Wind Turbine Fault Diagnosis Research Articles

A novel self-learning framework for fault identification of wind turbine drive bearings

The drive train is one of the core structures of a wind turbine, and its working condition seriously affects the performance quality. It is important to identify the fault pattern of the drive bearings in time to ensure the safety and reliability of the wind turbine. However, in traditional methods, offline modeling and online identification are often fragmented, and such a mechanism limits the adaptive updating of the model. To realize real-time updating and self-learning of the identification model, we proposed a novel self-learning framework for the intelligent fault identification of wind turbine drive bearings. First, a complete ensemble empirical mode decomposition with adaptive noise analysis–based quantification scheme for intrinsic mode function values is proposed. Then, based on the intrinsic mode function values, we offer an attention mechanism for fault feature identification and construct an initial fault pattern database using unsupervised clustering techniques. Second, abnormal data are identified by the proposed artificial immunity–based outlier detection algorithm to determine the type of immune response. Third, we design an automatic update strategy based on incremental learning to realize adaptive creation, deletion, and modification of fault patterns. The proposed intelligent framework is applied to the fault diagnosis of a real offshore wind turbine drive train, showing its advantages in intelligent fault identification and model updating.

Active learning-based wind turbine failure prediction with consideration of data from different wind farms

The SCADA system installed in each wind farm provides real-time and historical data required for fault diagnosis. However, labeling the data requires time and effort. Meanwhile, the performance of failure prediction and diagnostic relies on the volume of labeled failure data. Therefore, a fault diagnosis and prediction scheme for wind turbines based on active learning is proposed. Firstly, historical data from a selected wind turbine is screened out by residual analysis to set up the initial training data sets. Then a classifier is pre-trained by an improved active learning method. The active learning model based on the committee selection (QBC) sampling strategy and random forest (RF) learner is combined to realize the data labeling and, therefore, wind turbine fault detection. Afterward, the pre-trained classifier is applied to different wind turbines in the same/different wind farms to decide their operational status by labeling their operational data. Finally, the labeled data from different resources are fed back to retrain the classifier to improve its performance. Data from the SCADA system of wind turbines of different manufacturers in different wind farms are used as test cases, and simulation results show the effectiveness and feasibility of the proposed scheme.

Fault diagnosis of wind turbines under nonstationary conditions based on a novel tacho-less generalized demodulation

Abstract—The fault diagnosis of wind turbines under nonstationary conditions is still challenging. This paper proposes a novel tacho-less generalized demodulation (NTLGD) method for the wind turbine fault diagnosis. First, one instantaneous frequency is extracted from the time-frequency representation of the vibration signal. Second, a novel phase function design method is developed based on the extracted frequency, by which, different from traditional methods, the fault-related frequencies are mapped into the fixed predefined values. Then, the bandpass filters are designed according to the designed phase functions to separate the mapped frequencies. Finally, the diagnosis template is constructed, and the fault is localized by matching the peaks in the demodulated spectrum with the spectral lines in the template. The method is evaluated by the vibration signals of support bearings and the planetary gearbox in a test rig of wind turbine drive train. The results demonstrate that the proposed method can well pinpoint the fault-related frequency components without a tachometer and the demodulated values are independent of speed profiles.

Investigation of deep transfer learning for cross-turbine diagnosis of wind turbine faults

Data-driven fault diagnosis of wind turbines has gained popularity, and various deep learning models have been developed accordingly with massive amounts of data and achieved an excellent diagnosis performance. However, most existing deep learning models require a similar distribution of both training and testing data, thus the trained model cannot generalize new wind turbines with different data distributions. In addition, there are insufficient fault data in practice, and therefore the cost of training a new model from scratch is extremely high. To solve these problems, a cross-turbine fault diagnosis method based on deep transfer learning is proposed for wind turbines with the available supervisory control and data acquisition (SCADA) data. To better capture the spatial features of SCADA data, a deep multi-scale residual attention convolutional neural network (DMRACNN) is first designed. Then, the distribution differences between the source and target domain data are aligned at feature level. Specifically, we investigate the transfer performance of four different domain adaptation metrics. We evaluate our proposed method using SCADA data from two wind turbines to compare the diagnostic performance of four basic networks combined with four transfer metrics. Compared with traditional deep learning methods, our proposed DMRACNN achieved significant performance improvements. A cross-validation experiment using two turbines demonstrates the strong generalization ability of the proposed method.

