Predicting the malfunction timing of wind turbines is essential for maintaining the high profitability of the wind power generation business. Machine learning methods have been studied using condition monitoring system data, such as vibration data, and supervisory control and data acquisition (SCADA) data, to detect and predict anomalies in wind turbines automatically. Autoencoder-based techniques have attracted significant interest in the detection or prediction of anomalies through unsupervised learning, in which the anomaly pattern is unknown. Although autoencoder-based techniques have been proven to detect anomalies effectively using relatively stable SCADA data, they perform poorly in the case of deteriorated SCADA data. In this letter, we propose a power-curve filtering method, which is a preprocessing technique used before the application of an autoencoder-based technique, to mitigate the dirtiness of SCADA data and improve the prediction performance of wind turbine degradation. We have evaluated its performance using SCADA data obtained from a real wind-farm.
Masaki TAKANASHI
Toyota Central Research and Development Laboratories Incorporated
Shu-ichi SATO
Toyota Central Research and Development Laboratories Incorporated
Kentaro INDO
Eurus Technical Service Corporation
Nozomu NISHIHARA
Eurus Technical Service Corporation
Hiroto ICHIKAWA
Eurus Energy Holdings Corporation
Hirohisa WATANABE
Toyota Tsusho Corporation
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Masaki TAKANASHI, Shu-ichi SATO, Kentaro INDO, Nozomu NISHIHARA, Hiroto ICHIKAWA, Hirohisa WATANABE, "Anomaly Prediction for Wind Turbines Using an Autoencoder Based on Power-Curve Filtering" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 9, pp. 1506-1509, September 2021, doi: 10.1587/transinf.2020EDL8127.
Abstract: Predicting the malfunction timing of wind turbines is essential for maintaining the high profitability of the wind power generation business. Machine learning methods have been studied using condition monitoring system data, such as vibration data, and supervisory control and data acquisition (SCADA) data, to detect and predict anomalies in wind turbines automatically. Autoencoder-based techniques have attracted significant interest in the detection or prediction of anomalies through unsupervised learning, in which the anomaly pattern is unknown. Although autoencoder-based techniques have been proven to detect anomalies effectively using relatively stable SCADA data, they perform poorly in the case of deteriorated SCADA data. In this letter, we propose a power-curve filtering method, which is a preprocessing technique used before the application of an autoencoder-based technique, to mitigate the dirtiness of SCADA data and improve the prediction performance of wind turbine degradation. We have evaluated its performance using SCADA data obtained from a real wind-farm.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDL8127/_p
Copy
@ARTICLE{e104-d_9_1506,
author={Masaki TAKANASHI, Shu-ichi SATO, Kentaro INDO, Nozomu NISHIHARA, Hiroto ICHIKAWA, Hirohisa WATANABE, },
journal={IEICE TRANSACTIONS on Information},
title={Anomaly Prediction for Wind Turbines Using an Autoencoder Based on Power-Curve Filtering},
year={2021},
volume={E104-D},
number={9},
pages={1506-1509},
abstract={Predicting the malfunction timing of wind turbines is essential for maintaining the high profitability of the wind power generation business. Machine learning methods have been studied using condition monitoring system data, such as vibration data, and supervisory control and data acquisition (SCADA) data, to detect and predict anomalies in wind turbines automatically. Autoencoder-based techniques have attracted significant interest in the detection or prediction of anomalies through unsupervised learning, in which the anomaly pattern is unknown. Although autoencoder-based techniques have been proven to detect anomalies effectively using relatively stable SCADA data, they perform poorly in the case of deteriorated SCADA data. In this letter, we propose a power-curve filtering method, which is a preprocessing technique used before the application of an autoencoder-based technique, to mitigate the dirtiness of SCADA data and improve the prediction performance of wind turbine degradation. We have evaluated its performance using SCADA data obtained from a real wind-farm.},
keywords={},
doi={10.1587/transinf.2020EDL8127},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Anomaly Prediction for Wind Turbines Using an Autoencoder Based on Power-Curve Filtering
T2 - IEICE TRANSACTIONS on Information
SP - 1506
EP - 1509
AU - Masaki TAKANASHI
AU - Shu-ichi SATO
AU - Kentaro INDO
AU - Nozomu NISHIHARA
AU - Hiroto ICHIKAWA
AU - Hirohisa WATANABE
PY - 2021
DO - 10.1587/transinf.2020EDL8127
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2021
AB - Predicting the malfunction timing of wind turbines is essential for maintaining the high profitability of the wind power generation business. Machine learning methods have been studied using condition monitoring system data, such as vibration data, and supervisory control and data acquisition (SCADA) data, to detect and predict anomalies in wind turbines automatically. Autoencoder-based techniques have attracted significant interest in the detection or prediction of anomalies through unsupervised learning, in which the anomaly pattern is unknown. Although autoencoder-based techniques have been proven to detect anomalies effectively using relatively stable SCADA data, they perform poorly in the case of deteriorated SCADA data. In this letter, we propose a power-curve filtering method, which is a preprocessing technique used before the application of an autoencoder-based technique, to mitigate the dirtiness of SCADA data and improve the prediction performance of wind turbine degradation. We have evaluated its performance using SCADA data obtained from a real wind-farm.
ER -