Wind Turbine Fault Detection through Principal Component Analysis and Statistical Hypothesis Testing
This paper addresses the problem of online fault detection of an advanced wind turbine benchmark under actuators (pitch and torque) and sensors (pitch angle measurement) faults of different type: fixed value, gain factor, offset and changed dynamics. The fault detection scheme starts by computing th...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2015-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1996-1073/9/1/3 |
| _version_ | 1811278785134198784 |
|---|---|
| author | Francesc Pozo Yolanda Vidal |
| author_facet | Francesc Pozo Yolanda Vidal |
| author_sort | Francesc Pozo |
| collection | DOAJ |
| description | This paper addresses the problem of online fault detection of an advanced wind turbine benchmark under actuators (pitch and torque) and sensors (pitch angle measurement) faults of different type: fixed value, gain factor, offset and changed dynamics. The fault detection scheme starts by computing the baseline principal component analysis (PCA) model from the healthy or undamaged wind turbine. Subsequently, when the structure is inspected or supervised, new measurements are obtained are projected into the baseline PCA model. When both sets of data—the baseline and the data from the current wind turbine—are compared, a statistical hypothesis testing is used to make a decision on whether or not the wind turbine presents some damage, fault or misbehavior. The effectiveness of the proposed fault-detection scheme is illustrated by numerical simulations on a well-known large offshore wind turbine in the presence of wind turbulence and realistic fault scenarios. The obtained results demonstrate that the proposed strategy provides and early fault identification, thereby giving the operators sufficient time to make more informed decisions regarding the maintenance of their machines. |
| first_indexed | 2024-04-13T00:42:01Z |
| format | Article |
| id | doaj.art-54d2aeb557384929b54a3d2307fc2cff |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-13T00:42:01Z |
| publishDate | 2015-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-54d2aeb557384929b54a3d2307fc2cff2022-12-22T03:10:07ZengMDPI AGEnergies1996-10732015-12-01913010.3390/en9010003en9010003Wind Turbine Fault Detection through Principal Component Analysis and Statistical Hypothesis TestingFrancesc Pozo0Yolanda Vidal1Control, Dynamics and Applications (CoDAlab), Departament de Matemàtiques, Escola Universitària d’Enginyeria Tècnica Industrial de Barcelona (EUETIB), Universitat Politècnica de Catalunya (UPC), Comte d’Urgell, 187, Barcelona 08036, SpainControl, Dynamics and Applications (CoDAlab), Departament de Matemàtiques, Escola Universitària d’Enginyeria Tècnica Industrial de Barcelona (EUETIB), Universitat Politècnica de Catalunya (UPC), Comte d’Urgell, 187, Barcelona 08036, SpainThis paper addresses the problem of online fault detection of an advanced wind turbine benchmark under actuators (pitch and torque) and sensors (pitch angle measurement) faults of different type: fixed value, gain factor, offset and changed dynamics. The fault detection scheme starts by computing the baseline principal component analysis (PCA) model from the healthy or undamaged wind turbine. Subsequently, when the structure is inspected or supervised, new measurements are obtained are projected into the baseline PCA model. When both sets of data—the baseline and the data from the current wind turbine—are compared, a statistical hypothesis testing is used to make a decision on whether or not the wind turbine presents some damage, fault or misbehavior. The effectiveness of the proposed fault-detection scheme is illustrated by numerical simulations on a well-known large offshore wind turbine in the presence of wind turbulence and realistic fault scenarios. The obtained results demonstrate that the proposed strategy provides and early fault identification, thereby giving the operators sufficient time to make more informed decisions regarding the maintenance of their machines.http://www.mdpi.com/1996-1073/9/1/3wind turbinefault detectionprincipal component analysisstatistical hypothesis testingFAST (Fatigue, Aerodynamics, Structures and Turbulence) |
| spellingShingle | Francesc Pozo Yolanda Vidal Wind Turbine Fault Detection through Principal Component Analysis and Statistical Hypothesis Testing Energies wind turbine fault detection principal component analysis statistical hypothesis testing FAST (Fatigue, Aerodynamics, Structures and Turbulence) |
| title | Wind Turbine Fault Detection through Principal Component Analysis and Statistical Hypothesis Testing |
| title_full | Wind Turbine Fault Detection through Principal Component Analysis and Statistical Hypothesis Testing |
| title_fullStr | Wind Turbine Fault Detection through Principal Component Analysis and Statistical Hypothesis Testing |
| title_full_unstemmed | Wind Turbine Fault Detection through Principal Component Analysis and Statistical Hypothesis Testing |
| title_short | Wind Turbine Fault Detection through Principal Component Analysis and Statistical Hypothesis Testing |
| title_sort | wind turbine fault detection through principal component analysis and statistical hypothesis testing |
| topic | wind turbine fault detection principal component analysis statistical hypothesis testing FAST (Fatigue, Aerodynamics, Structures and Turbulence) |
| url | http://www.mdpi.com/1996-1073/9/1/3 |
| work_keys_str_mv | AT francescpozo windturbinefaultdetectionthroughprincipalcomponentanalysisandstatisticalhypothesistesting AT yolandavidal windturbinefaultdetectionthroughprincipalcomponentanalysisandstatisticalhypothesistesting |