Active noise control in free space using recurrent neural networks with EKF algorithm

R. T. Bambang, Kenko Uchida, R. R. Yacoub

    Research output: Contribution to journalArticle

    2 Citations (Scopus)

    Abstract

    This paper presents theoretical and experimental investigation of active noise control (ANC) in free space using recurrent neural networks. A learning algorithm for diagonal recurrent neural networks based on extended Kalman filter is developed and is referred to as diagonal recurrent extended Kalman filter (DREKF) algorithm. Based on DREKF, new control algorithm suited for ANC is developed to handle nonlinearity inherently arising in this application. Real-time experiment using floating point digital signal processor is carried out for both identification and control tasks required in ANC. The results show that the number of neurons in neural network can be reduced by introducing the diagonal recurrent elements, without deteriorating the system performance, and that DREKF produces better performance than linear adaptive controller in compensating the secondary path nonlinearity.

    Original languageEnglish
    Pages (from-to)267-276
    Number of pages10
    JournalControl and Intelligent Systems
    Volume36
    Issue number3
    Publication statusPublished - 2008

    Fingerprint

    Active noise control
    Recurrent neural networks
    Extended Kalman filters
    Control nonlinearities
    Digital signal processors
    Learning algorithms
    Neurons
    Neural networks
    Controllers
    Experiments

    Keywords

    • Active noise control
    • Diagonal recurrent neural networks
    • Digital signal processor
    • Extended Kalman filter
    • Free space
    • Nonlinearity

    ASJC Scopus subject areas

    • Hardware and Architecture
    • Control and Systems Engineering

    Cite this

    Active noise control in free space using recurrent neural networks with EKF algorithm. / Bambang, R. T.; Uchida, Kenko; Yacoub, R. R.

    In: Control and Intelligent Systems, Vol. 36, No. 3, 2008, p. 267-276.

    Research output: Contribution to journalArticle

    @article{01204462393d45b6a17a65f9afef8ce3,
    title = "Active noise control in free space using recurrent neural networks with EKF algorithm",
    abstract = "This paper presents theoretical and experimental investigation of active noise control (ANC) in free space using recurrent neural networks. A learning algorithm for diagonal recurrent neural networks based on extended Kalman filter is developed and is referred to as diagonal recurrent extended Kalman filter (DREKF) algorithm. Based on DREKF, new control algorithm suited for ANC is developed to handle nonlinearity inherently arising in this application. Real-time experiment using floating point digital signal processor is carried out for both identification and control tasks required in ANC. The results show that the number of neurons in neural network can be reduced by introducing the diagonal recurrent elements, without deteriorating the system performance, and that DREKF produces better performance than linear adaptive controller in compensating the secondary path nonlinearity.",
    keywords = "Active noise control, Diagonal recurrent neural networks, Digital signal processor, Extended Kalman filter, Free space, Nonlinearity",
    author = "Bambang, {R. T.} and Kenko Uchida and Yacoub, {R. R.}",
    year = "2008",
    language = "English",
    volume = "36",
    pages = "267--276",
    journal = "Mechatronic Systems and Control",
    issn = "2561-1771",
    publisher = "ACTA Press",
    number = "3",

    }

    TY - JOUR

    T1 - Active noise control in free space using recurrent neural networks with EKF algorithm

    AU - Bambang, R. T.

    AU - Uchida, Kenko

    AU - Yacoub, R. R.

    PY - 2008

    Y1 - 2008

    N2 - This paper presents theoretical and experimental investigation of active noise control (ANC) in free space using recurrent neural networks. A learning algorithm for diagonal recurrent neural networks based on extended Kalman filter is developed and is referred to as diagonal recurrent extended Kalman filter (DREKF) algorithm. Based on DREKF, new control algorithm suited for ANC is developed to handle nonlinearity inherently arising in this application. Real-time experiment using floating point digital signal processor is carried out for both identification and control tasks required in ANC. The results show that the number of neurons in neural network can be reduced by introducing the diagonal recurrent elements, without deteriorating the system performance, and that DREKF produces better performance than linear adaptive controller in compensating the secondary path nonlinearity.

    AB - This paper presents theoretical and experimental investigation of active noise control (ANC) in free space using recurrent neural networks. A learning algorithm for diagonal recurrent neural networks based on extended Kalman filter is developed and is referred to as diagonal recurrent extended Kalman filter (DREKF) algorithm. Based on DREKF, new control algorithm suited for ANC is developed to handle nonlinearity inherently arising in this application. Real-time experiment using floating point digital signal processor is carried out for both identification and control tasks required in ANC. The results show that the number of neurons in neural network can be reduced by introducing the diagonal recurrent elements, without deteriorating the system performance, and that DREKF produces better performance than linear adaptive controller in compensating the secondary path nonlinearity.

    KW - Active noise control

    KW - Diagonal recurrent neural networks

    KW - Digital signal processor

    KW - Extended Kalman filter

    KW - Free space

    KW - Nonlinearity

    UR - http://www.scopus.com/inward/record.url?scp=50249140163&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=50249140163&partnerID=8YFLogxK

    M3 - Article

    VL - 36

    SP - 267

    EP - 276

    JO - Mechatronic Systems and Control

    JF - Mechatronic Systems and Control

    SN - 2561-1771

    IS - 3

    ER -