Constructing Condition Monitoring Model of Wind Turbine Blades
Wind power has become an indispensable part of renewable energy development in various countries. Due to the high cost and complex structure of wind turbines, it is important to design a method that can quickly and effectively determine the structural health of the generator set. This research propo...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/6/972 |
| _version_ | 1827628037140643840 |
|---|---|
| author | Jong-Yih Kuo Shang-Yi You Hui-Chi Lin Chao-Yang Hsu Baiying Lei |
| author_facet | Jong-Yih Kuo Shang-Yi You Hui-Chi Lin Chao-Yang Hsu Baiying Lei |
| author_sort | Jong-Yih Kuo |
| collection | DOAJ |
| description | Wind power has become an indispensable part of renewable energy development in various countries. Due to the high cost and complex structure of wind turbines, it is important to design a method that can quickly and effectively determine the structural health of the generator set. This research proposes a method that could determine structural damage or weaknesses in the blades at an early stage via a model to monitor the sound of the wind turbine blades, so as to reduce the quantity of labor required and frequency of regular maintenance, and to repair the damage rapidly in the future. This study used the operating sounds of normal and abnormal blades as a dataset. The model used discrete wavelet transform (DWT) to decompose the sound into different frequency components, performed feature extraction in a statistical measure, and combined with outlier exposure technique to train a deep neural network model that could capture abnormal values deviating from the normal samples. In addition, this paper observed that the performance of the monitoring model on the MIMII dataset was also better than the anomaly detection models proposed by other papers. |
| first_indexed | 2024-03-09T13:25:10Z |
| format | Article |
| id | doaj.art-40ba21dd628c47309861c94c719cb9ba |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T13:25:10Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-40ba21dd628c47309861c94c719cb9ba2023-11-30T21:24:51ZengMDPI AGMathematics2227-73902022-03-0110697210.3390/math10060972Constructing Condition Monitoring Model of Wind Turbine BladesJong-Yih Kuo0Shang-Yi You1Hui-Chi Lin2Chao-Yang Hsu3Baiying Lei4Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei 106344, TaiwanDepartment of Computer Science and Information Engineering, National Taipei University of Technology, Taipei 106344, TaiwanDepartment of Computer Science and Information Engineering, National Taipei University of Technology, Taipei 106344, TaiwanDepartment of Computer Science and Information Engineering, National Taipei University of Technology, Taipei 106344, TaiwanHealth Science Center, School of Biomedical Engineering, Shenzhen University, Shenzhen 518037, ChinaWind power has become an indispensable part of renewable energy development in various countries. Due to the high cost and complex structure of wind turbines, it is important to design a method that can quickly and effectively determine the structural health of the generator set. This research proposes a method that could determine structural damage or weaknesses in the blades at an early stage via a model to monitor the sound of the wind turbine blades, so as to reduce the quantity of labor required and frequency of regular maintenance, and to repair the damage rapidly in the future. This study used the operating sounds of normal and abnormal blades as a dataset. The model used discrete wavelet transform (DWT) to decompose the sound into different frequency components, performed feature extraction in a statistical measure, and combined with outlier exposure technique to train a deep neural network model that could capture abnormal values deviating from the normal samples. In addition, this paper observed that the performance of the monitoring model on the MIMII dataset was also better than the anomaly detection models proposed by other papers.https://www.mdpi.com/2227-7390/10/6/972anomaly detectionmachine learningwavelet transform |
| spellingShingle | Jong-Yih Kuo Shang-Yi You Hui-Chi Lin Chao-Yang Hsu Baiying Lei Constructing Condition Monitoring Model of Wind Turbine Blades Mathematics anomaly detection machine learning wavelet transform |
| title | Constructing Condition Monitoring Model of Wind Turbine Blades |
| title_full | Constructing Condition Monitoring Model of Wind Turbine Blades |
| title_fullStr | Constructing Condition Monitoring Model of Wind Turbine Blades |
| title_full_unstemmed | Constructing Condition Monitoring Model of Wind Turbine Blades |
| title_short | Constructing Condition Monitoring Model of Wind Turbine Blades |
| title_sort | constructing condition monitoring model of wind turbine blades |
| topic | anomaly detection machine learning wavelet transform |
| url | https://www.mdpi.com/2227-7390/10/6/972 |
| work_keys_str_mv | AT jongyihkuo constructingconditionmonitoringmodelofwindturbineblades AT shangyiyou constructingconditionmonitoringmodelofwindturbineblades AT huichilin constructingconditionmonitoringmodelofwindturbineblades AT chaoyanghsu constructingconditionmonitoringmodelofwindturbineblades AT baiyinglei constructingconditionmonitoringmodelofwindturbineblades |