Search Results (288)

Images of wind turbine blades captured by drones often feature complex backgrounds, and small targets such as minor defects or images have low resolution, leading to reduced recognition rates. To address environments with complex feature backgrounds, this paper proposes the PPS-MSDeim model. Based on the lightweight end-to-end detection framework DEIM-N, it introduces three core innovations to tackle the challenge of detecting small, irregular defects on wind turbine blades against complex backgrounds. First, we design an inverted multi-scale deep separable convolutional module (MDSC). After compressing channels via a bottleneck layer, it concurrently processes 3 × 3, 5 × 5, and 7 × 7 inverted deep separable convolutions. By first fusing channel information and then extracting multi-receiver-field spatial features, this approach enhances the ability to characterize morphologically variable defects while reducing computational overhead. The MDSC is then embedded into the backbone network HGNetv2. Second, we construct a Multi-Scale Feature Aggregation and Diffusion Pyramid Network (MFADPN). Through a Multi-Scale Feature Aggregation Module (MSFAM), it directly fuses features from layers P2 to P5, achieving deep integration of high-level semantics and low-level details. Combining dilated convolutions with expansion ratios of 1, 3, and 5 captures multi-level context, and a Sobel edge branch is introduced to enhance defect contours; subsequently, a feature diffusion operation is performed to distribute the enhanced features back to each level, shortening information paths and preventing signal decay; simultaneously, a high-resolution detection head is added to P2 and the P5 head is removed to improve sensitivity for small object detection. Finally, we propose the PPSformer module to replace the original Transformer encoding layer. It uses patch embedding to convert images into sequences and introduces a multi-head probabilistic sparse self-attention mechanism that focuses only on key-value pairs during attention computation. This design efficiently captures irregularly varying feature information and globally detects data anomalies induced by external defects. This study uses real engineering data sets, and the results show that PPS-MSDeim, based on DEIM, increased mAP@0.5 by 6.7%, reaching 95.1%. mAP@0.5–0.95 increased by 12.0%, reaching 70.1%. This indicates that the proposed method has a significant advantage in detecting defects in wind turbine blades. Full article

Wind turbine blades are subjected to complex environmental conditions during long-term operation, which may lead to structural degradation and performance loss. To ensure structural integrity, fatigue testing prior to deployment is essential. This paper proposes a vision-based method for measuring the full-cycle breathing deformation of wind turbine blades during fatigue testing. The method captures dynamic image sequences of the blade’s hotspot cross-section using industrial cameras and employs a feature-based template matching approach to reconstruct the three-dimensional coordinates of target points. Through coordinate transformation, the deformation trajectories are obtained, enabling quantitative analysis of the blade’s dynamic responses in both flapwise and edgewise directions. A dedicated hardware–software system was developed and validated through full-scale fatigue experiments. Quantitative comparison with strain gage measurements shows that the proposed method achieves mean absolute deviations of 0.84 mm and 0.93 mm in two independent experiments, respectively, with closely matched deformation trends under typical loading conditions. These results demonstrate that the proposed method can reliably capture the global deformation behavior of the blade with millimeter-level accuracy, while significantly reducing instrumentation complexity compared to conventional contact-based approaches. The proposed method provides an effective and practical solution for full-field dynamic deformation measurement in blade fatigue testing, offering strong potential for structural health monitoring and early damage detection in wind turbine systems. Full article

The industrial X-ray inspection of turbine blade castings requires reliable and auditable decision support, yet defect indications are subtle, and data availability is limited. This study quantitatively assesses the diagnostic potential of handcrafted image descriptors by evaluating class separability in feature space, independently of any trained classifier. The dataset comprises 1600 16-bit DICOM radiograms of 200 blades (eight views per blade), including 156 defective images with 207 localized defects. Standardized 32 × 32 ROI patches were sampled randomly in the vicinity of indications and from defect-free regions to reduce sample correlation and to emulate localization uncertainty. Feature vectors were extracted using five descriptor families—first-order statistics, GLCM/Haralick, FFT and wavelet (DWT) features, Gabor filters, and LBP—and the standardized z-score. Separability was ranked using complementary distribution-based and distance-based metrics grouped into three sets, and the results were min–max-normalized to enable TOP-5 comparisons. Spectral descriptors, particularly DWT wavelets and FFT combined with DWT, consistently achieved the highest scores in distributional metrics, supporting a lightweight screening profile. In contrast, richer combinations dominated multidimensional geometric metrics, indicating benefits from multi-perspective representations for offline analysis. The proposed metric-driven framework provides an interpretable basis for representation selection prior to classifier development under industrial constraints. Full article

