1,721,092 research outputs found
Wind Turbine Drivetrain Condition Monitoring through SCADA-Collected Temperature Data: Discussion of Selected Recent Papers
No full textWind energy is going to be the leading renewable source of the next decades [...
Perspectives on SCADA Data Analysis Methods for Multivariate Wind Turbine Power Curve Modeling
No full textWind turbines are rotating machines which are subjected to non-stationary conditions and their power depends non-trivially on ambient conditions and working parameters. Therefore, monitoring the performance of wind turbines is a complicated task because it is critical to construct normal behavior models for the theoretical power which should be extracted. The power curve is the relation between the wind speed and the power and it is widely used to monitor wind turbine performance. Nowadays, it is commonly accepted that a reliable model for the power curve should be customized on the wind turbine and on the site of interest: this has boosted the use of SCADA for data-driven approaches to wind turbine power curve and has therefore stimulated the use of artificial intelligence and applied statistics methods. In this regard, a promising line of research regards multivariate approaches to the wind turbine power curve: these are based on incorporating additional environmental information or working parameters as input variables for the data-driven model, whose output is the produced power. The rationale for a multivariate approach to wind turbine power curve is the potential decrease of the error metrics of the regression: this allows monitoring the performance of the target wind turbine more precisely. On these grounds, in this manuscript, the state-of-the-art is discussed as regards multivariate SCADA data analysis methods for wind turbine power curve modeling and some promising research perspectives are indicated
Wind Turbine Operation Curves Modelling Techniques
No full textWind turbines are machines operating in non-stationary conditions and the power of a wind turbine depends non-trivially on environmental conditions and working parameters. For these reasons, wind turbine power monitoring is a complex task which is typically addressed through data-driven methods for constructing a normal behavior model. On these grounds, this study is devoted the analysis of meaningful operation curves, which are rotor speed-power, generator speed-power and blade pitch-power. A key point is that these curves are analyzed in the appropriate operation region of the wind turbines: the rotor and generator curves are considered for moderate wind speed, when the blade pitch is fixed and the rotational speed varies (Region 2); the blade pitch curve is considered for higher wind speed, when the rotational speed is rated (Region 2 12). The selected curves are studied through a multivariate Support Vector Regression with Gaussian Kernel on the Supervisory Control And Data Acquisition (SCADA) data of two wind farms sited in Italy, featuring in total 15 2 MW wind turbines. An innovative aspect of the selected models is that minimum, maximum and standard deviation of the independent variables of interest are fed as input to the models, in addition to the typically employed average values: using the additional covariates proposed in this work, the error metrics decrease of order of one third, with respect to what would be obtained by employing as regressors only the average values of the independent variables. In general it results that, for all the considered curves, the prediction of the power is characterized by error metrics which are competitive with the state of the art in the literature for multivariate wind turbine power curve analysis: in particular, for one test case, a mean absolute percentage error of order of 2.5% is achieved. Furthermore, the approach presented in this study provides a superior capability of interpreting wind turbine performance in terms of the behavior of the main sub-components and eliminates as much as possible the dependence on nacelle anemometer data, whose use is critical because of issues related to the sites complexity
Experimental Assessment of Data-driven Methods for Detecting Wind Power Ramps
No full textWind energy is a clean and cost-efficient source of energy that has gained widespread acceptance in power systems due to its numerous benefits. Despite its reliability, the variability of the source poses a challenge to wind energy integration into power grids, which require schedulable sources of electricity. To mitigate this challenge, wind power forecasting tools have been developed to reduce the uncertainty associated with power output. However, they may fail to predict large rapid power variations, known as relevant ramps. To address this limitation, novel tools for detecting and predicting ramps have been recently explored. As these tools are still in their early stages of development, it is essential to conduct further analysis to identify the optimal parameter settings for detecting relevant ramps. Therefore, this manuscript aims to analyze the impact of these parameters on ramp extraction using real-world data from a set of wind farms connected to a portion of the Italian sub-transmission grid. In particular, an interesting emerging aspect is that the number of detected ramp events decreases quadratic with the ramp amplitude definition and this in turn might affect the behavior of dedicated wind power ramp forecasting methods
About Robustness of Control Systems Embedding an Internal Model
