Search Results (2,767)

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

To elucidate the damping mechanism of platform dry friction dampers for turbine blades and optimize their design parameters, this study establishes a two-dimensional global–local unified sliding dry friction damping model. This model comprehensively accounts for the blade’s bending-torsion coupling vibration characteristics and the dual-state behavior of the damper, encompassing both stick and slip phases. An iterative solution strategy combining finite element methods with in-house developed programs is employed to simulate the vibration response of turbine blades equipped with dampers under multiple loading conditions. The influence of normal pressure and dimensionless normal pressure on the blade’s vibration characteristics, equivalent stiffness, and equivalent damping is systematically analyzed. To validate the reliability of the simulation results, a dedicated test platform capable of independently simulating centrifugal force effects was constructed, and modal tests as well as vibration response tests were conducted. The results demonstrate that the proposed model accurately describes the nonlinear energy dissipation behavior of dry friction damping, providing a reliable theoretical basis for blade vibration response analysis. Dimensionless normal pressure is identified as a key parameter influencing vibration reduction effectiveness. The resonant amplitude of the blade exhibits a non-monotonic trend, initially decreasing and then increasing with rising dimensionless normal pressure. The optimal dimensionless normal pressure range is found to be 20–30, within which the blade vibration amplitude can be reduced by more than 50%. Experimental verification confirms that the vibration reduction and energy dissipation mechanism of the damping block aligns closely with simulation results, achieving a maximum vibration reduction of 72.6%. Moreover, the optimal dimensionless normal pressure values correspond well with simulation predictions. Based on the optimal dimensionless normal pressure, a forward design method for platform dampers is proposed, which can provide theoretical support and engineering guidance for the optimal design of vibration reduction structures in aero-engine turbine blades. Full article

The transition toward renewable energy sources has positioned wind energy as a critical technology for achieving global carbon neutrality targets. While large-scale wind farms dominate current installations, micro-scale horizontal-axis wind turbines present significant potential for distributed energy generation in remote and rural areas. This study presents a comprehensive methodology for designing micro-scale wind turbine blades through comparative analysis of three computational approaches: classical blade element momentum theory (BEMT), QBlade 2.0.9.6 software, and Computational Fluid Dynamics (CFD) simulations, with the design methodology selected based on a trade-off between accuracy and computational cost. A numerical campaign for airfoil assessment was conducted to identify optimal blade geometries, with performance evaluated based on power coefficient distribution, peak power output, and cut-in wind speed. The investigation reveals that steady CFD simulations predict peak power coefficients 23.34% higher than those predicted by BEMT and 22.46% higher than those predicted by QBlade due to three-dimensional effects, including rotational stall delay. Considering unsteady effects, the CFD simulations show a decrease of 4.08% with respect to steady simulations. The addition of endplates to the optimized blade design demonstrates significant performance improvements. This multi-fidelity approach provides a robust framework for micro-scale wind turbine design, balancing computational efficiency with accuracy requirements, and examines the impact of adding endplates. Full article

The global expansion of wind energy increases the need for sustainable recycling strategies for glass fiber-reinforced plastic (GFRP) from end-of-life wind turbine blades (WTB). Mechanical recycling is currently the most economically and ecologically viable technology. This study compares post-industrial (PI) waste from laminate cutoffs and post-consumer (PC) GFRP waste from end-of-life WTBs to investigate the influence of waste origin, pretreatment of shredded GFRP, different particle sizes and various matrix formulations on the tensile modulus and tensile strength of pressed bulk molding compounds produced with virgin epoxy resin. Thermogravimetric analysis showed a fiber content of up to 70 wt.%, but the resin residues on the embedded glass fibers dimmish a sufficient bonding of the new matrix system. Finer GFRP fractions consistently yielded higher tensile modulus and strength, with PI and pretreated PC materials performing best. The findings of this study demonstrate that controlled particle size distribution, impurity removal and optimized resin viscosity are key factors to achieve reliable mechanical performance and enable high-value recycling routes for glass fiber composite waste. Full article

The limited self-starting capability of H-type Darrieus Vertical-Axis Wind Turbines (VAWT) remains one of the main obstacles to their deployment in low-power and urban applications, where wind conditions are typically weak and intermittent. Although several passive geometric modification strategies have been proposed to enhance initial torque generation, most available studies rely predominantly on numerical simulations, with limited systematic experimental validation under low tip-speed ratio (TSR) conditions. In this work, the influence of passive blade modifications on self-starting performance is assessed through a combined numerical–experimental approach. An integrated numerical–experimental framework was used to systematically compare passive blade configurations under equivalent low-wind conditions. Two modified configurations, a biomimetic profile incorporating passive trailing-edge devices and an asymmetric J-type geometry, were optimized using transient CFD simulations of the first rotation cycle and a Design of Experiments (DOE) framework. Additively manufactured full-rotor test blades were then manufactured via additive manufacturing and tested in a controlled wind tunnel at 3.0 m/s and 2.25 m/s. Start-up time, azimuthal robustness, tip-speed-ratio evolution, and static start-up torque (interpreted through its corresponding torque coefficient) were measured and compared against a baseline NACA0018 profile. The biomimetic configuration consistently produced higher start-up torque and shorter acceleration times, achieving self-starting in 66.7% of the evaluated azimuthal positions at 2.25 m/s, compared to 22.2% for the baseline profile. Within the investigated operating range, this configuration emerged as the most robust passive strategy. The agreement between CFD predictions and experimental measurements supports the use of first-cycle maximum torque as a representative indicator of self-starting performance. These findings highlight the comparative value of first-cycle maximum torque as a practical metric for passive self-starting design assessment in low-TSR Darrieus turbines. These findings provide direct experimental evidence to guide the rational design of Darrieus turbines intended for marginal wind conditions. Full article