Biological reactions are widely applied in processes such as bioenergy production, raw material manufacturing, and resource recovery from waste. As a main reactor type, the stirred-tank bioreactor exhibits prominent advantages of high mixing efficiency and strong adaptability. At present, the optimization of bioreactors mainly focuses on rigid impellers, and the research on flexible impellers is insufficient. Identifying the influence of flexible materials on bioreactor performance is of great significance. In this work, a stirred-tank bioreactor equipped with flexible blades was designed. In addition, a performance detection method coupling Particle Image Velocimetry (PIV) and image recognition was proposed to systematically study the effects of stirring speed, liquid environment, and impeller type. The results indicated that compared with rigid impellers, flexible impellers could reduce 7.7% low-velocity zones and save 15% mixing time. Velocity could be distributed more uniformly, and the suitable velocity ratio was increased by 7.88%. Moreover, the power consumption had been reduced by 7.49%. Taking into account the mixing efficiency and the impact of shear stress, the optimized structural combination and operating parameters were a pitched blade turbine (PBT)-propeller impeller type and a stirring speed of 300 rpm. This work provides important references for the design and optimization of stirred-tank bioreactors. Full article

Vortex generators (VGs) are considered in this study as an effective means of controlling the boundary-layer structure and suppressing flow separation on the suction sides of wind turbine blades. An original geometry of a surface-mounted VG has been developed and experimentally investigated, providing a stable modification of the near-wall flow over a wide range of incoming flow velocities. The aerodynamic effect is attributed to the formation of spatially diverging vortex structures that enhance momentum transfer from the outer flow region toward the near-wall layer, thereby increasing the energy level of the boundary layer. This results in an extension of the attached-flow region and an increase in the mean flow velocity over the suction side of the airfoil by up to 6.5%. The proposed configuration enables a 15% increase in the installation spacing of surface-mounted VGs without loss of control efficiency. Experimental investigations were carried out in a subsonic aerodynamic facility using the Particle Image Velocimetry (PIV) method at free-stream velocities of up to 30 m/s. The obtained data will be used for the development and validation of a mathematical model intended for parametric studies of the influence of surface-mounted VGs on various wind turbine blade airfoils under a wide range of atmospheric turbulence conditions. Full article

The trailing-edge design of a wind turbine airfoil is critical for balancing the aerodynamic performance and structural robustness of a wind turbine blade. In this paper, the S809 airfoil and its blunt trailing-edge variant, the S809-100 airfoil, are taken as the research objects. The aerodynamic and flow-field characteristics of both airfoils are analyzed by computational fluid dynamics, which is validated by U.S. National Renewable Energy Laboratory experiments and wind tunnel particle image velocimetry. The results show that the S809-100 airfoil achieves a higher lift coefficient across the entire angle of attack ($\alpha$) range 0–18°, with a superior lift-to-drag ratio within 8–12°. Three distinct states of aerodynamic response are identified for both airfoils, based on time series and spectral features of lift and drag coefficients, and flow-field structures: steady convergence state, periodic fluctuation state, and irregular fluctuation state. The two airfoils differ significantly in aerodynamic response transition with respect to $\alpha$: for the S809 airfoil, the aerodynamic response remains in a steady convergence state up to $\alpha =16°$ before shifting to a periodic fluctuation state, while for the S809-100 airfoil, it exhibits a periodic fluctuation state from $\alpha =0°$ and transitions to an irregular fluctuation state beyond $\alpha =14.2°$. This difference stems from trailing-edge thickening, which induces flow unsteadiness in the S809-100 airfoil. This shift in the aerodynamic response from the periodic fluctuation state to the irregular fluctuation state is attributed to the transition from single-frequency large-scale vortex shedding to a multi-scale vortex interaction, confirmed via spectral and flow-field analyses. This study focuses on the correlated flow structures of wind turbine airfoils and deepens the understanding of unsteady aerodynamic responses; the combined analysis of enhanced aerodynamic performance and induced unsteady fluctuation due to trailing-edge thickening offers a valuable reference for wind turbine blade design. Full article

