Fault Diagnosis of Wind Turbine Based on PCA and GSA-SVM

Hongmei Yan; Huina Mu; Xiaojian Yi; Yuanyuan Yang; Guangliang Chen

doi:10.1109/PHM-Paris.2019.00010

Fault Diagnosis of Wind Turbine Based on PCA and GSA-SVM

Hongmei Yan, Huina Mu, Xiaojian Yi^*, Yuanyuan Yang, Guangliang Chen

^*Corresponding author for this work

School of Mechatronical Engineering

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

13 Citations (Scopus)

Abstract

A fault diagnosis method based on principal component analysis (PCA) and support vector machine (SVM) model is proposed to solve the problem of high dimension and large sample size of wind turbine fault data. Firstly, The PCA is used to extract low-dimensional fault features from high-dimensional fault data to eliminate the correlation between features. Then, the grid search algorithm (GSA) is used to optimize the loss parameters and kernel function parameters of the SVM model. Secondly, low-dimensional fault features are used as input training classifiers for SVM. Finally, fault diagnosis is carried out through feature classification. Simulation results have shown that the diagnostic accuracy could reach 100% when Polynomial kernel function and two-dimensional principal component analysis were used, indicating that this method can quickly and effectively diagnose various faults.

Original language	English
Title of host publication	Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019
Editors	Chuan Li, Jose Valente de Oliveira, Ping Ding, Ping Ding, Diego Cabrera
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	13-17
Number of pages	5
ISBN (Electronic)	9781728103297
DOIs	https://doi.org/10.1109/PHM-Paris.2019.00010
Publication status	Published - May 2019
Event	2019 Prognostics and System Health Management Conference, PHM-Paris 2019 - Paris, France Duration: 2 May 2019 → 5 May 2019

Publication series

Name	Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019

Conference

Conference	2019 Prognostics and System Health Management Conference, PHM-Paris 2019
Country/Territory	France
City	Paris
Period	2/05/19 → 5/05/19

Keywords

Fault diagnosis
Grid parameter optimization method
Principal component analysis
Support vector machine
Wind turbine

Access to Document

10.1109/PHM-Paris.2019.00010

Cite this

Yan, H., Mu, H., Yi, X., Yang, Y., & Chen, G. (2019). Fault Diagnosis of Wind Turbine Based on PCA and GSA-SVM. In C. Li, J. V. de Oliveira, P. Ding, P. Ding, & D. Cabrera (Eds.), Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019 (pp. 13-17). Article 8756402 (Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PHM-Paris.2019.00010

Yan, Hongmei ; Mu, Huina ; Yi, Xiaojian et al. / Fault Diagnosis of Wind Turbine Based on PCA and GSA-SVM. Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019. editor / Chuan Li ; Jose Valente de Oliveira ; Ping Ding ; Ping Ding ; Diego Cabrera. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 13-17 (Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019).

@inproceedings{1cd28059471d45628f77d1b2746ff300,

title = "Fault Diagnosis of Wind Turbine Based on PCA and GSA-SVM",

abstract = "A fault diagnosis method based on principal component analysis (PCA) and support vector machine (SVM) model is proposed to solve the problem of high dimension and large sample size of wind turbine fault data. Firstly, The PCA is used to extract low-dimensional fault features from high-dimensional fault data to eliminate the correlation between features. Then, the grid search algorithm (GSA) is used to optimize the loss parameters and kernel function parameters of the SVM model. Secondly, low-dimensional fault features are used as input training classifiers for SVM. Finally, fault diagnosis is carried out through feature classification. Simulation results have shown that the diagnostic accuracy could reach 100% when Polynomial kernel function and two-dimensional principal component analysis were used, indicating that this method can quickly and effectively diagnose various faults.",

keywords = "Fault diagnosis, Grid parameter optimization method, Principal component analysis, Support vector machine, Wind turbine",

author = "Hongmei Yan and Huina Mu and Xiaojian Yi and Yuanyuan Yang and Guangliang Chen",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 Prognostics and System Health Management Conference, PHM-Paris 2019 ; Conference date: 02-05-2019 Through 05-05-2019",

