Performance Evaluation Of Wind Turbines Research Articles

Wind Turbine Performance Evaluation Method Based on Dual Optimization of Power Curves and Health Regions

The wind power curve serves as a critical metric for assessing wind turbine performance. Developing a model based on this curve and evaluating turbine efficiency within a defined health region, derived from the statically optimized power curve, holds significant value for wind farm operations. This paper proposes an optimized wind power curve segmentation modeling method based on an improved PCF algorithm to address the inconsistency between the function curve and the wind power curve, as well as the issues of prolonged curve modeling training time and susceptibility to local optima. A health region optimization method based on data increment inflection points is developed, which enables the delineation of the health performance evaluation region for wind turbines. Through the aforementioned optimization, the performance evaluation method for wind turbines is significantly improved. The effectiveness of the performance evaluation method is validated through experimental case studies, combining the wind power curve with the rotational speed stability, power characteristic consistency coefficient, and power generation efficiency indicators. The proposed modeling technique achieves a precision level of 0.998, confirming its applicability and effectiveness in practical engineering scenarios.

Condition Monitoring of Wind Turbine Systems by Explainable Artificial Intelligence Techniques

The performance evaluation of wind turbines operating in real-world environments typically relies on analyzing the power curve, which shows the relationship between wind speed and power output. However, conventional univariate models that consider only wind speed as an input variable often fail to fully explain the observed performance of wind turbines, as power output depends on multiple variables, including working parameters and ambient conditions. To overcome this limitation, the use of multivariate power curves that consider multiple input variables needs to be explored. Therefore, this study advocates for the application of explainable artificial intelligence (XAI) methods in constructing data-driven power curve models that incorporate multiple input variables for condition monitoring purposes. The proposed workflow aims to establish a reproducible method for identifying the most appropriate input variables from a more comprehensive set than is usually considered in the literature. Initially, a sequential feature selection approach is employed to minimize the root-mean-square error between measurements and model estimates. Subsequently, Shapley coefficients are computed for the selected input variables to estimate their contribution towards explaining the average error. Two real-world data sets, representing wind turbines with different technologies, are discussed to illustrate the application of the proposed method. The experimental results of this study validate the effectiveness of the proposed methodology in detecting hidden anomalies. The methodology successfully identifies a new set of highly explanatory variables linked to the mechanical or electrical control of the rotor and blade pitch, which have not been previously explored in the literature. These findings highlight the novel insights provided by the methodology in uncovering crucial variables that significantly contribute to anomaly detection.

Integrated LCA and DEA approach for circular economy-driven performance evaluation of wind turbine end-of-life treatment options

The purpose of this paper is to present an integrated joint application of Life Cycle Analysis (LCA) and Data Envelopment Analysis (DEA) in order to evaluate the efficiency of different end-of-life treatment options for wind turbine decommissioning, considering, technological, economic, and environmental aspects in a circular economy context. Eleven scenarios have been configurated concerning the material waste management of a representative type of wind turbine operating in Greece. Mechanical recycling, landfill disposal and advanced thermal recycling technologies, such as conventional or microwave pyrolysis are addressed. The proposed approach does not only evaluate the efficiency of each one of the different end-of-life treatment processes relative to one another, but it also suggests circular economy-driven policy-making scenarios towards more sustainable waste management in the country. Real-world data calculations indicate that improving the performance of the energy-intensive thermal recycling process could maximize the environmental benefits. Α circular zero-waste approach based on remanufacturing, repurposing or waste prevention through design-for-recycling of wind turbine blades, could also favor long-term sustainability.

Performance evaluation of wind turbines for sites in Chad

For the production of electricity, the use of wind energy has become more interesting in recent years. In this present study, the authors assessed wind potential using wind speed data measured at 10 m altitude for a period of 18–30 years in Chad. The statistical method of Rayleigh's law was deployed in this study. In addition, the performance of five wind turbines in five different sites were examined based on their capacity factor and annual energy production. The results shows that the average monthly velocities of the five sites range from 2.54 m/s to 3.25 m/s and the power density varies from 20.80 W/m2 to 44.17 W/m2. By focusing on the annual energy production of these turbines, the results obtained show that the Enercom E-82 can be adapted for all the five sites.

