A hammerstein-type fourier neural network-based identification with application to transformer vibration system modelling

Z. Jing, H. Hai, Jie Jie

    Research output: Chapter in Book/Conference paperConference paper

    1 Citation (Scopus)

    Abstract

    © 2015 IEEE. This paper aims to construct an appropriate model to represent the nonlinear transformer vibration system, with electric applies as the system inputs and the vibration response on the transformer tank as the outputs. A single-input and single-output (SISO) Hammerstein-type model is developed for identifying the nonlinear transformer vibration system, when the observed vibration on the transformer tank is derived into two components contributed by the individual vibration sources. The nonlinear system is identified by the Fourier neural network, which consists of a nonlinear element and a linear dynamic block. The order determination method based on the Lipschitz criterion as well as the back-propagation algorithm for weights update are both presented. The Hammerstein-type Fourier neural networkbased model is tested on a transformer, giving promising results for prediction of the transformer vibration.
    Original languageEnglish
    Title of host publicationProceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015
    Place of PublicationUSA
    PublisherWiley-IEEE Press
    Pages1974-1979
    ISBN (Print)9781467373173
    DOIs
    Publication statusPublished - 2015
    Event10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015 - Auckland, New Zealand
    Duration: 15 Jun 201517 Jun 2015

    Conference

    Conference10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015
    CountryNew Zealand
    CityAuckland
    Period15/06/1517/06/15

    Fingerprint

    Neural networks
    Backpropagation algorithms
    Nonlinear systems

    Cite this

    Jing, Z., Hai, H., & Jie, J. (2015). A hammerstein-type fourier neural network-based identification with application to transformer vibration system modelling. In Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015 (pp. 1974-1979). USA: Wiley-IEEE Press. https://doi.org/10.1109/ICIEA.2015.7334436
    Jing, Z. ; Hai, H. ; Jie, Jie. / A hammerstein-type fourier neural network-based identification with application to transformer vibration system modelling. Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015. USA : Wiley-IEEE Press, 2015. pp. 1974-1979
    @inproceedings{fc19c0c070a94661aed812e6a661fe98,
    title = "A hammerstein-type fourier neural network-based identification with application to transformer vibration system modelling",
    abstract = "{\circledC} 2015 IEEE. This paper aims to construct an appropriate model to represent the nonlinear transformer vibration system, with electric applies as the system inputs and the vibration response on the transformer tank as the outputs. A single-input and single-output (SISO) Hammerstein-type model is developed for identifying the nonlinear transformer vibration system, when the observed vibration on the transformer tank is derived into two components contributed by the individual vibration sources. The nonlinear system is identified by the Fourier neural network, which consists of a nonlinear element and a linear dynamic block. The order determination method based on the Lipschitz criterion as well as the back-propagation algorithm for weights update are both presented. The Hammerstein-type Fourier neural networkbased model is tested on a transformer, giving promising results for prediction of the transformer vibration.",
    author = "Z. Jing and H. Hai and Jie Jie",
    year = "2015",
    doi = "10.1109/ICIEA.2015.7334436",
    language = "English",
    isbn = "9781467373173",
    pages = "1974--1979",
    booktitle = "Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015",
    publisher = "Wiley-IEEE Press",

    }

    Jing, Z, Hai, H & Jie, J 2015, A hammerstein-type fourier neural network-based identification with application to transformer vibration system modelling. in Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015. Wiley-IEEE Press, USA, pp. 1974-1979, 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015, Auckland, New Zealand, 15/06/15. https://doi.org/10.1109/ICIEA.2015.7334436

    A hammerstein-type fourier neural network-based identification with application to transformer vibration system modelling. / Jing, Z.; Hai, H.; Jie, Jie.

    Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015. USA : Wiley-IEEE Press, 2015. p. 1974-1979.

    Research output: Chapter in Book/Conference paperConference paper

    TY - GEN

    T1 - A hammerstein-type fourier neural network-based identification with application to transformer vibration system modelling

    AU - Jing, Z.

    AU - Hai, H.

    AU - Jie, Jie

    PY - 2015

    Y1 - 2015

    N2 - © 2015 IEEE. This paper aims to construct an appropriate model to represent the nonlinear transformer vibration system, with electric applies as the system inputs and the vibration response on the transformer tank as the outputs. A single-input and single-output (SISO) Hammerstein-type model is developed for identifying the nonlinear transformer vibration system, when the observed vibration on the transformer tank is derived into two components contributed by the individual vibration sources. The nonlinear system is identified by the Fourier neural network, which consists of a nonlinear element and a linear dynamic block. The order determination method based on the Lipschitz criterion as well as the back-propagation algorithm for weights update are both presented. The Hammerstein-type Fourier neural networkbased model is tested on a transformer, giving promising results for prediction of the transformer vibration.

    AB - © 2015 IEEE. This paper aims to construct an appropriate model to represent the nonlinear transformer vibration system, with electric applies as the system inputs and the vibration response on the transformer tank as the outputs. A single-input and single-output (SISO) Hammerstein-type model is developed for identifying the nonlinear transformer vibration system, when the observed vibration on the transformer tank is derived into two components contributed by the individual vibration sources. The nonlinear system is identified by the Fourier neural network, which consists of a nonlinear element and a linear dynamic block. The order determination method based on the Lipschitz criterion as well as the back-propagation algorithm for weights update are both presented. The Hammerstein-type Fourier neural networkbased model is tested on a transformer, giving promising results for prediction of the transformer vibration.

    U2 - 10.1109/ICIEA.2015.7334436

    DO - 10.1109/ICIEA.2015.7334436

    M3 - Conference paper

    SN - 9781467373173

    SP - 1974

    EP - 1979

    BT - Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015

    PB - Wiley-IEEE Press

    CY - USA

    ER -

    Jing Z, Hai H, Jie J. A hammerstein-type fourier neural network-based identification with application to transformer vibration system modelling. In Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015. USA: Wiley-IEEE Press. 2015. p. 1974-1979 https://doi.org/10.1109/ICIEA.2015.7334436