Blade Fault Research Articles

Fault Diagnosis Method for Imbalanced Samples of Blade Fracture in Large Petrochemical Fan

Abstract The mechanism analysis of the sudden change in load inertia caused by the failure of large petrochemical fan blades is unclear, which makes it difficult to diagnose imbalanced samples faults based on data-driven methods and has the problem of poor interpretability. Based on this issue, a fault diagnosis method for imbalanced samples of broken blades in large petrochemical fan under sudden changes in load inertia is proposed. This method firstly establishes a failure mechanism model for large petrochemical fan blades, revealing the physical characteristics between inertia, torque and speed under sudden changes in load inertia. Secondly, based on the failure mechanism model, the fault characteristics of broken blades in petrochemical fan are extracted to solve the problem of difficult feature extraction of fault samples in imbalanced samples. Finally, a data-driven diagnostic model was constructed under the constraint of sudden changes in load inertia to improve the interpretability of fault diagnosis for large petrochemical fan with broken blades. The experiment shows that the proposed method significantly improves the diagnostic accuracy and effectiveness for detecting faults in broken blades of petrochemical fans, achieving a fault diagnosis accuracy of 99.03%.

A Spectral-Based Blade Fault Detection in Shot Blast Machines with XGBoost and Feature Importance

The optimal functionality and dependability of mechanical systems are important for the sustained productivity and operational reliability of industrial machinery, and have a direct impact on its longevity and profitability. Therefore, the failure of a mechanical system or any of its components would be detrimental to production continuity and availability. Consequently, this study proposes a robust diagnostic framework for analyzing the blade conditions of shot blast industrial machinery. The framework explores the spectral characteristics of the vibration signals generated by the industrial shot blast for discriminative feature excitement. Furthermore, a peak detection algorithm is introduced to identify and extract the unique features present in the peak magnitudes of each signal spectrum. A feature importance algorithm is then deployed as the feature selection tool, and these selected features are fed into ten machine learning classifiers (MLCs), with extreme gradient boosting (XGBoost (version 2.1.1)) as the core classifier. The results show that the XGBoost classifier achieved the best accuracy of 98.05%, with a cost-efficient computational cost of 0.83 s. Other global assessment metrics were also implemented in the study to further validate the model.

Fault Diagnosis of Wind Turbine Blades with Continuous Wavelet Transform based Deep Learning Model Using Vibration Signal

Wind Turbines are the most crucial devices in wind energy conversion systems to increase energy generation efficiency from wind sources. Blade failure in wind turbines is due to the induced vibrations of change in ecological variables. It is necessary to periodically inspect the state of the wind turbine blades to enhance safety by decreasing downtime, lessening the likelihood of unplanned failures requiring extensive repair, and progressively increasing power generation with reduced logistical costs. The primary goal of the proposed research is to adopt a hybrid strategy that combines convolutional neural network models and continuous wavelet transform. The bump wavelet-based continuous wavelet transform with a convolutional neural network model is employed to classify the faulty wind turbine blades based on the extracted vibration signals of turbine blades. This approach distinguishes between different states of blade faults affecting wind turbine blades during operational phases. The research considers blade faults in the horizontal axis wind turbine, including blade bending, erosion, and the connection looseness between the hub and blade. The cross-validation and hold-out methods are used to validate the classification accuracy and are compared with other existing popular methods. The hold-out method has a better classification accuracy of 97.916%.

A Novel Proposal in Wind Turbine Blade Failure Detection: An Integrated Approach to Energy Efficiency and Sustainability

This paper presents a novel methodology for detecting faults in wind turbine blades using computational learning techniques. The study evaluates two models: the first employs logistic regression, which outperformed neural networks, decision trees, and the naive Bayes method, demonstrating its effectiveness in identifying fault-related patterns. The second model leverages clustering and achieves superior performance in terms of precision and data segmentation. The results indicate that clustering may better capture the underlying data characteristics compared to supervised methods. The proposed methodology offers a new approach to early fault detection in wind turbine blades, highlighting the potential of integrating different computational learning techniques to enhance system reliability. The use of accessible tools like Orange Data Mining underscores the practical application of these advanced solutions within the wind energy sector. Future work will focus on combining these methods to improve detection accuracy further and extend the application of these techniques to other critical components in energy infrastructure.

