Wind Turbine Condition Monitoring Research Articles

Offshore field experimentation for novel hybrid condition monitoring approaches

This study details the development of a fully automated pipeline for the condition monitoring of wind turbine drive trains. Vibration data is collected using hardware designed and manufactured in-house and used directly to monitor the condition of the drive trains. The complex nature of wind turbine vibration signals, due to the large number of components and highly variable operating conditions, makes drive train condition monitoring a challenging task. This paper details the full data measurement and analysis flow from sensor to insights and proposes a hybrid automated pipeline with signal processing and data-driven techniques to address the complexity of dealing with wind turbine vibration data. The vibration signals are directly employed to estimate the wind turbine’s instantaneous angular speed to compensate for any rotation speed fluctuations. Pre-processing is performed on the speed-independent signals to evaluate condition indicators in both the time and spectral domain for the vibration signals and their envelopes. Machine learning is then employed to distinguish the healthy state of the machine from a faulty one using the computed condition indicators. Besides the scalar indicators, also two-dimensional vibration decompositions such as the cyclic spectral correlation maps are used as inputs to the machine learning pipeline. This comprehensive and automated approach ensures both an early and reliable fault detection. Experimental results demonstrate that the fully automated hybrid pipeline can effectively be used for fleet-based health tracking of offshore wind turbine drivetrains.

Multitarget Normal Behavior Model Based on Heterogeneous Stacked Regressions and Change-Point Detection for Wind Turbine Condition Monitoring

Multitarget Normal Behavior Model Based on Heterogeneous Stacked Regressions and Change-Point Detection for Wind Turbine Condition Monitoring

Wind turbine condition monitoring based on three fitted performance curves

AbstractBased on SCADA data, this study aims at fitting three performance curves (PCs), power curve, pitch angle curve, and rotor speed curve, to accurately describe the normal behaviour of a wind turbine (WT) for performance monitoring and identification of anomalous signals. The fitting accuracy can be undesirably affected by erroneous SCADA data. Hence, outliers generated from raw SCADA data should be removed to mitigate the prediction inaccuracy, so various outlier detection (OD) approaches are compared in terms of area under the curve (AUC) and mean average precision (mAP). Among them, a novel unsupervised SVM‐KNN model, integrated by support vector machine (SVM) and k nearest neighbour (KNN), is the optimum detector for PC refinements. Based on the refined data by the SVM‐KNN detector, several common nonparametric regressors have largely improved their prediction accuracies on pitch angle and rotor speed curves from roughly 86% and 90.6%, respectively, (raw data) to both 99% (refined data). Noticeably, under the SVM‐KNN refinement, the errors have been reduced by roughly five times and 10 times for pitch angle and rotor speed predictions, respectively. Ultimately, bootstrapped prediction interval is applied to conduct the uncertainty analysis of the optimal predictive regression model, reinforcing the performance monitoring and anomaly detection.

A hierarchical modeling strategy for condition monitoring and fault diagnosis of wind turbine using SCADA data

The development and utilization of wind energy can help promote the carbon neutrality. Condition monitoring and fault diagnosis based on supervisory control and data acquisition (SCADA) can effectively improve wind turbine reliability and reduce operation and maintenance (O&M) costs. However, the complex data characteristics (e.g., time-varying and distribution-free) make it difficult to use a unified model to comprehensively evaluate the turbine state. To finely detect and analyze the turbine faulty mode, a hierarchical condition monitoring and fault diagnosis (CMFD) method is proposed, which consists of variable-level and turbine-level. First, the SCADA data is divided into two blocks: the nonstationary part with time-varying distribution, and the stationary part with time-invariant but non-Gaussian distribution. At the variable-level, this paper proposed a local monitoring unit based on sparse cointegration analysis (SCA) and independent component analysis (ICA) to detect faulty samples of different variable blocks. And the fault-related variables are isolated based on the proposed distributed reconstruction. At the turbine-level, the evaluation results from variable-level are fused: on the one hand, Bayesian inference is used to integrate monitoring statistics of stationary and nonstationary parts to comprehensively evaluate the operational state of the turbine; on the other hand, the root fault subsystem is deduced from the fault-related variables isolated from the two parts based on Gaussian process regression. The proposed method is applied in the operation and maintenance of a real wind farm, and the performance advantages are verified by the comparison with popular benchmarks.

