Machine learnt prediction method for rain erosion damage on wind turbine blades

Abstract

This paper proposes a paradigm shift in the numerical simulation approach to predict rain erosion damage on wind turbine blades, given the blade geometry, its coating material, and the atmospheric conditions (wind and rain) expected at the installation site. Contrary to what has been done so far, numerical simulations (flow field and particle tracking) are used not to study a specific (wind and rain) operating condition but to build a large database of possible operating conditions of the blade section. A machine learning algorithm, trained on this database, defines a prediction module that gives the feature of the impact pattern over the 2-D section, given the wind and rain flow. The advantage of this approach is that the prediction becomes much faster than using the standard simulations; thus, the study of a large set of variable operating conditions becomes possible. The module, coupled with an erosion model, is used to compute the erosion damage of the blade working on specific installation site. In this way, the variations of the flow conditions due to dynamic effects such as variable wind, wind turbulence, and turbine control can be also considered in the erosion computation. Here, we describe the method, the database creation, and the development of the prediction tool. Then, the method is applied to predict the erosion damage on a blade section of a reference wind turbine, after one year of operation in a rainy onshore site. Results are in good agreement with on field observations, showing the potential of the approach.

Experimentally validated three‐dimensional computational aerodynamics of wind turbine blade sections featuring leading edge erosion cavities

“…The position of both pits and gouges on the model surface was determined by sampling a normal distribution centered at the model LE for the chordwise coordinate of the center of each cavity and a uniform distribution for the spanwise position of the same center. To account for the greater erosion extent on the airfoil lower side around the stagnation point, a feature observed in the field 2,9 and noted in the results of numerical simulations of WT blade LE erosion due to rain, 24 a ratio of 1:1.3 was used to define the erosion damage on the lower side of the model. With this choice, the lower side featured 260 pits and 130 gouges along a curvilinear length of 13% c starting from the LE.…”

The Springer Model for Lifetime Prediction of Wind Turbine Blade Leading Edge Protection Systems: A Review and Sensitivity Study

“…Machine learning based methods were applied to investigate the effect of erosion on the AEP of wind turbines [ 28 , 29 ]. The erosion of the blades was assumed to develop according to the Springer model.…”

Generation of Surface Maps of Erosion Resistance for Wind Turbine Blades under Rain Flows

“…In [24], an algorithm for performing CFD simulations of long-time erosion processes accounting for the geometry modification of the blade was presented, defining appropriate scale factors to simulate years of operating conditions. In the latest works ( [25,26]), a numerical prediction tool coupling CFD simulations with a machine learning approach was defined to predict rain erosion damage on a blade profile. This research represents a first and unique example of merging between rain erosion models, computational fluid and particles dynamics and wind turbine simulation over a full range of realistic operating conditions.…”

“…In this paper, we present the application of the technology defined in [26] to carry out a systematic study on the prediction of the erosion incubation period over the surface of a 5MW wind turbine blade, defining the methodology to obtain the measure and build up a comprehensive surface map to use along with the statistics of rain and wind associated to a given installation site. The paper is then structured as follows.…”

“…The paper is then structured as follows. The first section describes the methodology in terms of (i) the extension of the original model of [26] in order to measure the erosion incubation period and (ii) the verification and tuning of Springer's erosion model using rain erosion test data. The second section presents the particular application in the study and the wind turbine blade model and installation site characteristics.…”