Model-Based Control of SMA Actuators with a Recurrent Neural Network in the Shape Control of an Airfoil

Jari Ahola, Tomi Makkonen, Kalervo Nevala, Tomi Lindroos, Pekka Isto

    Research output: Chapter in Book/Report/Conference proceedingChapter or book articleScientificpeer-review

    2 Citations (Scopus)

    Abstract

    This paper describes the development of a neural network control for shape memory alloy (SMA) actuators as well as the control tests. Precise control of SMA actuators that are integrated in the composite structure is difficult because of the hysteretic behaviour of SMA and time delays in the control system. The weakness of the static model of SMA is that it does not take into account the actuator dynamics. The NARMA-L2 neural network model enables us to solve the inverse dynamic model of the nonlinear discrete-time dynamical system. In this study the NARMA-L2 model of the airfoil (a cross section of wind turbine blade) was created using Matlab Simulink software and neural networks. Data for network training was measured from the specimen. The performance of the constituted NARMA-L2 controller was tested in control tests. According to the control tests the NARMA-L2 controller is well suited for controlling embedded SMA actuators. The constituted controller enabled fast and stable actuation in step responses and it was also able to compensate for changes in cooling conditions.
    Original languageEnglish
    Title of host publicationMechatronic Systems and Materials III
    EditorsZdislaw Gosiewski, Zbigniew Kulesza
    Pages278-283
    DOIs
    Publication statusPublished - 2009
    MoE publication typeA3 Part of a book or another research book

    Publication series

    SeriesSolid State Phenomena
    Volume147-149
    ISSN1012-0394

    Fingerprint

    Recurrent neural networks
    Shape memory effect
    Airfoils
    Actuators
    Neural networks
    Controllers
    Step response
    Composite structures
    Wind turbines
    Turbomachine blades
    Dynamic models
    Time delay
    Dynamical systems
    Cooling
    Control systems

    Keywords

    • neural network (NN)
    • shape control
    • shape memory alloy
    • system identification

    Cite this

    Ahola, J., Makkonen, T., Nevala, K., Lindroos, T., & Isto, P. (2009). Model-Based Control of SMA Actuators with a Recurrent Neural Network in the Shape Control of an Airfoil. In Z. Gosiewski, & Z. Kulesza (Eds.), Mechatronic Systems and Materials III (pp. 278-283). Solid State Phenomena, Vol.. 147-149 https://doi.org/10.4028/www.scientific.net/SSP.147-149.278
    Ahola, Jari ; Makkonen, Tomi ; Nevala, Kalervo ; Lindroos, Tomi ; Isto, Pekka. / Model-Based Control of SMA Actuators with a Recurrent Neural Network in the Shape Control of an Airfoil. Mechatronic Systems and Materials III. editor / Zdislaw Gosiewski ; Zbigniew Kulesza. 2009. pp. 278-283 (Solid State Phenomena, Vol. 147-149).
    @inbook{7fd8293ae45544ba9eee8097769c75cd,
    title = "Model-Based Control of SMA Actuators with a Recurrent Neural Network in the Shape Control of an Airfoil",
    abstract = "This paper describes the development of a neural network control for shape memory alloy (SMA) actuators as well as the control tests. Precise control of SMA actuators that are integrated in the composite structure is difficult because of the hysteretic behaviour of SMA and time delays in the control system. The weakness of the static model of SMA is that it does not take into account the actuator dynamics. The NARMA-L2 neural network model enables us to solve the inverse dynamic model of the nonlinear discrete-time dynamical system. In this study the NARMA-L2 model of the airfoil (a cross section of wind turbine blade) was created using Matlab Simulink software and neural networks. Data for network training was measured from the specimen. The performance of the constituted NARMA-L2 controller was tested in control tests. According to the control tests the NARMA-L2 controller is well suited for controlling embedded SMA actuators. The constituted controller enabled fast and stable actuation in step responses and it was also able to compensate for changes in cooling conditions.",
    keywords = "neural network (NN), shape control, shape memory alloy, system identification",
    author = "Jari Ahola and Tomi Makkonen and Kalervo Nevala and Tomi Lindroos and Pekka Isto",
    year = "2009",
    doi = "10.4028/www.scientific.net/SSP.147-149.278",
    language = "English",
    isbn = "978-3-908451-65-5",
    series = "Solid State Phenomena",
    publisher = "Trans Tech Publications",
    pages = "278--283",
    editor = "Zdislaw Gosiewski and Zbigniew Kulesza",
    booktitle = "Mechatronic Systems and Materials III",