Under turbulent wind conditions, rapid wind speed fluctuations can markedly increase the fatigue loads borne by wind turbine blades and towers. In practice, conventional PID pitch control based on speed feedback often struggles to deliver satisfactory load mitigation, mainly because the wind turbine system is highly nonlinear, strongly coupled, and subject to time-delay effects. To overcome these limitations, this paper proposes a load-predictive pitch control strategy built on a Long Short-Term Memory (LSTM) network. Specifically, the LSTM model is first employed to predict the hub-fixed tilt and yaw moments ahead of time. These predicted values are then introduced as feedforward signals and combined with the conventional speed-based pitch control signal as well as a proportional feedback term. After that, the inverse Coleman transformation is used to generate the individual pitch commands for each blade. To verify the effectiveness of the proposed method, co-simulations were carried out in FAST and MATLAB/Simulink on a 5000 KW distributed pitch-controlled wind turbine under IEC Kaimal spectrum wind conditions, with a mean wind speed of 18 m/s and Class B turbulence intensity. The results show that the LSTM prediction model achieves an R² of 0.998 on the test dataset, with an RMSE as low as 0.0051. Compared with the conventional pitch-based power control strategy, the proposed approach maintains the same average power output while significantly reducing fatigue loads, thereby contributing to a longer service life for the wind turbine. Full article

In the 21st century, the desire for improved fuel efficiency of engines, lower fuel prices, and the need to reduce greenhouse gas emissions such as ${\mathrm{C}\mathrm{O}}_2$ and ${\mathrm{N}\mathrm{O}}_{\mathrm{x}}$ are leading the aviation industry to seek hybrid-electric jet engines for commercial aircraft. These aircraft will have greater maintenance challenges due to additional components requiring more reliable materials for the engine’s parts, such as turbine blades. Turbine blades must be composed of materials that have enhanced fatigue performance. Resistance to dynamic loads and high strength will be needed to ensure modern gas turbine blades are as reliable as possible. This review paper examines hybrid-electric engine turbine blades and subsequently introduces additive manufacturing (AM) and multi-principal element alloys (MPEAs) with a focus on laser powder bed fusion (LPBF), high-entropy alloys (HEAs), and medium-entropy alloys (MEAs). The tensile properties of LPBF HEAs range from 5 to 47% elongation and a UTS of 572–1640 MPa, while LPBF MEAs range from 8 to 73.9% and a UTS of 573–1382 MPa. This study focused on dynamic and fatigue properties while acknowledging gaps in high-temperature testing. The combination of mechanical properties with the ability to control internal geometry makes these AM alloys an attractive option for the next generation of gas turbine blades. Full article

Avian wings enable autonomous control over flight trajectory and speed, and their swept-wing geometry inspires the application of sweep modifications to horizontal-axis wind turbine blades, an approach that is critical for improving aerodynamic performance. Hence, wind tunnel experiments were performed to evaluate the output power and wake features of a baseline straight-bladed and a swept-blade wind turbine. The experimental results demonstrate that inflow turbulence intensity (T.I.) affects the peak power coefficient of the swept-bladed turbine, with power coefficient gains being more significant when the tip speed ratio is greater than 3.0 and under yawed conditions. At a yaw angle of 20°, when the T.I. is 0.5%, 10.5%, and 19.0%, respectively, the corresponding increased values are 13.17%, 3.44%, and 4.68%. Cross-stream velocity in the near-wake region of the swept-bladed turbine is markedly higher than that for the baseline condition. The averaged T.I. in the wake velocity region of the swept-blade conditions is greater than that of the baseline condition at most measurement positions. Moreover, power spectral density (PSD) magnitudes behind the blade tip for the swept-blade configuration are higher than those of the baseline, particularly in the medium- and high-frequency domains. This work clarifies the aerodynamic characteristics of swept-blade wind turbines to varying levels of turbulent inflow. Full article

As the population increases, the demand for power continues to rise. As fossil fuel resources reduce, wind energy emerges as a sustainable alternative and helps address adverse effects of global warming and environmental pollution caused by fossil fuels. Thus, this study focuses on increasing the efficiency of wind turbines by improving their energy conversion. In this study, the NREL Phase VI wind turbine blade was modified by adding a Gurney flap at trailing edge along the entire span. Computational fluid dynamics simulations using ANSYS CFX 19.2 were performed on the modified blades to evaluate their aerodynamic performance. Three different flap lengths were investigated with six wind speeds varying from 5 m/s to 20 m/s. The results obtained were compared with those from NREL Phase VI original shape and a blade equipped with a winglet. Computational domain was divided into a rotating cylindrical region and a stationary rectangular part. The aerodynamic parameters calculated include torque, thrust, and normal and tangential forces coefficients. At low velocities, the addition of a Gurney flap had an insignificant impact on torque and thrust, whereas at medium to high wind speeds, significant increases were observed on torque, indicating more power production. Full article

