Search

Wind turbine gearbox condition monitoring (C&M) is a key technology to promote wind farm maintenance cost reduction and power generation improvement. Existing gearbox C&M methods usually adopt the component‐by‐component modelling approach. Firstly, this approach is inefficient in modelling; secondly, due to the thermal conduction effect, abnormalities in one gearbox component usually affect other components, making it difficult to identify the source of faults. To solve these problems, a normal behaviour model (NBM) combining data adaptive noise reduction and an improved variational auto‐encoder (VAE) is proposed, which can monitor the operational condition of multiple components of one gearbox simultaneously and takes into account the correlation between components when warning of the specific abnormal component. As verified by practical cases, the method balances the modelling accuracy and efficiency of the multi‐component NBM and achieves effective early warning and accurate localization of gearbox abnormalities. The proposed model has lower false alarm and missed alarm rates compared to other single‐component and multi‐component NBMs. [ABSTRACT FROM AUTHOR]

The wind farm flow (WFF) models, which are enabled to predict the power output of downstream, located turbines within a wind farm. A WFF model consists of two main model components: a single wake model and a superposition model. Two WFF models, the Root Sum Square (RSS) superposition model incorporated into the single wake models (e.g. Bastankah and Porté-Agel wake (BPA) model and Jensen wake model), have been extensively applied in engineering. But the WFF models above-mentioned tend to overestimate the power deficit of the whole wind farm. Hence, a novel entrainment wind farm flow (NEWFF) model is proposed in this paper, which is a combination of a modified linear entrainment wake (MLEW) model and the RSS superposition model. Different from the previous linear entrainment wake (LEW) model, the MLEW model developed in this paper considers the impacts of terrain roughness variables on the wake distribution of downstream wind turbines. The MLEW model significantly improves the accuracy of the wake simulation over the advanced BPAW model and JW model, as well as the LEW model, as shown in two cases from the TNO wind tunnel. Finally, several cases of Horns Rev offshore wind farm and Lillgrund offshore wind farm are utilized to validate the NEWFF model. Compared with the latest advanced Zong and Agel superposition wake (ZASW) model and BPA wind farm flow (BPAWFF) model, it has been demonstrated that the prediction results obtained with the NEWFF model exhibit the best agreements with measured power data under full and partial wake conditions. [ABSTRACT FROM AUTHOR]

The wake model for stand-alone turbine is an essential ingredient of wind farm wake research, which is of great concern for optimization of wind turbine layout, power generation simulation, and operation control on a wind farm. One-dimensional wake models (e.g., Jensen model and Frandsen model) based on single conservation theorem were approximately described by top-hat shape, which cannot represent the non-uniform distribution characteristics of wind turbine wake in the crosswind direction accurately and tend to underestimate the velocity deficit. Different from the above-mentioned models, entrainment wake model (EWM) can conserve both of mass and momentum within the control volume, which improves the accuracy of wake simulation to a certain extent. But the top-hat hypothesis limits the wake prediction accuracy of EWM. In this case, a novel two-dimensional EWM is proposed for the first time in this paper. Different from the advanced two-dimensional Bastankah and Porté-Agel wake model and Jensen-Gaussian wake model, the proposed model considers the influence of variable entrainment parameter on wake recovery, of which the key entrainment parameter was considered as a variable that is associated with downstream distance, ambient turbulence, and wake turbulence. The proposed Gaussian EWM has been validated by the data from Garrad Hassan (GH) wind tunnel laboratory experiments, Sexberium wind farm measurements, and the field measurements with lidar in Northwestern China. It has been concluded that the proposed model can predict the wake velocity distribution most accurately and provides the minimal power prediction error under various scenarios. [ABSTRACT FROM AUTHOR]

The actuator disc model (ADM) incorporated into the k-ε turbulence model of EI Kasmi is able to simulate the wind farm wakes with high fidelity, which is essential for layout optimization and the evaluation of power production in modern wind farms. However, the effects of the parameter C4ε in the k-ε model of EI Kasmi on turbulent kinetic energy (TKE) in the superposition areas and the recovery of wind farm wake velocity have rarely been studied. To this end, the k-ε model of EI Kasmi is coupled with the advanced ADM in PHOENICS to investigate the influence of the parameter C4ε on the wake simulation of wind farms (e.g., two offshore wind farms, one onshore wind farm). It is concluded that a decreased parameter C4ε makes the generation range of TKE in the vicinity of the rotor smaller, but the TKE near the rotor becomes larger, and the wake recovery rate of the downstream turbine is less affected by the near wake. As the interwind turbine spacing increases, the influence area of TKE in the wake region of each downstream machine gradually reduces, and atmospheric turbulence plays a dominant role in wake recovery. A decreased parameter C4ε can effectively promote the inflow wind velocity and power output of downstream turbines. The power output simulated compares well with the measured power value when the parameter C4ε = 0.15. [ABSTRACT FROM AUTHOR]

