Failure warning of gearbox for wind turbine based on 3σ-median criterion and NSET
Wind turbine has been working in the harsh environment for a long time, which leads to frequent failures. It is of great practical significance to use reasonable and efficient methods to early-warning wind turbine components. In the actual operation, due to the influence of wind turbine equipment fa...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-11-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484721009549 |
| _version_ | 1818852535830577152 |
|---|---|
| author | Shaoke Wang Zhaoyan Zhang Peiguang Wang Yaru Tian |
| author_facet | Shaoke Wang Zhaoyan Zhang Peiguang Wang Yaru Tian |
| author_sort | Shaoke Wang |
| collection | DOAJ |
| description | Wind turbine has been working in the harsh environment for a long time, which leads to frequent failures. It is of great practical significance to use reasonable and efficient methods to early-warning wind turbine components. In the actual operation, due to the influence of wind turbine equipment failure and human factors, there are a large number of abnormal values in the data monitored by supervisory control and data acquisition system (SCADA). The existence of these abnormal data has a serious impact on the fault warning of wind turbine. Therefore, it is necessary to eliminate these abnormal data before using SCADA data modeling. In this paper, the 3σ-median combination method is used to preprocess the data, and then the nonlinear state estimate technology (NSET) method is used to predict the gearbox temperature of wind turbine. When the gearbox works abnormally, the residual error between the predicted value and the actual value increases, and an alarm message is sent out when the gearbox exceeds the preset threshold value. The experimental results show that the 3σ-median criterion proposed in this paper can effectively identify the outliers in the data. Then, the processed data are modeled by NSET, and the gearbox fault warning is realized by using NSET model. |
| first_indexed | 2024-12-19T07:22:28Z |
| format | Article |
| id | doaj.art-399f83f342db4f26abb598ce540b85d5 |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-12-19T07:22:28Z |
| publishDate | 2021-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-399f83f342db4f26abb598ce540b85d52022-12-21T20:30:54ZengElsevierEnergy Reports2352-48472021-11-01711821197Failure warning of gearbox for wind turbine based on 3σ-median criterion and NSETShaoke Wang0Zhaoyan Zhang1Peiguang Wang2Yaru Tian3College of Electronic Information Engineering, Hebei University, Baoding, Hebei 071002, China; Baoding Key Laboratory of Digital Intelligent Operation and Maintenance of Wind Power Generation, Hebei University, Baoding, Hebei 071002, ChinaCollege of Electronic Information Engineering, Hebei University, Baoding, Hebei 071002, China; Baoding Key Laboratory of Digital Intelligent Operation and Maintenance of Wind Power Generation, Hebei University, Baoding, Hebei 071002, China; Corresponding author at: College of Electronic Information Engineering, Hebei University, Baoding, Hebei 071002, China.College of Electronic Information Engineering, Hebei University, Baoding, Hebei 071002, China; Corresponding author.College of Electronic Information Engineering, Hebei University, Baoding, Hebei 071002, China; Baoding Key Laboratory of Digital Intelligent Operation and Maintenance of Wind Power Generation, Hebei University, Baoding, Hebei 071002, ChinaWind turbine has been working in the harsh environment for a long time, which leads to frequent failures. It is of great practical significance to use reasonable and efficient methods to early-warning wind turbine components. In the actual operation, due to the influence of wind turbine equipment failure and human factors, there are a large number of abnormal values in the data monitored by supervisory control and data acquisition system (SCADA). The existence of these abnormal data has a serious impact on the fault warning of wind turbine. Therefore, it is necessary to eliminate these abnormal data before using SCADA data modeling. In this paper, the 3σ-median combination method is used to preprocess the data, and then the nonlinear state estimate technology (NSET) method is used to predict the gearbox temperature of wind turbine. When the gearbox works abnormally, the residual error between the predicted value and the actual value increases, and an alarm message is sent out when the gearbox exceeds the preset threshold value. The experimental results show that the 3σ-median criterion proposed in this paper can effectively identify the outliers in the data. Then, the processed data are modeled by NSET, and the gearbox fault warning is realized by using NSET model.http://www.sciencedirect.com/science/article/pii/S2352484721009549Nonlinear state estimate technologyFault warningGearboxData cleaningSCADA |
| spellingShingle | Shaoke Wang Zhaoyan Zhang Peiguang Wang Yaru Tian Failure warning of gearbox for wind turbine based on 3σ-median criterion and NSET Energy Reports Nonlinear state estimate technology Fault warning Gearbox Data cleaning SCADA |
| title | Failure warning of gearbox for wind turbine based on 3σ-median criterion and NSET |
| title_full | Failure warning of gearbox for wind turbine based on 3σ-median criterion and NSET |
| title_fullStr | Failure warning of gearbox for wind turbine based on 3σ-median criterion and NSET |
| title_full_unstemmed | Failure warning of gearbox for wind turbine based on 3σ-median criterion and NSET |
| title_short | Failure warning of gearbox for wind turbine based on 3σ-median criterion and NSET |
| title_sort | failure warning of gearbox for wind turbine based on 3σ median criterion and nset |
| topic | Nonlinear state estimate technology Fault warning Gearbox Data cleaning SCADA |
| url | http://www.sciencedirect.com/science/article/pii/S2352484721009549 |
| work_keys_str_mv | AT shaokewang failurewarningofgearboxforwindturbinebasedon3smediancriterionandnset AT zhaoyanzhang failurewarningofgearboxforwindturbinebasedon3smediancriterionandnset AT peiguangwang failurewarningofgearboxforwindturbinebasedon3smediancriterionandnset AT yarutian failurewarningofgearboxforwindturbinebasedon3smediancriterionandnset |