Supervisory Control And Data Acquisition Data Research Articles

Prediction of Icing on Wind Turbines Based on SCADA Data via Temporal Convolutional Network

Icing on the blades of wind turbines during winter seasons causes a reduction in power and revenue losses. The prediction of icing before it occurs has the potential to enable mitigating actions to reduce ice accumulation. This paper presents a framework for the prediction of icing on wind turbines based on Supervisory Control and Data Acquisition (SCADA) data without requiring the installation of any additional icing sensors on the turbines. A Temporal Convolutional Network is considered as the model to predict icing from the SCADA data time series. All aspects of the icing prediction framework are described, including the necessary data preprocessing, the labeling of SCADA data for icing conditions, the selection of informative icing features or variables in SCADA data, and the design of a Temporal Convolutional Network as the prediction model. Two performance metrics to evaluate the prediction outcome are presented. Using SCADA data from an actual wind turbine, the model achieves an average prediction accuracy of 77.6% for future times of up to 48 h.

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.

Anomaly detection of wind turbine based on norm-linear-ConvNeXt-TCN

The supervisory control and data acquisition (SCADA) system of wind turbines continuously collects a large amount of monitoring data during their operation. These data contain abundant information about the operating status of the turbine components. Utilizing this information makes it feasible to provide early warnings and predict the health status of the wind turbine. However, due to the strong coupling between the various components of the wind turbine, the data exhibits complex spatiotemporal relationships, multiple state parameters, strong non-linearity, and noise interference, which brings great difficulty to anomaly detection of the wind turbine. This paper proposes a new method for detecting abnormal operating conditions of wind turbines, based on a cleverly designed multi-layer linear residual module and the improved temporal convolutional network (TCN) with a new norm-linear-ConvNeXt architecture (NLC-TCN). Initially, the NLC-TCN deep learning reconstruction model is trained with historical data of normal behavior to extract the spatiotemporal features of state parameters under normal operational conditions. Subsequently, the condition score of the unit is determined by calculating the average normalized root mean square error between the reconstructed data and actual data. The streaming peaks-over-threshold real-time calculation of the anomaly warning threshold, based on extreme value theory, is then used for preliminary fault monitoring. Moreover, by shielding the fault alarm for low wind speeds and implementing a continuous delay perception mechanism, issues related to wind speed fluctuations and internal and external interference are addressed, enabling early warning for faulty units. Finally, the effectiveness and reliability of the proposed method are validated through comparative experiments using actual offshore wind farm SCADA data. The performance of the proposed method surpasses that of other compared methods. Additionally, the results of the proposed method were evaluated using the uniform manifold approximation and projection dimensionality reduction technique and kernel density estimation.

Virtual sensing via Gaussian Process for bending moment response prediction of an offshore wind turbine using SCADA data

Offshore wind turbines (OWTs) can be equipped with two types of monitoring systems: (1) a Supervisory Control and Data Acquisition (SCADA) system that monitors operational data such as wind speed and power generation, and (2) vibration sensors like accelerometers and strain gauges to track structural dynamics. While strain gauges enable fatigue damage calculations, not all OWTs in a wind farm have these sensors installed. This paper proposes a Gaussian process regression (GPR) strategy to predict the bending moment time-histories of an OWT. The model takes into account various SCADA data such as wind speed, power, and nacelle acceleration as input and learns to predict the high and low-frequency dynamic response of the system. The strategy is implemented and tested to predict the bending moment response of a 6 MW offshore wind turbine in the fore-aft and side-side directions of the turbine. The accuracy and reliability of the proposed strategy are evaluated and demonstrated considering different operational conditions and multiple hotspot locations along the height of the turbine. The proposed strategy proves to be an efficient virtual sensing strategy and can be easily transferred to other turbines in the same wind farm without the need for widespread installation of strain gauges.

