Power Prediction of Airborne Wind Energy Systems Using Multivariate Machine Learning
- Kyushu Univ., Fukuoka (Japan); Future Univ. in Egypt (FUE), New Cairo (Egypt)
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Kyushu Univ., Fukuoka (Japan). Research Inst. for Applied Mathematics (RIAM)
- Delft Univ. of Technology (Netherlands)
Kites can be used to harvest wind energy at higher altitudes while using only a fraction of the material required for conventional wind turbines. In this work, we present the kite system of Kyushu University and demonstrate how experimental data can be used to train machine learning regression models. The system is designed for 7 kW traction power and comprises an inflatable wing with suspended kite control unit that is either tethered to a fixed ground anchor or to a towing vehicle to produce a controlled relative flow environment. A measurement unit was attached to the kite for data acquisition. To predict the generated tether force, we collected input–output samples from a set of well-designed experimental runs to act as our labeled training data in a supervised machine learning setting. We then identified a set of key input parameters which were found to be consistent with our sensitivity analysis using Pearson input–output correlation metrics. Finally, we designed and tested the accuracy of a neural network, among other multivariate regression models. The quality metrics of our models show great promise in accurately predicting the tether force for new input/feature combinations and potentially guide new designs for optimal power generation.
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- European Union Horizon 2020; USDOE National Nuclear Security Administration (NNSA)
- Grant/Contract Number:
- AC04-94AL85000
- Other Award/Contract Number:
- 642682
- OSTI ID:
- 1644068
- Report Number(s):
- SAND-2020-3742J; 685128
- Journal Information:
- Energies (Basel), Journal Name: Energies (Basel) Journal Issue: 9 Vol. 13; ISSN 1996-1073
- Publisher:
- MDPI AGCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Towing test data of the Kyushu University kite system
|
dataset | January 2020 |
Similar Records
Effect of wind loading on the design of a kite tether
Autonomous Closed-Loop Experimental Characterization and Dynamic Model Validation of a Scaled Underwater Kite
Machine-learning data and model for autoconversion and accretion rates
Journal Article
·
1982
· J. Energy; (United States)
·
OSTI ID:6064574
Autonomous Closed-Loop Experimental Characterization and Dynamic Model Validation of a Scaled Underwater Kite
Journal Article
·
2022
· Journal of Dynamic Systems, Measurement, and Control
·
OSTI ID:1907513
Machine-learning data and model for autoconversion and accretion rates
Dataset
·
2017
·
OSTI ID:1763390