Wind Turbine Operating Conditions Research Articles

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.

A PDMS coating with excellent durability for large-scale deicing

The icing of wind turbine blades leads to a decrease in output power, seriously jeopardizing the economic benefits and operational reliability of wind farms. Conventional deicing techniques require expensive equipment and consume a large amount of energy. Low-interfacial toughness coatings without energy dissipation are believed to be a highly potential passive deicing technology. However, the durability in service is facing challenges. Herein, low-interfacial toughness PDMS coatings were prepared by physical blending. Through the optimization of added plasticizers and SiO2, PDMS coatings with excellent large-scale deicing performance were obtained. The constant deicing force and ice adhesion strength were reduced to 14.69 N/cm and 12.63 kPa, respectively. Moreover, a systematic durability assessment of the PDMS coating was carried out to address the actual operating conditions of wind turbines. Fortunately, the results showed that the PDMS coating could withstand 200 icing/deicing cycles while maintaining constant deicing force and ice adhesion strength of less than 50 N/cm and 30 kPa, respectively. After long-term thermal aging (21 days), UV irradiation (42 days) and salt spray corrosion (20 days), the PDMS coating still retained superior icephobicity and outstanding large-scale deicing performance. This work contributes to the research and development of low-interfacial toughness materials for large-scale deicing applications on wind turbine blades.

Application of advanced signal processing techniques in vibration analysis and fault diagnosis of multi-dimensional anthropomorphic wind turbines

Abstract Wind turbine operating conditions are complex. To ensure the turbine’s safe operation, it is essential to carry out condition monitoring and fault diagnosis of its vibration. In this paper, from the structure of wind turbines, fault types, and fault formation mechanisms, a wind turbine vibration condition monitoring system is established by designing different vibration condition monitoring sensors and combining them with the Internet of Things technology. The discrete Fourier transform is employed to preprocess the time-frequency data before extracting the specific features of the vibration signal by combining the Hilbert-Huang transform after obtaining the wind turbine vibration signal. The SC-TSFN model with spatio-temporal deep fusion is established to realize the fault diagnosis of wind turbines by combining the replaceable null convolution module, BiLSTM module and the self-attention mechanism. It has been found that when the tertiary meshing frequency fluctuates around 506.98 Hz at a fault characteristic frequency of 16.14 Hz, it indicates a fault in the tertiary high-speed shaft gear. The SC-TSFN model has a fault identification time of approximately 52 days before the actual fault downtime, and the model has a 92.05% accuracy rate for wind turbine fault identification. Relying on the signal processing technology to carry out the wind turbine vibration signal analysis and then input it into the fault identification model can realize the accurate identification of the fault state of the unit and provide technical support for the stable operation of wind turbines.

An enhanced K-SVD denoising algorithm based on adaptive soft-threshold shrinkage for fault detection of wind turbine rolling bearing

Due to nonstationary operating conditions of wind turbines and surrounding harsh working environments, the impulse features induced by bearing faults are always overwhelmed by heavy noise, which brings challenges to accurately detect rolling bearing faults. Sparse representation exhibits excellent performance in nonstationary signal analysis, but it is closely bound up with the degree of similarity between the atoms in a dictionary and signals. Therefore, this paper investigates an enhanced K-SVD denoising method based on adaptive soft-threshold shrinkage to achieve high-precision extraction of impulse signals, and applies it to fault detection of generator bearing of wind turbines. An adaptive sparse coding shrinkage soft-threshold denoising is first proposed to remove noise and harmonic interference in the residual term of dictionary updating, so that the updated atoms show obvious impact characteristics. Furthermore, a soft-threshold shrinkage function with adaptive threshold is designed to further suppress clutter in atoms of the learned dictionary, so as to obtain an optimized dictionary for recovering impulse signals. Two actual engineering cases are selected for analysis, and the envelope spectrum correlation kurtosis corresponding to the results obtained by the proposed method is significantly higher than that of other comparison methods, thus verifying its superiority in detecting rolling bearing faults.

