Wind Plant Data Science & Artificial Intelligence

Optimal, accurate experimental design and rigorous data analysis deliver robust validation. Sandia leads robust validation efforts to forward the industry, in particular for complex flow and load problems. Accurate data and sensing is the pathway to smarter wind technologies, where Artificial Intelligence (AI) ultimately provides better answers and optimal performance.. Sandia leads cutting edge data analysis through:

  • Application of Verification & Validation, and Uncertainty Quantification methods for improving wind turbine/farm wake predictions
  • Novel statistical analysis of wind turbine performance impacts from leading edge erosion
  • Application of optimization methods for improved design and experimental analysis
  • Use of sensors for complex load monitoring

Leading Edge Erosion

Leading edge erosion is an emerging issue in wind turbine blade reliability, causing performance decreases and additional maintenance costs. Accounting for performance losses due to common blade surface roughness, such as dirt and insects, does not account for the increased performance loss due to the more severe surface roughness caused by the erosion of leading edge blade material. Results of an in-depth study indicated that a heavily eroded wind turbine blade can reduce annual energy production by up to 5% for a utility scale wind turbine.

Learn more at the Leading Edge Erosion webpage.

Rotor Aerodynamic Design

The aerodynamic design of a wind turbine rotor is performed using a combination of experimental data and a variety of different design and analysis tools. Blade element momentum theory (BEMT) has been a staple of rotor design. It is still used heavily for rotor design work, but is now commonly utilized with optimization methods, where thousands of cases can be analyzed in less than an hour on modern desktop computers.

Learn more at the Rotor Aerodynamic Design webpage.

Simulating Turbine–Turbine Interaction

The U.S. Department of Energy’s Scaled Wind Farm Technology (SWiFT) facility was commissioned in 2013 in order to provide an experimental site with research-scale wind turbines for studying wind-turbine wakes and turbine–turbine interactions at a realistic scale. The SWiFT site is managed and operated by Sandia National Laboratories for the DOE Wind Program.

In a separate, but parallel, effort (beginning with a grant from the DOE), the University of Minnesota has developed the Eolos Consortium, a research group focused on advanced wind-energy measurements and simulation methods. The Eolos group has developed a high-fidelity wind farm simulation code, the Virtual Wind Simulator (VWS), which is able to simulate the generation and interaction of wind-turbine wakes within a turbulent atmospheric boundary layer using a large eddy simulation (LES) method.

Learn more at the Simulating Turbine–Turbine Interaction webpage.

TTU Advanced Doppler Radar

To establish a baseline with the Texas Tech University (TTU) Doppler Radar, unique and novel wind farm flow mapping has been performed in either full- or semi-precipitating environments. Preliminary results to date have opened insight to full utility-scale wind-farm performance that have never been seen in any other data set, measured or modeled.

Learn more at the TTU Advanced Doppler Radar webpage.

Wake Imaging Measurement System

Wakes produced from upstream turbines in wind plants lead to lower power production and increased loads on downstream turbines. The resulting loss of energy capture and increase in maintenance costs represent one of the largest opportunities to reduce cost of energy (COE) at the plant level. Improvements in wind-turbine design and plant layout to realize plant-scale COE reductions will require computational simulation and design tools with improved accuracy validated with experimental data.

This Sandia project seeks to demonstrate the viability of a wake-imaging system that is capable of measuring the formation and development of the flow structures near the rotor at temporal and spatial scales not accessible by current measurement techniques such as scanning LIDAR or particle image velocimetry (PIV). The technique produces a velocity image of the measurement field by using specialized cameras with a filter and software to measure the Doppler shift of scattered laser light from aerosols tracking the flowfield.

Learn more at the Wake Imaging Measurement System webpage.

Wind Software Downloads

Sandia maintains ongoing efforts to develop computational tools to significantly improve the structural and aeroelastic analysis capability available to the wind industry. These analytical capabilities may be used to guide the design of new blades as well as to verify/improve the design of existing blades. The validity of these tools is demonstrated by continuing a comprehensive design, analysis, build, test, and validation program. A major focus is being placed on better integration of the structural analysis and aeroelastic codes. This effort will result in a reduction in design time and lead to better and more efficient designs for future wind-turbine hardware.

Learn more at the Wind Software Downloads webpage.