year = "2019",

month = may,

doi = "10.1109/PHM-Paris.2019.00010",

language = "English",

series = "Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "13--17",

editor = "Chuan Li and {de Oliveira}, {Jose Valente} and Ping Ding and Ping Ding and Diego Cabrera",

booktitle = "Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019",

address = "United States",

}

Yan, H, Mu, H , Yi, X, Yang, Y & Chen, G 2019, Fault Diagnosis of Wind Turbine Based on PCA and GSA-SVM. in C Li, JV de Oliveira, P Ding, P Ding & D Cabrera (eds), Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019., 8756402, Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019, Institute of Electrical and Electronics Engineers Inc., pp. 13-17, 2019 Prognostics and System Health Management Conference, PHM-Paris 2019, Paris, France, 2/05/19. https://doi.org/10.1109/PHM-Paris.2019.00010

Fault Diagnosis of Wind Turbine Based on PCA and GSA-SVM. / Yan, Hongmei; Mu, Huina ; Yi, Xiaojian et al.
Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019. ed. / Chuan Li; Jose Valente de Oliveira; Ping Ding; Ping Ding; Diego Cabrera. Institute of Electrical and Electronics Engineers Inc., 2019. p. 13-17 8756402 (Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019).

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

TY - GEN

T1 - Fault Diagnosis of Wind Turbine Based on PCA and GSA-SVM

AU - Yan, Hongmei

AU - Mu, Huina

AU - Yi, Xiaojian

AU - Yang, Yuanyuan

AU - Chen, Guangliang

PY - 2019/5

Y1 - 2019/5

N2 - A fault diagnosis method based on principal component analysis (PCA) and support vector machine (SVM) model is proposed to solve the problem of high dimension and large sample size of wind turbine fault data. Firstly, The PCA is used to extract low-dimensional fault features from high-dimensional fault data to eliminate the correlation between features. Then, the grid search algorithm (GSA) is used to optimize the loss parameters and kernel function parameters of the SVM model. Secondly, low-dimensional fault features are used as input training classifiers for SVM. Finally, fault diagnosis is carried out through feature classification. Simulation results have shown that the diagnostic accuracy could reach 100% when Polynomial kernel function and two-dimensional principal component analysis were used, indicating that this method can quickly and effectively diagnose various faults.

AB - A fault diagnosis method based on principal component analysis (PCA) and support vector machine (SVM) model is proposed to solve the problem of high dimension and large sample size of wind turbine fault data. Firstly, The PCA is used to extract low-dimensional fault features from high-dimensional fault data to eliminate the correlation between features. Then, the grid search algorithm (GSA) is used to optimize the loss parameters and kernel function parameters of the SVM model. Secondly, low-dimensional fault features are used as input training classifiers for SVM. Finally, fault diagnosis is carried out through feature classification. Simulation results have shown that the diagnostic accuracy could reach 100% when Polynomial kernel function and two-dimensional principal component analysis were used, indicating that this method can quickly and effectively diagnose various faults.

KW - Fault diagnosis

KW - Grid parameter optimization method

KW - Principal component analysis

KW - Support vector machine

KW - Wind turbine

UR - http://www.scopus.com/inward/record.url?scp=85070531810&partnerID=8YFLogxK

U2 - 10.1109/PHM-Paris.2019.00010

DO - 10.1109/PHM-Paris.2019.00010

M3 - Conference contribution

AN - SCOPUS:85070531810

T3 - Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019

SP - 13

EP - 17

BT - Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019

A2 - Li, Chuan

A2 - de Oliveira, Jose Valente

A2 - Ding, Ping

A2 - Cabrera, Diego

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019

Y2 - 2 May 2019 through 5 May 2019

ER -

Yan H, Mu H , Yi X, Yang Y, Chen G. Fault Diagnosis of Wind Turbine Based on PCA and GSA-SVM. In Li C, de Oliveira JV, Ding P, Ding P, Cabrera D, editors, Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 13-17. 8756402. (Proceedings - 2019 Prognostics and System Health Management Conference, PHM-Paris 2019). doi: 10.1109/PHM-Paris.2019.00010

Fault Diagnosis of Wind Turbine Based on PCA and GSA-SVM

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this