A coupled non-destructive testing (NDT) workflow is proposed that integrates active infrared thermography (IRT) with laser-scanning-based reverse engineering (RE) to increase the reliability of detecting and interpreting damage in composite wind turbine blades across laboratory specimens and real components. IRT provides rapid, image-based qualitative localisation of potential anomalies, while 3D scan analysis supplies quantitative, geometry-aware verification and measurement of defect magnitude, reducing both false positives (design-related thermal signatures) and false negatives (weak thermal contrast). On polystyrene-filled profiles, IRT alone produced thermal anomalies unrelated to delamination; co-registered scan maps identified or ruled out local indentation, correctly attributing heat-flow patterns to internal design rather than damage. Outcome: the fused method disambiguates thermal indications and quantifies defect magnitude. On a vertical-axis wind turbine (VAWT) blade, the integration distinguished genuine geometric change from architectural effects under unknown internal structure and without CAD/reference scans, preventing false calls. For three horizontal-axis wind turbine (HAWT) blades, fleet-level scan comparison detected a significant tip deviation despite no clear local IRT anomalies, demonstrating complementary roles: scan = global quantitative homogeneity; and IRT = local qualitative verification. These findings operationalise thermal–geometric cross-validation and outline a path toward UAV-enabled inspections combining passive IRT and laser scanning for hard-to-access structures under real environmental conditions. Full article

As critical components of wind energy systems, the structural integrity of wind turbine blades is directly tied to the operational safety and economic performance of wind turbines. With blade designs trending toward larger and more flexible structures and operating environments becoming increasingly harsh, maintenance strategies must urgently shift from reactive approaches to predictive maintenance paradigms. From an engineering application perspective, this study conducts a systematic and critical review of non-destructive testing (NDT) and structural health monitoring (SHM) technologies for wind turbine blades. Drawing on the literature published over the past decade, we examine the field applicability, limitations, and engineering challenges of core NDT techniques—including vision-based methods, acoustic approaches, vibration analysis, ultrasound, and infrared thermography. Particular emphasis is placed on the integration of data-driven approaches with engineering practice, evaluating the role of machine learning in fault classification and anomaly diagnosis, as well as the contributions of deep learning to automated defect detection in image and signal data. Moreover, this paper critically discusses the growing use of robotic inspection platforms, such as unmanned aerial vehicles and climbing robots, as multi-sensor carriers enabling rapid and comprehensive blade assessment. By comparatively analyzing detection performance, cost, and automation levels across technologies, we identify key engineering barriers, including environmental noise robustness, signal attenuation within complex blade structures, and the persistent gap between laboratory methods and field deployment. Finally, we outline forward-looking research directions, encompassing multi-modal sensor fusion, edge computing for real-time diagnostics, and the development of standardized SHM systems aimed at supporting full lifecycle blade management. Full article

In stirred tank reactors, especially without using baffles, the liquid surface can deform, which in stirring technology is referred to a vortex. These vortices can be advantageous for some mixing tasks, such as obtaining emulsions, they can also impair a consistent product quality. Therefore, it is important for the production and process industry, to know whether a vortex occurs or not. Prediction is only possible with an outdated dimensionless baffle index and research on vortex formation with baffles is limited. In this study, two industrially important axial stirring systems—Propeller and Pitched-blade turbine—with different baffle geometries (rectangular, cylindrical, triangular) and numbers are assessed in regard to power input, vortex characteristics (depth, width, volume) and baffle state prediction. Power is recorded using strain gauges, while vortices are evaluated using an optical image evaluation method. The final vortex result is made dimensionless, accessible to the industry to enable improved predictions about the size of the vortices on an industrial scale in order to make the stirred tanks more economical and sustainable. Furthermore, an initial improvement of the baffle index for the investigated stirrers is given, because the original index incorrectly predicts the baffle state in 12.5% of cases. Full article