Classification of Highly Imbalanced Supervisory Control and Data Acquisition Data for Fault Detection of Wind Turbine Generators

It is common knowledge that wind energy is a crucial, strategic component of the mix needed to create a green economy. In this regard, optimizing the operations and maintenance (O&M) of wind turbines (WTs) is key, as it will serve to reduce the levelized cost of electricity (LCOE) of wind energy. Since most modern WTs are equipped with a Supervisory Control and Data Acquisition (SCADA) system for remote monitoring and control, condition-based maintenance using SCADA data is considered a promising solution, although certain drawbacks still exist. Typically, large amounts of normal-operating SCADA data are generated against small amounts of fault-related data. In this study, we use high-frequency SCADA data from an operating WT with a significant imbalance between normal and fault classes. We implement several resampling techniques to address this challenge and generate synthetic generator fault data. In addition, several machine learning (ML) algorithms are proposed for processing the resampled data and WT generator fault classification. Experimental results show that ADASYN + Random Forest obtained the best performance, providing promising results toward wind farm O&M optimization.

Wind energy system fault classification and detection using deep convolutional neural network and particle swarm optimization‐extreme gradient boosting

AbstractWind energy is crucial in the global shift towards a sustainable energy system. Thus, this research innovatively addresses the challenges in wind energy system fault classification and detection, emphasising the integration of robust machine learning methodologies. Our study focuses on enhancing fault management through supervisory control and data acquisition (SCADA) systems, addressing imbalanced data representation issues and error vulnerabilities. A key innovation lies in applying particle swarm optimisation‐tuned extreme gradient boosting (XGBoost) on imbalanced SCADA datasets, combining resampled SCADA data with deep learning features produced by deep convolutional neural networks. The novel use of PSO‐XGBoost showcases effectiveness in optimising parameters and ensuring model robustness. Furthermore, our research contributes to supervised and unsupervised anomaly detection models using Seasonal‐Trend decomposition using locally estimated scatterplot smoothing and PSO‐XGBoost, presenting substantial advancements in fault classification and prediction metrics. Overall, the study offers a unique, integrated framework for fault management, demonstrating improved reliability in predictive maintenance architectures. Lastly, it highlights the transformative potential of advanced machine learning in enhancing sustainability within efficient and clean energy production.

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.

A comprehensive review on enhancing wind turbine applications with advanced SCADA data analytics and practical insights

AbstractThe aim of this study is to explore the potential and economic benefits of utilising Supervisory Control and Data Acquisition (SCADA) data to improve wind turbine operation and maintenance activities. The review identifies a gap in the current understanding of how to effectively use SCADA data in wind turbine applications. It emphasises the need for pre‐processing SCADA data to ensure data integrity by addressing outliers and employing interpolation techniques. Additionally, it highlights the challenges associated with early fault detection methods using SCADA data, including the development of physical models, data‐driven machine learning models, and statistical regression models. The review also recognises the limitations caused by the lack of public data from wind turbine developers and the imbalance between normal operation data samples and abnormal data samples, negatively impacting model accuracy. The key findings of the review demonstrate that SCADA data‐driven techniques can lead to significant improvements in wind turbine operations and maintenance. The application of data‐driven technologies based on SCADA data has proven effective in reducing operation and maintenance costs and enhancing wind power generation. Moreover, the development of robust decision support systems using SCADA data minimises the need for frequent maintenance interventions in offshore wind farms. To bridge the gap and further enhance wind turbine applications using SCADA data, several recommendations are provided. These include encouraging greater openness in sharing SCADA data to improve the robustness and accuracy of AI models, adopting transfer learning techniques to overcome the scarcity of quality datasets, establishing unified standards and taxonomies, and providing specialised resources such as software applications with interactive graphical user interfaces for easier storage, annotation, and analysis of SCADA data.The authors’ review paper identifies a gap in the current understanding of how to effectively utilise SCADA data in wind turbine applications. It emphasises the importance of pre‐processing SCADA data to ensure data integrity by addressing outliers and employing interpolation techniques. Furthermore, the authors highlight the challenges associated with early fault detection methods using SCADA data, including the development of physical models, data‐driven machine learning models, and statistical regression models.

