Anomaly Detection on Small Wind Turbine Blades Using Deep Learning Algorithms
Wind turbine blade maintenance is expensive, dangerous, time-consuming, and prone to misdiagnosis. A potential solution to aid preventative maintenance is using deep learning and drones for inspection and early fault detection. In this research, five base deep learning architectures are investigated...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/17/5/982 |
| _version_ | 1797264682954784768 |
|---|---|
| author | Bridger Altice Edwin Nazario Mason Davis Mohammad Shekaramiz Todd K. Moon Mohammad A. S. Masoum |
| author_facet | Bridger Altice Edwin Nazario Mason Davis Mohammad Shekaramiz Todd K. Moon Mohammad A. S. Masoum |
| author_sort | Bridger Altice |
| collection | DOAJ |
| description | Wind turbine blade maintenance is expensive, dangerous, time-consuming, and prone to misdiagnosis. A potential solution to aid preventative maintenance is using deep learning and drones for inspection and early fault detection. In this research, five base deep learning architectures are investigated for anomaly detection on wind turbine blades, including Xception, Resnet-50, AlexNet, and VGG-19, along with a custom convolutional neural network. For further analysis, transfer learning approaches were also proposed and developed, utilizing these architectures as the feature extraction layers. In order to investigate model performance, a new dataset containing 6000 RGB images was created, making use of indoor and outdoor images of a small wind turbine with healthy and damaged blades. Each model was tuned using different layers, image augmentations, and hyperparameter tuning to achieve optimal performance. The results showed that the proposed Transfer Xception outperformed other architectures by attaining 99.92% accuracy on the test data of this dataset. Furthermore, the performance of the investigated models was compared on a dataset containing faulty and healthy images of large-scale wind turbine blades. In this case, our results indicated that the best-performing model was also the proposed Transfer Xception, which achieved 100% accuracy on the test data. These accuracies show promising results in the adoption of machine learning for wind turbine blade fault identification. |
| first_indexed | 2024-04-25T00:32:47Z |
| format | Article |
| id | doaj.art-f0300a50bc2c400fa1cb158143752c42 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-25T00:32:47Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-f0300a50bc2c400fa1cb158143752c422024-03-12T16:42:55ZengMDPI AGEnergies1996-10732024-02-0117598210.3390/en17050982Anomaly Detection on Small Wind Turbine Blades Using Deep Learning AlgorithmsBridger Altice0Edwin Nazario1Mason Davis2Mohammad Shekaramiz3Todd K. Moon4Mohammad A. S. Masoum5Information Dynamics Lab., Electrical and Computer Engineering Department, Utah State University, Logan, UT 84322, USAMachine Learning and Drone Lab., Engineering Department, Utah Valley University, Orem, UT 84097, USAMachine Learning and Drone Lab., Engineering Department, Utah Valley University, Orem, UT 84097, USAMachine Learning and Drone Lab., Engineering Department, Utah Valley University, Orem, UT 84097, USAInformation Dynamics Lab., Electrical and Computer Engineering Department, Utah State University, Logan, UT 84322, USAMachine Learning and Drone Lab., Engineering Department, Utah Valley University, Orem, UT 84097, USAWind turbine blade maintenance is expensive, dangerous, time-consuming, and prone to misdiagnosis. A potential solution to aid preventative maintenance is using deep learning and drones for inspection and early fault detection. In this research, five base deep learning architectures are investigated for anomaly detection on wind turbine blades, including Xception, Resnet-50, AlexNet, and VGG-19, along with a custom convolutional neural network. For further analysis, transfer learning approaches were also proposed and developed, utilizing these architectures as the feature extraction layers. In order to investigate model performance, a new dataset containing 6000 RGB images was created, making use of indoor and outdoor images of a small wind turbine with healthy and damaged blades. Each model was tuned using different layers, image augmentations, and hyperparameter tuning to achieve optimal performance. The results showed that the proposed Transfer Xception outperformed other architectures by attaining 99.92% accuracy on the test data of this dataset. Furthermore, the performance of the investigated models was compared on a dataset containing faulty and healthy images of large-scale wind turbine blades. In this case, our results indicated that the best-performing model was also the proposed Transfer Xception, which achieved 100% accuracy on the test data. These accuracies show promising results in the adoption of machine learning for wind turbine blade fault identification.https://www.mdpi.com/1996-1073/17/5/982deep learningconvolutional neural networkssmall wind turbine bladesdamage detectiontransfer learningVGG-19 |
| spellingShingle | Bridger Altice Edwin Nazario Mason Davis Mohammad Shekaramiz Todd K. Moon Mohammad A. S. Masoum Anomaly Detection on Small Wind Turbine Blades Using Deep Learning Algorithms Energies deep learning convolutional neural networks small wind turbine blades damage detection transfer learning VGG-19 |
| title | Anomaly Detection on Small Wind Turbine Blades Using Deep Learning Algorithms |
| title_full | Anomaly Detection on Small Wind Turbine Blades Using Deep Learning Algorithms |
| title_fullStr | Anomaly Detection on Small Wind Turbine Blades Using Deep Learning Algorithms |
| title_full_unstemmed | Anomaly Detection on Small Wind Turbine Blades Using Deep Learning Algorithms |
| title_short | Anomaly Detection on Small Wind Turbine Blades Using Deep Learning Algorithms |
| title_sort | anomaly detection on small wind turbine blades using deep learning algorithms |
| topic | deep learning convolutional neural networks small wind turbine blades damage detection transfer learning VGG-19 |
| url | https://www.mdpi.com/1996-1073/17/5/982 |
| work_keys_str_mv | AT bridgeraltice anomalydetectiononsmallwindturbinebladesusingdeeplearningalgorithms AT edwinnazario anomalydetectiononsmallwindturbinebladesusingdeeplearningalgorithms AT masondavis anomalydetectiononsmallwindturbinebladesusingdeeplearningalgorithms AT mohammadshekaramiz anomalydetectiononsmallwindturbinebladesusingdeeplearningalgorithms AT toddkmoon anomalydetectiononsmallwindturbinebladesusingdeeplearningalgorithms AT mohammadasmasoum anomalydetectiononsmallwindturbinebladesusingdeeplearningalgorithms |