Turbine blades serve as critical components in aircraft engines, yet casting defects inevitably arise during manufacturing. Therefore, accurate pre-service turbine blade defect detection is critical for aircraft engine safety. However, existing deep learning-based detection methods face several challenges: poor image quality, intraclass variance, interclass similarity, and irregular defect geometries. Moreover, most existing defect detection methods rely primarily on spatial-domain features, which are insufficient for capturing fine-grained texture information, limiting their ability to discriminate complex defect patterns. To address these challenges, we propose a novel Spatial-Frequency Complementary Fusion Network (SFCF-Net) that synergistically integrates spatial and frequency-domain features through complementary cross-modal fusion for accurate defect segmentation. First, a Selective Cross-modal Calibration (SCC) module is introduced that selectively calibrates spatial-frequency features through gated cross-modal interactions, effectively preserving fine-grained details under poor image conditions. Next, we propose a Cross-modal Refinement and Complementation (CRC) module that employs dual-stage attention mechanisms to model intra- and inter-modal feature dependencies, enabling robust discrimination between similar defect categories while maintaining consistency within the same defect class. Finally, we propose an Asymmetric Window Attention (AWA) module that employs bidirectional rectangular windows for accurate defect geometric characterization. Comprehensive experiments on the Aero-engine Turbine Blade Casting Defect Segmentation (ATBCD-Seg) dataset and a public benchmark demonstrate that SFCF-Net consistently outperforms state-of-the-art methods across multiple evaluation metrics, meeting practical requirements for automated quality control in blade manufacturing. Full article

During fatigue tests of tidal turbine blades, digital image correlation (DIC) is used to collect vital information about the specimen. DIC provides high-resolution displacement and strain maps of selected blade sections; however, continuous operation is hindered by the need to acquire, transfer, and process large volumes of high-resolution images, precluding real-time use during long tests. We address this problem by optimising sparse sensing locations on the blade surface so that full-field maps can be accurately reconstructed from a small subset of pixel measurements. In contrast to most DIC improvements found in the literature, which focus on accelerating the processing stage, this approach circumvents the need to collect high-resolution data. We evaluate this approach in a case study at FastBlade, a dedicated testing facility for tidal turbine blades. With less than 1% of the original pixels measured, the mean relative error evaluated on the dataset is 0.4% and 16% for displacement and strain maps, respectively, with the larger strain error reflecting the higher spatial complexity of strain fields. The optimised layouts outperform random and grid-like arrangements. The framework enables real-time monitoring and, subject to relevant validation, might be applied to reconstruct high-resolution strain maps directly from strain-gauge readings, potentially extending to in-ocean blade monitoring. Given the high accuracy of deflection reconstructions, using them to derive strain fields is suggested as a direction for further study. Full article

Carbon nanotube (CNT) cathode materials exhibit excellent electron emission performance and have become a key research focus in the field of vacuum electronics. However, their practical applications are still restricted by challenges, including emission instability and ambiguity in temporal resolution capability. This work investigated the thermal-assisted field emission characteristics of CNT and their application in pulsed X-ray imaging. Systematic characterization of the turn-on field strength, emission stability, pulse response characteristics, and pulsed X-ray imaging performance demonstrated that the thermal-assisted operating mode reduced current fluctuations to below 1%. Increasing the heating power further enhanced emission stability and lowered the turn-on field strength. In thermal-assisted pulsed emission mode, CNT cathodes exhibited reduced power consumption compared to conventional thermionic cathodes and achieved microsecond-scale pulse response. Further X-ray imaging experiments confirmed that the X-ray dose generated by CNT in this operational mode exhibited higher stability, enabling 100 μs pulsed imaging and clear visualization of rotating blades operating at 600 Hz. This study validated the feasibility of CNT cathodes for high-speed X-ray imaging and could provide a reference for the development of advanced pulsed X-ray sources and related technologies. Full article

