Search Results (163)

Performance degradation of wind turbine blades often stems from geometric asymmetry induced by damage. Existing methods for assessing damage face challenges in balancing accuracy and efficiency due to their limited ability to capture fine-grained geometric asymmetries associated with multi-scale damage under complex background interference. To address this, based on the high-speed detection model YOLOv10-N, this paper proposes a novel detection model named MMC-YOLO. First, the Multi-Scale Perception Gated Convolution (MSGConv) Module was designed, which constructs a full-scale receptive field through multi-branch fusion and channel rearrangement to enhance the extraction of geometric asymmetry features. Second, the Multi-Scale Enhanced Feature Pyramid Network (MSEFPN) was developed, integrating dynamic path aggregation and an SENetv2 attention mechanism to suppress background interference and amplify damage response. Finally, the Channel-Compensated Filtering (CCF) module was constructed to preserve critical channel information using a dynamic buffering mechanism. Evaluated on a dataset of 4818 wind turbine blade damage images, MMC-YOLO achieves an 82.4% mAP [0.5:0.95], representing a 4.4% improvement over the baseline YOLOv10-N model, and a 91.1% recall rate, an 8.7% increase, while maintaining a lightweight parameter count of 4.2 million. This framework significantly enhances geometric asymmetry defect detection accuracy while ensuring real-time performance, meeting engineering requirements for high efficiency and precision. Full article

Timely and accurate detection of wind turbine blade surface defects is crucial for ensuring operational safety and improving maintenance efficiency with respect to large-scale wind farms. However, existing methods often suffer from poor generalization, background interference, and inadequate real-time performance. To overcome these limitations, we developed an end-to-end defect recognition framework, structured as a three-stage process: blade localization using YOLOv5, robust feature extraction via the large vision model DINOv2, and defect classification using a Stochastic Configuration Network (SCN). Unlike conventional CNN-based approaches, the use of DINOv2 significantly improves the capability for representation under complex textures. The experimental results reveal that the proposed method achieved a classification accuracy of 97.8% and an average inference time of 19.65 ms per image, satisfying real-time requirements. Compared to traditional methods, this framework provides a more scalable, accurate, and efficient solution for the intelligent inspection and maintenance of wind turbine blades. Full article

Real-time non-intrusive monitoring of wind turbines, blades, and defect surfaces poses a set of complex challenges related to accuracy, safety, cost, and computational efficiency. This work introduces an enhanced deep learning-based framework for real-time detection of wind turbine blade defects. The WindDefNet is introduced, which features the Inception-ResNet modules, Visual Transformer (ViT), and multi-scale attention mechanisms. WindDefNet utilizes modified cross-convolutional blocks, including the powerful Inception-ResNet hybrid, to capture both fine-grained and high-level features from input images. A multi-scale attention module is added to focus on important regions in the image, improving detection accuracy, especially in challenging areas of the wind turbine blades. We employ pertaining to Inception-ResNet and ViT patch embedding architectures to achieve superior performance in defect classification. WindDefNet’s capability to capture and integrate multi-scale feature representations enhances its effectiveness for robust wind turbine condition monitoring, thereby reducing operational downtime and minimizing maintenance costs. Our model WindDefNet integrates a novel advanced attention mechanism, with custom-pretrained Inception-ResNet combining self-attention with a Visual Transformer encoder, to enhance feature extraction and improve model accuracy. The proposed method demonstrates significant improvements in classification performance, as evidenced by the evaluation metrics attain precision, recall, and F1-scores of 0.88, 1.00, and 0.93 for the damage, 1.00, 0.71, and 0.83 for the edge, and 1.00, 1.00, and 1.00 for both the erosion and normal surfaces. The macro-average and weighted-average F1 scores stand at 0.94, highlighting the robustness of our approach. These results underscore the potential of the proposed model for defect detection in industrial applications. Full article