Wind power curve modeling: A probabilistic Beta regression approach

Wind turbine power curves play a key role in various aspects during the life of a wind farm. Typical uses range from wind power forecasting to wind turbine condition monitoring. This paper addresses the identification of probabilistic models of wind power curves from observed data. The main challenge is the need to handle a statistical distribution of wind energy whose shape not only may be highly skewed, but can also change with wind speed. To address these issues, we resort to the framework of Generalized Linear Models (GLMs), proposing a Beta regression approach, with constant or variable dispersion and an appropriate preconditioning step. The proposed methodology was tested on three real SCADA measurements retrieved from public datasets, including a comparison with Quantile Regression Forests (QRFs), also in terms of robustness to outliers. The results suggest that Beta regression can be a valuable resource in the development of probabilistic models for wind energy, as it provides a high degree of flexibility while preserving an interpretable structure.

Fuzzy-Based Image Contrast Enhancement for Wind Turbine Detection: A Case Study Using Visual Geometry Group Model 19, Xception, and Support Vector Machines

Traditionally, condition monitoring of wind turbines has been performed manually by certified rope teams. This method of inspection can be dangerous for the personnel involved, and the resulting downtime can be expensive. Wind turbine inspection can be performed using autonomous drones to achieve lower downtime, cost, and health risks. To enable autonomy, the field of drone path planning can be assisted by this research, namely machine learning that detects wind turbines present in aerial RGB images taken by the drone before performing the maneuvering for turbine inspection. For this task, the effectiveness of two deep learning architectures is evaluated in this paper both without and with a proposed fuzzy contrast enhancement (FCE) image preprocessing algorithm. Efforts are focused on two convolutional neural network (CNN) variants: VGG19 and Xception. A more traditional approach involving support vector machines (SVM) is also included to contrast a machine learning approach with our deep learning networks. The authors created a novel dataset of 4500 RGB images of size 210×210 to train and evaluate the performance of these networks on wind turbine detection. The dataset is captured in an environment mimicking that of a wind turbine farm, and consists of two classes of images: with and without a small-scale wind turbine (12V Primus Air Max) assembled at Utah Valley University. The images were used to describe in detail the analysis and implementation of the VGG19, Xception, and SVM algorithms using different optimization, model training, and hyperparameter tuning technologies. The performances of these three algorithms are compared in depth alongside those augmented using the proposed FCE image preprocessing technique.

Probabilistic Prognosis of Wind Turbine Faults With Feature Selection and Confidence Calibration

With the ever-increasing expansion of the installed capacity of wind power generation, reliable condition monitoring for wind turbines (WTs) has become increasingly important. To this end, this paper proposes a probabilistic WT fault prognosis (WTFP) scheme to output reliable fault probabilities in addition to class predictions. First, a multivariate time series (MTS) based mutual information estimator (MIE) is developed to integrate with combinational optimization, selecting features that contain more beneficial temporal data patterns for WTFP. Then, a multi-fault prognosis model for WTs is trained based on the selected features and MTS learning network. Next, a confidence calibration (CC) post-processing module is appended to re-construct the mapping relation between network logits and posterior probabilities by minimizing negative log-likelihood, thereby calibrating confidence estimates to approximate the true correctness likelihood as much as possible while keeping the high accuracy of the trained MTS learning network. These components finally drive a comprehensive WTFP model. Test results on the field data of WT verify the efficacy of MTS-based MIE and CC, and show that the proposed probabilistic WTFP scheme can provide more reliable probability estimates, contributing to better decision-making.

Multivariate Anomaly Detection and Early Warning Framework for Wind Turbine Condition Monitoring Using SCADA Data

Multivariate Anomaly Detection and Early Warning Framework for Wind Turbine Condition Monitoring Using SCADA Data

Wind turbine condition monitoring based on double‐layer ensemble KNN method

AbstractAn ensemble K‐nearest neighbor model based on the double‐layer sampling method was proposed for the condition monitoring of wind turbine (WT) gearboxes. The distance function was improved to affinity distance, which helped overcome the limitation of obtaining local optimums. The feature priority was calculated based on the regularized mutual information, and a double‐layer sampling method combining data and feature sampling was designed. On the basis of the statistical process control technology, the warning threshold was designed and the real‐time residual was analyzed. The condition of the gearbox was monitored by combining the failure rate. Experimental results with real supervisory control and data acquisition (SCADA) data demonstrated that the proposed method improved the estimation accuracy of the model and could realize early fault warnings of a WT gearbox approximately 20 days earlier than the SCADA system.

