Wind Turbine Blade Damage Research Articles

Impact of wind turbine nominal power limitation over wind turbine blade remaining useful life and its economic consequences

The present paper investigates the effects of wind turbine nominal power limitation on the remaining useful life of turbine blades. It also looks at the economic impact of this limitation. In this context, the paper provides wind turbine owners and operators with an overview of how to potentially extend the remaining useful life of wind turbine blades and lays out the economic benefits that can be achieved via the modulation of nominal power. In investigating wind turbine blade damage, prior studies focused mainly on predictive models based on the 10 minutes SCADA data wind speed history, without however, trying to protract the remaining useful life of the blades. Only a handful of papers have explored the possibility of increasing the remaining useful life by adjusting the start-up and shutdown procedures with poor results. It would appear that wind turbine blade fatigue damage mainly increases when the wind turbine is in a power production regime, and the mechanical stresses associated with this regime are a function of the nominal power of the wind turbine. The present work therefore investigates the impacts of nominal power changes on both the remaining useful life of wind turbine blades and the economic value of the wind turbine in a bid to identify an optimal control mode. The wind turbine blade damage evaluation is based on 10 minutes SCADA data and the FAST simulation tool with the ultimate goal of providing wind turbine operators with an easy application. The damage evaluation is then applied considering different nominal power levels for the same wind turbine model in order to see the resulting impact on the remaining useful life. This project therefore takes a pioneering approach by proposing a remaining useful life optimization tool to wind turbine operators, in effect, a decision-making tool regarding which exploitation strategy to adopt.

An unsupervised damage detection method for an operating wind turbine blade

Wind turbine blades are normally exposed to significant dynamic loads over their lifetime, including extreme conditions. This can lead to several types of damages such as cracking and delamination. Monitoring the structural condition of the blades to detect damages before they become catastrophic can be important. In recent years, the concept of data-driven structural health monitoring (SHM) approaches for wind turbine blade damage detection has become popular. These methods employ features collected from time series obtained from monitored wind turbine blades to identify damages. However, selecting an optimum number of features, which can reduce computational cost and minimize the effects of environmental and operational conditions, is still a challenge. In this paper, a data-driven approach is developed combining a feature extraction strategy and un-supervised anomaly detection. Monitoring data collected from several accelerometers mounted on a blade of an operating Vestas V27 wind turbine in healthy and damaged scenarios are used in this regard. Several time-domain, temporal, and time-frequency domain features are employed for the purpose of anomaly detection using unsupervised learning methods. Isolation Forest and One-class Support Vector Machine are used to train for anomaly detection. A threshold of detection is established to distinguish between the healthy and damaged states. Results show that the proposed approach can successfully identify the damage cases, but environmental and operational conditions still have some effect when it comes to identifying the extent of the damage.

WTBD-YOLOv8: An Improved Method for Wind Turbine Generator Defect Detection

Wind turbine blades are the core components responsible for efficient wind energy conversion and ensuring stability. To address challenges in wind turbine blade damage detection using image processing techniques such as complex image backgrounds, decreased detection performance due to high image resolution, prolonged inference time, and insufficient recognition accuracy, this study introduces an enhanced wind turbine blade damage detection model named WTDB-YOLOv8. Firstly, by incorporating the GhostCBS and DFSB-C2f modules, the aim is to reduce the number of model parameters while enhancing feature extraction capability. Secondly, by integrating the MHSA-C2f module, which incorporates a multi-head self-attention mechanism, the focus on global information is enabled, thereby mitigating irrelevant background interference and reducing the impact of complex backgrounds on damage detection. Lastly, adopting the Mini-BiFPN structure improves the retention of features for small target objects in shallow networks and reinforces the propagation of these features in deep networks, thereby enhancing the detection accuracy of small target damage and reducing false negative rates. Through training and testing on the Wind Turbine Blade Damage Dataset (WTBDD), the WTDB-YOLOv8 model achieves an average precision of 98.3%, representing a 2.2 percentage point improvement over the original YOLOv8 model. Particularly noteworthy is the increase in precision from 93.1% to 97.9% in small target damage detection. Moreover, the total parameter count of the model decreases from 3.22 million in YOLOv8 to 1.99 million, marking a reduction of 38.2%. Therefore, the WTDB-YOLOv8 model not only enhances the detection performance and efficiency of wind turbine blade damage but also significantly reduces the model parameter count, showcasing its practical advantages in engineering applications.

