Wind Turbine Fault Detection Research Articles

Wind turbine fault detection and identification via self-attention-based dynamic graph representation learning and variable-level normalizing flow

Effective wind turbine (WT) condition monitoring is significant to improve wind power generation efficiency and reduce operation and maintenance costs. Supervisory control and data acquisition (SCADA) data are widely utilized for WT condition monitoring due to their low cost and accessibility. However, the intricate interdependencies among SCADA variables affect the accuracy of WT fault detection, and few methods provide identification for the anomaly cause. To solve these issues, this paper proposes an unsupervised fault detection and identification method based on self-attention-based dynamic graph representation learning and variable-level normalizing flow. Firstly, a dynamic graph representation learning model based on spatial and temporal self-attention mechanisms is proposed. It can effectively learn the dynamic and mutual relations among variables for early fault detection. Secondly, a variable-level normalizing flow is proposed for discriminative density estimation of variables, which can realize component fault localization. Finally, a node deviation index based on contrast graph is proposed to identify the root cause of anomalies. Experimental results using WT data from a wind farm in Northwest China prove that the proposed method has better accuracy and interpretability in WT fault detection and identification, which displays better effectiveness in practical wind energy applications.

Research on Wind Turbine Fault Detection Based on CNN-LSTM

With the wide application of wind energy as a clean energy source, to cope with the challenge of increasing maintenance difficulty brought about by the development of large-scale wind power equipment, it is crucial to monitor the operating status of wind turbines in real time and accurately identify the specific location of faults. In this study, a CNN-LSTM-based wind motor fault detection model is constructed for four types of typical faults, namely gearbox faults, electrical faults, yaw faults, and pitch faults of wind motors, combining CNN’s advantages of excelling in feature extraction and LSTM’s advantages of dealing with long-time sequence data, to achieve the simultaneous detection of multiple fault types. The accuracy of the CNN-LSTM-based wind turbine fault detection model reaches 90.06%, and optimal results are achieved for the effective discovery of yaw system faults, pitch system faults, and gearbox faults, obtaining 94.09%, 96.46%, and 97.39%, respectively. The CNN-LSTM wind turbine fault detection model proposed in this study improves the fault detection effect, avoids the further deterioration of faults, provides direction for preventive maintenance, reduces downtime loss due to restorative maintenance, and is essential for the sustainable use of wind turbines and maintenance of wind turbine service life, which helps to improve the operation and maintenance level of wind farms.

A self-supervised learning method for fault detection of wind turbines

Abstract As promising solutions to condition-based maintenance of wind turbines, artificial intelligence-based techniques have drawn extensive attention in the era of industry 4.0. However, accurate fault detection is still challenging owing to volatile operating conditions in real-world settings. To handle this problem, a novel method is proposed for fault detection of wind turbines. Specifically, a data augmentation scheme is developed to simulate the effects of time-varying environments and noise. Then, a self-supervised proxy task of variant prediction is designed and conducted. In this way, valid data representations can be extracted to represent the health status of wind turbines. Additionally, the compactness of data representations is guaranteed by the directional evolution, which can relieve the confusion of health conditions. The effectiveness of the proposed method is verified with actual measurements. Using the proposed method, several faults can be detected more than 10 d earlier, and blade breakage can be identified more than 22 h earlier. Furthermore, the developed method outperforms several benchmark approaches.

Retraction Note: Fault classification and detection in wind turbine using Cuckoo-optimized support vector machine

Retraction Note: Fault classification and detection in wind turbine using Cuckoo-optimized support vector machine

A Review of Machine Learning

The ever-growing complexity of engineering systems and the vast amount of data generated necessitate advanced data analysis techniques like machine learning (ML). This review explores the motivations and advantages of integrating ML into real-world engineering applications. The paper highlights the limitations of traditional deterministic models in handling intricate interactions within modern engineering systems. ML offers significant benefits including improved efficiency, enhanced decision-making, advanced automation and control, adaptability, and cost savings. Real-world applications across various disciplines are explored, including image recognition and computer vision in self-driving cars, predictive maintenance for optimizing equipment lifespans, structural health monitoring for identifying potential damage, and signal processing for control systems in airplanes and traffic lights. The review concludes by summarizing key findings from case studies on autonomous vehicle navigation, smart grid optimization, wind turbine fault detection, and HVAC system optimization in smart buildings. These case studies showcase the power of machine learning techniques like deep learning, reinforcement learning, sensor fusion, and ensemble learning in achieving superior performance and efficiency in various engineering domains. Key Words: Machine Learning, Engineering Applications, Artificial Intelligence, Big Data, Predictive Maintenance, Robotics, Structural Design, Smart Grids, Fault Detection, Optimization, Control Systems.

