Home > Research > Publications & Outputs > Nonlinear system identification for model-based...

Research

Associated organisational units

Links

Text available via DOI:

Keywords

View graph of relations

Nonlinear system identification for model-based condition monitoring of wind turbines

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Nonlinear system identification for model-based condition monitoring of wind turbines. / Cross, Philip; Ma, Xiandong.
In: Renewable Energy, Vol. 71, 11.2014, p. 166-175.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Cross, P & Ma, X 2014, 'Nonlinear system identification for model-based condition monitoring of wind turbines', Renewable Energy, vol. 71, pp. 166-175. https://doi.org/10.1016/j.renene.2014.05.035

APA

Cross, P., & Ma, X. (2014). Nonlinear system identification for model-based condition monitoring of wind turbines. Renewable Energy, 71, 166-175. https://doi.org/10.1016/j.renene.2014.05.035

Vancouver

Cross P, Ma X. Nonlinear system identification for model-based condition monitoring of wind turbines. Renewable Energy. 2014 Nov;71:166-175. Epub 2014 Jun 7. doi: 10.1016/j.renene.2014.05.035

Author

Cross, Philip ; Ma, Xiandong. / Nonlinear system identification for model-based condition monitoring of wind turbines. In: Renewable Energy. 2014 ; Vol. 71. pp. 166-175.

Bibtex

@article{e73f200333de48d8a154e762d46cbba2,
title = "Nonlinear system identification for model-based condition monitoring of wind turbines",
abstract = "This paper proposes a data driven model-based condition monitoring scheme that is applied to wind turbines. The scheme is based upon a non-linear data-based modelling approach in which the model parameters vary as functions of the system variables. The model structure and parameters are identifieddirectly from the input and output data of the process. The proposed method is demonstrated with data obtained from a simulation of a grid-connected wind turbine where it is used to detect grid and power electronic faults. The method is evaluated further with SCADA data obtained from an operational wind farm where it is employed to identify gearbox and generator faults. In contrast to artificial intelligence methods, such as artificial neural network-based models, the method employed in this paper provides a parametrically efficient representation of non-linear processes. Consequently, it is relatively straightforward to implement the proposed model-based method on-line using a field-programmable gate array.",
keywords = "Distributed generation , Wind turbine , Condition monitoring , Fault detection , Modelling and simulation , SCADA data",
author = "Philip Cross and Xiandong Ma",
note = "Open Access funded by Engineering and Physical Sciences Research Council Under a Creative Commons license",
year = "2014",
month = nov,
doi = "10.1016/j.renene.2014.05.035",
language = "English",
volume = "71",
pages = "166--175",
journal = "Renewable Energy",
issn = "0960-1481",
publisher = "Elsevier BV",

}

RIS

TY - JOUR

T1 - Nonlinear system identification for model-based condition monitoring of wind turbines

AU - Cross, Philip

AU - Ma, Xiandong

N1 - Open Access funded by Engineering and Physical Sciences Research Council Under a Creative Commons license

PY - 2014/11

Y1 - 2014/11

N2 - This paper proposes a data driven model-based condition monitoring scheme that is applied to wind turbines. The scheme is based upon a non-linear data-based modelling approach in which the model parameters vary as functions of the system variables. The model structure and parameters are identifieddirectly from the input and output data of the process. The proposed method is demonstrated with data obtained from a simulation of a grid-connected wind turbine where it is used to detect grid and power electronic faults. The method is evaluated further with SCADA data obtained from an operational wind farm where it is employed to identify gearbox and generator faults. In contrast to artificial intelligence methods, such as artificial neural network-based models, the method employed in this paper provides a parametrically efficient representation of non-linear processes. Consequently, it is relatively straightforward to implement the proposed model-based method on-line using a field-programmable gate array.

AB - This paper proposes a data driven model-based condition monitoring scheme that is applied to wind turbines. The scheme is based upon a non-linear data-based modelling approach in which the model parameters vary as functions of the system variables. The model structure and parameters are identifieddirectly from the input and output data of the process. The proposed method is demonstrated with data obtained from a simulation of a grid-connected wind turbine where it is used to detect grid and power electronic faults. The method is evaluated further with SCADA data obtained from an operational wind farm where it is employed to identify gearbox and generator faults. In contrast to artificial intelligence methods, such as artificial neural network-based models, the method employed in this paper provides a parametrically efficient representation of non-linear processes. Consequently, it is relatively straightforward to implement the proposed model-based method on-line using a field-programmable gate array.

KW - Distributed generation

KW - Wind turbine

KW - Condition monitoring

KW - Fault detection

KW - Modelling and simulation

KW - SCADA data

U2 - 10.1016/j.renene.2014.05.035

DO - 10.1016/j.renene.2014.05.035

M3 - Journal article

VL - 71

SP - 166

EP - 175

JO - Renewable Energy

JF - Renewable Energy

SN - 0960-1481

ER -