A simulation tool for the fast prediction of rain erosion in wind
EBLADER is an essential tool, based on MACHINE LEARNING, for the design and maintenance of wind turbine blades.
WHAT IS IT?
It is a new software-based solution designed to assist in decision-making related to rain erosion of wind turbine blades.
WHAT RESULTS ARE OBTAINED?
From an operational scenario, EBLADER predicts the remaining lifetime and, in the case of erosion, quantifies the damage and estimates efficiency losses.
WHAT IS THE ADDITIONAL VALUE?
The user has access to an intelligent, robust, and customized assisted work environment (UI), designed for decision-making related to the stages of design, operation, and maintenance of wind turbines.
WHAT IS THE TECHNOLOGICAL DIFFERENTIAL?
The efficient calculation engine of EBLADER is based on validated predictive models (Springer, for rainfall erosion) and integrates Machine Learning technologies (ANN, XGBOOST), numerical methods, and statistical models (erosion, CFD, aeroelasticity)
The accumulated damage and remaining useful life are calculated through the intelligent calculation core based on the definition of weather conditions, geometric characteristics, material properties, and operating conditions of the wind turbine.
For a fast and accurate prediction of the remaining useful life and/or damage produced, EBLADER uses:
- Springer’s model for rain erosion in coated materials
- Characterization of impacts via a homogenized CFD solution based on the novel Pseudo-Direct Numerical Simulation (P-DNS) method.
- Aeroelastic simulations using OpenFAST with turbulent conditions via turbSim
- Reduced models based on modern machine learning technologies (XGBOOST)
- Fatigue properties of the composite and the coating.
- Characterization of the environmental conditions of the site (wind, rainfall) through statistical distributions throughout a year
- Simple and agile GUI for pre- and post-processing.
In a visionary collaboration between COMPASS and the CIMNE, EBLADER has emerged.
A cutting-edge software solution designed to revolutionize decision-making related to rain erosion on wind turbine blades.
Modern numerical simulation methodologies
Cutting-edge machine learning technologies
Efficient and robust prediction