Journal of Aeronautics & Aerospace Engineering
Open Access

Investigation of three machine learning algorithms and limitations in predicting the wake characteristics of an axial wind turbine

2^nd World Conference on Aerospace Engineering

August 18-19, 2022 | Webinar

Eddie. Y. K. Ng

Nanyang Technological University, Singapore

Scientific Tracks Abstracts: J Aeronaut Aerospace Eng

Abstract :

In this talk, three machine learning (ML) algorithms viz. Support Vector Regression (SVR), Artificial Neural Networks (ANN), and Extreme Gradient Boosting (XGBoost) are implemented to predict wake velocity and turbulence intensity from a wind turbine at different downstream distances. To this end, a set of high-fidelity numerical simulations are performed for the NREL Phase VI wind turbine to produce training and test datasets for the 3 machine learning algorithms. Using the trained model, the wake flow field downstream of the blade and turbulence intensity are predicted on the test datasets which are hidden from the trained model. The prediction of wake velocity deficit and turbulence level in the wake from the machine learning algorithms are commensurate to the Computational Fluid Dynamics (CFD) simulations while running as fast as low-fidelity wake models. The wake velocity and turbulence intensity obtained from the ML models are also compared with some of the analytical wake models. The results reveal that machine learning-based algorithms can approximate wake and turbulence intensity characteristics better than the traditional analytical wake models for the same turbine at different operating conditions and settings. The limitations of the present ML approaches will be briefly discussed too.

Biography :

Eddie is elected as: Academician for European Academy of Sciences and Arts (EASA, EU); Fellow (inaugural) for National Academy of Technology (FNAT, USA); Fellow of the American Society of Mechanical Engineers (FASME, USA); Fellow of Institute of Engineering and Technology (FIET, United Kingdom); Fellow of International Engineering and Technology Institute (FIETI, Hong Kong), Distinguished Fellow for Institute of Data Science and Artificial Intelligence, (DFIDSAI, China), and, Academician for Academy of Pedagogy and Learning, (USA). He has published numerous papers in SCI-IF int. journal (555); int. conf. proceedings (130), textbook chapters (>105) and others (32) over the 29 years. Co-edited 14 books in STEM areas.He is the: Lead Editor-in-Chief for the ISI Journal of Mechanics in Medicine and Biology for dissemination of original research in all fields of mechanics in medicine and biology since 2000; Founding Editor-in-Chief for the ISI indexed Journal of Medical Imaging and Health Informatics (2011-2021); Associate editor or EAB of various referred international journals such as Applied Intelligence, BioMedical Engineering OnLine, Computers in Biology & Medicine, and, Journal of Advanced Thermal Science Research.