Characterization and Prediction of Wind Turbine Blade Damage Based on Fiber Grating Sensor

INTRODUCTION: As a renewable and clean use of energy, wind power generation has a very important role in the new energy generation industry. For the many parts of various wind turbines, the safety and reliability of wind turbine blades are very important. OBJECTIVES: The energy spectrum simulation algorithm included in the wavelet analysis method is used to simulate and analyzewind turbine blade damage, to verify the correctness and validity of wind turbine blade damage analysis. METHODS: Matlab simulation is used to introduce the experiments related to the static and dynamic detection of fiber grating sensors, analyze the signal characteristics of the wind turbine blade when it is damaged by the impact, and provide a basis for the analysis of the external damage of large wind turbine blade. RESULTS: The main results obtained in this paper are the following. By analyzing the decomposition of wavelet packets, the gradient change of wavelet impact energy spectrum before and after the wavelet damage was obtained and compared with the histogram, and the impact energy spectrum of each three-dimensional wavelet energy packet in the image was compared and analyzed, which can well realize the recognition of wavelet damage gradient for solid composite materials. CONCLUSION: With the help of Matlab simulation to collect the impact response signal, using the wavelet packet energy spectrum method to analyze the signal, can derive the characteristics of wind turbine blade damage.

Wind Turbine Blade Damage Evaluation under Multiple Operating Conditions and Based on 10-Min SCADA Data

The present paper aims to enable the assessment of the fatigue damage of wind turbine blades over a long duration (e.g., several months/years) in conjunction with different operating regimes and based on two information sources: the 10-min SCADA data and an interpolation using response surfaces identified using the FAST aeroelastic numerical tool. To assess blade damage, prior studies highlighted the need for a high-frequency (>1 Hz) sampling rate. Because of data availability and computation resource limitations, such methods limit the duration of the analysis period, making the direct use of such an approach based on a 1 Hz wind speed signal in current wind farms impractical. The present work investigates the possibility of overcoming these issues by estimating the equivalent damage using a 1 Hz wind speed for each 10-min sample stored in the SCADA data. In the literature, the influence of operating regimes is not considered in fatigue damage estimation, and for the first time, the present project takes a pioneering approach by considering these operating regimes.

Damage identification of wind turbine blades based on deep learning and ultrasonic testing

ABSTRACT Ultrasonic testing (UT) is an effective method for detecting internal damage in wind turbine blades. However, manual interpretation is time-consuming and subjective. To automate UT in the wind turbine industry, an image detection model based on deep learning called UCD-YOLO (Ultrasonic C-scan image Detection You Only Look Once) is proposed to detect internal damage such as stratified and lack of glue in wind turbine blades. In order to enhance the feature extraction ability under complex damage forms, the use of deformable convolutional networks and context augmentation module are proposed. Designing a lightweight cross stage partial spatial pyramid pool fast (LCSP_SPPF) module, which allows the model to learn more information and improve detection accuracy. The introduction of wise intersection over union (WIoU) improves the convergence speed while reducing the regression error. Using UT devices to collect damage images of wind turbine blades and conducting comprehensive evaluation experiments on the detection performance of the proposed method. Results show that compared to the YOLOv5, UCD-YOLO is not only lighter but also achieves a 7.5% increase in mean average precision (mAP50). And compared with other detection methods, further verifying that the proposed method can quickly and effectively detect wind turbine blade internal damage, improving power generation efficiency.