Hybrid physical and data driven modeling for dynamic operation characteristic simulation of wind turbine

Accurate simulation of wind turbines is the key to achieve efficient control of wind turbines and optimal scheduling of wind power systems. Most of the existing methods are physical simulation models, which have heavy computational burden, especially for large-scale wind turbines, and the simulation accuracy is poor under complex dynamic operating conditions. In response, this paper proposes a hybrid physical and data driven model for dynamic operation characteristic simulation of wind turbines. Firstly, a database of dynamic characteristics of wind turbine operation under various wind conditions is constructed, and then the sequence learning (Seq2Seq) model is used to mine the time series characteristics of wind turbine operation parameters. Combining with long short-term memory (LSTM) network, the mapping relationship between various operating parameter time series to establish. On this basis, an attention mechanism is added to the model to learn the dynamic response characteristics of rotor inertia to natural wind process. Through numerical example analysis, the method proposed in this paper can accurately excavate and learn the time sequence dynamic characteristics of wind turbine operating conditions and parameters under various wind conditions, thereby improving the simulation accuracy and calculation efficiency of wind turbine output power and load dynamic characteristics. Taking the actual wind turbine operation data as an example, the simulation accuracy of wind turbine output power reaches 99.8%. Compared with traditional methods, and the simulation accuracy of tower root load reaches 88.5%.

Impact mechanism of frequency response on wind turbine fatigue load

Wind turbines' participation in frequency response is known to improve the frequency stability of power systems, but it can also have a negative impact on the fatigue load of wind turbines. The objective of this paper is to investigate the effect of frequency response on the fatigue loads experienced by various components of a wind turbine, including the low-speed shaft, tower, and blade. To achieve this goal, the authors develop a model of a variable speed horizontal-axis wind turbine based on a doubly fed induction generator. They derive explicit analytical equations of low-speed shaft torque, tower bending moment, and blade bending moment to describe the fluctuations of torque and moment related to the operating states of wind turbines, such as generator torque, rotor speed, and pitch angle, under frequency response. These equations allow for the evaluation of the impact of frequency response on torque and moment changes and fatigue load. Spectral density analysis and modal analysis are used to further analyze the analytical equations, examining the influence of frequency response on different operating conditions of wind turbines and determining the mechanism by which frequency response affects fatigue load qualitatively and quantitatively. The authors use the FAST V8 Code based on the NREL offshore 5-MW baseline wind turbine to demonstrate the effectiveness of the proposed analysis method in evaluating fatigue loads affected by frequency response. The results show that the fatigue load on the low-speed shaft and the lateral side of the tower will significantly increase due to wind turbine participation in frequency response.

OC6 project Phase III: validation of the aerodynamic loading on a wind turbine rotor undergoing large motion caused by a floating support structure

Abstract. This paper provides a summary of the work done within Phase III of the Offshore Code Comparison Collaboration, Continued, with Correlation and unCertainty (OC6) project, under the International Energy Agency Wind Technology Collaboration Programme Task 30. This phase focused on validating the aerodynamic loading on a wind turbine rotor undergoing large motion caused by a floating support structure. Numerical models of the Technical University of Denmark 10 MW reference wind turbine were validated using measurement data from a 1:75 scale test performed during the UNsteady Aerodynamics for FLOating Wind (UNAFLOW) project and a follow-on experimental campaign, both performed at the Politecnico di Milano wind tunnel. Validation of the models was performed by comparing the loads for steady (fixed platform) and unsteady (harmonic motion of the platform) wind conditions. For the unsteady wind conditions, the platform was forced to oscillate in the surge and pitch directions under several frequencies and amplitudes. These oscillations result in a wind variation that impacts the rotor loads (e.g., thrust and torque). For the conditions studied in these tests, the system aerodynamic response was almost steady. Only a small hysteresis in airfoil performance undergoing angle of attack variations in attached flow was observed. During the experiments, the rotor speed and blade pitch angle were held constant. However, in real wind turbine operating conditions, the surge and pitch variations would result in rotor speed variations and/or blade pitch actuations, depending on the wind turbine controller region that the system is operating. Additional simulations with these control parameters were conducted to verify the fidelity of different models. Participant results showed, in general, a good agreement with the experimental measurements and the need to account for dynamic inflow when there are changes in the flow conditions due to the rotor speed variations or blade pitch actuations in response to surge and pitch motion. Numerical models not accounting for dynamic inflow effects predicted rotor loads that were 9 % lower in amplitude during rotor speed variations and 18 % higher in amplitude during blade pitch actuations.