Wind Turbine Blade Fault Diagnosis: Approximate Entropy as a Tool to Detect Erosion and Mass Imbalance

Wind energy is a clean, sustainable, and renewable source. It is receiving a large amount of attention from governments and energy companies worldwide as it plays a significant role as an alternative source of energy in reducing carbon emissions. However, due to long-term operation in reduced and difficult weather conditions, wind turbine blades are always seriously damaged. Hence, damage detection in blade structure is essential to evaluate its operational condition and ensure its structural integrity and safety. We aim to use fractal, entropy, and chaos concepts as descriptors for the diagnosis of wind turbine blade condition. They are, respectively, estimated by the correlation dimension, approximate entropy, and the Lyapunov exponent. Formal statistical tests are performed to check how they are different across wind turbine blade conditions. The experimental results follow. First, the correlation dimension is not able to distinguish between all conditions of wind turbine blades. Second, approximate entropy is suitable to distinguish between healthy and erosion conditions and between healthy and mass imbalance conditions. Third, chaos is not a discriminative feature to distinguish between wind turbine blade conditions. Fourth, wind turbine blades with either erosion or mass imbalance exhibit less irregularity in their respective signals than healthy wind turbine blades.

Identification and Localization of Wind Turbine Blade Faults Using Deep Learning

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

Wind turbine blade fault diagnosis technology based on Efficient-YOLOv5s algorithm

Abstract The daily operation and maintenance of wind turbine blades in wind power plants requires the application of target detection algorithms that are both accurate in detection and fast in training. For the current wind turbine blade fault detection algorithms in the dataset when the number of samples of the problem of slow training time through the bi-directional feature pyramid network of the fast weighted normalised fusion to improve the training speed, for the small size of the fault detection of the low accuracy of the problem through the bi-directional feature pyramid network of the better use of multiscale information to improve the detection accuracy and through the coordinate attention to generate bidirectional complementary feature maps to enhance the object of interest to further improve the accuracy of detection. In this way, an efficient wind turbine blade fault detection model (Efficent-YOLOv5s) is proposed on the basis of the YOLOv5s model. Through the experimental validation of the homemade dataset, the results show that compared with the YOLOv5s model, the detection map0.5 value and accuracy of the efficient wind turbine blade fault detection model are improved by 0.5% and 0.6%, respectively, and the average training time is shortened by 4s/epoch, which verifies that the model is effective.

Blade imbalance fault identification in doubly fed induction generator through current signature analysis using wavelet transform

Using wind turbines (WTs) equipped with doubly fed induction generators (DFIG) is a popular technology for generating renewable energy. To ensure safe operation, prompt maintenance, and better operational reliability, the induction generator used in wind energy must be monitored. In this paper, an analysis is carried out on stator currents of the DFIG machine in a wind farm to identify any blade imbalances in the wind farm. A fault characteristics extraction analysis is carried out on the machine stator currents to detect the fault in the system. Firstly, the mathematical equation of the DFIG blade unbalanced stator current is generated using the DFIG model. Secondly, Park's Transformation is used to modify the stator's 3-phase current. Further, by evaluating the feature frequency amplitude variation in the squared signal by doing a spectral analysis on the stator current vector's squared signal. Lastly, a Simulink model for the DFIG is developed. The suggested approach analyses the fault signal of the imbalanced blade fault at various wind velocities. The outcomes show that the suggested method for diagnosing impeller imbalance faults can successfully locate the fault.

Parameter identification based on iterative signal space in blade tip timing

Blade tip timing (BTT), as an effective non-contact measurement technology, is widely used for health monitoring of rotating blades. Due to the installed number of probes is limited by the engine structure, the requirement of BTT sampling frequency is difficult to meet the Nyquist sampling theorem, which leads the BTT signal is severely under-sampled. Therefore, it is difficult to extract vibration parameters, such as frequency, amplitude. Many algorithms was proposed to solve the undersampling problem. In this paper, a new BTT signal processing algorithm is proposed based iterative signal space, which expands individual data into subspace level data geometrically. Compared to some previous methods, the iterative signal space algorithm can identify the blade vibration parameters more accurately, which is verified in both numerical simulation and experiment. Furthermore, different degrees of noise is used to show the feasibility and robustness. The results are very significant for online blade fault diagnosis and health monitoring of turbines.