Research on an Intelligent Identification Method for Wind Turbine Blade Damage Based on CBAM-BiFPN-YOLOV8

To address challenges in the detection of wind turbine blade damage images, characterized by complex backgrounds and multiscale feature distribution, we propose a method based on an enhanced YOLOV8 model. Our approach focuses on three key aspects: First, we enhance the extraction of small target features by integrating the CBAM attention mechanism into the backbone network. Second, the feature fusion process is refined using the Weighted Bidirectional Feature Pyramid Network (BiFPN) to replace the path aggregation network (PANet). This modification prioritizes small target features within the deep features and facilitates the fusion of multiscale features. Lastly, we improve the loss function from CIoU to EIoU, enhancing sensitivity to small targets and the perturbation resistance of bounding boxes, thereby reducing the gap between computed predictions and real values. Experimental results demonstrate that compared with the YOLOV8 model, the CBAM-BiFPN-YOLOV8 model exhibits improvements of 1.6%, 1.0%, 1.4%, and 1.1% in precision rate, recall rate, mAP@0.5, and mAP@0.5:.95, respectively. This enhanced model achieves substantial performance improvements comprehensively, demonstrating the feasibility and effectiveness of our proposed enhancements at a lower computational cost.

Research on wind turbine blade damage based on pre-stressed FBG strain sensors

Research on wind turbine blade damage based on pre-stressed FBG strain sensors

Wind turbine blade damage detection and classification based on sound feature signal using machine learning

Wind turbine blades experience variable environmental conditions and are prone to failure due to fatigue and weather-induced damage. In this study, the aerodynamic sound signal of wind turbine blades is collected while in operation. Short-Time Fourier Transform method identified and used to analyze the periodic signal of the rotation of the wind turbine blades. The spectral centroid of the pulse signal and the variation of the corresponding three blades spectral centroid are extracted as the input features for supervised machine learning. Gaussian mixture model algorithm classified features and used with blades damage trend for structural health monitoring. Through the Gaussian mixture model established by using the mean value and standard deviation of the peak value of the spectral centroid, the results after the model test show the accuracy of the damaged blade judgment can reach 98 %. In addition, from the visual classification chart, it can be known that the blade will enter the damage state, and maintenance should be carried out in advance to avoid damage to the blade and maintain the stable operation of the wind turbine.

Parametric and numerical Finite Element simulation of wind turbine blades subjected to thermal residual stresses

This study aims to contribute to the ongoing efforts to enhance the reliability and durability of wind turbine blades, a critical component in wind energy generation. Specifically, this research addresses the issue of tunneling cracking and severe damage that can occur in wind turbine blades due to cohesive failure of the trailing edge. To achieve this objective, the study employs a rigorous approach, utilizing a full three-dimensional (3D) modeling strategy with finite element analysis (FEA) to simulate the behavior of wind turbine blades. The effect of cohesive materials and layered simulation methods on the thermal residual stress and crack propagation is thoroughly investigated. In particular, the study assesses the influence of carbon fiber-reinforced polymer (CFRP) and glass fiber-reinforced polymer (GFRP) materials on the phenomenon under consideration. In addition, the study undertakes a comprehensive parametric analysis to identify the independent effects of material properties and numerical simulation on thermal residual stress. Moreover, the research explores the behavior of the cohesive zone model in terms of thermal residual stress and crack propagation. The findings of this study have significant implications for researchers and practitioners in the wind energy industry. The study’s outcomes can aid in the development of improved materials and simulation techniques to mitigate thermal residual stress and prevent the occurrence of tunneling cracking and other types of damage in wind turbine blades. As such, this research contributes to the broader efforts to advance the reliability, efficiency, and sustainability of wind energy generation.