Accessibility estimation is significant to the offshore wind farm operation and maintenance (O&M) due to the extremely limited weather window and its sensitive effects on O&M tasks. Wave forecasting can be one solution to help maintenance decision‐making. However, the uncertain and dynamic properties of wave forecasts are seldom considered in the accessibility estimation process. This paper presents an uncertain accessibility estimation method based on a multi‐step probabilistic wave height forecasting (MPWHF) model and Monte Carlo simulation. First, an MPWHF model is proposed using the wavelet decomposition and the sequence to sequence (Seq2Seq) network with quantile outputs. Second, the O&M missions are randomly given a start time and simulated in the O&M flow chart by the Monte Carlo method. Finally, several access indexes, including accessibility probability, delay time, and delay probability, are evaluated based on the simulation results. Verification of the proposed MPWHF model and uncertain accessibility estimation is based on 7‐year observation data of a buoy station. The results show that the MPWHF model outperforms other counterparts and the probability of offshore accessibility is nonlinearly dependent on the weather limits and the O&M required time. [ABSTRACT FROM AUTHOR]

Wake effect leads to the power loss and fatigue damage increase on wind turbines. Therefore, wind turbine wake is seriously considered as one of the key parameters in the micro-sitting and layout optimization. Interestingly, according to the recent research of observations and simulations, similar to individual wind turbine wake, the wake of large-scale wind farm also exists which has significant impact on surrounding wind farms and the local meteorology. However, few research focused on quantitative study of wind farm wake. As a result, in this research, firstly, the numerical simulation for the neutral atmospheric flow has been carried out and preliminarily verified. By using actuator disc model, the horizontal and vertical velocity profiles behind the wind farm are analyzed. Secondly, the effective wind-farm drag coefficient has been decomposed into two components, which represent the vertical and horizontal momentum flux, respectively. By analyzing the drag coefficient, the momentum transport of wind farm was studied. The average velocity behind wind farm was also calculated, from which it was found that, with the length scale increasing, the wind farm starts to absorb energy from upper atmosphere. Lastly, the velocity decay behind wind farm can also be modeled by the formulation of Jensen wake model. [ABSTRACT FROM AUTHOR]

The Reynolds‐averaged Navier–Stokes (RANS) method coupling with the actuator disc model (ADM) is considered as a promising numerical simulation technology of wind turbine wake, and it is widely utilised in the aerodynamics of wind turbines and optimal layout of wind farms. The k−ε turbulence model is widely adopted, among the RANS‐based turbulence models. However, the k−ε turbulence model easily overestimates the turbulence viscosity in the wake, which results in fast recovery of wake velocity and failure in wake forecasting. In addition, ADM with the oversimplified geometrical structure ignores the effects of nacelle and tower on the wind turbine wake, which further lowers the accuracy of wake simulation. Therefore, the numerical simulation of wind turbine wake based on the extended k−ε turbulence model of EI Kasmi coupling with ADM considering nacelle and tower is proposed. Comparing the results of Marchwood Engineering Laboratories (MEL) ABL wind tunnel measurements and TNO wind tunnel experiments, it has been found that the proposed model improves the simulation effect for the near wake and has a certain contribution to the wake prediction accuracy overall. [ABSTRACT FROM AUTHOR]

The wind speed sequences at different spatial positions have a certain spatiotemporal coupling relationship. It is of great significance to analyze the clustering effect of the wind farm(s) and reduce the adverse impact of large-scale wind power integration if we can grasp this relationship at multiple scales. At present, the physical method cannot optimize the time-shifting characteristics in real time, and the research scope is concentrated on the wind farm. The statistical method cannot quantitatively describe the temporal relationship and the speed variation among wind speed sequences at different spatial positions. To solve the above problems, a quantification method of wind speed time-shifting characteristics based on wind process is proposed in this paper. Two evaluation indexes, the delay time and the decay speed, are presented to quantify the time-shifting characteristics. The effectiveness of the proposed method is verified from the perspective of the correlation between wind speed sequences. The time-shifting characteristics of wind speed sequences under the wind farms scale and the wind turbines scale are studied, respectively. The results show that the proposed evaluation method can effectively achieve the quantitative analysis of time-shifting and could improve the results continuously according to the actual wind conditions. Besides, it is suitable for any spatial scale. The calculation results can be directly applied to the wind power system to help obtain the more accurate output of the wind farm. [ABSTRACT FROM AUTHOR]