Advanced wind turbine blade inspection with hyperspectral imaging and 3D convolutional neural networks for damage detection

In the context of global efforts to mitigate climate change by pursuing sustainable energy sources, wind energy has emerged as a critical contributor. However, the wind energy industry faces substantial challenges in maintaining and preserving the integrity of wind turbine blades. Timely and accurate detection and classification of blade faults, encompassing issues such as cracks, erosion, and ice buildup, are imperative to uphold wind turbines' ongoing efficiency and safety. This study introduces an inventive approach that amalgamates hyperspectral imaging and 3D Convolutional Neural Networks (CNNs) to augment the precision and efficiency of wind turbine blade fault detection and classification. Hyperspectral imaging is harnessed to capture comprehensive spectral information from blade surfaces, facilitating exact fault identification. The process is streamlined through Incremental Principal Component Analysis (IPCA), reducing data dimensions while maintaining integrity. The 3D CNN model demonstrates remarkable performance, achieving high accuracy in detecting all fault categories in full-band hyperspectral images. The model retains high accuracy even with dimensionality reduction to 20 spectral bands. The reduced processing time of the 20-band image enhances the practicality of real-world applications, thereby reducing downtime and maintenance expenditures. This research represents a significant advancement in wind turbine blade inspection, contributing to the sustainability and dependability of wind energy systems and furthering the cause of a cleaner and more sustainable energy future as part of the broader fight against climate change.

A novel transformer-enhanced and acoustic-based approach for wind turbine blade fault detection with integrated system implementation

Rising global wind power capacity urgently requires effective real-time turbine monitoring. Complex installations, high maintenance costs, and the occasional need for turbine shutdown hinder conventional monitoring methods. Acoustic-based techniques, while cost-efficient for health assessments, currently face challenges with detection precision and signal processing capabilities in complex acoustic environments. To overcome these challenges, this study proposes a low-cost, AI-driven acoustic-based health monitoring system framework for wind turbine blades, featuring enhanced detection accuracy and signal processing capabilities in complex sound environments. Firstly, a microphone array is employed to capture blade sounds with rich spatial attributes, while beamforming algorithms with a fixed orientation integrate prior spatial information. Furthermore, to further strengthen signal processing and fault detection capabilities, the Transformer model based on self-attention mechanisms is employed for feature extraction and fault diagnosis. An actual wind turbine blade health monitoring system is designed and developed to validate the usability of the proposed framework. Experimental results based on a scaled-down wind turbine model validate the proposed algorithm's effectiveness and practicality, presenting an effective approach in the wind turbine blade health monitoring domain.

Fault diagnosis of mine main ventilator based on multi-eigenvalue selection and data fusion

As a strong nonlinear complex system, the mine main ventilator is difficult to select eigenvalues of the ventilator fault. This study proposed a multiple eigenvalue selection method based on ensemble empirical modal decomposition (EEMD). Firstly, an experimental platform of axial flow fan was built to simulate the bearing fault and fan blade fault. Secondly, the vibration and wind pressure data of the above three faults and the normal state were collected, and the vibration signals were decomposed by EEMD. The normalized Root Mean Square Error was used to evaluate the signal separation degree of different faults under the same eigenvalue and to select the eigenvalue. Then, combined with wind pressure information, multi-data information fusion was used to construct the failure indicator vector table. Finally, the BP neural network was trained and tested with a vector table, and the fault diagnosis of the mine main ventilator was achieved. The experiment results showed that the diagnostic accuracy of test results was 98.87% after eigenvalue selection and data fusion. The method has high accuracy and adaptability, and is very suitable for mechanical equipment such as mine ventilator.