A wavelet-LSTM model for short-term wind power forecasting using wind farm SCADA data

Supervisory Control and Data Acquisition (SCADA) system collects massive operation and environment information which directly or indirectly affects the output power in wind farms. Therefore, it becomes an imperious demand to analyze the underlying information from SCADA data for improving the performance of short-term wind power prediction. In this paper, an effective deep learning framework for short-term wind power forecasting based on SCADA data analysis is proposed. A data denoising scheme is designed based on wavelet decomposition. In this method, all SCADA signals (except the wind power signal itself) are decomposed into low-frequency component A and high-frequency component D respectively by the wavelet transform. Then, the maximum information coefficient (MIC) method is applied to choose features that have strong correlation with wind power. Finally, all the selected features and wind power are defined as input vector that are used to train long short-term memory networks. The simulation results based on real data extracted from a SCADA system installed in wind farm indicate that the designed deep learning framework can significantly improve the accuracy of short-term wind power prediction.

The Atmospheric Stability Dependence of Far Wakes on the Power Output of Downstream Wind Farms

Stability-dependent far-field offshore wind-farm wakes are detected in Supervisory Control and Data Acquisition (SCADA) wind power records from wind farms located in the North Sea. The results are used to assess the strengths and weaknesses of the Openwind engineering model, which in turn enables understanding of the wake signal captured by the SCADA data. Two experimental model set-ups are evaluated, the current standard set-up considering a neutral atmosphere and extended for stable conditions, and the other using a new atmospheric stability implementation called the far-wake atmospheric stability model (ASM) previously reported in Energies. The ASM approach enables the identification within wind power records of wakes of length at least 30 km depending on the atmospheric stability. The ASM approach would be useful for assessing which neighboring wind farms are likely to affect the wind turbine power output and to what extent the power output is affected by stability.

Wind Turbine Damage Equivalent Load Assessment Using Gaussian Process Regression Combining Measurement and Synthetic Data

Assessing the structural health of operational wind turbines is crucial, given their exposure to harsh environments and the resultant impact on longevity and performance. However, this is hindered by the lack of data in commercial machines and accurate models based on manufacturers’ proprietary design data. To overcome these challenges, this study focuses on using Gaussian Process Regression (GPR) to evaluate the loads in wind turbines using a hybrid approach. The methodology involves constructing a hybrid database of aero-servo-elastic simulations, integrating publicly available wind turbine models, tools and Supervisory Control and Data Acquisition (SCADA) measurement data. Then, constructing GPR models with hybrid data, the prediction is validated against the hybrid and SCADA measurements. The results, derived from a year of SCADA data, demonstrate the GPR model’s effectiveness in interpreting and predicting turbine performance metrics. The findings of this study underscore the potential of GPR for the health and reliability assessment and management of wind turbine systems.

Feature Engineering and Supervised Machine Learning to Forecast Biogas Production during Municipal Anaerobic Co-Digestion.

Municipalities with excess anaerobic digestion capacity accept offsite wastes for co-digestion to meet sustainability goals and create more biogas. Despite the benefits inherent to co-digestion, the temporal and compositional heterogeneity of external waste streams creates operational challenges that lead to upsets or conservative co-digestion. Given the complex microbial bioprocesses occurring during anaerobic digestion, prediction and modeling of the outcomes can be challenging, and machine learning has the potential to improve understanding and control of co-digestion processes. Biogas flows are a surrogate for process health, and here, we predicted biogas production from historical data collected by a water resource recovery facility (WRRF) during normal operation. We tested a daily lab and operational data set (n = 1089 after cleaning) and a minute-by-minute supervisory control and data acquisition (SCADA) operational data set (n = 491,761 after cleaning) to determine if forecasting biogas flow for a 24 h time horizon is feasible without collecting additional data. We found that a multilayer perceptron (MLP) neural network model outperformed tree-based and multiple linear regression models. Using a high-resolution SCADA data set for the first time, we showed that MLP neural networks could predict biogas production with an adjusted coefficient of determination (R2) of 0.78 and a mean absolute percentage error of 13.4% on a holdout test set. Adding daily laboratory analyses to the model did not appreciably improve the prediction of biogas flows. Feature engineering was essential to an accurate prediction, and 11 of the 15 most important features in the SCADA model were calculated from raw SCADA outputs. In summary, this paper demonstrates that minute-scale SCADA information collected at a municipal co-digestion facility can forecast biogas production, as a first step toward a digital twin model, without additional data collection.

