Grey-box Model Identification and Fault Detection of Wind Turbines Using Artificial Neural Networks

Reihane Rahimilarki; Zhiwei Gao

doi:10.1109/INDIN.2018.8471943

Grey-box Model Identification and Fault Detection of Wind Turbines Using Artificial Neural Networks

Reihane Rahimilarki, Zhiwei Gao

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

12 Citations (Scopus)

Abstract

In this paper, a model identification method based on artificial neural networks (ANN) for wind turbine dynamics is studied. Due to the fact that wind turbine has a nonlinear dynamics with partially measured states, ANN cannot be applied directly. To cope with this problem, first a Luenberger observer is designed to estimate the states (both measured and unmeasured ones) and then, for the nonlinear part, a multi-input multi-output (MIMO) back propagation neural-network based observer is proposed. By having an ANN model as the reference, a fault detection method is studied based on the residual of the system. This algorithm is evaluated in simulation on a 4.8 MW wind turbine benchmark and the results approve satisfactory performance of the proposed approach.

Original language	English
Title of host publication	2018 IEEE 16th International Conference on Industrial Informatics (INDIN)
Publisher	IEEE
Pages	647-652
Number of pages	6
ISBN (Electronic)	9781538648292
ISBN (Print)	9781538648308
DOIs	https://doi.org/10.1109/INDIN.2018.8471943
Publication status	Published - 18 Jul 2018

Keywords

fault detection
neural network
wind turbine systems

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/INDIN.2018.8471943

Cite this

@inproceedings{fa066b45b3db463392c69036d809d5fc,

title = "Grey-box Model Identification and Fault Detection of Wind Turbines Using Artificial Neural Networks",

abstract = "In this paper, a model identification method based on artificial neural networks (ANN) for wind turbine dynamics is studied. Due to the fact that wind turbine has a nonlinear dynamics with partially measured states, ANN cannot be applied directly. To cope with this problem, first a Luenberger observer is designed to estimate the states (both measured and unmeasured ones) and then, for the nonlinear part, a multi-input multi-output (MIMO) back propagation neural-network based observer is proposed. By having an ANN model as the reference, a fault detection method is studied based on the residual of the system. This algorithm is evaluated in simulation on a 4.8 MW wind turbine benchmark and the results approve satisfactory performance of the proposed approach.",

keywords = "fault detection, neural network, wind turbine systems",

author = "Reihane Rahimilarki and Zhiwei Gao",

year = "2018",

month = jul,

day = "18",

doi = "10.1109/INDIN.2018.8471943",

language = "English",

isbn = "9781538648308",

pages = "647--652",

booktitle = "2018 IEEE 16th International Conference on Industrial Informatics (INDIN)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Grey-box Model Identification and Fault Detection of Wind Turbines Using Artificial Neural Networks

AU - Rahimilarki, Reihane

AU - Gao, Zhiwei

PY - 2018/7/18

Y1 - 2018/7/18

N2 - In this paper, a model identification method based on artificial neural networks (ANN) for wind turbine dynamics is studied. Due to the fact that wind turbine has a nonlinear dynamics with partially measured states, ANN cannot be applied directly. To cope with this problem, first a Luenberger observer is designed to estimate the states (both measured and unmeasured ones) and then, for the nonlinear part, a multi-input multi-output (MIMO) back propagation neural-network based observer is proposed. By having an ANN model as the reference, a fault detection method is studied based on the residual of the system. This algorithm is evaluated in simulation on a 4.8 MW wind turbine benchmark and the results approve satisfactory performance of the proposed approach.

AB - In this paper, a model identification method based on artificial neural networks (ANN) for wind turbine dynamics is studied. Due to the fact that wind turbine has a nonlinear dynamics with partially measured states, ANN cannot be applied directly. To cope with this problem, first a Luenberger observer is designed to estimate the states (both measured and unmeasured ones) and then, for the nonlinear part, a multi-input multi-output (MIMO) back propagation neural-network based observer is proposed. By having an ANN model as the reference, a fault detection method is studied based on the residual of the system. This algorithm is evaluated in simulation on a 4.8 MW wind turbine benchmark and the results approve satisfactory performance of the proposed approach.

KW - fault detection

KW - neural network

KW - wind turbine systems

UR - https://www.scopus.com/pages/publications/85055499857

U2 - 10.1109/INDIN.2018.8471943

DO - 10.1109/INDIN.2018.8471943

M3 - Conference contribution

SN - 9781538648308

SP - 647

EP - 652

BT - 2018 IEEE 16th International Conference on Industrial Informatics (INDIN)

PB - IEEE

ER -

Grey-box Model Identification and Fault Detection of Wind Turbines Using Artificial Neural Networks

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this