A Review of Fault Diagnosis, Status Prediction, and Evaluation Technology for Wind Turbines

With the rapid development and increasing energy production capacity of high-power wind turbines, a corresponding increase in maintenance requirements has been observed. Reducing the failure rate of wind turbines is a critical objective, alongside decreasing affiliated operation and maintenance costs. This review focuses on the status monitoring, fault diagnosis, fault prediction, and status evaluation of wind turbines. The early fault diagnosis of wind turbines is explored with regard to existing condition monitoring technology. Moreover, the current mathematics-based fault diagnosis and smart fault diagnosis technologies are further explored. Through comprehensive investigation, this paper summarizes the research status of wind turbine fault prediction and complete machine status evaluation, conclusively presenting relevant research points and trends in the fault diagnosis, fault prediction, and status assessment of high-power wind turbines.

Fault diagnosis of wind turbine based on multi-signal CNN-GRU model

Deep Learning has been widely used in the monitoring and diagnosis of wind turbines. However, most of the current fault diagnosis methods only use single sensor signal as the input of DL model, which leads to the limitation of the model performance. Therefore, this paper proposes a multi-signal CNN-GRU model. Firstly, the acquired multiple sensor signals are converted to time–frequency images by Multi-Synchrosqueezing S-Transform, the frequency domain features of multiple sensors are extracted by Convolutional Neural Network and fused by Attention Mechanism, then the multi-source time-frequency features are extracted by Gated Recurrent Unit and finally classified by SoftMax. Experiments are conducted on the CWRU dataset and the field gearbox dataset. The results show that the proposed method achieves an average accuracy of 99.69% and 100% on the two datasets, which are both higher than existing DL-based fault diagnosis methods. The proposed method can effectively fuse signals from multiple sensors, thus improving the classification accuracy and stability of the model, which has high practicality and reliability for fault diagnosis of wind turbines.

Fault diagnosis of wind turbines with generative adversarial network-based oversampling method

Due to the complex working environment, effective fault data from wind turbine gears are often difficult to obtain. Aiming at this practical issue, a generative adversarial network (GAN)-based oversampling method is proposed in this paper, which can achieve fault classification with a small dataset. In the initial stage, wavelet packet transform is applied to generate and extract features. Then, the optimal discriminator and generator trained by GAN are used to generate data to compensate for the imbalanced fault dataset. Random forest, eXtreme gradient boosting and support vector machines are chosen to classify a real dataset, imbalanced dataset and generated dataset, respectively. Experiments indicate that the data generated by the proposed method stay at the same distribution as the real data. Therefore, for small or imbalanced dataset situations, the proposed method could be a solution to compensate for the dataset.

A correlation-graph-CNN method for fault diagnosis of wind turbine based on state tracking and data driving model

Due to the multidimensional parameters and the weak correlations with faults, it is still a challenge for the fault diagnosis of wind turbine based on the large amount of supervisory control and data acquisition (SCADA) data. In this work, a correlation-graph-convolutional neural network (CNN) method was proposed to develop a new methodology to predict the faults of wind turbine. We proposed a state tracking strategy by setting all the 24 h SCADA data before fault emergence as the input data. Meanwhile, the state parameters of wind turbine under normal status were also considered for comparison. Pearson correlation coefficient was conducted to quantitatively calculate the coupling level between state parameters, and a hotspot graph was designed to aggregate the correlation coefficients of all the state parameters to reconstruct an image that was adopted as the input data of CNN model. Finally, two practical faults were employed as the samples to study the performances of the correlation-graph-CNN method. The results showed that the accuracy of fault diagnosis can reach about 90%, that was greatly valuable in practical applications. Hence, our proposed method would have the important contribution on fault diagnosis of wind turbine.