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.

Imbalanced learning for wind turbine blade icing detection via spatio-temporal attention model with a self-adaptive weight loss function

Accurate blade icing detection of wind turbines is of great significance to avoid secondary damages or accidents. Recently, data-driven methods have attracted increasing attention due to the availability of supervisory control and data acquisition (SCADA) data with their low-cost and high volume. However, SCADA data usually present complex characteristics of high dimensionality and strong spatio-temporal correlations among different sensor variables and severe class imbalance. It is challenging to extract effective features for accurate and reliable icing detection from imbalanced SCADA data. To address these challenges, we propose an imbalanced learning method for blade icing detection. First, we propose a spatio-temporal attention model to extract and assign weights to temporal-spatial features based on their contributions to blade icing detection. Then, to address the class imbalance issue, we design a self-adaptive weight (SAW) loss function to divide SCADA data into multiple batches and then classify them during model training. Unlike conventional loss functions, our SAW loss can adaptively assign weights to each data category according to their numbers in the divided batches. The effectiveness of the proposed method is verified on real SCADA datasets. The results demonstrate our designed spatio-temporal attention and SAW loss achieved better classification results and superior self-adaptability.

Typical fault prediction method for wind turbines based on an improved stacked autoencoder network

Abstract Timely prediction of wind turbine states is valuable for reduction of potential significant losses resulting from deterioration of health condition. To enhance the accuracy of fault diagnosis and early warning, data collected from supervisory control and data acquisition (SCADA) system of wind turbines is graphically processed and used as input for a deep learning mode, which effectively reflects the correlation between the faults of different components of wind turbines and the multi-state information in SCADA data. An improved stacked autoencoder (ISAE) framework is proposed to address the issue of ineffective fault identification due to the scarcity of labeled samples for certain fault types. In the data augmentation module, synthetic samples are generated using SAE to enhance the training data. Another SAE model is trained using the augmented dataset in the data prediction module for future trend prediction. The attribute correlation information is embedded to compensate for the shortcomings of SAE in learning attribute relationships, and the optimal factor parameters are searched using the particle swarm optimization (PSO) algorithm. Finally, the state of wind turbines is predicted using a CNN-based fault diagnosis module. Experimental results demonstrate that the proposed method can effectively predict faults and identify fault types in advance, which is helpful for wind farms to take proactive measures and schedule maintenance plans to avoid significant losses.

Characterizing the Wake Effects on Wind Power Generator Operation by Data-Driven Techniques

Wakes between neighboring wind turbines are a significant source of energy loss in wind farm operations. Extensive research has been conducted to analyze and understand wind turbine wakes, ranging from aerodynamic descriptions to advanced control strategies. However, there is a relatively overlooked research area focused on characterizing real-world wind farm operations under wake conditions using Supervisory Control And Data Acquisition (SCADA) parameters. This study aims to address this gap by presenting a detailed discussion based on SCADA data analysis from a real-world test case. The analysis focuses on two selected wind turbines within an onshore wind farm operating under wake conditions. Operation curves and data-driven methods are utilized to describe the turbines’ performance. Particularly, the analysis of the operation curves reveals that a wind turbine operating within a wake experiences reduced power production not only due to the velocity deficit but also due to increased turbulence intensity caused by the wake. This effect is particularly prominent during partial load operation when the rotational speed saturates. The turbulence intensity, manifested in the variability of rotational speed and blade pitch, emerges as the crucial factor determining the extent of wake-induced power loss. The findings indicate that turbulence intensity is strongly correlated with the proximity of the wind direction to the center of the wake sector. However, it is important to consider that these two factors may convey slightly different information, possibly influenced by terrain effects. Therefore, both turbulence intensity and wind direction should be taken into account to accurately describe the behavior of wind turbines operating within wakes.

