MURAL - Maynooth University Research Archive Library



    Design issues in applying neural networks to model highly non-linear processes


    Doherty, Sean and Gomm, J.B. and Williams, D. and Eardley, D.C. (1994) Design issues in applying neural networks to model highly non-linear processes. In: 1994 International Conference on Control - Control '94. IET, pp. 1478-1483. ISBN 0852966105

    [img]
    Preview
    Download (413kB) | Preview


    Share your research

    Twitter Facebook LinkedIn GooglePlus Email more...



    Add this article to your Mendeley library


    Abstract

    his paper looks at the selection of some of the design parameters which are crucially important for the training of a valid artificial neural network (ANN) model of processes with strong nonlinearities. Arbitrary selection of data sample time and network structure can result in an ANN model with unacceptable prediction errors. Useful guidelines concerning data sample time and model structure can be obtained by studying local linear models. The Akaike's final prediction error (AFPE) and Akaike's information criterion (AIC) penalise overparameterised networks and are therefore useful indicators of model parsimony. They can be used in conjunction with correlation analysis for model selection and validation.

    Item Type: Book Section
    Keywords: control nonlinearities; control system synthesis; neural nets; nonlinear control systems;
    Academic Unit: Faculty of Science and Engineering > Electronic Engineering
    Item ID: 9708
    Identification Number: https://doi.org/10.1049/cp:19940355
    Depositing User: Seán Doherty
    Date Deposited: 20 Jul 2018 14:23
    Publisher: IET
    Refereed: Yes
    URI:

    Repository Staff Only(login required)

    View Item Item control page

    Downloads

    Downloads per month over past year