Discussion on the Suitability of SCADA-Based Condition Monitoring for Wind Turbine Fault Diagnosis through Temperature Data Analysis

Wind turbines are expected to provide on the order of 50% of the electricity worldwide in the near future, and it is therefore fundamental to reduce the costs associated with this form of energy conversion, which regard maintenance as the first item of expenditure. SCADA-based condition monitoring for anomaly detection is commonly presented as a convenient solution for fault diagnosis on turbine components. However, its suitability is generally proven by empirical analyses which are limited in time and based on a circumscribed number of turbines. To cope with this lack of validation, this paper performs a controlled experiment to evaluate the suitability of SCADA-based condition monitoring for fault diagnosis in a fleet of eight turbines monitored for over 11 years. For the controlled experiment, a weakly supervised method was used to model the normal behavior of the turbine component. Such a model is instantiated as a convolutional neural network. The method, instantiated as a threshold-based method, proved to be suitable for diagnosis, i.e. the identification of all drivetrain failures with a considerable advance time. On the other hand, the wide variability between the time the alarm is raised and the fault is observed suggests its limited suitability for prognosis.

Fault Diagnosis of Wind Turbine Based on CNN-LSTM Parallel Network Model

Fault Diagnosis of Wind Turbine Based on CNN-LSTM Parallel Network Model

FLEXIBLE ADAPTIVE MARINE PREDATOR ALGORITHM FOR HIGH-DIMENSION OPTIMIZATION AND APPLICATION IN WIND TURBINE FAULT DIAGNOSIS

The marine predator algorithm (MPA) is the latest metaheuristic algorithm proposed in 2020, which has an outstanding merit-seeking capability, but still has the disadvantage of slow convergence and is prone to a local optimum. To tackle the above problems, this paper proposed the flexible adaptive MPA. Based on the MPA, a flexible adaptive model is proposed and applied to each of the three stages of population iteration. By introducing nine benchmark test functions and changing their dimensions, the experimental results show that the flexible adaptive MPA has faster convergence speed, more accurate convergence ability, and excellent robustness. Finally, the flexible adaptive MPA is applied to feature selection experiments. The experimental results of 10 commonly used UCI high-dimensional datasets and three wind turbine (WT) fault datasets show that the flexible adaptive MPA can effectively extract the key features of high-dimensional datasets, reduce the data dimensionality, and improve the effectiveness of the machine algorithm for WT fault diagnosis (FD).

CAD system for inter-turn fault diagnosis of offshore wind turbines via multi-CNNs & feature selection

Condition monitoring, fault diagnosis, and scheduled maintenance of wind turbines (WTs) are becoming a necessity to maximize their economic benefits and reduce their downtime. One of the critical faults in WTs is inter-turn short-circuit faults (ITSCF) in their rotating machines. Being dependent on higher wind speeds, offshore wind farms are more efficient than onshore ones, yet at the cost of higher ITSCF, more maintenance requirements, and difficulty in accessibility. Thus, they require an efficient non-contact fault diagnosis technique to enable operators to inspect all WT components with minimal contact. Among existing fault detection technologies, Infrared thermography (IRT) is considered as a non-invasive and non-destructive anomaly detection technique based on capturing thermal images by IR cameras, making it suitable for offshore harsh environments. Meanwhile, deep learning (DL) fault diagnosis approaches have proven to be promising intelligent tools with minimum human labor. This paper proposes an efficient and robust ensemble DL-based diagnosis method for ITSCF detection in induction rotating machines, besides identifying fault locations and short-circuit severity. The proposed technique is quite convenient for early diagnosis of offshore WT generator faults since it depends on IRT technology. Compared to previous studies, the proposed approach outperforms its counterparts since it integrates eight DL models, rather than using a single model, thus merging all their structural benefits altogether. Moreover, a cascaded feature fusion and selection procedure is introduced. First, the deep features extracted from the DL models are fused, then the most influential features are selected using a hybrid feature selection scheme. Thus, the classification accuracy is enhanced to reach 100% and meanwhile, the input features’ size to the classifier is reduced, decreasing classification complexity and training time. Finally, no clustering or segmentation phases are required in the proposed technique, resulting in a further decrease in the diagnosis time and computation burden.

Framework for Bidirectional Knowledge-Based Maintenance of Wind Turbines.

