Szczegóły publikacji
Opis bibliograficzny
Condition monitoring and fault diagnosis of wind turbines based on structural break detection in SCADA data / Phong B. DAO // Renewable Energy ; ISSN 0960-1481. — 2022 — vol. 185, s. 641–654. — Bibliogr. s. 654, Abstr. — Publikacja dostępna online od: 2021-12-20
Autor
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 138484 |
|---|---|
| Data dodania do BaDAP | 2022-01-08 |
| Tekst źródłowy | URL |
| DOI | 10.1016/j.renene.2021.12.051 |
| Rok publikacji | 2022 |
| Typ publikacji | artykuł w czasopiśmie |
| Otwarty dostęp |  |
| Czasopismo/seria | Renewable Energy |
Abstract
This paper presents a new approach – based on structural break detection in SCADA data – for condition monitoring and fault diagnosis of wind turbines. Chow test – a commonly used testing method for structural breaks in economic and financial data – has been adapted for this purpose. A five-step Chow's test-based computation procedure is proposed. The method is applied for condition monitoring of a wind turbine drivetrain with a nominal power of 2 MW using temperature-related SCADA data. A multiple linear regression model is formed using gearbox and generator temperature data as the independent variables and generator speed data as the dependent variable. The Chow test is used to assess the stability of regression coefficients in the model. Any coefficient instability means a structural change in the regression model, which can be interpreted as the occurrence of a fault in the wind turbine. The scheme used to detect structural changes is based on control charts, where sequences of the calculated probability (p-values) are plotted together with the critical line, defined by the significance level. The method is validated using two known fault events. The results demonstrate that the proposed method can effectively monitor the wind turbine and reliably detect abnormal problems.