Early stage damage detection of wind turbine blades based on UAV images and deep learning

In response to the shortcomings of existing image detection algorithms in the early damage detection of wind turbine blades, such as insufficient applicability and unsatisfactory detection results, this paper proposes an improved DINO (DETR with improved denoizing anchor boxes for end-to-end object detection) model for wind turbine blade damage detection called WTB-DINO. The improvement strategy of the DINO model is obtained by collecting and analyzing unmanned aerial vehicle (UAV) daily inspection image data in wind farms. First, the lightweight design of DINO's feature extraction backbone is implemented to meet the requirement of fast and effective video inspection by drones. Based on this, the Focus down-sampling and enhanced channel attention mechanism are incorporated into the model to enhance the feature extraction ability of the Backbone for damaged areas according to the characteristics of wind turbine blade images. Second, a parallel encoder structure is built, and a multi-head attention mechanism is used to model the relationship between samples for each type of damage with uneven distribution in the dataset to improve the feature modeling effect of the model for less-sample damage categories. Experimental results show that the WTB-DINO model achieves a detection precision and recall rate of up to 93.2% and 93.6% for wind turbine blade damage, respectively, while maintaining a high frame rate of 27 frames per second. Therefore, the proposed WTB-DINO model can accurately and in real-time classify and locate damaged areas in wind turbine blade images obtained by UAVs.

Research on Wind Turbine Blade Damage Fault Diagnosis Based on GH Bladed

With the increasing installed capacity of wind turbines, ensuring the safe operation of wind turbines is of great significance. However, the failure of wind turbines is still a severe problem, especially as blade damage can cause serious harm. To detect blade damage in time and prevent the accumulation of microdamage of blades evolving into severe injury, a damage dataset based on GH Bladed simulation of blade damage is proposed. Then, based on the wavelet packet analysis theory method, the MATLAB software can automatically analyze and extract the energy characteristics of the signal to identify the damage. Finally, the GH Bladed simulation software and MATLAB software are combined for fault diagnosis analysis. The results show that the proposed method based on GH Bladed to simulate blade damage and wavelet packet analysis can extract damage characteristics and identify single-unit damage, multiple-unit damage, and different degrees of damage. This method can quickly and effectively judge the damage to wind turbine blades; it provides a basis for further research on wind turbine blade damage fault diagnosis.

WT-YOLOX: An Efficient Detection Algorithm for Wind Turbine Blade Damage Based on YOLOX

Wind turbine blades will suffer various surface damages due to their operating environment and high-speed rotation. Accurate identification in the early stage of damage formation is crucial. The damage detection of wind turbine blades is a primarily manual operation, which has problems such as high cost, low efficiency, intense subjectivity, and high risk. The rise of deep learning provides a new method for detecting wind turbine blade damage. However, in detecting wind turbine blade damage in general network models, there will be an insufficient fusion of multiscale small target features. This paper proposes a lightweight cascaded feature fusion neural network model based on YOLOX. Firstly, the lightweight area of the backbone feature extraction network concerning the RepVGG network structure is enhanced, improving the model’s inference speed. Second, a cascaded feature fusion module is designed to cascade and interactively fuse multilevel features to enhance the small target area features and the model’s feature perception capabilities for multiscale target damage. The focal loss is introduced in the post-processing stage to enhance the network’s ability to learn complex positive sample damages. The detection accuracy of the improved algorithm is increased by 2.95%, the mAP can reach 94.29% in the self-made dataset, and the recall rate and detection speed are slightly improved. The experimental results show that the algorithm can autonomously learn the blade damage features from the wind turbine blade images collected in the actual scene, achieve the automatic detection, location, and classification of wind turbine blade damage, and promote the detection of wind turbine blade damage towards automation, rapidity, and low-cost development.

Wind turbine blade damage aerodynamic profile analysis and its repair techniques

With the rapid maintenance cost increase of wind turbine blades, aerodynamic repairing principle can be a supplement to the structural repairing principle, which not only protects the blades from structural damage, but also meets the requirement of power generation efficiency. In this paper, the two-dimensional multi-scale flow field analysis method was employed to investigate the aerodynamic performance of the wind turbine blades damage and its corresponding repair techniques. Repairing principle for airfoil defects on the outer surface of the blade are given according to the blade’s extended position. Firstly, the aerodynamic profile maintenance theory of wind turbine blades is introduced. Then, numerical simulation is performed for the pressure surface and suction surface of 45.3 shape blade damage. Corresponding repair principles are presented. Further, the generality of aerodynamic repairing principle is verified by the numerical simulation on 56.5 shape blade. Finally, the relevant case of Haiyuan Wind Power Station in Ningxia shows that the proposed aerodynamic repairing principle can effectively improve the power generation efficiency in practice.