Performance evaluation of wind turbines for energy production in Morocco’s coastal regions

This study investigates the wind energy potential in Morocco’s coastal regions, the analysis utilizes wind speed data based on hourly wind speed and wind directions range over period 2015–2018. The Weibull probability function is widely used for prediction wind energy potential, in this method, the shape and scale parameters are calculated using following methods: Maximum likelihood (ML), modified maximum likelihood (MML), energy pattern factor (EPF) and WAsP method. The monthly and yearly power and energy densities at various hub heights are estimated using extrapolated Weibull parameters. Different statistical tests are used to determine the most appropriate method in adjusting Weibull parameters. Moreover, a new expression of shape and scale Weibull parameters based on linear and polynomial regressions is introduced in order to calculate these parameters for different wind speed and at various hub heights. Five wind turbines with rated power varied from 100 ​kW to 1000 ​kW are examined for evaluation the performance of wind energy in each location site, the most suitable model of wind turbine was selected based on the output energy and high values of annual capacity factor, which the most parameter for analyzing wind turbine performance, it has a direct effect on the cost of generated electricity. The higher values of wind speed are observed during winter in northern regions and wind speed can reach up to 8,5 ​m/s in February, and during summer in southern regions and wind speed reach up to 10 ​m/s in July at height 50 ​m. Moreover, in the regions of Boujdour and Essaouira, the highest values of power density are recorded on July at the height of 50 ​m with 642.981 ​W/m2 and 634.699 ​W/m2 respectively. While, in Tantan region, the lowest monthly power densities recorded on October with 132.563 ​W/m2 at the height 50 ​m.

Construction of wind turbine performance model based on SCADA data

Compared with traditional wind turbine performance evaluation methods such as operating power curve fitting, the wind turbine performance model construction method using SCADA data on machine learning has gradually attracted attention in the industry in recent years. In this technical route, the choice of input SCADA data type will directly affect the accuracy of the wind turbine performance model construction. However, in the past, selecting key SCADA data types in the performance evaluation of wind turbines were mostly subjective judgments or correlation analyses. This paper proposed a key SCADA data type selection method based on mutual information calculation and a wind turbine performance model construction method based on deep neural network training. The selected key SCADA data types based on mutual information were applied to the deep neural network to construct the wind turbine performance model, and the actual SCADA operation data of the wind farm was applied to test the model. The results show that the model construction method’s accuracy and generalizability using the above technical route can satisfy the industry demand in the same wind farm with the same wind turbine type.

Performance evaluation of wind turbines based on SCADA data

This paper proposed a new hybrid performance evaluation model of wind turbine (WT) based on Morlet wavelet neural network (MWNN), self-organizing map (SOM) neural network and Markov chain. All the data are collected from supervisory control and data acquisition (SCADA) system. Firstly, the WT power prediction model is presented based on Morlet neural network and the number of input variables, learning rates, and hidden layer nodes are discussed to obtain the optimal one. The prediction deviations under the optimal model are calculated accordingly. Then, the wind power deviations are clustered by SOM neural network, and classified by Markov chain. Two wind turbine anomaly indices (AI), which are represented by AI1 and AI2, are proposed to analyze the WTs’ performance. The results show that the proposed indices could accurately evaluate the operation state of the WTs and have important reference value for improving the operation and maintenance efficiency of the wind farm concerned.

Data-Dirven Method for Wake Effect Analysis on Nacelle Anemometer

For most wind turbines, blade wakes affect the measurement of nacelle anemometer, result in the inconsistency between nacelle wind speed (NWS) and free stream wind speed, which seriously affects the power forecasting and performance evaluation of wind turbine. This paper proposes a data-driven method to analyse the wake effect on nacelle anemometer. At first, we use Relevance Vector Machine to establish a site calibration model between Lidar wind speed (LWS) and NWS. After that, we can use the calibrated LWS to replace the free stream wind speed, and wake effect on nacelle anemometer can be evaluated by comparing the calibrated LWS and NWS. Then, Wind Turbine Power Curve (WTPC) is applied to make a detail analysis of wake effect on nacelle anemometer. The experimental results show that wake effect accelerates the air velocity behind the impeller. Therefore, WTPC fitted by NWS is “lower” than the real one. However, SCADA system overcorrects the wake effect, thus WTPC fitted by SCADA data is “higher” than the real power curve.