Wind Power Curve Modeling With Large-Scale Generalized Kernel-Based Regression Model

Accurate wind power curves (WPCs) are crucial for wind energy development and utilization, e.g., wind power forecasting and wind turbine condition monitoring. In the era of big data, large-scale datasets make the training of power curve models inefficient, especially for kernel-based models. Furthermore, most models do not take into account the error characteristics of WPC modeling. In this study, a large-scale generalized kernel-based regression model is proposed to solve the above problem. First, a generalized loss function, which can model both symmetric and asymmetric error distributions, is designed for model training. Then, the Nyström technique is employed to get the approximate kernel matrix, based on which an eigenvalue-based kernel regression framework is constructed. Next, a large-scale generalized kernel-based regression model is developed with model parameters tuned using the alternating direction method of multipliers. Before WPC modeling, a three-step data processing method based on isolation forest is designed to process missing data, irrational data, and outliers in the collected data. The WPC modeling results on four large-scale wind datasets demonstrate that the proposed model generates accurate WPCs with high efficiency. Furthermore, the effect of turbulence intensity on WPC modeling and the effectiveness of LSGKRM with multivariate inputs are also verified.

Correlation analysis based relevant variable selection for wind turbine condition monitoring and fault diagnosis

Wind turbines’ fault diagnosis under complex environments and disturbances is significant to maintaining high reliability and secure operation over a prolonged period of time. Due to the difficulty of installing additional sensors, the supervisory control and data acquisition system is the only path for condition monitoring and fault diagnosis. However, the complexity of numerous variables bogged down the situation of diagnosis. Hence, this paper proposes a correlation analysis method to filter the variables for maximizing redundant data suppression first. Secondly, a data utility maximization method based on a prior-posterior support vector machine is proposed. Finally, a series of parallel support vector machines are used to realize multi-condition monitoring and fault diagnosis. Experiment results illustrate the effectiveness, robustness, and generality of the method.

Multivariate wind power curve modeling using multivariate adaptive regression splines and regression trees.

Wind turbine power curve (WTPC) serves as an important tool for wind turbine condition monitoring and wind power forecasting. Due to complex environmental factors and technical issues of the wind turbines, there are many outliers and inconsistencies present in the recorded data, which cannot be removed through any pre-processing technique. However, the current WTPC models have limited ability to understand such complex relation between wind speed and wind power and have limited non-linear fitting ability, which limit their modelling accuracy. In this paper, the accuracy of the WTPC models is improved in two ways: first is by developing multivariate models and second is by proposing MARS as WTPC modeling technique. MARS is a regression-based flexible modeling technique that automatically models complex the nonlinearities in the data using spline functions. Experimental results show that by incorporating additional inputs the accuracy of the power curve estimation is significantly improved. Also by studying the error distribution it is proved that multivariate models successfully mitigate the adverse effect of hidden outliers, as their distribution has higher peaks and lesser standard deviation, which proves that the errors, are more converged to zero compared to the univariate models. Additionally, MARS with its superior non-linear fitting ability outperforms the compared methods in terms of the error metrics and ranks higher than regression trees and several other popular parametric and non-parametric methods. Finally, an outlier detection method is developed to remove the hidden outliers from the data using the error distribution of the modeled power curves.

A robust fleet-based anomaly detection framework applied to wind turbine vibration data

Large amounts of unlabeled data are produced from wind turbine condition monitoring systems to catch their operational status. With this unmanageable amount of data, developing robust systems with good performance on unseen test data to detect incipient wind turbine faults is crucial to maximizing wind farm performance. This paper presents an implementation of a robust unsupervised machine-learning approach capable of executing fleet-based anomaly detection in wind turbines’ critical components. The proposed methodology is applied to noisy, unlabeled, and unstructured vibration data, which must go through the databank decoding, data engineering, preprocessing, and feature extraction. Twelve operational wind turbines with varying health conditions are used to train, validate, and test the models. Features from different domains (time, frequency, and mechanical domain) are extracted and represented in the model’s input. A labeling procedure from expert analysis regarding the condition of each wind turbine component through the evaluation of CMS output was carried out. Combining distinctive approaches to optimize eleven unsupervised machine learning algorithms through an unusual 5×2 cross-validation approach applied to real, noisy, and unstructured wind turbine data represents the paper’s novelty. The methodology selected the six best models (k-nearest neighbors, clustering-based local outlier, histogram-based outlier, isolation forest, principal component analysis, and minimum covariance determinant) based on robust performance metrics such as accuracy, F1-score, precision, recall, and area under the ROC (Receiver Operating Characteristic Curve). These models generalized the problem well and returned reasonable classification metrics for such a complex problem, with values above 90% for the area under the ROC.

