Wind turbine condition monitoring based on SCADA data using normal behavior models: Part 1: System description

Publication: Research - peer-reviewJournal article – Annual report year: 2013

Standard

Wind turbine condition monitoring based on SCADA data using normal behavior models : Part 1: System description. / Schlechtingen, Meik; Santos, Ilmar; Achiche, Sofiane.

In: Applied Soft Computing, Vol. 13, 2013, p. 259-270.

Publication: Research - peer-reviewJournal article – Annual report year: 2013

Harvard

APA

CBE

MLA

Vancouver

Author

Schlechtingen, Meik; Santos, Ilmar; Achiche, Sofiane / Wind turbine condition monitoring based on SCADA data using normal behavior models : Part 1: System description.

In: Applied Soft Computing, Vol. 13, 2013, p. 259-270.

Publication: Research - peer-reviewJournal article – Annual report year: 2013

Bibtex

@article{d7e9c9c2cb11475f8c1ff8c11603c97c,
title = "Wind turbine condition monitoring based on SCADA data using normal behavior models: Part 1: System description",
keywords = "ANFI models, Condition monitoring, Wind turbine, SCADA data, Normal behavior models",
publisher = "Elsevier BV",
author = "Meik Schlechtingen and Ilmar Santos and Sofiane Achiche",
year = "2013",
doi = "10.1016/j.asoc.2012.08.033",
volume = "13",
pages = "259--270",
journal = "Applied Soft Computing",
issn = "1568-4946",

}

RIS

TY - JOUR

T1 - Wind turbine condition monitoring based on SCADA data using normal behavior models

T2 - Part 1: System description

A1 - Schlechtingen,Meik

A1 - Santos,Ilmar

A1 - Achiche,Sofiane

AU - Schlechtingen,Meik

AU - Santos,Ilmar

AU - Achiche,Sofiane

PB - Elsevier BV

PY - 2013

Y1 - 2013

N2 - This paper proposes a system for wind turbine condition monitoring using Adaptive Neuro-Fuzzy Interference <br/>Systems (ANFIS). For this purpose: (1) ANFIS normal behavior models for common Supervisory Control And Data Acquisition (SCADA) data are developed in order to detect abnormal behavior of the captured signals and indicate component malfunctions or faults using the prediction error. 33 different standard SCADA signals are used and described, for which 45 normal behavior models are developed. The performance of these models is evaluated in terms of the prediction error standard deviations to show the applicability of ANFIS models for monitoring wind turbine SCADA signals. The computational time needed for model training is compared to Neural Network (NN) models showing the strength of ANFIS in training speed. (2) For automation of fault diagnosis Fuzzy Interference Systems (FIS) are used <br/>to analyze the prediction errors for fault patterns. The outputs are both the condition of the component and a possible root cause for the anomaly. The output is generated by the aid of rules that capture the existing expert knowledge linking observed prediction error patterns to specific faults. The work is based on continuously measured wind turbine SCADA data from 18 turbines of the 2 MW class covering a period of 30 months. <br/>The system proposed in this paper shows a novelty approach with regard to the usage of ANFIS models in this context and the application of the proposed procedure to a wide range of SCADA signals. The applicability of the set up ANFIS models for anomaly detection is proved by the achieved performance of the models. In combination with the FIS the prediction errors can provide information about the condition of the monitored components. <br/>In this paper the condition monitoring system is described. Part two will entirely focus on application examples and further efficiency evaluation of the system.

AB - This paper proposes a system for wind turbine condition monitoring using Adaptive Neuro-Fuzzy Interference <br/>Systems (ANFIS). For this purpose: (1) ANFIS normal behavior models for common Supervisory Control And Data Acquisition (SCADA) data are developed in order to detect abnormal behavior of the captured signals and indicate component malfunctions or faults using the prediction error. 33 different standard SCADA signals are used and described, for which 45 normal behavior models are developed. The performance of these models is evaluated in terms of the prediction error standard deviations to show the applicability of ANFIS models for monitoring wind turbine SCADA signals. The computational time needed for model training is compared to Neural Network (NN) models showing the strength of ANFIS in training speed. (2) For automation of fault diagnosis Fuzzy Interference Systems (FIS) are used <br/>to analyze the prediction errors for fault patterns. The outputs are both the condition of the component and a possible root cause for the anomaly. The output is generated by the aid of rules that capture the existing expert knowledge linking observed prediction error patterns to specific faults. The work is based on continuously measured wind turbine SCADA data from 18 turbines of the 2 MW class covering a period of 30 months. <br/>The system proposed in this paper shows a novelty approach with regard to the usage of ANFIS models in this context and the application of the proposed procedure to a wide range of SCADA signals. The applicability of the set up ANFIS models for anomaly detection is proved by the achieved performance of the models. In combination with the FIS the prediction errors can provide information about the condition of the monitored components. <br/>In this paper the condition monitoring system is described. Part two will entirely focus on application examples and further efficiency evaluation of the system.

KW - ANFI models

KW - Condition monitoring

KW - Wind turbine

KW - SCADA data

KW - Normal behavior models

U2 - 10.1016/j.asoc.2012.08.033

DO - 10.1016/j.asoc.2012.08.033

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

VL - 13

SP - 259

EP - 270

ER -