The increasing demand for wind power requires more frequent inspections to identify defects in the Wind Turbine Blades (WTBs). These defects, if not detected, can compromise the structural integrity and safety of wind turbines. As WTBs are crucial and costly components, they may suffer material degradation and fatigue failure, which affects their performance and safety. Thus, the urgency for efficient and regular monitoring to maintain their structural integrity is greater than ever. This review paper explores innovative methods in fatigue testing, damage detection, and structural reliability in WTBs, focusing on the use of recent inspection methods, including those that take advantage of drones. Drones are used to identify defects such as cracks, erosion, and coating irregularities using high-resolution imagery with the onboard cameras. Various investigators have developed novel data-driven approaches, incorporating machine learning and deep learning, to accurately identify these defects. Although deep learning-based image processing has been successful in other public infrastructure contexts, its application to wind turbine inspection from aerial images presents unique challenges. This paper also highlights the critical role of failure inspection in enhancing the operational integrity of WTBs, showcasing state-of-the-art deep learning techniques that are pivotal for identifying and analyzing failures in WTBs from images captured by drones. The paper provides insights into the latest developments in using drone imagery for blade defect detection, contrasting this method with traditional non-destructive techniques. This approach could significantly transform the wind energy industry by offering a more efficient, automated, and precise way of ensuring the structural health of wind turbines. Unlike previous studies that predominantly focus on isolated aspects such as inspection or fatigue, this review paper not only integrates the three major aspects of WTBs integrity in terms of aerial inspection, image processing using machine learning, and structural integrity of the blade but also undertakes an extensive examination of the prevailing methodologies in the field, pinpointing crucial gaps and challenges. It provides a detailed review of existing research, covering various areas including automated inspection, image processing techniques, fatigue analysis, and the reliability of wind turbines. This approach enriches the discourse by offering a multifaceted perspective on WTB maintenance, thereby advancing the understanding of operational integrity within the field of wind energy.

This paper introduces an innovative approach to Wind Turbine Blade (WTB) inspection through the synergistic use of thermal and RGB imaging, coupled with advanced deep learning techniques. We curated a unique dataset of 1000 thermal images of healthy and faulty blades using a FLIR C5 Compact Thermal Camera, which is equipped with Multi-Spectral Dynamic Imaging technology for enhanced imaging. This paper focuses on evaluating 35 deep learning classifiers, with a standout ensemble model combining Vision Transformer (ViT) and DenseNet161, achieving a remarkable 100% accuracy on the dataset. This model demonstrates the exceptional potential of deep learning in thermal diagnostic applications, particularly in predictive maintenance within the renewable energy sector. Our findings underscore the synergistic combination of ViT’s global feature analysis and DenseNet161’s dense connectivity, highlighting the importance of controlled environments and sophisticated preprocessing for accurate thermal image capture. This research contributes significantly to the field by providing a comprehensive dataset and demonstrating the efficacy of several deep learning models in ensuring the operational efficiency and reliability of wind turbines.

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.

This study addresses the challenges inherent in the maintenance and inspection of wind turbines through the application of deep learning methodologies for fault detection on Wind Turbine Blades (WTBs). Specifically, this research focuses on defect detection on the blades of small-scale WTBs due to the unavailability of commercial wind turbines. This research compared popular object localization architectures, YOLO and Mask R-CNN, to identify the most effective model to detect common WTB defects, including cracks, holes, and erosion. YOLOv9 C emerged as the most effective model, with the highest scores of mAP50 and mAP50-95 of 0.849 and 0.539, respectively. Modifications to Mask R-CNN, specifically integrating a ResNet18-FPN network, reduced computational complexity by 32 layers and achieved a mAP50 of 0.8415. The findings highlight the potential of deep learning and computer vision in improving WTB fault analysis and inspection.

As climate change and human activity increase the likelihood of devastating wildfires, the need for early fire detection methods is inevitable. Although, it has been shown that deep learning and artificial intelligence can offer a solution to this problem, there is still a lot of room for improvement. In this research, two new deep learning approaches to fire detection are developed and investigated utilizing pre-trained ResNet-50 and Xception for feature extraction with a detailed comparison against support vector machine (SVM), ResNet-50, Xception, and MobileViT architectures. Each architecture was tuned utilizing hyperparameter searches and trials to seek ideal combinations for performance. To address the under-representation of desert features in the current fire detection datasets, we have created a new dataset. This novel dataset, Utah Desert Fire, was created using controlled fires and aerial imaging with a DJI Mini 3 Pro drone. The proposed modified ResNet-50 architecture achieved the best performance on the Utah Desert Fire dataset, reaching 100% detection accuracy. To further compare the proposed methods, the popular forest fire detection dataset, DeepFire, was deployed with resulting performance analyzed against most recent literature. Here, our proposed modified Xception model outperformed latest publications attaining 99.221% accuracy. The performance of the proposed solutions show an increase in classification accuracy which can be leveraged for the identification of both desert and forest fires.

We consider the sparse recovery problem of signals with an unknown clustering pattern in the context of multiple measurement vectors (MMVs) using the compressive sensing (CS) technique. For many MMVs in practice, the solution matrix exhibits some sort of clustered sparsity pattern, or clumpy behavior, along each column, as well as joint sparsity across the columns. In this paper, we propose a new sparse Bayesian learning (SBL) method that incorporates a total variation-like prior as a measure of the overall clustering pattern in the solution. We further incorporate a parameter in this prior to account for the emphasis on the amount of clumpiness in the supports of the solution to improve the recovery performance of sparse signals with an unknown clustering pattern. This parameter does not exist in the other existing algorithms and is learned via our hierarchical SBL algorithm. While the proposed algorithm is constructed for the MMVs, it can also be applied to the single measurement vector (SMV) problems. Simulation results show the effectiveness of our algorithm compared to other algorithms for both SMV and MMVs.