Multiple faults detection in doubly-fed induction generator wind turbine using artificial neural network

The development of fault detection methods in wind turbine (WT), especially for single fault detection, is continuously increasing. However, the rapid growth of fault detection in WT leads to another challenge where multiple faults can occur. The single fault detection method in WT is no longer reliable, especially when multiple faults occur simultaneously. Therefore, multiple faults detection in doubly-fed induction generators (DFIG) WT was proposed using an artificial neural networks (ANN) model. These multiple faults include internal and external stator faults happening simultaneously. Internal stator faults cover inter-turn short circuit faults and open circuit faults, while external stator faults cover loss of excitation and external short circuit faults. The performance of the developed multiple faults detection model was measured using accuracy and the root mean square error (RMSE) value. The results show that the developed model performs well with high accuracy and a low RMSE value. Thus, the developed model can accurately detect the coexistence of multiple faults in DFIG WT.

Recursive demodulated synchro spline-kernelled chirplet extracting transform: a useful tool for non-linear behavior estimation of non-stationary signal and application to wind turbine fault detection

Non-linear behavior is widespread in many kinds of signals from nature and engineering fields. Although the high energy-concentration level of various advanced time-frequency (TF) analysis (TFA) techniques currently developed ensure a fine representation of non-linear behavior of time-varying component (TVC) of the signal, it is far from sufficient to solely consider the single aspect of energy-concentration level, because the actual signal composition is always more complicated, especially for some thorny difficulties such as strong noise interference and the early weak TVC, etc., these negative factors bring significant challenges to reveal the non-linear behavior of TVC of practical signals. A new TFA method aimed at this issue, called recursive demodulated synchro spline-kernelled chirplet extracting transform (RDSSCET), is proposed in this paper. The proposed RDSSCET is developed on the frame of synchro spline-kernelled chirplet extracting transform (SSCET) and a newly designed external-internal nested double iteration mechanism, which effectively addresses the limitation of SSCET in handling multicomponent signals while also exhibiting superior high energy concentration and noise robustness. As such, the proposed RDSSCET can yield a more favorable outcome when revealing the non-linear behavior of TVC, particularly for weak TVC with strong noise interference. Comparison analysis results in numerical simulations verified the performance of RDSSCET. Its effectiveness in real applications is fully tested via two real-world sound signals and a practical case of wind turbine fault detection.

Research on fault detection and remote monitoring system of variable speed constant frequency wind turbine based on Internet of Things

In order to study the operating characteristics of variable speed constant frequency wind turbine under different working conditions and the monitoring system of wind turbine. In this paper, the simulation model of each component system of wind turbine is established by MATLAB/Simulink module, and the influence law of different wind speed and ground fault types on the output power of wind turbine is studied. The active power of wind turbines under different short-circuit fault types is compared. At the same time, in order to realize real-time monitoring of wind turbine speed and output power, an online monitoring system for wind turbine operation based on industrial Internet of Things is proposed, and the composition and operation characteristics of this remote monitoring system are given. The practical application shows that the on-line monitoring system can accurately and remotely monitor the running status of the wind turbine and avoid the unstable running of the wind turbine. The research conclusions of this paper can provide reference for the design and construction of wind turbines and the operation of connecting to the power grid.

Wind turbine fault detection based on the transformer model using SCADA data

The growth of installed wind power worldwide and its significant contribution to the energy market is mainly due to the evolution of wind turbines (WTs) and their ability to withstand a wide range of dynamic loads. WT failures can be costly and lead to extended downtime. Early detection of such failures is critical in reducing the costs associated with operation and maintenance (O&M) tasks and unscheduled shutdowns of WTs. This paper applies two Deep Learning (DL) models based on the Transformer model to predict failures in the IGBT module of WTs at an onshore wind farm in Ecuador. To this end, SCADA (Supervisory Control and Data Acquisition) operational and alarm data are used, together with the maintenance record (MR). These data are analyzed and processed, applying different feature selection methods. The results show that the two proposed models perform well, with high accuracy and an approximate prediction of 4.25 months before failure occurrence. The results are promising due to the possibility of using SCADA data for early and accurate identification of faults in different components of WTs.