Blade impact faults degrade power generation quality, if not detected in time, may lead to turbine malfunction or even complete failure. Moreover, the accuracy of blade impact fault detection in tidal current turbine (TCT) is significantly affected by variations in flow velocity and tidal flow period. To solve this problem, a self-adaptive detection method based on stator current signals and k-nearest neighbor-multiplicative score (KNN-MS) is proposed. The method first employs the KNN algorithm to characterize local feature distributions. Then, robustness under unstable flow conditions is improved through variance-based weighting. Finally, a cumulative multiplicative scoring mechanism is proposed to amplify and quantify fault-related anomaly indicators. The experimental results show that the proposed method achieves high diagnostic accuracy and stability across steady, periodic, and variable-period flow scenarios. Full article

This paper presents a collaborative optimization design methodology aimed at improving heat dissipation efficiency through the modulation of microstructural variations. The approach addresses the thermal protection requirements of high-temperature components, such as ceramic matrix composite turbine blades, which are subjected to complex and elevated thermal loads. Through the integration of numerical simulation and experimental validation, a bidirectional mapping model linking carbon nanotube (CNT) content with the macroscopic anisotropic thermal conductivity of the material was developed. Furthermore, a thermal conduction analysis and optimization framework for Ceramic Matrix Composite (CMC) high-temperature components under non-uniform thermal loads was established. This study expands the adjustable range of the material’s thermal conductivity by allowing flexible modulation of carbon nanotube content. The results demonstrate that this methodology effectively enhances the heat dissipation capacity of CMC materials in extreme thermal environments: the maximum surface temperature of the optimized flat plate is reduced by 8.96%, the peak temperature gradient is lowered by 46.64%, and the maximum thermal stress is decreased by 38.17%. This research provides new insights into the comprehensive integration of thermal dissipation requirements for CMC hot components. Full article

In various parts of Indonesia, particularly in coastal areas, wind energy can be used as a source of electricity, using wind turbines, whose energy depends on wind speed. Basically, the number of blades in a wind turbine affects the overall turbine performance. This research analyzes the influence of the blade number on the performance of a small-scale horizontal-axis wind turbine using experimental measurements and Computational Fluid Dynamics (CFD) simulations. The CFD simulations were conducted using ANSYS 2022 R2 software on a small-scale horizontal-axis wind turbine with variations in the number of blades, specifically three, four, and five blades, conducted at various wind speeds. It should be noted that due to the setup limitation in the experiment, only the RPM of the three-bladed turbine was measured. Other variables such as torque and power were derived from CFD simulations. The results of this research indicate that an increase in the number of turbine blades tends to result in higher power output, where the highest output obtained was 46.25 Watts. Furthermore, as the number of turbine blades increases, the turbine efficiency also tends to increase, but as wind speed increases, the efficiency decreases. This is demonstrated by the research results, where a wind turbine with five blades achieved the highest efficiency at a speed of 3 m/s, at 38.00%, while at a speed of 6 m/s, the efficiency was 34.80%. Overall, through experiments and cross-validation of CFD and QBlade version 0.963.1, the present study could confirm the significant effect of the number of blades on the power produced by a small-scale horizontal-axis wind turbine under low-speed conditions. Full article

Accurately predicting the temperature field of turbine blades is of great significance for evaluating the thermal reliability and service life of high-temperature components in aero-engines. However, due to the high computational cost of numerical simulations and the limitations imposed by complex geometric structures and harsh operating environments, experimental measurements can usually only obtain sparse sensor data, making the acquisition of complete temperature distributions still challenging. Therefore, reconstructing the complete temperature field under sparse measurement conditions has become a key research issue in turbine thermal analysis. To address this problem, this paper proposes an attention-enhanced CNN–LSTM framework for reconstructing transient turbine blade temperature fields from sparse data. The model combines the spatial feature extraction capability of Convolutional Neural Networks (CNNs) with the time-series modeling capability of Long Short-Term Memory networks (LSTM). An SE channel attention module is introduced in the CNN feature extraction stage to achieve adaptive recalibration of channel features, and a temporal attention mechanism is incorporated after the LSTM layer to highlight key transient thermal features. A multi-condition temperature field dataset was constructed by conducting Computational Fluid Dynamics (CFD) simulations on low-pressure turbine guide vanes, and the model was experimentally validated through thermal shock tests. The results show that the proposed model can accurately reconstruct the spatial distribution and transient evolution of the turbine blade temperature field under sparse measurement conditions. Under different operating conditions, the predicted temperature fields are highly consistent with the CFD results, with the maximum Reconstruction error remaining below 19 °C. Error distribution analysis indicates that the model has stable Reconstruction performance and good generalization ability. 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