A Case for Micromachines in Laboratory-Based DFIG Wind Turbine Systems for Fault Studies

For laboratory-based systems, the selection of components is critical to ensure proper representation of the actual system. In past investigations, researchers made use of small-scale off-the-shelf wound rotor induction machines (WRIMs) to perform laboratory-based studies. However, there are no reports validating their applicability in comparison to using the actual machines. In this regard, this paper investigates the correlation between the dimensional parameters and the electrical asymmetry indicators for a large-scale wind generator and laboratory-based generators. For the latter, a comparison is made between using a standard small-scale off-the-shelf WRIM and a micromachine. It is shown that the harmonic frequencies in a healthy machine and those due to inherent asymmetries appear at the same positions on the stator current spectrum for the three machines. However, there is a difference in the amplitudes of these components, given their dependence on the winding factors for a specific machine. The dimensional analysis techniques used to scale down the large-scale generator into a micromachine ensure that these parameters are related. However, this is not the case for the standard small-scale WRIM. Further work demonstrates the correlation of the fault-related harmonics between the micromachine and the large-scale machine for a rotor inter-turn fault condition. Micromachines are designed to ensure that the time constants are proportional representations of the larger machine, thus providing an accurate reflection of what is expected under transient operating conditions of wind turbines. This would assist in the development of condition monitoring strategies that are suited for the actual systems in the industry.

Simulation methodology for the identification of critical operating conditions of planetary journal bearings in wind turbines

The usage of journal bearings as planetary bearings in wind turbines instead of roller bearings has become more common in recent years. Their usage is advantageous, due to smaller installation space needed compared to roller bearings allowing for higher power densities of wind turbine drive trains. However, this technology presents a challenge since there is currently no standardized approach for the design of planetary journal bearings regarding wear. Due to varying wind speeds and dynamic operating events a large variation of loads has to be considered in the design process of a planetary journal bearing for wind turbines. Some of these loads are considered potentially critical to the journal bearing in terms of wear. Identifying these critical load areas early in the design phase supports a reliable bearing design and wind turbine operation.This paper introduces a method to identify critical operating conditions for planetary journal bearings using a simulation tool chain, which couples a multi body simulation (MBS) model of a wind turbine with an elasto-hydrodynamic (EHD) model of the planetary journal bearing. Based on the EHD results critical operating conditions are determined for the planetary bearing. Furthermore, methods are implemented to reduce the number of required EHD simulations for analysing the bearing design. The combination of the identification of critical operating conditions, while reducing the computational effort leads to a simulation methodology, which enables a faster bearing design assessment considering the wide variation of wind turbine operating conditions. The applicability of this method is demonstrated by a simplified use case.Firstly, this paper introduces the MBS model and the parameter space that describes possible combinations of bearing loads such as forces, moments and rotational speed. Due to the number of combinations and the EHD computing effort, the identified parameter space is secondly sampled statistically to reduce the simulation effort. A risk map is derived from the EHD results, to easily indicate potentially critical operating conditions for the planetary journal bearing.