Modeling and performance evaluation of wind turbine based on ant colony optimization-extreme learning machine

In this paper, an innovative hybrid multi-variable generator’s actual-output-power predicting model is proposed based on ant colony optimization algorithm and extreme learning machine network, and a data-driven performance evaluation model is presented based on the two indices, K-means clustering algorithm and Markov chain for the performance evaluation of the wind turbines. Ant colony optimization algorithm is used to optimize the initial weights and thresholds of the extreme learning machine network, then the optimized combinations of weights and thresholds are provided into the extreme learning machine models to overcome the sensitivity problem of initialization setting and the disadvantage of easily falling into local optimum. Through the actual-output-power prediction of the WTs in a wind farm, the results show that the proposed model has more higher prediction accuracy than other methods mentioned in this paper. The optimization process also shows that the prediction accuracy is sensitive to the number of hidden-layer nodes and is relatively insensitive to other model parameters. Then, the data-driven performance evaluation models are proposed based on the error sequences obtained above. The case study is conducted and the results show that the method can evaluate the operating performance of the wind turbines correctly. The effectiveness of the evaluation results is also verified by the actual operation results.

A Fast Abnormal Data Cleaning Algorithm for Performance Evaluation of Wind Turbine

A fast wind turbine abnormal data cleaning algorithm via image processing for wind turbine power generation performance measurement and evaluation is proposed in this paper. The proposed method includes two stages, data cleaning and data classification. At the data cleaning stage, pixels of normal data are extracted via image processing based on pixel spatial distribution characteristics of abnormal and normal data in wind power curve (WPC) images. At the data classification stage, wind power data points are classified as normal and abnormal based on the existence of corresponding pixels in the processed WPC image. To accelerate the proposed method, the cleaning operation is executed parallelly using graphics processing units (GPUs) via compute unified device architecture (CUDA). The effectiveness of the proposed method is validated based on real data sets collected from 37 wind turbines of two commercial farms and three types of GPUs are employed to implement the proposed algorithm. The computational results prove the proposed approach has achieved better performance in cleaning abnormal wind power data while the execution time is tremendously reduced. Therefore, the proposed method is available and practical for real wind turbine power generation performance evaluation and monitoring tasks.

Performance Evaluation of Wind Turbines on the basis of Power Generation

Wind energy is one of the promising solution for future demand and need of energy. Main application of wind energy is in electricity sector. India is having potential for wind installation which is not yet fully explored. This paper compares the results from test rig small scale wind turbine and scale up data for different sizes of turbine as power from small size turbine was very low. A mathematical formulation for wind power is developed for finding total power from the available wind at certain speed. Three factors considered for analysis of three responses. Factors are Wind Speed, Rotor diameter and Swept area for getting response for wind power, torque and wind power density. For different wind speed and different rotor diameter wind power, torque and wind power density calculations done. Response surface method is used to design the experiments and ANOVA (Analysis of Variance) is used to analyze that experiment results are significant or not. Wind data analysis shows that wind speed gives a fairly good response in the range of wind speed 8m/s to 12m/s in practical grounds.

Comparative Analysis for Interval Modeling Algorithms of Wind Turbine Power Curve

Considering the stochastic uncertainty of wind power generation, joint estimation of wind turbine power curve (WTPC) in point and interval forms is carefully studied in this paper. Firstly, inducing factors of uncertain data and outliers types in measured data are analyzed to show necessity of uncertainty modeling of WTPC. Then, theoretical principles of different methods for WTPC modeling such as Gaussian Bin method, kernel density estimation (KDE), conditional kernel density estimation (CKDE), conditional probability via Copula, Gaussian process regression (GPR) and relevance vector machine (RVM), are seriously straightened up. Their theoretical essences are discussed and compared in depth. Subsequently, evaluation indexes for point and interval estimations of WTPC are defined to quantify modeling performance. Finally, using measured data from actual 1.5MW variable-speed variable-pitch (VSVP) wind turbines, simulations are executed to show diversities of these methods and their features are discussed from different views. Meanwhile, their potential application scenarios and usage strategies are carefully analyzed, including wind power prediction and operational performance evaluation of wind turbine in an infinite-time-horizon form or a sliding-window form. It is helpful to enhance development of WTPC modeling techniques.

Performance Assessment of Wind Turbines: Data-Derived Quantitative Metrics

Deteriorating performance of wind turbines results in power loses. A two-phase approach for performance evaluation of wind turbines is presented at past and future time intervals. Historical wind turbine data is utilized to determine the past performance, while performance at future time horizons calls for power prediction. In phase I of the proposed approach, wind power is predicted by an ensemble of extreme learning machines using parameters such as wind speed, air temperature, and the rotor speed. In phase II, the predicted power is used to construct Copula models. It has been demonstrated that the parameters of the Copula models serve as usable metrics for expressing performance of wind turbines. The Frank Copula model performs best among the five parametric models tested.