Single-crystal superalloys have attracted considerable interest in aero engine blade manufacture due to their superior mechanical properties, which maintain structural integrity at high temperatures. However, their anisotropic microstructure results in direction-dependent properties that pose a challenge for defect detection. This study proposes a methodology to determine the crystal orientation, which is subsequently used to improve the Total Focusing Method (TFM) by incorporating the refracted beam directivity. Firstly, simulations were performed using semi-analytical models (CIVA software 2023 SP4.1) to reproduce different grain orientations. The results were then post-processed to determine the grain orientation. Finally, the TFM was adapted to take into account not only the velocity variations due to orientation but also the directivity of the ultrasonic beam based only on slowness curves. The implementation of this methodology has improved the defect detection capability, optimizing the defect positioning by up to 61% and increasing the signal-to-noise ratio by up to 5 dB. This study demonstrates the effectiveness of an adapted inspection procedure for single crystals. Full article

In this study, a conceptual turbine blade model with internal cooling channels was designed and fabricated using the selective laser melting (SLM) process. The optimal manufacturing orientation was evaluated through simulations, and the results indicated that vertical orientation yielded the best outcomes, minimizing support material usage and distortion despite increased manufacturing time. Two configurations were produced, namely, an entire-turbine blade model and a cross-sectional model. Non-destructive analyses, including 3D laser scanning for dimensional accuracy, surface roughness measurements, and liquid penetrant testing, were conducted. Visual inspection revealed manufacturing limitations, particularly in the cooling channels at the leading and trailing edges. The trailing edge was too thin to accommodate the 0.5 mm channel diameter, and the channels in the leading edge were undersized and potentially clogged with unmelted powder. The dimensional deviations were within the acceptable limits for the SLM-fabricated metal parts. The surface roughness measurements were aligned with the literature values for metal additive manufacturing. Liquid penetrant testing confirmed the absence of cracks, pores, and lack-of-fusion defects. The SLM is a viable manufacturing process for turbine blades with internal cooling channels; however, significant attention should be paid to the design of additive manufacturing conditions to obtain the best results after manufacturing. Full article

Compared with powder metallurgy, centrifugal casting, jet molding, and other technologies, Laser Melting Deposition (LMD) stands out as an advanced additive manufacturing technology that provides substantial advantages in the melt forming of functional gradient materials and composites. However, when high-temperature and high-speed laser energy is applied, the resulting materials are susceptible to porosity, which restricts their extensive use in fatigue-sensitive applications such as turbine engine blades, engine connecting rods, gears, and suspension system components. Since fatigue cracks generally originate near pore defects or at stress concentration points, it is crucial to investigate evaluation methods for pore defects and stress concentration in LMD applications. This study examines the effect of pore defects on stress concentration in LMD-manufactured AlSi10Mg using the crystal plasticity finite element method and proposes a stress concentration coefficient characterization approach that considers pore size, morphology, and location. The simulation results indicate a competitive mechanism between pores and grains, where the larger entity dominates. Regarding the influence of aspect ratio on stress concentration, as the aspect ratio decreases along the stress direction, the stress concentration increases significantly. When pores are just emerging from the surface (s/r = 1), the stress concentration caused by the pore reaches its maximum, posing the highest risk of material failure. To assess the extent to which the aspect ratio, position, and size of pores affect stress concentration, a statistical correlation analysis of these variables was conducted. Full article

Wind turbines’ volume and power generation capacity have increased worldwide. Consequently, their inspection, maintenance, and repair are garnering increasing attention. Structural defects are common in turbine blades, but their detection is difficult due to the relatively large size of the blades. Therefore, engineers often use nondestructive testing. This study employed an unmanned aerial vehicle (UAV) to simultaneously capture visible-light and infrared thermal images of wind power blades. Subsequently, instant neural graphic primitives and neural radiance fields were used to reconstruct the visible-light image in three dimensions (3D) and generate a 3D mesh model. Experiments determined that after converting parts of the orthographic-view images to elevation- and depression-angle images, the success rate of camera attitude calculation increased from 85.6% to 97.4%. For defect measurement, the system first filters out the perspective images that account for 6–12% of the thermal image foreground area, thereby excluding most perspective images that are difficult to analyze. Based on the thermal image data of wind power generation blades, the blade was considered to be in a normal state when the full range, average value, and standard deviation of the relative temperature grayscale value in the foreground area were within their normal ranges. Otherwise, it was classified as abnormal. A heat accumulation percentage map was established from the perspective image of the abnormal state, and defect detection was based on the occurrence of local minima. When a defect was observed in the thermal image, the previously reconstructed 3D image was switched to the corresponding viewing angle to confirm the actual location of the defect on the blade. Thus, the proposed 3D image reconstruction process and thermal image quality analysis method are effective for the long-term monitoring of wind turbine blade quality. Full article