Accurate modeling of the wind turbine power curve (WTPC) is crucial for calculating the theoretical wind power for the integration of renewable energies and electric vehicles. However, existing WTPC modeling methods cannot simultaneously guarantee high modeling accuracy and efficiency for data samples with a large amount of accumulated abnormal data. To address this problem, this paper presents a WTPC modeling method based on interval extreme probability density, which does not require complicated and time-consuming abnormal data cleaning and can significantly improve the modeling efficiency while guaranteeing high modeling accuracy. To verify the applicability and validity of the proposed method, firstly, WTPC models were constructed using actual operation data from 12 wind turbines in a Chinese wind farm and were compared with the manufacturer's power curve and with WTPC modeling methods based on abnormal data cleaning algorithms. Secondly, the theoretical wind power was calculated and compared with the commonly used manufacturer's power curve. The results demonstrated that the proposed WTPC modeling method has high modeling accuracy and efficiency and can improve the calculation accuracy of the theoretical wind power effectively, providing more reliable data support for the integrated planning of renewable energies and electric vehicles in nearby regions. • Wind turbine power curve modeling based on interval extreme probability density. • A modeling method without complicated and time-consuming abnormal data cleaning. • Wind turbine power curves can be modeled with high accuracy and efficiency. • The proposed model supports the planning of renewable energies and electric vehicles. [ABSTRACT FROM AUTHOR]

Unsteady motion of the atmosphere incurs nonlinear and spatiotemporally coupled uncertainties in the wind power prediction (WPP) of multiple wind farms. This brings both opportunities and challenges to wind power probabilistic forecasting (WPPF) of a wind farm cluster or region, particularly when wind power is highly penetrated within the power system. This paper proposes an Improved Deep Mixture Density Network (IDMDN) for short-term WPPF of multiple wind farms and the entire region. In this respect, a deep multi-to-multi (m2m) mapping Neural Network model, which adopts the beta kernel as the mixture component to avoid the density leakage problem, is established to produce probabilistic forecasts in an end-to-end manner. A novel modified activation function and several general training procedures are then introduced to overcome the unstable behavior and NaN (Not a Number) loss issues of the beta kernel function. Verification of IDMDN is based on an open-source dataset collected from seven wind farms, and comparison results show that the proposed model improves the WPPF performance at both wind farm and regional levels. Furthermore, a laconic and accurate probabilistic expression of predicted power at each time step is produced by the proposed model. [ABSTRACT FROM AUTHOR]

Highlights • A sequence transfer correction algorithm (STCA) for NWP wind speed is proposed. • By applying STCA, the NWP wind speed error is reduced by 0.1–2.3 m/s in 2 wind farms. • The wind power forecasting accuracy is improved by 1.7–16.1% in 2 wind farms. Abstract Little Numerical Weather Prediction (NWP) error may incur huge error in wind power forecasting due to the cubic relationship between wind speed and wind power. The current correction algorithms for NWP wind speed are all based on the priori statistics laws of NWP error at the same time, i.e., the mapping relationship between NWP error and NWP wind speed at time t + 1. However, this mapping relationship has strong random uncertainty, which limits the correction accuracy of existing algorithms. To address this problem, a sequence transfer correction algorithm (STCA) for NWP wind speed is proposed in this paper. In addition to the NWP wind speed at time t + 1, the measured wind speed at time t is also introduced as an input variable in the wind speed correction model, thus the sequence transfer relationship is incorporated, and the certainty of the mapping relationship between inputs and outputs of the correction model is improved. By applying STCA, 5 frequently-used models are established for correcting the NWP wind speed error. The actual operation data of two wind farms in northern and southern China are taken as examples for this study. The correction error for NWP wind speed is reduced by 0.2–1.5 m/s in wind farm 1 and 0–0.7 m/s in wind farm 2, when compared with the second-ranking algorithm model. It can be seen that the proposed correction algorithm for NWP wind speed has higher accuracy in both ultra-short-term and short-term time scales, and has strong generalization ability to different correction models. To validate that the proposed correction algorithm can be used for real applications, STCA is also applied to the wind power forecasting system for these 2 wind farms. Results show that the wind power forecasting accuracy is improved by 3.2–16.1% in wind farm 1 and 1.7–7.5% in wind farm 2. [ABSTRACT FROM AUTHOR]