Full text linkRobustness is a basic property of any control system. In the context of linear output regulation, it was proved that embedding an internal model of the exogenous signals is necessary and sufficient to achieve tracking of the desired reference signals in spite of external disturbances and parametric uncertainties. This result is commonly known as the internal model principle. A complete extension of such linear result to general nonlinear systems is still an open problem, exacerbated by the large number of alternative definitions of uncertainty and desired control goals that are possible in a nonlinear setting. In this paper, we develop a general framework in which all these different notions can be formally characterized in a unifying way. Classical results are reinterpreted in the proposed setting, and new results and insights are presented with a focus on robust rejection/tracking of arbitrary harmonic content. Moreover, we show by counter-example that, in the relevant case of continuous unstructured uncertainties, there are problems for which no smooth finite-dimensional robust regulator exists ensuring exact regulation
Wind turbine power curve upgrades: Methods for the assessment and test cases study
No full textThe research about wind turbine control and blade design optimization has flourished in the latest years and has provided the opportunity of diffusely updating the technology of operating wind turbines. Due to multivariate dependence of wind turbine power on ambient conditions and working parameters, it is complex to estimate the actual impact of power optimization strategies. This problem therefore calls for devoted operation data mining and statistical techniques, which are explored in the present work. In particular, two test cases of multi-MW wind turbines power upgrades are discussed: the former is a combined aerodynamic and control optimization, the latter is the optimization of the yaw control. The assessment of the upgrades impact is performed through the comparison between the post-upgrade measured production and a model estimate of the pre-upgrade production in the same conditions. The wind turbines nearby to the target upgraded ones are employed as references for the operation conditions and their working parameters are employed for a principal component regression of the power of the target wind turbine. The proposed method is general and, for the selected test cases, it arises that the aerodynamic and control optimization improves the Annual Energy Production of the order of the 3%, while the yaw control optimization provides a 1% AEP improvement
An operation data-based method for the diagnosis of zero-point shift of wind turbines yaw angle
No full textThe alignment of the wind turbine yaw to the wind direction is an important topic for wind turbine technology by several points of view. For example, the negative impact on power production of an undesired non-optimal yaw alignment can be impressive. The diagnosis of zero-point shifting of the yaw angle is commonly performed by adopting supplementary measurement sources, as for example, light detection and ranging (LIDAR) anemometers. The drawback is that these measurement campaigns have a certain cost against an uncertain diagnosis outcome. There is therefore an increasing interest from wind turbine practitioners in the formulation of zero-point yaw angle shift diagnosis techniques through the use of nacelle anemometer data. This work is devoted to this task and is organized as a test case discussion: a wind farm featuring six multi-megawatt wind turbines is considered. The study of the power factor Cp as function of the yaw error (estimated through nacelle anemometer data) is addressed. The proposed method has been validated through the detection of a 8 deg zero-point shift of the yaw angle of one wind turbine in the test case wind farm. After the correction of this offset, the performance of the wind turbine of interest is shown to be comparable with the nominal. The results of this work therefore support that an appropriate analysis of nacelle anemometer and operation data can be effective for the diagnosis of zero-point shift of the yaw angle of wind turbines
Wind Power Applications of eXplainable Artificial Intelligence Techniques
No full textThe worldwide growth of wind power capacity underscores the need for more extensive data utilization in critical areas such as Operation & Maintenance, condition monitoring, and forecasting. However, the widespread use of Machine Learning in wind power carries the risk of excessive reliance on complex black-box models. To address this, our study focuses on developing an eXplainable Artificial Intelligence (XAI) framework for multivariate wind power problems. The workflow involves a Sequential Features Selection algorithm to identify suitable variables for regression. Shapley coefficients are then computed to estimate each feature's impact on the output, revealing hidden patterns and relationships. The framework effectiveness is validated through two substantial test cases: multivariate power curve analysis for turbine condition monitoring and ultra-short-term forecasting for wind farm operations. The outcomes underscore the algorithm's proficiency in fine-tuning feature selection and providing comprehensive explanations for output behaviors. By adopting this XAI framework, wind power researchers and practitioners can navigate multivariate problems with enhanced interpretability, developing transparent models for specific applications within the wind power domain
- …