Wind turbine fault detection and identification using a two-tier machine learning framework

A proactive approach is essential to optimize wind turbine maintenance and minimize downtime. By utilizing advanced data analysis techniques on the existing Supervisory Control and Data Acquisition (SCADA) system data, valuable insights can be gained into wind turbine performance without incurring high costs. This allows for early fault detection and predictive maintenance, ensuring that unscheduled or reactive maintenance is minimized and revenue loss is mitigated. In this study, data from a wind turbine SCADA system in the southeast of Ireland were collected, preprocessed, and analyzed using statistical and visualization techniques to uncover hidden patterns related to five fault types within the system. The paper introduces a conditional function designed to test two given scenarios. The first scenario employs a two-tier approach involving fault detection followed by fault identification. Initially, faulty samples are detected in the first tier and then passed to the second tier, which is trained to diagnose the specific fault type for each sample. In contrast, the second scenario involves a simpler solution referred to as naive, which treats fault types and normal cases together in the same dataset and trains a model to distinguish between normal samples and those related to specific fault types. Machine learning models, particularly robust classifiers, were tested in both scenarios. Thirteen classifiers were included, ranging from tree-based to traditional classifiers, neural networks, and ensemble learners. Additionally, an averaging feature importance technique was employed to select the most impactful features on the model decisions as a starting point. A comparison of the results reveals that the proposed two-tier approach is more accurate and less time-consuming, achieving 95% accuracy in separating faulty from normal samples and approximately 91% in diagnosing each fault type. Furthermore, ensemble learners, particularly bagging and stacking, demonstrated superior fault detection and identification performance. The performance of the classifiers was validated using t-SNE and explainable AI techniques, confirming that the impactful features align with the findings and that the proposed two-tier solution outperforms the naive solution. These results strongly indicate that the proposed solution is accurate, independent, and less complex compared to existing solutions.

Hierarchical spatial–temporal autocorrelation graph neural network for online wind turbine pitch system fault detection

The advancement of low-cost, non-manually labeled big data technologies for fault detection in wind turbines is crucial to guarantee their safe and efficient operation. In this context, Normal Behavior Modelling (NBM) is a prevalent approach. However, existing NBM methods for wind turbine fault detection inadequately utilize complex spatial–temporal correlations within the Supervisory Control and Data Acquisition (SCADA) during the normal behavior prediction stage. To cope with this limitation, this paper propose a hierarchical spatial-temporal autocorrelation graph neural network method for online wind turbine pitch system fault detection. This approach integrates a dynamic graph network with an adaptive structure for spatial correlation learning and a transformer model with autocorrelation attention to identify periodic time-distance correlations. Furthermore, a hierarchical neural network, specifically designed for wind turbine physical structure, enhances local information extraction through seven latent graph neural networks and a probsparse attention mechanism. The proposed method demonstrates significant effectiveness in real-world applications, as evidenced by data from a Shanghai wind farm.

Fault detection in wind turbines: a supervised learning approach with multilayer perceptron neural network

The expansion of energies aligning with sustainable development requirements is continually progressing. A particular focus on wind turbines (WT), characterized as a highly intricate system, has brought attention to the costs associated with operation and maintenance. This has prompted a quest for increasingly efficient maintenance procedures. This article proposes that deviations from expected behavior be detected and classified as failure using operational data from permanent magnet direct drive wind turbines, obtained through the supervisory control and data acquisition system. To achieve real-time fault detection and gather information on the state of faults, the CFS subset evaluator method was employed to extract the most relevant attributes from the dataset. Experimental results demonstrate that the strategy of selecting the most pertinent attributes for the Multilayer Perceptron algorithm (MLP), comprising four layers, in fault classification, resulted in a high recognition rate for detecting and classifying faults in wind turbines. Computational results validating the models are presented.

