Browsing by Author "Lombardi, Andrea"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item Open Access Data-driven assessment of wind turbine performance decline with age and interpretation based on comparative test case analysis(MDPI, 2022-04-21) Astolfi, Davide; Pandit, Ravi; Celesti, Ludovica; Vedovelli, Matteo; Lombardi, Andrea; Terzi, Ludovicon increasing amount of wind turbines, especially in Europe, are reaching the end of their expected lifetimes; therefore, long data sets describing their operation are available for scholars to analyze the performance trends. On these grounds, the present work is devoted to test case studies for the evaluation and the interpretation of wind turbine performance decline with age. Two wind farms were studied, featuring widely employed wind turbine models: the former is composed of 6 Senvion MM92 and the latter of 11 Vestas V52 wind turbines, owned by the ENGIE Italia company. SCADA data spanning, respectively, 10 and 7 years were analyzed for the two test cases. The effect of aging on the performance of the test case wind turbines was studied by constructing a data-driven model of appropriate operation curves, selected depending on the working region. For the Senvion MM92, we found that it is questionable to talk about performance aging because there is no evident trend in time: the performance variation year by year is in the order of a few kW and is therefore irrelevant for practical applications. For the Vestas V52 wind turbines, a much wider variability is observed: two wind turbines are affected by a remarkable performance drop, after which the behavior is stable and under-performing with respect to the rest of the wind farm. Particular attention is devoted to the interpretation of the results: the comparative discussion of the two test cases indicates that the observed operation curves are compatible with the hypothesis that the worsening with age of the two under-performing Vestas V52 can be ascribed to the behavior of the hydraulic blade pitch. Furthermore, for both test cases, it is estimated that the gearbox-aging contributes negligibly to the performance decline in time.Item Open Access Diagnosis of wind turbine systematic yaw error through nacelle anemometer measurement analysis(Elsevier, 2023-05-26) Astolfi, Davide; Pandit, Ravi; Lombardi, Andrea; Terzi, LudovicoThe power produced by a wind turbine can be considerably affected by the presence of systematic errors, which are particularly difficult to diagnose. This study deals with wind turbine systematic yaw error and proposes a novel point of view for diagnosing and quantifying its impact on the performance. The keystone is that, up to now in the literature, the effect of the yaw error on the nacelle wind speed measurements of the affected wind turbine has been disregarded. Given this, in this work a new method based on the general principle of flow equilibrium is proposed for the diagnosis of such type of error. It is based on recognizing that a misaligned wind turbine measures the wind speed differently with respect to when it is aligned. The method is shown to be effective for the diagnosis of two test cases, about which an independent estimate of the yaw error is available from upwind measurements (spinner anemometer). A data-driven generalization of the concept of relative performance is then formulated and employed for estimating how much the systematic yaw error affects wind turbine performance. It is shown that the proposed method is more appropriate than methods employing wind speed measurements (like the power curve), which are biased by the presence of the error. The results of this study support that SCADA-collected data can be very useful to diagnose wind turbine systematic yaw error, provided that a critical analysis about their use is done.Item Open Access Discussion of wind turbine performance based on SCADA data and multiple test case analysis(MDPI, 2022-07-22) Astolfi, Davide; Pandit, Ravi; Terzi, Ludovico; Lombardi, AndreaThis work is devoted to the formulation of innovative SCADA-based methods for wind turbine performance analysis and interpretation. The work is organized as an academia–industry collaboration: three test cases are analyzed, two with hydraulic pitch control (Vestas V90 and V100) and one with electric pitch control (Senvion MM92). The investigation is based on the method of bins, on a polynomial regression applied to operation curves that have never been analyzed in detail in the literature before, and on correlation and causality analysis. A key point is the analysis of measurement channels related to the blade pitch control and to the rotor: pitch manifold pressure, pitch piston traveled distance and tower vibrations for the hydraulic pitch wind turbines, and blade pitch current for the electric pitch wind turbines. The main result of this study is that cases of noticeable under-performance are observed for the hydraulic pitch wind turbines, which are associated with pitch pressure decrease in time for one case and to suspected rotor unbalance for another case. On the other way round, the behavior of the rotational speed and blade pitch curves is homogeneous and stable for the wind turbines electrically controlled. Summarizing, the evidence collected in this work identifies the hydraulic pitch as a sensible component of the wind turbine that should be monitored cautiously because it is likely associated with performance decline with age.Item Open Access Multivariate data-driven models for wind turbine power curves including sub-component temperatures(MDPI, 2022-12-23) Astolfi, Davide; Pandit, Ravi; Lombardi, Andrea; Terzi, LudovicoThe most commonly employed tool for wind turbine performance analysis is the power curve, which is the relation between wind intensity and power. The diffusion of SCADA systems has boosted the adoption of data-driven approaches to power curves. In particular, a recent research line involves multivariate methods, employing further input variables in addition to the wind speed. In this work, an innovative contribution is investigated, which is the inclusion of thirteen sub-component temperatures as possible covariates. This is discussed through a real-world test case, based on data provided by ENGIE Italia. Two models are analyzed: support vector regression with Gaussian kernel and Gaussian process regression. The input variables are individuated through a sequential feature selection algorithm. The sub-component temperatures are abundantly selected as input variables, proving the validity of the idea proposed in this work. The obtained error metrics are lower with respect to benchmark models employing more typical input variables: the resulting mean absolute error is 1.35% of the rated power. The results of the two types of selected regressions are not remarkably different. This supports that the qualifying points are, rather than the model type, the use and the selection of a potentially vast number of input variables.