Neural predictive controller of nonlinear systems based on quasi-ARX neural network

Imam Sutrisno, Mohammad Abu Jami'in, Jinglu Hu

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    4 Citations (Scopus)

    Abstract

    This paper present a neural predictive controller (NPC) based on improved quasi-ARX neural network (IQARXNN) for nonlinear dynamical systems. The IQARXNN is used as a model identifier with switching algorithm and switching stability analysis. The primary controller is designed based on a modified Elman neural network (MENN) controller using back-propagation (BP) learning algorithm with modified particle swarm optimization (MPSO) to adjust the learning rates in the BP process to improve the learning capability. The adaptive learning rates of the controller are investigated via Lyapunov stability theorem, which are respectively used to guarantee the convergences of the predictive controller. Performance of the proposed MENN controller with MPSO is verified by simulation results to show the effectiveness of the proposed method both on stability and accuracy.

    Original languageEnglish
    Title of host publicationICAC 12 - Proceedings of the 18th International Conference on Automation and Computing: Integration of Design and Engineering
    Pages78-83
    Number of pages6
    Publication statusPublished - 2012
    Event18th International Conference on Automation and Computing, ICAC 2012 - Loughborough, Leicestershire
    Duration: 2012 Sep 72012 Sep 8

    Other

    Other18th International Conference on Automation and Computing, ICAC 2012
    CityLoughborough, Leicestershire
    Period12/9/712/9/8

    Fingerprint

    Nonlinear systems
    Neural networks
    Controllers
    Backpropagation
    Particle swarm optimization (PSO)
    Nonlinear dynamical systems
    Learning algorithms

    Keywords

    • improved quasi-ARX neural network (IQARXNN)
    • modified Elman neural network (MENN)
    • modified particle swarm optimization (MPSO)
    • neural predictive controller (NPC)
    • stability and accuracy

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Software

    Cite this

    Sutrisno, I., Jami'in, M. A., & Hu, J. (2012). Neural predictive controller of nonlinear systems based on quasi-ARX neural network. In ICAC 12 - Proceedings of the 18th International Conference on Automation and Computing: Integration of Design and Engineering (pp. 78-83). [6330529]

    Neural predictive controller of nonlinear systems based on quasi-ARX neural network. / Sutrisno, Imam; Jami'in, Mohammad Abu; Hu, Jinglu.

    ICAC 12 - Proceedings of the 18th International Conference on Automation and Computing: Integration of Design and Engineering. 2012. p. 78-83 6330529.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Sutrisno, I, Jami'in, MA & Hu, J 2012, Neural predictive controller of nonlinear systems based on quasi-ARX neural network. in ICAC 12 - Proceedings of the 18th International Conference on Automation and Computing: Integration of Design and Engineering., 6330529, pp. 78-83, 18th International Conference on Automation and Computing, ICAC 2012, Loughborough, Leicestershire, 12/9/7.
    Sutrisno I, Jami'in MA, Hu J. Neural predictive controller of nonlinear systems based on quasi-ARX neural network. In ICAC 12 - Proceedings of the 18th International Conference on Automation and Computing: Integration of Design and Engineering. 2012. p. 78-83. 6330529
    Sutrisno, Imam ; Jami'in, Mohammad Abu ; Hu, Jinglu. / Neural predictive controller of nonlinear systems based on quasi-ARX neural network. ICAC 12 - Proceedings of the 18th International Conference on Automation and Computing: Integration of Design and Engineering. 2012. pp. 78-83
    @inproceedings{8e9178a214504619b113dc2daaf30b69,
    title = "Neural predictive controller of nonlinear systems based on quasi-ARX neural network",
    abstract = "This paper present a neural predictive controller (NPC) based on improved quasi-ARX neural network (IQARXNN) for nonlinear dynamical systems. The IQARXNN is used as a model identifier with switching algorithm and switching stability analysis. The primary controller is designed based on a modified Elman neural network (MENN) controller using back-propagation (BP) learning algorithm with modified particle swarm optimization (MPSO) to adjust the learning rates in the BP process to improve the learning capability. The adaptive learning rates of the controller are investigated via Lyapunov stability theorem, which are respectively used to guarantee the convergences of the predictive controller. Performance of the proposed MENN controller with MPSO is verified by simulation results to show the effectiveness of the proposed method both on stability and accuracy.",
    keywords = "improved quasi-ARX neural network (IQARXNN), modified Elman neural network (MENN), modified particle swarm optimization (MPSO), neural predictive controller (NPC), stability and accuracy",
    author = "Imam Sutrisno and Jami'in, {Mohammad Abu} and Jinglu Hu",
    year = "2012",
    language = "English",
    isbn = "9781908549006",
    pages = "78--83",
    booktitle = "ICAC 12 - Proceedings of the 18th International Conference on Automation and Computing: Integration of Design and Engineering",

    }

    TY - GEN

    T1 - Neural predictive controller of nonlinear systems based on quasi-ARX neural network

    AU - Sutrisno, Imam

    AU - Jami'in, Mohammad Abu

    AU - Hu, Jinglu

    PY - 2012

    Y1 - 2012

    N2 - This paper present a neural predictive controller (NPC) based on improved quasi-ARX neural network (IQARXNN) for nonlinear dynamical systems. The IQARXNN is used as a model identifier with switching algorithm and switching stability analysis. The primary controller is designed based on a modified Elman neural network (MENN) controller using back-propagation (BP) learning algorithm with modified particle swarm optimization (MPSO) to adjust the learning rates in the BP process to improve the learning capability. The adaptive learning rates of the controller are investigated via Lyapunov stability theorem, which are respectively used to guarantee the convergences of the predictive controller. Performance of the proposed MENN controller with MPSO is verified by simulation results to show the effectiveness of the proposed method both on stability and accuracy.

    AB - This paper present a neural predictive controller (NPC) based on improved quasi-ARX neural network (IQARXNN) for nonlinear dynamical systems. The IQARXNN is used as a model identifier with switching algorithm and switching stability analysis. The primary controller is designed based on a modified Elman neural network (MENN) controller using back-propagation (BP) learning algorithm with modified particle swarm optimization (MPSO) to adjust the learning rates in the BP process to improve the learning capability. The adaptive learning rates of the controller are investigated via Lyapunov stability theorem, which are respectively used to guarantee the convergences of the predictive controller. Performance of the proposed MENN controller with MPSO is verified by simulation results to show the effectiveness of the proposed method both on stability and accuracy.

    KW - improved quasi-ARX neural network (IQARXNN)

    KW - modified Elman neural network (MENN)

    KW - modified particle swarm optimization (MPSO)

    KW - neural predictive controller (NPC)

    KW - stability and accuracy

    UR - http://www.scopus.com/inward/record.url?scp=84869398510&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84869398510&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:84869398510

    SN - 9781908549006

    SP - 78

    EP - 83

    BT - ICAC 12 - Proceedings of the 18th International Conference on Automation and Computing: Integration of Design and Engineering

    ER -