A Novel Wind Turbine Fault Detection Method Based on Fuzzy Logic System Using Neural Network Construction Method
| Autor: | Hegui Zhu, Hongfei Zhu, Danyu Lu, Jinhai Liu, Zhiqiang Wang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Fuzzy logic system Artificial neural network Computer science 020208 electrical & electronic engineering Control engineering 02 engineering and technology Turbine Fault detection and isolation 020901 industrial engineering & automation Construction method Control and Systems Engineering 0202 electrical engineering electronic engineering information engineering Membership function |
| Zdroj: | IFAC-PapersOnLine. 53:664-668 |
| ISSN: | 2405-8963 |
| DOI: | 10.1016/j.ifacol.2021.04.157 |
| Popis: | Fuzzy logic system is commonly used in wind turbine fault detection. However, traditional fuzzy logic systems are built through human experience. The fuzzy logic system constructed in this way will have inaccurate problems. In order to solve this problem, this paper proposes a novel fuzzy logic system (FLS) based on neural network construction method to improve accuracy rate of wind turbine fault detection. First, a neural network construction method is proposed. Using this method, membership function can be constructed more accurately. Then, a FLS based on the extended data-driven membership function is proposed. When environment changes, such FLS can improve accuracy rate of wind turbine fault detection with the extended data-driven membership function. Finally, experiments using data from actual wind fields are performed, and the experimental results show that the method proposed in this paper is effective. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|