Comparative efficiency of wind turbines with different heights of rotor hubs: performance evaluation for Latvia

Performance evaluation of wind turbines (WT) for different heights of the rotor hub is made based on the wind speed and direction data obtained in 2009–2013 on-shore in the north of Latvia using a LOGGER 9200 Symphonie measurement system mounted on a 60 m mast. Based on the measurement analysis results, wind speed distribution curves have been modelled for heights of up to 200 m using power and logarithmic (log) law approximation methods. The curves for the modelled Weibull's parameters are plotted in dependence on height. The efficiency comparison is made for different WT types taking into account the distribution of the wind energy potential in height in the Latvian territory. The annual electric energy production was calculated for the WTs with different heights of rotor hubs. In the calculations the technical data on the following WT types were used: E-3120 (50 kW, hub height 20.5/30.5/36.5/42.7 m), E-33 (330 kW, hub height 37/44/49/50 m), E-48 (800 kW, hub height 50/60/75 m) and E-82 (2.3 MW, hub height of 78/85/98/108/138 m).

Performance evaluation of wind turbines for energy generation in Niger Delta, Nigeria

This paper evaluates wind energy potentials of seven selected locations spreading across Niger-Delta region of Nigeria using wind speed data that extend over 9 to 37years and subjected to 2-parameter Weibull distribution functions. The performance of four wind turbine models ranging from 35 to 500kW was simulated in all the locations considered. The results show that the performance of all the wind energy conversion systems gave the least energy output values at Ikom. In addition, annual energy output ranged from 4.07MWh at Ikom to 145.57MWh at Ogoja with Polaris America (100kW) and Zeus Energy (500kW) wind turbines respectively. It was also observed that, irrespective of the site, G-3120 (35kW) wind turbine has the highest capacity factor among the models considered. Therefore, for wind energy development, G-3120 model or wind turbine with similar rated wind speed would be most suitable in all the locations. The number of inhabitants that can be served by the energy produced using G-3120 turbine in each location was estimated.

Comparison of Three Methods for Wind Turbine Capacity Factor Estimation

Three approaches to calculating capacity factor of fixed speed wind turbines are reviewed and compared using a case study. The first “quasiexact” approach utilizes discrete wind raw data (in the histogram form) and manufacturer-provided turbine power curve (also in discrete form) to numerically calculate the capacity factor. On the other hand, the second “analytic” approach employs a continuous probability distribution function, fitted to the wind data as well as continuous turbine power curve, resulting from double polynomial fitting of manufacturer-provided power curve data. The latter approach, while being an approximation, can be solved analytically thus providing a valuable insight into aspects, affecting the capacity factor. Moreover, several other merits of wind turbine performance may be derived based on the analytical approach. The third “approximate” approach, valid in case of Rayleigh winds only, employs a nonlinear approximation of the capacity factor versus average wind speed curve, only requiring rated power and rotor diameter of the turbine. It is shown that the results obtained by employing the three approaches are very close, enforcing the validity of the analytically derived approximations, which may be used for wind turbine performance evaluation.

Evaluation of Comparative Performance of Three Wind Turbine Rotors

This study presents the performance evaluation of wind turbine implementing the mathematical model based on Blade Element Momentum (BEM) theory. The investigation concentrates on the comparison of power producing characteristics of three types of rotors for a horizontal axis wind turbine. The rotors considered have rectangular plan form shape with sections fabricated from aerofoil sections of NACA families. The three families of NACA airfoils used in this investigation are NACA4424, NACA23024 and NACA62-206. The lift and drag characteristics, of the rotors were experimentally obtained using 250 mm span and 60 mm chord rotor blades in an Armfield 300×300 mm subsonic, suction type and closed jet wind tunnel. The wind speeds used in the investigation were in the range of 8 to 11 m/s, which is the range of wind speeds found near the coastal belt and the mountainous parts of Saudi Arabia. Three bladed rotor subscale models of the wind turbines rotors having 250 mm rotor diameter, 100 mm blade span and 30 mm chord were used for testing rotational behavior of the wind turbines in a Plinth 600×600 mm blow down wind tunnel facility. The parameters used for the comparison in this study include variations in setting angle, diameters, tip speed ratio, taper, wind speed and angle of attack. It is observed that rotors with NACA4424 aerofoil sectioned blades produce more power at lower wind speeds and lower angles of attack where as rotors with NACA23024 aerofoil sectioned blades generate better performance at higher wind speeds and higher angles of attack. Further the taper of the rotors produced more decrease in the mass of the rotors than the decrease power produced by these. The reduction in mass could drastically decrease the inertia of the rotors which could result in higher rotational motions. Results depict the dependence of power produced on the Cd/Cl characteristics of the rotors.