Wind Speed Power Data Cleaning Method for Wind Turbines Based on Fan Characteristics and Isolated Forests

To address the situations that wind turbine operating conditions are complex and variable, the wind speed and power data are confusing, and there are many anomalies with significant differences, which make data analysis difficult, a method of cleaning wind speed and power data of wind turbines based on turbine characteristics and isolated forests is established. Firstly, the wind turbine power data is initially screened with the actual wind turbine characteristics. Then, isolated trees are constructed based on the initial filtered data. Afterward, the built isolated trees are used to calculate the power anomalies to be cleaned and to distinguish the anomalies, which finally achieves effective and efficient data cleaning. The experimental analysis results with the actual unit data of a wind farm show that this method is more efficient and more general than that of the traditional cleaning methods.

Velocity data in a fully developed experimental wind turbine array boundary layer

AbstractExperimental data are reported for a wind turbine array boundary layer (WTABL) in a model wind farm. An array of 95 model wind turbines consisting of 5 streamwise columns by 19 spanwise rows was studied in a high Reynolds number boundary layer in the Flow Physics Facility (FPF) at the University of New Hampshire. The wind turbine array was constructed of porous disks of 0.25 m diameter, which were drag (thrust) matched to typical offshore wind turbine operating conditions. The turbine spacing was 8 diameters in the streamwise and 4 diameters in the spanwise directions. Spires were used to thicken the boundary layer and achieve a boundary layer thickness on the order of 1 m at the first row of the wind turbine array, which is located 33 m downstream from the test section inlet, thus placing the turbines in the bottom 1/3 of the boundary layer. Velocity profiles were measured with a pitot tube in the center column of the array. To within experimental uncertainty, a fully developed WTABL condition is observed in the mean velocity, for defined inlet conditions and spacings, from row 12 on. The wind turbine array acts as a sparse displaced roughness: it creates an internal layer whose origin (in the wall‐normal direction) remains fixed in space, while the turbulent boundary layer the array was placed in continues to grow. Careful consideration was given to an expanded uncertainty analysis, which elucidates the need for long measurement times in large facilities. Porous disk turbine models are the experimental equivalent of numerical actuator disks; therefore, this publicly available data set is expected to be useful for numerical model validation.

New Condition-Based Monitoring and Fusion Approaches With a Bounded Uncertainty for Bearing Lifetime Prediction

Condition Monitoring (CM) is an essential element of securing reliable operating conditions of Wind Turbines (WT) in a wind farm. CM helps optimize maintenance by providing Remaining Useful Life (RUL) forecast. However, the expected RUL is not often reliable due to uncertainty associated with the prediction horizon. In this paper, we employ high-level fusion methods to expect the RUL of WT bearings. For this purpose, various features are extracted by vibration signals to capture deterioration paths. Then, a Bayesian algorithm is utilized to determine RUL for each selected feature. Eventually, high-level fusion schemes, including Hurwicz, Choquet integral, Ordered Weighted Averaging operator, are employed to integrate RUL numbers and lessen associated uncertainty in the prediction horizons. Besides, a pessimistic fusion strategy is driven to obtain a bounded uncertainty for the worst RUL prediction. The fusion methods are assessed by ten-year vibration signals of Canadian wind farms. Experimental results confirm accurate results with bounded uncertainty for high-level fusion approaches.

Influence of pitch control method of offshore medium speed wind power based on lateral damping strategy on blade vibration

The operating conditions of offshore wind turbines are complex due to the coupling effects of wind waves and other factors. The blade is subjected to uneven load for a long time, which not only increases the difficulty of control and causes fatigue damage, but also leads to the vibration of the tower and affects the service life of the wind turbine. This article mainly GH simulation software was used to simulate sea under variable load condition, based on join the lateral damping strategy, by comparing the independent variable pitch and variable pitch unified control method, analyzed the low frequency vibration of blade root and spindle hub, verified the effectiveness and control advantages of the independent variable pitch control method with lateral damping. It provides effective control measures to solve the vibration problems of the unit and improves the operation reliability.