Using high-resolution remote sensing imagery to obtain the wind turbine height is a fast and effective method for monitoring the status of wind turbines after natural disasters such as earthquakes, landslides, and typhoons. A height estimation method tailored for wind turbines is proposed using high-resolution satellite images. First, deep learning techniques are employed to identify wind turbines and extract their shadow information from GaoFen-2 (GF-2) satellite imagery. Specifically, YOLOv5-CBAM and MSASDNet are used for target recognition and shadow extraction, achieving an identification accuracy of 96% and a shadow extraction accuracy of 82.53%. Next, the line-by-line scanning method is applied to remove blade shadow from the whole wind turbine shadow. By calculating the number of pixels occupied by the shadow length of the wind turbine after removing the blade shadow and multiplying by the image resolution, the wind turbine shadow length is obtained. Finally, a spatial geometry model involving the satellite angles, solar angles, and wind turbine shadow length is constructed to retrieve the wind turbine height. An experiment was conducted using GF-2 satellite remote sensing data from a wind farm in Huailai County of China. The actual heights of wind turbines in the estimation area were measured by the field experiment, and the average absolute error was verified to be 2.2 m, demonstrating the effectiveness of the proposed method. The experimental results show that this method can detect the post-disaster status of wind turbines. Full article

The condition of technical surfaces strongly influences the functionality and lifetime of many components. In particular, the performance of aero-engines can be impaired by increased roughness of the turbine blade surfaces. In this work, an LED- and camera-based illumination sensor is presented for reflection-based characterisation of turbine blade surfaces, with a focus on rapid, wide-area assessment rather than direct roughness measurement. Traditional roughness measurements (e.g., profilometry, confocal microscopy) provide micrometre-scale height information but are limited in working distance and measurement volume, making complete surface coverage time-consuming. The proposed sensor acquires multi-illumination image data, from which an anisotropic BRDF (bidirectional reflectance distribution function) model is fitted on a per-pixel basis to obtain reflectance parameters. Independently, surface roughness parameters (Sa, Sq, Sz, Ssk, Sku) are measured using a confocal laser scanning microscope in accordance with ISO 25178 and used as reference data. Using two turbine blades with contrasting surface conditions (comparatively smooth vs. visibly rough), the study qualitatively investigates whether there are indications of relationships between BRDF model parameters and roughness characteristics. The results show weak relationships with height-based parameters (Sa, Sq, Sz), but clearer trends for distribution parameters (Ssk, Sku) and a good qualitative agreement between directional BRDF parameters and texture orientation. These findings indicate that the illumination sensor provides a complementary, reflectance-based approach for surface condition triage in MRO and QA contexts, highlighting regions that warrant more detailed roughness measurements. Extension of the approach to other component geometries and a comprehensive quantitative analysis of BRDF–roughness relationships are planned for follow-up studies. Full article

Wind turbine blades (WTBs) are inevitably exposed to harsh environmental conditions, leading to surface damages such as cracks and corrosion that compromise power generation efficiency. While UAV-based inspection offers significant potential, it frequently encounters challenges in handling irregular defect shapes and preserving fine edge details. To address these limitations, this paper proposes DMR-YOLO, an Improved Wind Turbine Blade Surface Damage Detection Method Based on YOLOv8. The proposed framework incorporates three key innovations: First, a C2f-DCNv2-MPCA module is designed to dynamically adjust feature weights, enabling the model to more effectively focus on the geometric structural details of irregular defects. Secondly, a Multi-Scale Edge Perception Enhancement (MEPE) module is introduced to extract edge textures directly within the network. This approach prevents the decoupling of edge features from global context information, effectively resolving the issue of edge information loss and enhancing the recognition of small targets. Finally, the detection head is optimized using a Re-parameterized Shared Convolution Detection Head (RSCD) strategy. By employing weight sharing combined with Diverse Branch Blocks (DBB), this design significantly reduces computational redundancy while maintaining high localization accuracy. Experimental results demonstrate that DMR-YOLO outperforms the baseline YOLOv8n, achieving a 1.8% increase in mAP@0.5 to 82.2%, with a notable 3.2% improvement in the “damage” category. Furthermore, the computational load is reduced by 9.9% to 7.3 GFLOPs, while maintaining an inference speed of 92.6 FPS, providing an effective solution for real-time wind farm defect detection. Full article