Fault Diagnosis of Wind Turbine Blades Based on Image Fusion and ResNet

In the diagnosis of wind turbine blade faults, the information provided by a single sensor is limited. To address this issue and take advantage of complementary features among multiple fault information sources, while enhancing fault diagnosis accuracy, a method for diagnosing wind turbine blade faults is proposed. This method combines Image Fusion Convolutional Neural Network (IFCNN) with the ResNet network. Firstly, the time-frequency representation of vibration data is obtained using wavelet transform. The time-frequency representation and blade fault images are input into the IFCNN to obtain fused images containing two categories of fault features. Next, the ResNet convolutional neural network is employed to automatically extract non-linear features from the fused images, establishing a classification model for blade fault images. Experimental results demonstrate that, with limited training data, the classification accuracy of this method can reach 86.7%, outperforming fault diagnosis models trained with single fault information. This approach offers a new perspective and method for the fusion of multiple fault information in the field of wind turbine blade fault diagnosis

Fault Diagnosis of Wind Turbine Bolts based on ICEEMD-SSA-SVM Model

Background: Compared with traditional power generation systems, wind turbines have more units and work in a more harsh environment, and thus have a relatively high failure rate. Among blade faults, the faults of high-strength bolts are often difficult to detect and need to be analyzed with high-precision sensors and other equipment. However, there is still little research on blade faults. Methods: The improved complete ensemble empirical mode decomposition (ICEEMD) model is used to extract the fault features from the time series data, and then combined with the support vector machine optimized by sparrow search algorithm (SSA-SVM) to diagnose the bolt faults of different degrees, so as to achieve the purpose of early warning. Results: The results show that the ICEEMD model used in this paper can extract the bolt fault signals well, and the SSA-SVM model has a shorter optimization time and more accurate classification compared with models such as PSO-SVM. Conclusion: The hybrid model proposed in this paper is important for bolt fault diagnosis of operation monitoring class.

Anomaly Detection on Small Wind Turbine Blades Using Deep Learning Algorithms

Wind turbine blade maintenance is expensive, dangerous, time-consuming, and prone to misdiagnosis. A potential solution to aid preventative maintenance is using deep learning and drones for inspection and early fault detection. In this research, five base deep learning architectures are investigated for anomaly detection on wind turbine blades, including Xception, Resnet-50, AlexNet, and VGG-19, along with a custom convolutional neural network. For further analysis, transfer learning approaches were also proposed and developed, utilizing these architectures as the feature extraction layers. In order to investigate model performance, a new dataset containing 6000 RGB images was created, making use of indoor and outdoor images of a small wind turbine with healthy and damaged blades. Each model was tuned using different layers, image augmentations, and hyperparameter tuning to achieve optimal performance. The results showed that the proposed Transfer Xception outperformed other architectures by attaining 99.92% accuracy on the test data of this dataset. Furthermore, the performance of the investigated models was compared on a dataset containing faulty and healthy images of large-scale wind turbine blades. In this case, our results indicated that the best-performing model was also the proposed Transfer Xception, which achieved 100% accuracy on the test data. These accuracies show promising results in the adoption of machine learning for wind turbine blade fault identification.

Simulation and experimental research on vibration response of microcracked compressor blades under variable working conditions

Compressor blades play a crucial role in aero-engines, experiencing complex alternating loads under variable working conditions (VWC). Resonance is inevitable under these conditions, leading to the development of blade crack faults. To understand and analyze this phenomenon, a finite element (FE) model of a microcracked blade was created using ANSYS. The model's accuracy was verified through a hammering experiment. Additionally, a resonance fatigue test was used to accurately obtain dynamic characteristics for prefabricated breathing cracks. The experiment demonstrated that cracked blades exhibit smaller responses in the time domain compared to intact blades, while showing super-harmonics in the frequency domain, thus validating the effectiveness of numerical simulation. The effects of VWC on the nonlinear vibration characteristics (VC) of the blade with a breathing microcrack were investigated. These VWC included variable speed, the amplitude of the exciting force (F0), depth of the microcrack (D), and length of the microcrack (L). The results revealed significant increases in the frequency domain response amplitude of the blade at super-harmonics with the increase of F0, D, and L at variable speeds. Furthermore, the breathing behavior of microcracked blades diminished with increasing rotating speed (N), D, and L. The observed decrease in frequency and the emergence of super-harmonic serves as indicators of the presence and severity of blade cracks. These findings are of great significance for the development of online monitoring technology for blade faults.