Performance optimization of a dual-rotor ducted wind turbine by using response surface method

• The effect of different dual-rotor wind turbine operating conditions on ducted wind turbines was studied. • ANOVA was used to model the effect of dual rotor design factors on extracted power. • Response Surface Method applied to experimental data in order to optimize the dual rotor wind turbine performance. • Key parameters were affecting the performance of the turbine investigated by RSM. • A suitable dual rotor wind turbine for ducted wind turbines was designed, and RSM was an excellent method to optimize DWTs. The presented study evaluates and optimizes the performance of dual-rotor wind turbines installed inside a developed duct. The effect of different operating conditions on the extracted power was compared between dual-rotor wind turbines (DRWT) and single rotor wind turbines (SRWT). These operating conditions include the type of dual-rotor wind turbines installed in the throat section of the duct, the distance between the two rotors of a turbine, and the flow velocity through the duct throat that were evaluated by the multivariate statistical method response surface methodology. The central composite design of the response surface method was utilized to fit the designed model based on the least-squares method. Also, the multiple regression method was applied for the empirical data to match variable operating conditions with the developed model by analysis of variance (ANOVA). Afterward, some experiments were carried on to validate this method. The results showed a maximum power ratio of about 55% at the optimized conditions for dual rotor wind turbines. Determined P-values for designed parameters of models were less than 0.05, which makes its effect on the model significant. Furthermore, the power ratio obtained from empirical data was compatible with the considered model.

Prediction of power generation of two 30 kW Horizontal Axis Wind Turbines with Gaussian model

In order to improve the total efficiency of power generation in a wind farm, this paper investigated the effect of different operating conditions of the upstream wind turbine on the power of the downstream wind turbine by Gaussian wake model. A three-bladed Horizontal Axis Wind Turbine with the generator capacity of 30 kW was used. Firstly, Gaussian model for evaluating the wake flow was developed, which fit well with experiment data. Then, the influence of the operating condition of the upstream turbine on the downstream turbine performance was estimated by calculating the energy amount resulted from the velocity deficit of the wake. Finally, the effect of the installation position of the downstream wind turbine was analyzed. In consequence, the total power coefficient Ptotal of the wind turbines was relatively higher when the upstream turbine was at tip speed ratio λ = 6.4 and pitch angle β = 2° among different test conditions. Meanwhile, the Ptotal showed the maximum value when the downstream turbine was installed at the streamwise location x/D = 2.0 and lateral offset location y/R = 1.5 when the inflow turbulence intensity is 0.22≤TIref ≤ 0.35. This paper provided a better guidance for optimizing the wind turbine layout and improving the total power output of the entire wind farm.

Vibration monitoring of wind turbine tower based on XGBoost

A tower vibration monitoring method based on XGBoost is proposed to predict the tower vibration trends under different operating conditions. Firstly, the wind turbine operating conditions are classified based on the Kmeans clustering algorithm. Secondly, the impact of state parameters of the wind turbine on the tower vibration is analyzed, and the tower vibration monitoring model is established based on XGBoost algorithm. Finally, the actual SCADA data of the wind farm is used to verify the proposed method. The results show that the vibration monitoring accuracy of tower is effectively improved by considering the operating conditions of the wind turbine.

Special cases in fatigue analysis of wind turbines

The turbine industry demands a reliable design with affordable cost. As technological advances begin to support turbines of huge sizes, and the increasing importance of wind turbines from day to day make design safety conditions more important. Wind turbines are exposed to environmental conditions that can affect their installation, durability, and operation. International Electrotechnical Commission (IEC) 61400-1 design load cases consist of analyses involving wind turbine operating conditions. This design load cases (DLC) is important for determining fatigue loads (i.e., forces and moments) that occur as a result of expected conditions throughout the life of the machine. With the help of FAST (Fatigue, Aerodynamics, Structures, and Turbulence), an open source software, the NREL 5MW land base wind turbine model was used. IEC 61400-1 wind turbine design standard procedures assessed turbine behavior and fatigue damage to the tower base of dynamic loads in different design conditions. Real characteristic wind speed distribution and multi-directional effect specific to the site were taken into consideration. The effect of these conditions on the economic service life of the turbine has been studied.

