Investigation of Welding Effect on Rebars Using Neural Networks

    Volume 26, Issue 3 (May 1998)

    ISSN: 0090-3973

    CODEN: JTEOAD

    Page Count: 8


    Mo, YL
    Professor and graduate student, National Cheng Kung University, Tainan,

    Koan, KJ
    Professor and graduate student, National Cheng Kung University, Tainan,

    (Received 30 May 1995; accepted 10 October 1997)

    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 of computation and knowledge representation paradigm, called a neural network, to model material behavior. The main benefits in using a neural network approach are that all behavior can be represented within the unified environment of a neural network and that the network is built directly from experimental data using the self-organizing capabilities of the neural network, meaning that 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 mechanical behavior of rebars affected by welds is modeled with a back-propagation neural network. The results of using networks to study the effect of welds on rebars look very promising.


    Paper ID: JTE12003J

    DOI: 10.1520/JTE12003J

    ASTM International is a member of CrossRef.

    Author
    Title Investigation of Welding Effect on Rebars Using Neural Networks
    Symposium , 0000-00-00
    Committee E28