An analysis of defects creation in the vicinity of the selector-root connection plane in single-crystalline turbine blades made of CMSX-4 Ni-base superalloy was performed using several experimental methods. A coupling of scanning electron microscopy and X-ray diffraction topography allowed the visualization of dendritic arrays and surface defects in the root part of the blades. As a result, contrast inversions and areas where internal stresses occur were observed. The defects on a microscopic scale were characterized using positron annihilation lifetime spectroscopy and transmission electron microscopy. The registered positron lifetimes, above 0.5 ns, beyond the range characteristic for defects generally reported in metals and their alloys suggest the presence extremely large void type defects. Herein, we have identified large defects, ca. 2–5 nm in diameter, formed due to the contraction of fluid metal, captured in inter-dendritic regions during the liquid-to-solid transition. This work is a precursor to the almost untouched area of the discussion of lifetimes characteristic for positron bound states, called positronium (>0.5 ns) in relation to the morphology of void-type defects in single-crystalline superalloys. Full article

In industrial manufacturing, product quality is of paramount importance, as surface defects not only compromise product appearance but may also lead to functional failures, resulting in substantial economic losses. Detecting defects on complex surfaces remains a significant challenge due to the variability of defect characteristics, interference from specular reflections, and imaging non-uniformity. Traditional computer vision algorithms often fall short in addressing these challenges, particularly for defects on highly reflective curved surfaces such as aircraft engine blades, bearing surfaces, or vacuum flasks. Although various optical imaging techniques and advanced detection algorithms have been explored, existing approaches still face limitations, including high system complexity, elevated costs, and insufficient capability to detect defects with diverse morphologies. To address these limitations, this study proposes an innovative approach that analyzes the propagation of light on complex surfaces and constructs a polarization imaging system to eliminate glare interference. This imaging technique not only effectively suppresses glare but also enhances image uniformity and reduces noise levels. Moreover, to tackle the challenges posed by the diverse morphology of defects and the limited generalization ability of conventional algorithms, this study introduces a novel multi-scale edge information selection module and a Focal Modulation module based on the YOLOv11 architecture. These enhancements significantly improve the model’s generalization capability across different defect types. Experimental results show that, compared to state-of-the-art object detection models, the proposed model achieves a 3.9% increase in precision over the best-performing baseline, along with notable improvements in recall, mAP50, and other key performance indicators. Full article

This study proposes a novel defect detection method to address the low accuracy and insufficient efficiency encountered during surface defect detection on aeroengine turbine blades (ATBs). The proposed approach employs the LDconv model to adjust the size and shape of convolutional kernels dynamically, integrates the deformable attention mechanism (DAT) to capture minute defect features effectively, and uses Focaler-CIoU to optimize the bounding box loss function of the detection network. Our approaches collectively provide precise detection of surface defects on ATBs. The results show that the proposed method achieves a mean average precision (mAP_0.5) of 96.2%, an F-measure of 96.7%, and an identification rate (I_r) of 98.8%, while maintaining a detection speed of over 25 images per second. The proposed method meets the stringent requirements for accuracy and real-time performance in ATB surface defect detection. Full article

Wind turbine blades are made from fiberglass, whose faces are eroded due to environmental conditions. Polyurethane (PU) coatings are broadly used in several types of coatings due to their strong adhesion. However, their inferior mechanical properties limit their application on fiberglass. In this study, graphene oxide (GO) was modified through a dielectric barrier plasma (DBP) treatment at atmospheric pressure to improve the dispersion of GO in PU and increase its adhesion to fiberglass (GF) substrates, resulting in excellent adhesion properties of the PU/GO coating on fiberglass. Additionally, PU/GO coatings are crucial for preventing and protecting against erosion. The results obtained for the intensity ratio of the $I_D/I_G$ peaks observed through Raman spectroscopy exhibited that the plasma treatment increased the defects in the GO structure through covalent and non-covalent interactions with the PU. Contact angle tests and surface free energy measurements indicated the deoxygenation of the GO structure, enhancing its dispersion in the PU matrix, as observed through XRD. The plasma treatment increased the PU/GO adhesion by 27.6% after 10 min of treatment, suggesting that more defects in the GO structure were correlated with greater adhesion strength. Full article