Wind turbine fault detection and isolation robust against data imbalance using KNN

AbstractDue to the difficulties of system modeling, nonlinearity effects, uncertainties, and the availability of Wind Turbines (WTs) SCADA system data, data‐driven Fault Detection and Isolation (FDI) methods for WTs have received increasing attention. In this paper, using the wind turbine SCADA data, an effective FDI scheme is proposed using the K‐Nearest Neighbors (KNN) classifier. The operational data set is labeled by the status and warning data sets, and the labeled operational data set, after eliminating invalid data, feature selection, and standardization, is used for training and validation of the FDI model. Data imbalance, which is common in real data sets, does not affect the performance of the proposed method, hence there is no need for data balancing methods in this algorithm and the performance is not deteriorated by occurring false alarms. Therefore, the proposed method has provided impressive performance in FDI compared with previous research on this data set. Also, many of the fault classes addressed in this paper were not considered in previous works on this data set.

Conditional monitoring and fault detection of wind turbines based on Kolmogorov–Smirnov non-parametric test

This research presents a new method for conditional monitoring based on the wind turbine power curve. The Kolmogorov-Smirnov (K-S) distribution test is employed in the assessment of turbine data and the detection of abnormality (faults) in wind turbines. The process begins with anomaly detection and filtration of faulty SCADA data by a quantile-based filtration approach. Suitable data comprising wind speed, air density, ambient temperature, and pitch angle are utilized in the development of wind turbine power curve models that represents actualities within wind farms. The radial basis function (RBF), multi-layer Perceptron (MLP), and gradient boosting (GBR) methods utilized for model development are compared for predictive accuracy using Mariano-Preve test. The null hypothesis assumes equal predictive ability (EPA); if rejected, an algorithm compares the coefficients of correlation of the models and selects the closest to one (unity). The most accurate model is utilized for the creation of a bin-wise distribution from past data, and bin-wise confidence levels from the plot of wind speed and output power. Cochran’s method was utilized to validate the minimum sample size that will possess a sampling distribution similar to that of the population, and a fault is detected if there is a reasonable difference between the sample distribution and population distribution. The K-S test, having a null hypothesis of equivalent distributions, signals a fault if the null hypothesis is rejected. Two wind turbine SCADA datasets associated with two fault events are used for the assessment of our method. The results indicate that our method effectively discovers abnormalities in power output relating to increased bearing temperature and reduced generator rpm, thereby aiding in the detection of faults long before they occur.

Wind Turbine Multi-Fault Detection based on SCADA Data via an AutoEncoder

Nowadays, wind turbine fault detection strategies aresettled as a meaningful pipeline to achieve required levels of effi-ciency, availability, and reliability, considering there is an increasinginstallation of this kind of machinery, both in onshore and offshoreconfiguration. In this work, it has been applied a strategy that makesuse of SCADA data with an increased sampling rate. The employedwind turbine in this study is based on an advanced benchmark,established by the National Renewable Energy Laboratory (NREL)of USA. Different types of faults on several actuators and sensed bycertain installed sensors have been studied. The proposed strategy isbased on a normality model by means of an autoencoder. As of this,faulty data are used for testing from which prediction errors werecomputed to detect if those raise a fault alert according to a definedmetric which establishes a threshold on which a wind turbine workssecurely. The obtained results determine that the proposed strategyis successful since the model detects the considered three types offaults. Finally, even when prediction errors are small, the model isable to detect the faults without problems.

Fault Detection and Isolation in Wind Turbines: Type-3 Fuzzy Logic Systems and Adaptive Random Search Learning

Fault Detection and Isolation in Wind Turbines: Type-3 Fuzzy Logic Systems and Adaptive Random Search Learning

A hybrid 3DSE-CNN-2DLSTM model for compound fault detection of wind turbines

In recent years, intelligent fault detection methods have achieved dramatic results for wind power generation. However, a majority of the available intelligent detected methods can only detect single faults. The supervisory control and data acquisition (SCADA) system is widely applied in wind turbines (WTs). SCADA data is a timestream of variable data. Considering spatial correlation and temporal correlation among SCADA data, this study proposes a WT compound fault detection model combining a three-dimensional squeeze-excitation convolutional neural network (3DSE-CNN), and a two-dimensional long and short-term memory network (2DLSTM). The proposed 3DSE-CNN-2DLSTM model consists of three parts: data preprocessing, spatiotemporal feature extraction, and fault detection. First, one-dimensional data is converted into a 2D image by a sliding window method. Then, in the proposed 3DSE-CNN model, the SE attention module is applied to enhance the convolutional channel information and extract spatial features. The proposed 2DLSTM model extracts spatiotemporal fusion features. Finally, the label of the fault category is obtained by argmax function. To validate 3DSE-CNN-2DLSTM, a 3 MW WT SCADA dataset from the south coast of Ireland is applied in the experiment. The proposed 3DSE-CNN-2DLSTM model achieves specific compound fault detection and improves detection accuracy.