Quantitative detection of multiple damages in wind turbine blade based on the operating deflection shape and natural frequencies

Structural damage detection based on vibration signals has gained significant attention from researchers due to its ease of implementation. However, while the detection of damage using natural frequencies and mode shapes is effective for static structures, it is not directly applicable to structures in operation. To address this limitation, a two-stage multi-damage detection method has been developed to quantitatively detect damage in wind turbine (WT) blades during operation. This method utilizes the operating deflection shape (ODS) and random forest (RF) techniques. In the first stage, a two-dimensional (2D) wavelet transform is employed to decompose the ODS of the WT blade and reveal the multi-damage locations represented by the singularity points in the third detailed map. In the second stage, the finite element method (FEM) is applied to establish relationships between the natural frequencies and damage severities at fixed damage locations of the blade. This relationships form a natural frequency database, which is then used in conjunction with the RF algorithm to search for the damage severity when the natural frequency of a damaged blade is known. To verify the performance of the proposed two-stage multi-damage detection method, simulations of WT blades with two or three damages were performed. In addition, experimental tests were conducted using a laser scanning vibrometer to measure the ODS and natural frequencies of small WT blades in the two damage conditions. Both the numerical simulations and experimental investigations demonstrate that the proposed method can achieve acceptable damage-detection precision.

Operational Wind Turbine Blade Damage Evaluation Based on 10-min SCADA and 1 Hz Data

This work aims to propose a method enabling the evaluation of wind turbine blade damage and fatigue related to a 1 Hz wind speed signal applied to a large period and based on standard 10-min SCADA data. Previous studies emphasize the need for sampling with a 1 Hz frequency when carrying out blade damage computation. However, such methods cannot be applied to evaluate the damage for a long period of time due to the complexity of computation and data availability. Moreover, 1 Hz SCADA data are not commonly used in the wind farm industry because they require a large data storage capacity. Applying such an approach, which is based on a 1 Hz wind speed signal, to current wind farms is not a trivial pursuit. The present work investigates the possibility of overcoming the preceding issues by estimating the equivalent 1 Hz wind speed damage over a 10-min period characterized by SCADA data in terms of measured mean wind speed and turbulence intensity. Then, a discussion is carried out regarding a method to estimate the uncertainty of the simulation, in a bid to come up with a tool facilitating decision-making by the operator. A statistical analysis of the damage assessed for different wind turbines is thus proposed to determine which one has sustained the most damage. Finally, the probability of reaching a critical damage level over time is then proposed, allowing the operator to optimize the operating and maintenance schedule.

Review on the Damage and Fault Diagnosis of Wind Turbine Blades in the Germination Stage

In recent years, wind turbines have shown a maximization trend. However, most of the wind turbine blades operate in areas with a relatively poor natural environment. The stability, safety, and reliability of blade operation are facing many challenges. Therefore, it is of great significance to monitor the structural health of wind turbine blades to avoid the failure of wind turbine outages and reduce maintenance costs. This paper reviews the commonly observed types of damage and damage detection methods of wind turbine blades. First of all, a comprehensive summary of the common embryonic damage, leading edge erosion, micro-cracking, fiber defects, and coating defects damage. Secondly, three fault diagnosis methods of wind turbine blades, including nondestructive testing (NDT), supervisory control and data acquisition (SCADA), and vibration signal-based fault diagnosis, are introduced. The working principles, advantages, disadvantages, and development status of nondestructive testing methods are analyzed and summarized. Finally, the future development trend of wind turbine blade detection and diagnosis technology is discussed. This paper can guide the use of technical means in the actual detection of wind turbine blades. In addition, the research prospect of fault diagnosis technology can be understood.