Artificial intelligence (AI) techniques, such as machine learning (ML), are being developed and applied for the monitoring, tracking, and fault diagnosis of wind turbines. Current prediction systems are largely limited by their inherent disadvantages for wind turbines. For example, frequency or vibration analysis simulations at a part scale require a great deal of computational power and take considerable time, an aspect that can be essential and expensive in the case of a breakdown, especially if it is offshore. An integrated digital framework for wind turbine maintenance is proposed in this study. With this framework, predictions can be made both forward and backward, breaking down barriers between process variables and key attributes. Prediction accuracy in both directions is enhanced by process knowledge. An analysis of the complicated relationships between process parameters and process attributes is demonstrated in a case study based on a wind turbine prototype. Due to the harsh environments in which wind turbines operate, the proposed method should be very useful for supervising and diagnosing faults.

Unsupervised fault diagnosis of wind turbine bearing via a deep residual deformable convolution network based on subdomain adaptation under time-varying speeds

Recent years have seen the rapid development and marvelous achievement of deep learning-based fault diagnosis (FD) methods which assume that training data and testing data have the same distribution. However, in real FD of wind turbine bearing (WTB), the particularity of time-varying speeds makes a huge difference in the distribution of training data and testing data, greatly increasing the difficulty of FD. Accordingly, in this paper, a novel deep residual deformable subdomain adaptation framework is proposed for cross-domain failure diagnosis of WTB under time-varying speeds. In the proposed approach, the traditional residual network is improved by using a deformable convolution module to replace plain counterparts, which can make the feature representation of an object adapt its configuration and enhance the ability of the model to extract transferable features. Moreover, the popular FD model based on domain adversarial neural nets and global maximum mean discrepancy is improved by removing the adversarial training mechanism and employing a local maximum mean discrepancy to align the distributions of the identical fault type in different domains, making the diagnostic model simpler and more efficient. Two experimental cases under time-varying speeds are conducted to analyze the performance of the proposed approach and the results indicate that this method can utilize the knowledge in the source domain to diagnose the fault in the target domain. Compared with the existing methods, the diagnosis accuracy and efficiency are significantly improved, demonstrating its effectiveness and potential applications in fault transfer diagnosis of wind turbine bearing.

The fault frequency priors fusion deep learning framework with application to fault diagnosis of offshore wind turbines

In fault diagnosis, deep learning plays an important role, but still lacks good interpretability. To address this issue, we develop a novel fault frequency priors fusion deep learning (FFP-DL) framework by introducing fault frequency priors into deep learning. The FFP-DL framework contains two branches: fault frequency priors learning branch (FFPLB) and self-learning branch (SLB). We then propose a pre-training algorithm which can shorten the overall training time especially for training multiple models simultaneously. To illustrate its efficacy, we take convolutional neural network (CNN) as the specific deep learning model in the FFP-DL framework (FFP-CNN), and apply the FFP-CNN model to a private offshore wind turbines (OWTs) data. The experimental results show that the FFP fusion does help improve the performance of fault diagnosis in terms of accuracy and Marco-F1-score and provide good interpretability to the diagnosis results with the distinguished feature of predicted FFP. With the training data reduction, the performance of the FFP-CNN model does not deteriorate quickly, which implies that this framework is also suitable for less data. In addition, the result reveals the fact that the pre-training algorithm does reduce convergence epochs, which will help the FFP-CNN model train faster during the training process.

Fault Diagnosis and Fault Tolerant Control of Wind Turbines: An Overview

Wind turbines are playing an increasingly important role in renewable power generation. Their complex and large-scale structure, however, and operation in remote locations with harsh environmental conditions and highly variable stochastic loads make fault occurrence inevitable. Early detection and location of faults are vital for maintaining a high degree of availability and reducing maintenance costs. Hence, the deployment of algorithms capable of continuously monitoring and diagnosing potential faults and mitigating their effects before they evolve into failures is crucial. Fault diagnosis and fault tolerant control designs have been the subject of intensive research in the past decades. Significant progress has been made and several methods and control algorithms have been proposed in the literature. This paper provides an overview of the most recent fault diagnosis and fault tolerant control techniques for wind turbines. Following a brief discussion of the typical faults, the most commonly used model-based, data-driven and signal-based approaches are discussed. Passive and active fault tolerant control approaches are also highlighted and relevant publications are discussed. Future development tendencies in fault diagnosis and fault tolerant control of wind turbines are also briefly stated. The paper is written in a tutorial manner to provide a comprehensive overview of this research topic.