A Novel Adaptive Parallel Model with Knowledge-Aided Conversion Efficiency Assessment for Wind Turbine Condition Monitoring

A Novel Adaptive Parallel Model with Knowledge-Aided Conversion Efficiency Assessment for Wind Turbine Condition Monitoring

Condition Monitoring of Wind Turbines Based on Anomaly Detection Using Deep Support Vector Data Description

Abstract Wind turbine condition monitoring is considered a key task in the wind power industry. A plethora of methodologies based on machine learning have been proposed for monitoring wind turbines, but the absence of faulty data at the amount and the variety needed still set limitations. Therefore, anomaly detection (AD) methodologies are proposed as alternatives for fault detection. Deep learning tools have been introduced in the research field of wind turbine monitoring for the purpose of higher detection accuracy. In this work, a deep learning-based anomaly detection method, the deep support vector data description (deep SVDD), is proposed for the monitoring of wind turbines. Compared to the classic SVDD anomaly detection approach, this method combines a deep network, more specifically, a convolutional neural network, with the SVDD detector in order to automatically extract effective features. To test and validate the effectiveness of the proposed method, we apply the deep SVDD method to supervisory control and data Acquisition data from a real wind turbine use case, targeting the ice detection on wind turbine blades. The experimental results show that the method can effectively detect the generation of ice on wind turbines' blades with a successful detection rate of 91.45%.

An efficient federated transfer learning framework for collaborative monitoring of wind turbines in IoE-enabled wind farms

Wind turbine (WT) condition monitoring has gained increasing interests in the era of the Internet of Energy (IoE), and existing monitoring approaches mainly focus on training a reliable model in a centralized manner. However, there are three main challenges: data islands due to data privacy and strict confidentiality of wind farm owners, domain shift due to distribution difference of different WTs, and computing and communication burden due to a large number of model parameters. To address these challenges, we propose an efficient federated transfer learning framework (EFTLWT) for collaborative monitoring of WTs in IoE-enabled wind farms, which integrates the adversarial domain adaptation into the federated framework to address the domain shift issue across multiple WTs from different wind farms. It is the first attempt to apply federated transfer learning into the field of WTs monitoring. Specifically, we design a lightweight multiscale neural network model to reduce the computation and communication cost between the client and the server. Furthermore, we propose a partial aggregation strategy to aggregate partial model parameters to reduce the model weight during the uploading and downloading, thus further reducing the burden of communication bandwidth and speeding up the response of the monitoring system. We carry out extensive experiments on real operating datasets of WTs and the results show that our EFTLWT can effectively reduce the domain shift and communication cost, decrease the response time, and greatly improve the performance of the local and federated model while maintaining the favorably comparable performance as the centralized model.

Condition monitoring of wind turbine using novel deep learning method and dynamic kernel principal components Mahalanobis distance

Condition monitoring (CM) of wind turbine (WT) has been increasingly adopted for its fault diagnosis and maintenance decision-making. However, the data collected in CM is typically noisy, multidimensional, and highly nonlinear, which causes significant challenges in achieving the effective CM of WT. This paper proposes a novel CM method using a deep learning model with temporal pattern attention (TPA) and a dynamic kernel principal components Mahalanobis distance (DKPMD). The method can evaluate the WT performance accurately for detecting faults. First, outliers are recognized and removed using isolation forest improved by sparse autoencoder and fuzzy c-means clustering (FSIF) from raw wind turbine data of health state for enhancing the quality and reliability of data in modeling. Then, a gated recurrent unit (GRU) is developed for data reconstruction of the objective variables using LassoNet and TPA, which can capture the short- and long-term temporal relationships under different time steps based on selected variables. Meanwhile, kernel RMSE (KRMSE) is applied as a loss function, which avoids the negative effects of large reconstructed errors in parameter optimization. A condition index (CI) is constructed using DKPMD based on the reconstructed errors to consider the dynamic correlation between the variables. Finally, a delay perception-based IF(DPIF) is utilized to determine the threshold. Experiments with data from real WT demonstrate the effectiveness of the developed approach in detecting early abnormal conditions, which outperforms other state-of-the-art methods.