Research on Wind Turbine Blade Surface Damage Identification Based on Improved Convolution Neural Network

Wind turbine blades are easily affected by the working environment and often show damage features such as cracks and surface shedding. An improved convolution neural network, ED Net, is proposed to identify their damage features. An EAC block based on the improved asymmetric convolution is introduced which strengthens the feature extraction during convolution. A DPCI_SC block, which is improved based on the attention module, is embedded to enhance the ability to obtain spatial location information of the damage. GELU is used as the activation function. The loss function is smoothed and labeled during training. Finally, three sets of experiments were conducted. Experiment 1 confirmed the efficacy of the ED Net for identifying damaged wind turbine blades. Experiment 2 confirmed the efficacy of the relevant improvements proposed in this work. Experiment 3 compares the recognition of wind turbine blade damage by commonly used lightweight networks and shows that the ED Net model proposed has a better performance with an accuracy range of 99.12% to 99.23% and a recall of 99.23%

Research on infrared nondestructive detection of small wind turbine blades

To obtain the optimal light conditions for field infrared nondestructive detection of wind turbine blades, this paper used a 2kw small wind turbine blade with different damage types and degrees of damage as the research object. Using the passive infrared thermal imaging detection method, the damage of the wind turbine blade was naturally stimulated under outdoor conditions with enough light in summer to collect infrared thermal images, and the numerical simulation of the damage was performed. The experimental and simulation results show that light intensity has a large influence on damage detection, and the three typical damage of the best detection conditions are obtained. Among them, the light intensity of a foreign body attached reaches 950 W/m2 or higher for the best detection effect, while facial wear and crack damage were best detected at a light intensity of around 1000 W/m2 in the sunny noon. The simulation results agree well with the experimental results when using COMSOL multiple physical field coupling software for wear and crack damage scene reconstruction of finite element simulation, proving that the use of solar radiation as a source of passive infrared thermal imaging detection technology to detect wind turbine blade damage within a certain range of light intensity is feasible. Meanwhile, the numerical model was used to thermodynamically couple the wear-damaged blade, yielding a positive linear relationship between light intensity and the blade's highest temperature, stress, and strain. Furthermore, the degree of wear damage and the stress-strain corresponding to the highest temperature of the blade are both positively linear.

Review of the Typical Damage and Damage-Detection Methods of Large Wind Turbine Blades

With global warming and the depletion of fossil energy sources, renewable energy is gradually replacing non-renewable energy as the main energy in the future. As one of the fastest growing renewable energy sources, the safety and reliability of wind energy have been paid more and more attention. The size of modern wind turbines is becoming larger and larger. As the main component of wind turbines to capture energy, the blade is often damaged by various complex environments and irregular loads. Therefore, the health monitoring and damage identification of wind turbine blades have become a main research focus. At present, in addition to the overview of various detection methods of wind turbine blades, there is a lack of comprehensive classifications and overviews of the main damage types, damage-generation mechanisms, and basic principles of the damage-detection technology of wind turbine blades. In this paper, firstly, the common fault types of wind turbine blades, such as trailing edge cracking, lightning strike, leading edge corrosion pollution, icing, and delamination, as well as their generation mechanism, are comprehensively analyzed. Then, the basic principles and the latest research progress of the current main detection technologies, such as vision, ultrasonic, thermal imaging, vibration, acoustic emission, and so on, are comprehensively reviewed. The advantages and limitations of the various detection technologies for practical application are summarized. Finally, through a comparative analysis of the various damage-detection technologies, we try to find potential future research directions, and draw conclusions. This paper will provide a reference for understanding the mechanism behind the main damage types and the damage-detection methods of wind turbine blades. It has important reference value for further promoting practical research of wind turbine blade damage-detection technology and grasping this research direction.