Editorial: Wind turbine fault and damage diagnosis and prognosis

Editorial: Wind turbine fault and damage diagnosis and prognosis

A novel fault diagnosis method of wind turbine bearings based on compressed sensing and AlexNet

The bearing is the core component which ensures the normal operation of the wind turbine. The vibration signal based on fault diagnosis is non-linear, non-stationary and causes serious noise pollution. Conventional methods are difficult to demodulate, and the operation is complex. With the increasing capacity of wind turbine assemblers, the signal samples based on Shannon sampling theorem are also increasing, which brings great pressure to data transmission and storage. Deep learning based on big data-driven for wind turbine running condition monitoring plays an effective role in the field of fault diagnosis. However, data training depends on a large amount of data and takes a long time. Therefore, a novel fault diagnosis method based on compressed sensing (CS) and AlexNet is proposed. This method used small sample data. Firstly, the signal is sparsely processed by stagewise orthogonal matching pursuit algorithm, so that the sparse signal is convenient for signal transmission and can alleviate the pressure of signal storage. Secondly, the CS theory is used to restore the signal and reduce the noise of the signal. Thirdly, a fault-free signal is selected and compared with the fault signal with the same phase to obtain the characteristic residual signal. Next, they are subjected to continuous wavelet transform to obtain the wavelet spectrum of the signal. Finally, it is constructed into a pseudo-trichromatic graph and put into the improved AlexNet network to obtain the effect of fault diagnosis. Compared with other methods, experiment shows that the proposed method has higher accuracy in wind turbine fault diagnosis

Application of Machine Learning Technique Using Support Vector Machine in Wind Turbine Fault Diagnosis

Wind energies are one of the most used resources worldwide and favours the economy by not emitting harmful gases that could lead to global warming. It is a cost-efficient method and environmentally friendly. Hence, explains the popularity of wind energy production over the years. Unfortunately, a minor fault could be contagious by affecting the nearby components, then a more complicated problem might arise, which may be costly. Thus, this article conducted a machine learning technique, support vector machine (SVM) to monitor the health of the wind turbine system by classifying the class of healthy data and faulty data. Some SVM types were experimented with, including Linear, Quadratic, Cubic, Fine Gaussian, Medium Gaussian, and Coarse Gaussian. Then these models were trained under different validation schemes that are cross-validation, holdout validation, and re-substitution validation as an approach to evaluate the performance of each model. In the end, Cubic SVM is proven to outperformed other models under the provision of 10-fold cross-validation with an accuracy of 98.25%. The result showed that Cubic SVM has the best performance while Linear SVM has the least accuracy among other models. Hence choosing the default value is preferred as the final product to diagnose the fault in wind turbine systems.

A velocity-guided Harris hawks optimizer for function optimization and fault diagnosis of wind turbine.

Harris hawks optimizer (HHO) is a relatively novel meta-heuristic approach that mimics the behavior of Harris hawk over the process of predating the rabbits. The simplicity and easy implementation of HHO have attracted extensive attention of many researchers. However, owing to its capability to balance between exploration and exploitation is weak, HHO suffers from low precision and premature convergence. To tackle these disadvantages, an improved HHO called VGHHO is proposed by embedding three modifications. Firstly, a novel modified position search equation in exploitation phase is designed by introducing velocity operator and inertia weight to guide the search process. Then, a nonlinear escaping energy parameter E based on cosine function is presented to achieve a good transition from exploration phase to exploitation phase. Thereafter, a refraction-opposition-based learning mechanism is introduced to generate the promising solutions and helps the swarm to flee from the local optimal solution. The performance of VGHHO is evaluated on 18 classic benchmarks, 30 latest benchmark tests from CEC2017, 21 benchmark feature selection problems, fault diagnosis problem of wind turbine and PV model parameter estimation problem, respectively. The simulation results indicate that VHHO has higher solution quality and faster convergence speed than basic HHO and some well-known algorithms in the literature on most of the benchmark and real-world problems.