Condition Monitoring and Fault Detection of Wind Turbine Driveline With the Implementation of Deep Residual Long Short-Term Memory Network

In view of the wide application of wind power, it is critically essential to develop solutions to the high fault rate and the long mean time to repair (MTTR). Multi-sensor fusion methods have been widely applied in condition monitoring and anomaly detection of industrial installation. Aimed at the wind turbine driveline, a new method utilizing the deep residual LSTM network with Attention model (ResLSTM-AM) is proposed in this paper. Firstly, data from multi-sensor fusion systems like supervisory control and data acquisition (SCADA) is preprocessed by quartile data cleaning and corresponding selection using the calculation of maximal information coefficient (MIC) to enhance its reliability. Secondly, we establish the neural network by the deep residual network (ResNet), long short-term memory network (LSTM), and attention mechanism (AM) for time series forecasting of wind turbines. The newly added residual connecting architecture in LSTM layers ensures a higher learning rate in feature extraction and provides a more flexible data flow both in forward and backward signals. Additionally, the attention mechanism after a LSTM layer amplifies the influence of vital data. The model gets validated based on historical SCADA data from actual wind turbines containing healthy conditions and anomaly conditions, showing ResNet contributes more. Based on the root-mean-square error (RMSE), the alarming threshold is calculated by an exponential weighted moving average (EWMA). For two chosen variables, the proposed method is confirmed to be efficient and reliable with the accuracy of 0.9945 and 0.9880 in the results of trials and comparisons with other existing models.

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.

Research on force model and characteristics of large wind turbine pitch system based on SCADA data

In large-scale wind turbines, the force state of the pitch system greatly influences safe operation and service life. This paper provides a novel method to estimate blade pitch load, bearing friction torque, and motor pitch torque. In this method, the force equilibrium equations are established by investigating the force of the pitch system under multiple operating conditions. The multidimensional BIN method is employed to classify the supervisory control and data acquisition (SCADA) data of wind turbines into several intervals. The multidimensional scatter data is processed in a single-valued way. Then, the estimating model of the pitch system forces is established by combining the obtained data and the equilibrium equations. Taking a 2 MW wind turbine as an example, the variation characteristics of blade pitch load, bearing friction torque, and motor pitch torque under multiple operating conditions are analyzed. Some interesting and valuable conclusions are obtained. For example, when the wind speed increases, the blade pitch load increases significantly in the maximum wind energy tracking region, but there is no obvious change in the observed constant power output region. The wind speed and azimuth have little effect on the bearing friction torque. The variation trend of motor pitch torque is consistent with that of blade pitch load in the maximum wind energy tracking region.

Wide area measurement systems based Power System State Estimation using a Robust Linear-Weighted Least Square method

The accuracy and robustness of Power System State Estimation (PSSE) are paramount for monitoring and surveillance of Energy Management Systems (EMS). To enhance the PSSE accuracy, phasor measurement units (PMUs) are widely used in Wide-area measurement systems (WAMS). The essential aspects of enhancing PSSE accuracy are systems observability and redundancy. These can be accomplished through an optimal PMU placement strategy. Iterative-based algorithms for estimating power system states using PMU and traditional Supervisory Control and Data Acquisition (SCADA) measurements face challenges such as non-linearity and lack of convergence. In this paper, a Robust Linear Weighted Least Square (RLWLS) estimator is proposed by combining conventional SCADA data with phasor measurements. Further, The RLWLS state estimator overcomes the issues mentioned above. Extensive simulations on various test systems, including traditional IEEE 14, 30, 57, and IEEE-118 bus systems and the real-time Indian Northern Region Power Grid (INRPG)-246 bus system in India, have shown to prove the resilience of this technique. Finally, compared to the prior PSSE approaches, the RLWLS methodology significantly improves the efficacy and performance of the state estimate solution.