    }

    Ahola, J, Makkonen, T, Nevala, K, Lindroos, T & Isto, P 2009, Model-Based Control of SMA Actuators with a Recurrent Neural Network in the Shape Control of an Airfoil. in Z Gosiewski & Z Kulesza (eds), Mechatronic Systems and Materials III. Solid State Phenomena, vol. 147-149, pp. 278-283. https://doi.org/10.4028/www.scientific.net/SSP.147-149.278

    Model-Based Control of SMA Actuators with a Recurrent Neural Network in the Shape Control of an Airfoil. / Ahola, Jari; Makkonen, Tomi; Nevala, Kalervo; Lindroos, Tomi; Isto, Pekka.

    Mechatronic Systems and Materials III. ed. / Zdislaw Gosiewski; Zbigniew Kulesza. 2009. p. 278-283 (Solid State Phenomena, Vol. 147-149).

    Research output: Chapter in Book/Report/Conference proceedingChapter or book articleScientificpeer-review

    TY - CHAP

    T1 - Model-Based Control of SMA Actuators with a Recurrent Neural Network in the Shape Control of an Airfoil

    AU - Ahola, Jari

    AU - Makkonen, Tomi

    AU - Nevala, Kalervo

    AU - Lindroos, Tomi

    AU - Isto, Pekka

    PY - 2009

    Y1 - 2009

    N2 - This paper describes the development of a neural network control for shape memory alloy (SMA) actuators as well as the control tests. Precise control of SMA actuators that are integrated in the composite structure is difficult because of the hysteretic behaviour of SMA and time delays in the control system. The weakness of the static model of SMA is that it does not take into account the actuator dynamics. The NARMA-L2 neural network model enables us to solve the inverse dynamic model of the nonlinear discrete-time dynamical system. In this study the NARMA-L2 model of the airfoil (a cross section of wind turbine blade) was created using Matlab Simulink software and neural networks. Data for network training was measured from the specimen. The performance of the constituted NARMA-L2 controller was tested in control tests. According to the control tests the NARMA-L2 controller is well suited for controlling embedded SMA actuators. The constituted controller enabled fast and stable actuation in step responses and it was also able to compensate for changes in cooling conditions.

    AB - This paper describes the development of a neural network control for shape memory alloy (SMA) actuators as well as the control tests. Precise control of SMA actuators that are integrated in the composite structure is difficult because of the hysteretic behaviour of SMA and time delays in the control system. The weakness of the static model of SMA is that it does not take into account the actuator dynamics. The NARMA-L2 neural network model enables us to solve the inverse dynamic model of the nonlinear discrete-time dynamical system. In this study the NARMA-L2 model of the airfoil (a cross section of wind turbine blade) was created using Matlab Simulink software and neural networks. Data for network training was measured from the specimen. The performance of the constituted NARMA-L2 controller was tested in control tests. According to the control tests the NARMA-L2 controller is well suited for controlling embedded SMA actuators. The constituted controller enabled fast and stable actuation in step responses and it was also able to compensate for changes in cooling conditions.

    KW - neural network (NN)

    KW - shape control

    KW - shape memory alloy

    KW - system identification

    U2 - 10.4028/www.scientific.net/SSP.147-149.278

    DO - 10.4028/www.scientific.net/SSP.147-149.278

    M3 - Chapter or book article

    SN - 978-3-908451-65-5

    T3 - Solid State Phenomena

    SP - 278

    EP - 283

    BT - Mechatronic Systems and Materials III

    A2 - Gosiewski, Zdislaw

    A2 - Kulesza, Zbigniew

    ER -

    Ahola J, Makkonen T, Nevala K, Lindroos T, Isto P. Model-Based Control of SMA Actuators with a Recurrent Neural Network in the Shape Control of an Airfoil. In Gosiewski Z, Kulesza Z, editors, Mechatronic Systems and Materials III. 2009. p. 278-283. (Solid State Phenomena, Vol. 147-149). https://doi.org/10.4028/www.scientific.net/SSP.147-149.278