Exploitation of renewable energy resources for environment‐friendly sustainable development in Saudi Arabia

The recent increase in energy costs, driven by a surge in oil prices, has increased world‐wide efforts on the exploitation of renewable/wind energy resources for environment‐friendly sustainable development and to mitigate future energy challenges. Moreover, experience in the wind energy industry has reached high levels in the field of manufacturing and application. This inevitably increases the merits of wind energy exploitation. In order to exploit wind resources, through the establishment of wind power plants, specific attention must be focused on the characteristics of wind and wind machines. The literature indicates that wind‐energy resources are relatively better along coastlines. In the present study, long‐term hourly mean wind speed data for the period 1986–2003, recorded at Dhahran (Eastern Coastal region, Saudi Arabia), has been analysed to examine the wind characteristics including (but not limited to): yearly/monthly/diurnal variations of wind speed, frequency distribution of wind speed, impact of hub‐height/machine‐size on energy production, etc. Data have been checked/validated for completeness. Data analysis indicated that long‐term monthly average wind speeds ranged from 3.8 to 5.8 m/s. Concurrently, the study determined monthly average daily energy generation from different sizes of commercial wind machines (150, 250, 600 kW, etc.) to assess the impact of wind machine size on energy yield. The study also estimated annual energy production (MWh/year) from wind farms of different capacities (3, 6, 12, 24 MW, etc.) by utilising different commercial wind energy conversion systems (WECS). It was observed that, for a given 6 MW wind farm size, a cluster of 150 kW wind machines (at 50 m hub‐height) yielded about 32% more energy when compared to a cluster of 600 kW wind machines. The study also estimated the cost of wind‐based electricity (COE, US$/kWh) by using different capacities of commercial WECS. It was found that the COE per kWh is 0.045 US$/kWh for 150 kW wind machine (at 50 m hub‐height) whereas COE was 0.039 US$/kWh for 600 kW wind machine (at 50 m hub‐height). The study also dealt with wind turbine characteristics (such as capacity factor and availability factor). These characteristics are important indicators of wind turbine performance evaluation.

Combined analytical/FEA-based coupled aero structure simulation of a wind turbine with bend–twist adaptive blades

The simulation of wind turbines with bend–twist adaptive blades is a coupled aero-structure (CAS) procedure. The blade twist due to elastic coupling is a required parameter for wind turbine performance evaluation and can be predicted through a finite element (FE) structural analyser. FEA-based codes are far too slow to be useful in the aerodynamic design/optimisation of a blade. This paper presents a combined analytical/FEA-based method for CAS simulation of wind turbines utilising bend–twist adaptive blades. This method of simulation employs the induced twist distribution and the flap bending at the hub of the blade predicted through a FEA-based CAS simulation at a reference wind turbine run condition to determine the wind turbine performance at other wind turbine run conditions. This reduces the computational time significantly and makes the aerodynamic design/optimisation of bend–twist adaptive blades practical. Comparison of the results of a case study which applies both combined analytical/FEA-based and FEA-based CAS simulation shows that when using the combined method the required computational time for generating a power curve reduces to less than 5%, while the relative difference between the predicted powers by two methods is only about 1%.

Site calibration for the wind turbine performance evaluation

The accurate wind speed information at the hub height of a wind turbine is very essential to the exact estimation of the wind turbine power performance testing. Several methods on the site calibration, which is a technique to estimate the wind speed at the wind turbine's hub height based on the measured wind data using a reference meteorological mast, are introduced. A site calibration result and the wind resource assessment for the TaeK wanRyung test site are presented using three-month wind data from a reference meteorological mast and the other mast temporarily installed at the site of wind turbine. Besides, an analysis on the uncertainty allocation for the wind speed correction using site calibration is performed.