A methodological approach for detecting multiple faults in wind turbine blades based on vibration signals and machine learning

Abstract Wind turbines generate clean and renewable energy for the international market. The most ‎‎important aspect of wind turbine maintenance is reducing failures, downtime, and operating and maintenance expenses. ‎This study aims to detect multiple faults exhibited by wind turbine blades; failures such as cracks (tip crack, mid-span crack, and crack ‎near the root) were observed in the blades at different locations. The research suggests a new approach, incorporating vibration signals and machine learning techniques to identify various failures in wind turbine blades. The technology of ranking features such as ReliefF algorithms, chi-squares, and information gains was adopted to discuss a method framework to diagnose several problems in wind turbine blades, such as cracks in different locations. The k-nearest neighbors (KNNs), support vector machines, and random forests are used to classify data based on measured vibration signals. The eight main time-domain features are calculated from the vibration signals. The proposed methodology was validated using four databases. The results showed good classification accuracy in four databases, with at least three non-conventional features in each database’s top nine features of the three classification techniques. The results also showed that when the ReliefF selection algorithm is applied with the KNN classification algorithm, it generates the highest classification accuracy under all failure conditions, and the value is 97%. Finally, the performance of the proposed classification model is compared with other machine learning classification models, and a promising result is obtained. ‎

In Situ Structural Health Monitoring of Full-Scale Wind Turbine Blades in Operation Based on Stereo Digital Image Correlation

Structural health monitoring (SHM) and the operational condition assessment of blades are greatly important for the operation of wind turbines that are at a high risk of disease in service for more than 5 years. Since certain types of blade faults only occur during wind turbine operation, it is more significant to perform in situ SHM of rotating full-scale blades than existing SHM of small-scale blades or static testing of full-scale blades. Considering that these blades are usually not prefabricated with relevant sensors, this study performed SHM and condition assessment of full-scale blades in operation with stereo digital image correlation. A self-calibration method adapted to the outdoors with a large field of view was introduced based on the speckled patterns. To accurately obtain the in- and off-plane deformation, a new reference frame is constructed at the center of the rotation of the blades. The 3D displacements of the points of interest (POIs) on the blade of a 2 MW wind turbine were characterized. Furthermore, the frequency spectrum of the measured 3D displacements of the blades was compared with the blades with the faults. The results showed that the introduced technique is a convenient and nondestructive technique that enables SHM of full-scale wind turbine blades in operation.

Transfer learning-based fault detection in wind turbine blades using radar plots and deep learning models

ABSTRACT Faults in wind turbine blades are considered a critical issue that can affect the safety and performance of wind turbines. The proposed research aimed to monitor wind turbine blades and identify fault conditions using a transfer learning approach. The study utilized one good and four faulty blade conditions: bend, hub-blade loose connection, erosion, and pitch angle twist. Vibration signals for each blade condition were collected and converted as radar plots that were fed and analyzed using pre-trained deep learning models including ResNet-50, AlexNet, VGG-16, and GoogleNet. Hyperparameters including optimizer, train-test split ratio, batch size, epochs, and learning rate were examined to determine the optimal configuration for each network. The study’s core findings indicate that ResNet-50 outperformed all other models, achieving an impressive accuracy rate of 99.00%. The other models achieved lower accuracy rates, with AlexNet achieving 96.70%, GoogleNet achieving 97.00%, and VGG-16 achieving 95.00%. These findings highlight the potential of using deep learning models for wind turbine monitoring and fault detection, which could significantly improve the efficiency and reliability of wind turbines.

Study on blade fault diagnosis of free flying UAV based on multiparameter and deep learning method

With the widespread application of UAV (UAV) in various fields, more and more attention has been paid to the operation status monitoring and fault diagnosis of UAV. During the use of UAV, the motors, blades, connectors and other components may inevitably experience wear, fatigue, and breakage, which are difficult to directly monitor through sensors. Therefore, a fault identification method based on one-dimensional convolutional neural network (1D-CNN) is proposed to provide ideas for the research on the mechanical fault diagnosis of UAV. A Bluetooth wireless acceleration-attitude sensor is used to collect the acceleration, angular velocity and angle of the free flying UAV in X, Y, and Z directions. With these characteristic parameters as sample data, fault identification can be implemented using deep learning model. Besides, to deal with over-fitting, a data reconstruction method of partition sampling is proposed. By comparing different input parameters and optimization functions, we found that when using multi-parameter + RMSProp optimization, the recognition accuracy reaches 98%. In addition, a comparative analysis is carried out using shallow neural network PNN and SVM methods, and the results show that the proposed 1D-CNN model outperforms both shallow neural networks and traditional machine learning methods.