The accurate evaluation and fair comparison of wind farms power generation performance is of great significance to the technical transformation and operation and maintenance management of wind farms. However, problems exist in the evaluation indicator systems such as confusion, coupling and broadness, and the influence of wind energy resource differences not being able to be effectively eliminated, which makes it difficult to achieve the fair comparison of power generation performance among different wind farms. Thus, the evaluation indicator system and comprehensive evaluation method of wind farm power generation performance, including the influence of wind energy resource differences, are proposed in this paper to address the problems above, to which some new concepts such as resource conditions, ideal performance, reachable performance, actual performance, and performance loss are introduced in the proposed indicator system; the combination of statistical and comparative indicators are adopted to realize the quantitative evaluation, indicator decoupling, fair comparison, and loss attribution of wind farm power generation performance. The proposed comprehensive evaluation method is based on improved CRITIC (Criteria Importance though Intercrieria Correlation) weighting method, in which the uneven situation of different evaluation indicators and the comprehensive comparison of power generation performance among different wind farms shall be overcome and realized. Several sets of data from Chinese wind farms in service are used to validate the effectiveness and applicability of the proposed method by taking the comprehensive evaluation models based on CRITIC weighting method and entropy weighting method as the benchmarks. The results demonstrated that the proposed evaluation indicator system works in the quantitative evaluation and fair comparison of wind farm design, operation, and maintenance and traces the source of power generation performance loss. In addition, the results of the proposed comprehensive evaluation model are more in line with the actual power generation performance of wind farms and can be applied to the comprehensive evaluation and comparison of power generation performance of different wind farms. [ABSTRACT FROM AUTHOR]

In recent years, the accuracy of the wind power prediction has been urgently studied and improved to satisfy the requirements of power system operation. In this paper, the relevance vector machine (RVM)-based models are established to predict the wind power and its interval for a given confidence level. An NWP improvement module is presented considering the characteristic of NWP error. Moreover, two parameter optimization algorithms are applied to further improve the prediction model and to compare each performance. To take three wind farms in China as examples, the performance of two RVM-based models optimized, respectively, by genetic algorithm (GA) and particle swarm optimization (PSO) are compared with predictions based on a genetic algorithm-artificial neural network (GA-ANN) and support vector machine. Results show that the proposed models have better prediction accuracy with GA-RVM model and more efficient calculation with PSO-RVM. [ABSTRACT FROM AUTHOR]

The quantitative evaluation of cluster wind power output volatility and source-load timing matching is vital to the planning and operation of the future power system dominated by new energy. However, the existing volatility evaluation methods of cluster wind power output do not fully consider timing volatility, or are not suitable for small sample data scenarios. Meanwhile, the existing source-load timing matching evaluation indicator ignores the impact of wind power permeability on the timing matching degree between wind power output and load. Therefore, the authors propose quantitative evaluation methods of cluster wind power output volatility and source-load timing matching in regional power grid. Firstly, the volatility-based smoothing coefficient is defined to quantitatively evaluate the smoothing effect of wind-farm cluster power output. Then, the source-load timing matching coefficient considering wind power permeability is proposed to quantitatively evaluate the timing matching degree of regional wind power output and load, and the corresponding function model of volatility-based smoothing coefficient and source-load timing matching coefficient is established. Finally, the validity and applicability of the proposed methods are verified by MATLAB software based on the actual power output of 10 wind farms and actual grid load in a certain grid dispatching cross-section of northeast China. The results demonstrated that the proposed volatility-based smoothing coefficient can accurately represent the smoothing effect of wind farm cluster power output while maintaining the volatility continuity of wind power output time series and without affect from the data sample size. The source-load timing matching coefficient can accurately characterize the difference in the timing matching degree between wind power output and grid load under different wind power permeability and the influence degree on grid load. [ABSTRACT FROM AUTHOR]