Wind turbine fault detection based on spatial-temporal feature and neighbor operation state

Wind turbines (WTs) are complex pieces of engineering. They are generally exposed to harsh environmental conditions. Thus, major changeable working conditions and multidimensional dynamic correlation arise, resulting in unsatisfactory fault detection accuracy. A WT fault detection method based on spatio-temporal features and neighbor operation state is proposed in this study to tackle the aforementioned challenge. A spatio-temporal feature extraction method based on accumulated mutual information is proposed to describe the dynamic correlation of multiple features during the offline phase. Then, the spatio-temporal features are applied to build the weighted k-nearest neighbor fault detection model. In the online phase, the weighted distance between the online sample and the neighbor operation state is adopted to identify the anomaly state. Moreover, a dynamic threshold based on the neighbor sample is designed to cope with the changeable operating conditions. The proposed methods are demonstrated using FAST data and supervisory control and data acquisition data, which consider different fault types. The experiment results show that compared with similar methods and traditional fault detection methods, the operational characteristics of WTs’ components can be better described by the proposed spatio-temporal feature extraction method, and the false alarm rates can be considerably reduced by the dynamic threshold.

Fault Detection Method for Wind Turbine Generators Based on Attention-Based Modeling

Aiming at the problem that existing wind turbine gearbox fault prediction models often find it difficult to distinguish the importance of different data frames and are easily interfered with by non-important and irrelevant signals, thus causing a reduction in fault diagnosis accuracy, a wind turbine gearbox fault prediction model based on the attention-weighted long short-term memory network (AW-LSTM) is proposed. Specifically, the gearbox vibration signal is decomposed by empirical modal decomposition (EMD), to contain seven different frequency components and one residual component. The decomposed signal is passed through a four-layer LSTM network, to extract the fault features. The attention mechanism is introduced, to reweight the hidden states, in order to strengthen the attention to the important features. The proposed method captures the intrinsic long-term temporal correlation of timing gearbox signals through a long short-term memory network, and resorts to recursive attentional weighting, to efficiently distinguish the contribution of different frames and to exclude the influence of irrelevant or interfering data on the model. The results show that the proposed AW-LSTM wind turbine gearbox fault prediction model has an inference time of 36 s on two publicly available wind turbine fault detection datasets, with a root mean square error of 1.384, an average absolute error of 0.983, and an average absolute percentage error of 9.638, and that the AW-LSTM prediction model is able to efficiently extract the characteristics of wind turbine gearbox faults, with a shorter inference time and better fault prediction.

Enhancing Wind Turbine Performance: Statistical Detection of Sensor Faults Based on Improved Dynamic Independent Component Analysis

Efficient detection of sensor faults in wind turbines is essential to ensure the reliable operation and performance of these renewable energy systems. This paper presents a novel semi-supervised data-based monitoring technique for fault detection in wind turbines using SCADA (supervisory control and data acquisition) data. Unlike supervised methods, the proposed approach does not require labeled data, making it cost-effective and practical for wind turbine monitoring. The technique builds upon the Independent Component Analysis (ICA) approach, effectively capturing non-Gaussian features. Specifically, a dynamic ICA (DICA) model is employed to account for the temporal dynamics and dependencies in the observed signals affected by sensor faults. The fault detection process integrates fault indicators based on I2d, I2e, and squared prediction error (SPE), enabling the identification of different types of sensor faults. The fault indicators are combined with a Double Exponential Weighted Moving Average (DEWMA) chart, known for its superior performance in detecting faults with small magnitudes. Additionally, the approach incorporates kernel density estimation to establish nonparametric thresholds, increasing flexibility and adaptability to different data types. This study considers various types of sensor faults, including bias sensor faults, precision degradation faults, and freezing sensor faults, for evaluation. The results demonstrate that the proposed approach outperforms PCA and traditional ICA-based methods. It achieves a high detection rate, accurately identifying faults while reducing false alarms. It could be a promising technique for proactive maintenance, optimizing the performance and reliability of wind turbine systems.