, T. Y. Lin International, Taipei,

    Zhong, J
    Ph. D. Student, University of Houston, Houston, TX

    (Received 22 December 1998; accepted 19 February 2002)

    Abstract

    Typically, material modeling has involved the development of mathematical models of material behavior derived from human observation of experimental data. An alternative procedure, discussed in this paper, is to use a computation and knowledge representation paradigm, called a network, to model material behavior. The main benefits in using a neural network is that the network is built directly from experimental data using the self-organizing capabilities of the neural network, i.e., the network is presented with the experimental data and learns the relationships between stresses and strains. Such a modeling strategy has important implications for modeling the behavior of complex materials. In this paper, the stress-strain relationship of confined concrete in hollow bridge columns is modeled with a back-propagation neural network. The results of using networks to study the behavior of confined concrete look very promising.


    Paper ID: JTE12323J

    DOI: 10.1520/JTE12323J

    ASTM International is a member of CrossRef.

    Author
    Title Investigation of Stress-Strain Relationship of Confined Concrete in Hollow Bridge Columns Using Neural Networks
    Symposium , 0000-00-00
    Committee D18