Cargando…

Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification

Demand for wind power has grown, and this has increased wind turbine blade (WTB) inspections and defect repairs. This paper empirically investigates the performance of state-of-the-art deep learning algorithms, namely, YOLOv3, YOLOv4, and Mask R-CNN for detecting and classifying defects by type. The...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Jiajun, Cosma, Georgina, Watkins, Jason
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321286/
https://www.ncbi.nlm.nih.gov/pubmed/34460702
http://dx.doi.org/10.3390/jimaging7030046
_version_ 1783730815109169152
author Zhang, Jiajun
Cosma, Georgina
Watkins, Jason
author_facet Zhang, Jiajun
Cosma, Georgina
Watkins, Jason
author_sort Zhang, Jiajun
collection PubMed
description Demand for wind power has grown, and this has increased wind turbine blade (WTB) inspections and defect repairs. This paper empirically investigates the performance of state-of-the-art deep learning algorithms, namely, YOLOv3, YOLOv4, and Mask R-CNN for detecting and classifying defects by type. The paper proposes new performance evaluation measures suitable for defect detection tasks, and these are: Prediction Box Accuracy, Recognition Rate, and False Label Rate. Experiments were carried out using a dataset, provided by the industrial partner, that contains images from WTB inspections. Three variations of the dataset were constructed using different image augmentation settings. Results of the experiments revealed that on average, across all proposed evaluation measures, Mask R-CNN outperformed all other algorithms when transformation-based augmentations (i.e., rotation and flipping) were applied. In particular, when using the best dataset, the mean Weighted Average (mWA) values (i.e., mWA is the average of the proposed measures) achieved were: Mask R-CNN: 86.74%, YOLOv3: 70.08%, and YOLOv4: 78.28%. The paper also proposes a new defect detection pipeline, called Image Enhanced Mask R-CNN (IE Mask R-CNN), that includes the best combination of image enhancement and augmentation techniques for pre-processing the dataset, and a Mask R-CNN model tuned for the task of WTB defect detection and classification.
format Online
Article
Text
id pubmed-8321286
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83212862021-08-26 Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification Zhang, Jiajun Cosma, Georgina Watkins, Jason J Imaging Article Demand for wind power has grown, and this has increased wind turbine blade (WTB) inspections and defect repairs. This paper empirically investigates the performance of state-of-the-art deep learning algorithms, namely, YOLOv3, YOLOv4, and Mask R-CNN for detecting and classifying defects by type. The paper proposes new performance evaluation measures suitable for defect detection tasks, and these are: Prediction Box Accuracy, Recognition Rate, and False Label Rate. Experiments were carried out using a dataset, provided by the industrial partner, that contains images from WTB inspections. Three variations of the dataset were constructed using different image augmentation settings. Results of the experiments revealed that on average, across all proposed evaluation measures, Mask R-CNN outperformed all other algorithms when transformation-based augmentations (i.e., rotation and flipping) were applied. In particular, when using the best dataset, the mean Weighted Average (mWA) values (i.e., mWA is the average of the proposed measures) achieved were: Mask R-CNN: 86.74%, YOLOv3: 70.08%, and YOLOv4: 78.28%. The paper also proposes a new defect detection pipeline, called Image Enhanced Mask R-CNN (IE Mask R-CNN), that includes the best combination of image enhancement and augmentation techniques for pre-processing the dataset, and a Mask R-CNN model tuned for the task of WTB defect detection and classification. MDPI 2021-03-04 /pmc/articles/PMC8321286/ /pubmed/34460702 http://dx.doi.org/10.3390/jimaging7030046 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) ).
spellingShingle Article
Zhang, Jiajun
Cosma, Georgina
Watkins, Jason
Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification
title Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification
title_full Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification
title_fullStr Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification
title_full_unstemmed Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification
title_short Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification
title_sort image enhanced mask r-cnn: a deep learning pipeline with new evaluation measures for wind turbine blade defect detection and classification
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8321286/
https://www.ncbi.nlm.nih.gov/pubmed/34460702
http://dx.doi.org/10.3390/jimaging7030046
work_keys_str_mv AT zhangjiajun imageenhancedmaskrcnnadeeplearningpipelinewithnewevaluationmeasuresforwindturbinebladedefectdetectionandclassification
AT cosmageorgina imageenhancedmaskrcnnadeeplearningpipelinewithnewevaluationmeasuresforwindturbinebladedefectdetectionandclassification
AT watkinsjason imageenhancedmaskrcnnadeeplearningpipelinewithnewevaluationmeasuresforwindturbinebladedefectdetectionandclassification