Wind Turbine Condition Monitoring Using the SSA-Optimized Self-Attention BiLSTM Network and Changepoint Detection Algorithm

Condition-monitoring and anomaly-detection methods used for the assessment of wind turbines are key to reducing operation and maintenance (O&M) cost and improving their reliability. In this study, based on the sparrow search algorithm (SSA), bidirectional long short-term memory networks with a self-attention mechanism (SABiLSTM), and a binary segmentation changepoint detection algorithm (BinSegCPD), a condition-monitoring method (SSA-SABiLSTM-BinSegCPD, SSD) used for wind turbines is proposed. Specifically, the self-attention mechanism, which can mine the nonlinear dynamic characteristics and spatial–temporal features inherent in the SCADA time series, was introduced into a two-layer BiLSTM network to establish a normal-behavior model for wind turbine key components. Then, as a result of the advantages of searching precision and convergence rate methods, the sparrow search algorithm was employed to optimize the constructed SABiLSTM model. Moreover, the BinSegCPD algorithm was applied to the predicted residual sequence to achieve the automatic identification of deterioration conditions for wind turbines. Case studies conducted on multiple wind turbines located in south China showed that the established SSA-SABiLSTM model was superior to other contrast models, achieving a better prediction precision in terms of RMSE, MAE, MAPE, and R2. The MAE, RMSE, and MAPE of SSA-SABiLSTM were 0.2543 °C, 0.3412 °C, and 0.0069, which were 47.23%, 42.19%, and 53.38% lower than those of SABiLSTM, respectively. The R2 of SABiLSTM was 0.9731, which was 4.6% higher than that of SABiLSTM. The proposed SSD method can detect deterioration conditions 47–120 h in advance and trigger fault alarm signals approximately 36 h ahead of the actual failure time.

A novel fault diagnosis method for wind turbine based on adaptive multivariate time-series convolutional network using SCADA data

Actual wind farms usually perform condition monitoring of wind turbines based on simple trigger logic, which often have high false alarm rates and overlapping warnings. Supervisory control and data acquisition (SCADA) data contain operational information of wind turbines, based on which automatic fault diagnosis is extremely valuable. However, SCADA data have complex characteristics such as high-dimensional variable correlation, dynamic variability, and temporal correlation which bring challenges to fault diagnosis. Therefore, this paper proposes a novel fault diagnosis method to automatically identify the operating state of wind turbines: adaptive multivariate time-series convolutional network (AdaMTCN). AdaMTCN resamples SCADA data with multiple time steps at first, and the obtained resampling matrices contain multivariate time series information of different states. Then, multivariate time series convolutional networks (MTCN) are innovatively proposed, which extract enriched features from the multiple time step resampling matrices. Finally, according to the proposed adaptive decision fusion method, multiple MTCN models are weighted and fused into the overall AdaMTCN. Experimental results based on real case show that the AdaMTCN has excellent diagnostic performance in the face of SCADA data with complex characteristics.

Genetic least square estimation approach to wind power curve modelling and wind power prediction

Wind power curve (WPC) is an important index of wind turbines, and it plays an important role in wind power prediction and condition monitoring of wind turbines. Motivated by model parameter estimation of logistic function in WPC modelling, aimed at the problem of selecting initial value of model parameter estimation and local optimum result, based on the combination of genetic algorithm and least square estimation method, a genetic least square estimation (GLSE) method of parameter estimation is proposed, and the global optimum estimation result can be obtained. Six evaluation indices including the root mean square error, the coefficient of determination R2, the mean absolute error, the mean absolute percentage error, the improved Akaike information criterion and the Bayesian information criterion are used to select the optimal power curve model in the different candidate models, and avoid the model’s over-fitting. Finally, to predict the annual energy production and output power of wind turbines, a two-component Weibull mixture distribution wind speed model and five-parameter logistic function power curve model are applied in a wind farm of Jiangsu Province, China. The results show that the GLSE approach proposed in this paper is feasible and effective in WPC modelling and wind power prediction, which can improve the accuracy of model parameter estimation, and five-parameter logistic function can be preferred compared with high-order polynomial and four-parameter logistic function when the fitting accuracy is close.