In a wind farm some wind turbines may be affected by multiple upwind wakes. The commonly used approach in engineering to simulate the interaction effect of different wakes is to combine the single analytical wake model and the interaction model. The higher turbulence level and shear stress profile generated by upwind turbines in the superposed area leads to faster wake recovery. The existing interaction models are all analytical models based on some simple assumptions of superposition, which cannot characterize this phenomenon. Therefore, in this study, a mixing coefficient is introduced into the classical energy balance interaction model with the aim of reflecting the effect of turbulence intensity on velocity recovery in multiple wakes. An empirical expression is also given to calculate this parameter. The performance of the new model is evaluated using data from the Lillgrund and the Horns Rev I offshore wind farms, and the simulations agree reasonably with the observations. The comparison of different interaction model simulation results with measured data show that the calculation accuracy of this new interaction model is high, and the mean absolute percentage error of wind farm efficiency is reduced by 5.3% and 1.58%, respectively, compared to the most commonly used sum of squares interaction model. [ABSTRACT FROM AUTHOR]

Accurate and credible operation data sets of wind and solar power stations are the basis of many research works. However, such data sets often contain abnormal data due to failure, maintenance, energy curtailment, etc. The existing identification methods fail to consider the operating characteristics of power stations and the forms of abnormal data, resulting in low identification ability. Therefore, an adaptive identification method of abnormal data (AIMAD) in the wind and solar power stations is proposed in this paper, including the bidirectional one-sided quartile method and double DBSCAN method to deal with unevenly distributed abnormal data; the improved K-means clustering method based on the distance between the cluster center and benchmark power curve to process the abnormal data that are densely accumulated and closely connected with normal data in the power scatter diagram. The proposed method can adjust adaptively according to the forms of abnormal data to realize accurate identification and has strong robustness for power stations. The operation data of 30 wind farms and 8 solar plants in China are taken as examples to verify the effectiveness and superiority of the proposed method. • BOQ and d-DBSCAN are proposed to deal with unevenly distributed abnormal data. • Improved K-means method is proposed for identifying stacked abnormal data. • AIMAD is proposed to realize accurate identification of abnormal data. • Operation data in 38 stations are used to verify the effectiveness of AIMAD. [ABSTRACT FROM AUTHOR]

Highlights • Probabilistic power curve model to quantify uncertainty of wind energy conversion. • Data clearing methods based on intuitive rules and density-based clustering. • Use of new model inputs – pitch angle and wind direction – improves model accuracy. • Novel index is proposed to evaluate performance of probabilistic power curve model. Abstract This paper proposes probabilistic wind turbine power curve (WTPC) models to quantify the uncertainties of energy conversion and highly scattered relationships of actual wind speed to power. First, new model inputs (i.e. pitch angle and wind direction) and novel data clearing methods are presented to improve the model accuracy, which is rare in the previous studies. Second, the models are established based on three nonparametric algorithms, i.e. Monte Carlo, neural network, and fuzzy clustering. Third, to fill the research gap on model evaluation, the desirable properties of a probabilistic WTPC model are defined as expected variance ratio (EVR), and this index is formulated by calculating the cumulative gaps between the simulated and actual power distribution in each wind speed segment. Data from two Chinese wind farms are used to validate and compare the proposed methods using the mainstream deterministic index and the proposed EVR. Results show that (i) new model inputs and data clearing methods are able to improve the accuracy for probabilistic models regardless of the afterwards modelling method; (ii) fuzzy outperforms other probabilistic models. [ABSTRACT FROM AUTHOR]

• Concept of quantile power curve of the wind turbine is proposed. • Quantile loss based neural network algorithm to establish the quantile power curve. • Index to evaluate the performance and uncertainty of a wind turbine is proposed. Wind turbine power curve is an indicator of wind turbine performance and important input of wind farm design or power prediction, therefore can serve the system planning and operation. However, a good power curve model is difficult to obtain because of the uncertain relationship between wind speed and its power output. Existing works focus on a deterministic model or use probabilistic distribution to represent such uncertain relation, which is not easy to be employed by the following decision-makers. This paper presents a novel concept termed as quantile power curve, which generates a series of power curves under any confidence level. Quantile loss based neural network algorithm is proposed to establish the quantile power curve. Index to measure the wind turbine performance and power generation uncertainty is also proposed based on the quantile power curve. Based on the operational data of a Chinese wind farm, the proposed model and index are validated and employed to estimate the wind energy yield when planning a system with wind, solar and electric vehicle charging loads. The results show that quantile power curve provides more comprehensive information about the uncertainty during the power generation process and helps to improve the renewable supply rate to charging loads. [ABSTRACT FROM AUTHOR]