Wind turbine inspections are traditionally performed by certified rope teams, a manual process that poses safety risks to personnel and leads to operational downtime, resulting in revenue loss. To address some of these challenges, this study explores the use of deep learning and drones for automated inspections. Three Mask R-CNN models, leveraging different convolutional neural network (CNN) backbones—VGG19, Xception, and ResNet-50—were constructed and trained on a novel dataset of 3000 RGB images (size 300 × 300 pixels) annotated with defects, including cracks, holes, and edge erosion. To improve defect detection performance, a multi-variable fuzzy (MVF) voting system is proposed. This method demonstrated superior accuracy compared to the individual models. The best-performing standalone model, Mask R-CNN with Xception, achieved an mAP of 77.48%, while the MVF system achieved an mAP of 80.10%. These findings highlight the effectiveness of combining fuzzy voting systems with Mask R-CNN models for defect detection on wind turbine blades, offering a safer and more efficient alternative to traditional inspection methods. Full article

Innovative structures technologies can contribute to increasing the sustainability of next-generation aircraft. Advanced multi-disciplinary physics models, combined with data-based models, are needed to obtain optimized structures with maximum contributions to sustainability throughout the life cycle. Such models are needed for next-generation aircraft products, for better production of their parts, and for representative testing of their innovative systems. Modeling challenges addressed recently will be presented and illustrated in their industrial context. In particular, fast in-line detection of defects in large composite aircraft parts during their high-rate production, induction welding of thermoplastic carbon-fiber reinforced parts, and accurate design of composite fan blades for wind tunnel testing of fuel-efficient Ultra-High Bypass Ratio (UHBR) turbofan engines will be presented. Full article

Background: Mandibular reconstruction has evolved significantly since its inception in the early 1900s. Currently, the fibula free flap (FFF) is considered the gold standard for mandibular and maxillary reconstructions, particularly for extensive defects, and the introduction of Extended Reality (XR) and virtual surgical planning (VSP) is revolutionizing maxillofacial surgery. Methods: This study focuses on evaluating the accuracy of using in-house cutting guides for mandibular reconstruction with FFF supported by virtual surgical planning (VSP). Planned and intraoperative osteotomies obtained from postoperative CT scans were compared in 17 patients who met the inclusion criteria. The proposed analysis included measurements of deviation angles, thickness at the centre of gravity, and the maximum thickness of the deviation volume. Additionally, a mandibular resection coding including 12 configurations was defined to classify and analyze the precision of mandibular osteotomies and investigate systematic errors. Preoperative, planned, and postoperative models have been inserted in an interactive VR environment, VieweR, to enhance surgical planning and outcome analysis. Results: The results proved the efficiency of adopting customized cutting guides and highlighted the critical role of advanced technologies such as CAD/CAM and VR in modern maxillofacial surgery. A novel coding system including 12 possible configurations was developed to classify and analyze the precision of mandibular osteotomies. This system considers (1) the position of the cutting blade relative to the cutting plane of the mandibular guide; (2) the position of the intersection axis between the planned and intraoperative osteotomy relative to the mandible; (3) the direction of rotation of the intraoperative osteotomy plane around the intersection axis from the upper view of the model. Conclusions: This study demonstrates the accuracy and reliability of in-house cutting guides for mandibular reconstruction using fibula free flaps (FFF) supported by virtual surgical planning (VSP). The comparison between planned and intraoperative osteotomies confirmed the precision of this approach, with minimal deviations observed. These findings highlight the critical role of CAD/CAM and XR technologies in modern maxillofacial surgery, offering improved surgical precision and optimizing patient outcomes. Full article

This study proposes a method for detecting internal defects in wind turbine blades using deep learning, eliminating the reliance on inspectors’ experiments. To address the class imbalance problem inherent in defect detection environments, synthetic thermographic datasets were generated using a synthetic data generation technique. To minimize the domain gap between synthetic and real thermographic data, preprocessing with a transformation module was employed, enhancing the similarity between datasets. ResNet-50, DenseNet-121, and Vision Transformer (ViT) models were trained on the synthetic dataset, and their defect detection performance was evaluated on real thermographic data. The results validated the effectiveness of the transformation module in improving the similarity between synthetic and real data, particularly enhancing precision and recall. Full article