Wake and Performance Predictions of Two- and Three-Bladed Wind Turbines Based on the Actuator Line Model1

Abstract This paper challenges the standard wind turbine design numerically assessing the wake and aerodynamic performance of two- and three-bladed wind turbine models implementing downwind and upwind rotor configurations, respectively. The simulations are conducted using the actuator line model (ALM) coupled with a three-dimensional Navier Stokes solver implementing the k−ω shear stress transport turbulence model. The sensitivity of the ALM to multiple simulation parameters is analyzed in detail and numerical results are compared against experimental data. These analyses highlight the most suitable Gaussian radius at the rotor to be equal to twice the chord length at 95% of the blade for a tip-speed ratio (TSR) of ten, while the Gaussian radius at the tower and the number of actuator points have a low incidence on the flow field computations overall. The numerical axial velocity profiles show better agreement upstream than downstream the rotor, while the discrepancies are not consistent through all the assessed operating conditions, thus highlighting that the ALM parameters are also dependent on the wind turbine's operating conditions rather than being merely geometric parameters. Particularly, for the upwind three-bladed wind turbine model, the accuracy of the total thrust computations improves as the TSR increases, while the least accurate wake predictions are found for its design TSR. Finally, when comparing both turbine models, an accurate representation of the downwind configuration is observed as well as realistic power extraction estimates. Indeed, the results confirm that rotors with fewer blades are more suitable to operate at high TSRs.

SCADA data as a powerful tool for early fault detection in wind turbine gearboxes

The different operating conditions of wind turbines pose great challenges for efficient and reliable fault detection. Therefore, a good analysis of wind turbine data is essential in assessing the state of the wind turbines, since the traditional threshold cannot provide a timely warning as it indicates that the malfunction has already occurred. This paper presents a new method for analyzing the actual data of the turbines, using aggregated model consisting of the neighborhood comparison method, K-means clustering and decision tree model to diagnose faults. The wind speed of the adjacent turbines is compared with each other, then other parameters of the same wind speed are also compared with each other. The purpose of comparison is that, the wind turbines which are similar in wind speed are similar in performance as well. This approach helps us to discover the abnormal data for turbine performance with in the normal operating range. The abnormal performance of any turbine destroys the similarity relationship between its data and the neighboring unit’s data. The main advantage of this approach is the possibility to detect the beginning of abnormal performance in real time, a case study using real SCADA data is used to validate this approach, which demonstrates its effectiveness and advantages.

Climate change impacts on wind power generation

Wind energy is a virtually carbon-free and pollution-free electricity source, with global wind resources greatly exceeding electricity demand. Accordingly, the installed capacity of wind turbines grew at an annualized rate of >20% from 2000 to 2019 and is projected to increase by a further 50% by the end of 2023. In this Review, we describe the factors that dictate the wind resource magnitude and variability and illustrate the tools and techniques that are being used to make projections of wind resources and wind turbine operating conditions. Natural variability due to the action of internal climate modes appears to dominate over global-warming-induced non-stationarity over most areas with large wind energy installations or potential. However, there is evidence for increased wind energy resources by the end of the current century in northern Europe and the US Southern Great Plains. New technology trends are changing the sensitivity of wind energy to global climate non-stationarity and, thus, present new challenges and opportunities for innovative research. The evolution of climate modelling to increasingly address mesoscale processes is providing improved projections of both wind resources and wind turbine operating conditions, and will contribute to continued reductions in the levelized cost of energy from wind power generation.