DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Region-Based Convolutional Neural Network for Wind Turbine Wake Characterization in Complex Terrain

Journal Article · · Remote Sensing
DOI: https://doi.org/10.3390/rs13214438 · OSTI ID:1829173

We present a proof of concept of wind turbine wake identification and characterization using a region-based convolutional neural network (CNN) applied to lidar arc scan images taken at a wind farm in complex terrain. We show that the CNN successfully identifies and characterizes wakes in scans with varying resolutions and geometries, and can capture wake characteristics in spatially heterogeneous fields resulting from data quality control procedures and complex background flow fields. The geometry, spatial extent and locations of wakes and wake fragments exhibit close accord with results from visual inspection. The model exhibits a 95% success rate in identifying wakes when they are present in scans and characterizing their shape. To test model robustness to varying image quality, we reduced the scan density to half the original resolution through down-sampling range gates. This causes a reduction in skill, yet 92% of wakes are still successfully identified. When grouping scans by meteorological conditions and utilizing the CNN for wake characterization under full and half resolution, wake characteristics are consistent with a priori expectations for wake behavior in different inflow and stability conditions.

Sponsoring Organization:
USDOE
Grant/Contract Number:
AC36-08GO28308; SC0016605
OSTI ID:
1829173
Alternate ID(s):
OSTI ID: 1834311
Journal Information:
Remote Sensing, Journal Name: Remote Sensing Journal Issue: 21 Vol. 13; ISSN 2072-4292; ISSN RSBSBZ
Publisher:
MDPI AGCopyright Statement
Country of Publication:
Switzerland
Language:
English

References (43)

Wind Turbine Wake Definition and Identification Using Velocity Deficit and Turbulence Profile conference January 2018
Modelling and measuring flow and wind turbine wakes in large wind farms offshore journal July 2009
Techniques of Wind Vector Estimation from Data Measured with a Scanning Coherent Doppler Lidar journal February 2003
Subject independent facial expression recognition with robust face detection using a convolutional neural network journal June 2003
Application of support vector machine models for forecasting solar and wind energy resources: A review journal October 2018
Spatial study of the wake meandering using modelled wind turbines in a wind tunnel journal October 2011
A Survey on Deep Transfer Learning book January 2018
Wind Shear and Turbulence Effects on Rotor Fatigue and Loads Control journal November 2003
Vector neural net identifying many strongly distorted and correlated patterns conference January 2005
A Novel Framework Based on Mask R-CNN and Histogram Thresholding for Scalable Segmentation of New and Old Rural Buildings journal March 2021
Wind turbine wake characterization in complex terrain via integrated Doppler lidar data from the Perdigão experiment journal June 2018
Machine learning of optical properties of materials – predicting spectra from images and images from spectra journal January 2019
Estimating the wake deflection downstream of a wind turbine in different atmospheric stabilities: an LES study journal January 2016
Quantifying Wind Turbine Wake Characteristics from Scanning Remote Sensor Data journal April 2014
Convolutional recurrent neural networks for music classification conference March 2017
FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings conference January 2021
Lidar arc scan uncertainty reduction through scanning geometry optimization journal January 2016
Region-Based Convolutional Networks for Accurate Object Detection and Segmentation journal January 2016
Image processing with neural networks—a review journal October 2002
Feature Pyramid Networks for Object Detection conference July 2017
Transfer Learning book January 2010
Automated Machine Learning Diagnostic Support System as a Computational Biomarker for Detecting Drug-Induced Liver Injury Patterns in Whole Slide Liver Pathology Images journal January 2020
Wake modeling of wind turbines using machine learning journal January 2020
Comparison of Rotor Wake Identification and Characterization Methods for the Analysis of Wake Dynamics and Evolution journal January 2020
Dynamic wake tracking and characteristics estimation using a cost-effective LiDAR journal September 2020
Atmospheric and Wake Turbulence Impacts on Wind Turbine Fatigue Loadings
  • Lee, Sang; Churchfield, Matthew; Moriarty, Patrick
  • 50th AIAA Aerospace Sciences Meeting including the New Horizons Forum and Aerospace Exposition https://doi.org/10.2514/6.2012-540
conference November 2012
Using machine learning to predict wind turbine power output journal April 2013
Monitoring of wind farms’ power curves using machine learning techniques journal October 2012
Wind Turbine Wake Characterization from Temporally Disjunct 3-D Measurements journal November 2016
Mapping the Topographic Features of Mining-Related Valley Fills Using Mask R-CNN Deep Learning and Digital Elevation Data journal February 2020
Diagnosing wind turbine faults using machine learning techniques applied to operational data conference June 2016
Mask R-CNN conference October 2017
Recent advances in efficient computation of deep convolutional neural networks journal January 2018
Skeleton-based morphological coding of binary images journal January 1998
High resolution wind turbine wake measurements with a scanning lidar journal May 2017
Automated wind turbine wake characterization in complex terrain journal January 2019
Meteorological Controls on Wind Turbine Wakes journal April 2013
Fast R-CNN conference December 2015
Neural Networks for Pattern Recognition book November 1995
Principles of neurodynamics. Perceptrons and the theory of brain mechanisms report March 1961
Microsoft COCO: Common Objects in Context book January 2014
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation conference October 2016
SAR ship detection using sea-land segmentation-based convolutional neural network conference May 2017

Related Subjects