Adaptive Neuro-Fuzzy System for Detection of Wind Turbine Blade Defects
Wind turbines are the most frequently used objects of renewable energy today. However, issues that arise during their operation can greatly affect their effectiveness. Blade erosion, cracks, and other defects can slash turbine performance while also forcing maintenance costs to soar. Modern defect d...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/17/24/6456 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846104862935220224 |
|---|---|
| author | Lesia Dubchak Anatoliy Sachenko Yevgeniy Bodyanskiy Carsten Wolff Nadiia Vasylkiv Ruslan Brukhanskyi Volodymyr Kochan |
| author_facet | Lesia Dubchak Anatoliy Sachenko Yevgeniy Bodyanskiy Carsten Wolff Nadiia Vasylkiv Ruslan Brukhanskyi Volodymyr Kochan |
| author_sort | Lesia Dubchak |
| collection | DOAJ |
| description | Wind turbines are the most frequently used objects of renewable energy today. However, issues that arise during their operation can greatly affect their effectiveness. Blade erosion, cracks, and other defects can slash turbine performance while also forcing maintenance costs to soar. Modern defect detection applications have significant computing resources needed for training and insufficient accuracy. The goal of this study is to develop the improved adaptive neuro-fuzzy inference system (ANFIS) for wind turbine defect detection, which will reduce computing resources and increase its accuracy. Unmanned aerial vehicles are deployed to photograph the turbines, and these images are beamed back and processed for early defect detection. The proposed adaptive neuro-fuzzy inference system processes the data vectors with lower complexity and higher accuracy. For this purpose, the authors explored grid partitioning and subtractive clustering methods and selected the last one because it uses three rules only for fault detection, ensuring low computational costs and enabling the discovery of wind turbine defects quickly and efficiently. Moreover, the proposed ANFIS is implemented in a controller, which has an accuracy of 91%, that is 1.4 higher than the accuracy of the existing similar controller. |
| format | Article |
| id | doaj-art-8d9aa69bde25494c88aa5d0f9d2a7ace |
| institution | Kabale University |
| issn | 1996-1073 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-8d9aa69bde25494c88aa5d0f9d2a7ace2024-12-27T14:23:54ZengMDPI AGEnergies1996-10732024-12-011724645610.3390/en17246456Adaptive Neuro-Fuzzy System for Detection of Wind Turbine Blade DefectsLesia Dubchak0Anatoliy Sachenko1Yevgeniy Bodyanskiy2Carsten Wolff3Nadiia Vasylkiv4Ruslan Brukhanskyi5Volodymyr Kochan6Faculty of Computer Information Technologies, West Ukrainian National University, 46001 Ternopil, UkraineFaculty of Computer Information Technologies, West Ukrainian National University, 46001 Ternopil, UkraineFaculty of Computer Science, Kharkiv National University of Radio Electronics, 61166 Kharkiv, UkraineFaculty of Computer Science, Dortmund University of Applied Science and Arts, 44139 Dortmund, GermanyFaculty of Computer Information Technologies, West Ukrainian National University, 46001 Ternopil, UkraineEducation and Research Institute of Innovation, Nature Management and Infrastructure, West Ukrainian National University, 46001 Ternopil, UkraineFaculty of Computer Information Technologies, West Ukrainian National University, 46001 Ternopil, UkraineWind turbines are the most frequently used objects of renewable energy today. However, issues that arise during their operation can greatly affect their effectiveness. Blade erosion, cracks, and other defects can slash turbine performance while also forcing maintenance costs to soar. Modern defect detection applications have significant computing resources needed for training and insufficient accuracy. The goal of this study is to develop the improved adaptive neuro-fuzzy inference system (ANFIS) for wind turbine defect detection, which will reduce computing resources and increase its accuracy. Unmanned aerial vehicles are deployed to photograph the turbines, and these images are beamed back and processed for early defect detection. The proposed adaptive neuro-fuzzy inference system processes the data vectors with lower complexity and higher accuracy. For this purpose, the authors explored grid partitioning and subtractive clustering methods and selected the last one because it uses three rules only for fault detection, ensuring low computational costs and enabling the discovery of wind turbine defects quickly and efficiently. Moreover, the proposed ANFIS is implemented in a controller, which has an accuracy of 91%, that is 1.4 higher than the accuracy of the existing similar controller.https://www.mdpi.com/1996-1073/17/24/6456wind turbineadaptive neuro-fuzzy inference systemdefect detectionsubtractive clusteringgrid partitioning |
| spellingShingle | Lesia Dubchak Anatoliy Sachenko Yevgeniy Bodyanskiy Carsten Wolff Nadiia Vasylkiv Ruslan Brukhanskyi Volodymyr Kochan Adaptive Neuro-Fuzzy System for Detection of Wind Turbine Blade Defects Energies wind turbine adaptive neuro-fuzzy inference system defect detection subtractive clustering grid partitioning |
| title | Adaptive Neuro-Fuzzy System for Detection of Wind Turbine Blade Defects |
| title_full | Adaptive Neuro-Fuzzy System for Detection of Wind Turbine Blade Defects |
| title_fullStr | Adaptive Neuro-Fuzzy System for Detection of Wind Turbine Blade Defects |
| title_full_unstemmed | Adaptive Neuro-Fuzzy System for Detection of Wind Turbine Blade Defects |
| title_short | Adaptive Neuro-Fuzzy System for Detection of Wind Turbine Blade Defects |
| title_sort | adaptive neuro fuzzy system for detection of wind turbine blade defects |
| topic | wind turbine adaptive neuro-fuzzy inference system defect detection subtractive clustering grid partitioning |
| url | https://www.mdpi.com/1996-1073/17/24/6456 |
| work_keys_str_mv | AT lesiadubchak adaptiveneurofuzzysystemfordetectionofwindturbinebladedefects AT anatoliysachenko adaptiveneurofuzzysystemfordetectionofwindturbinebladedefects AT yevgeniybodyanskiy adaptiveneurofuzzysystemfordetectionofwindturbinebladedefects AT carstenwolff adaptiveneurofuzzysystemfordetectionofwindturbinebladedefects AT nadiiavasylkiv adaptiveneurofuzzysystemfordetectionofwindturbinebladedefects AT ruslanbrukhanskyi adaptiveneurofuzzysystemfordetectionofwindturbinebladedefects AT volodymyrkochan adaptiveneurofuzzysystemfordetectionofwindturbinebladedefects |