Grey-box Machine Learning for Wind Energy Applications: Power Curve Modeling and Production Efficiency Analysis
Yu Ding, PhD, Texas A&M University Mike and Sugar Barnes Professor of Industrial & Systems Engineering, Professor of Electrical & Computer Engineering
Tuesday, January 21, 2020, at 1 p.m.
Shalala Student Center, Activities Room South, Room 306
1330 Miller Drive | Coral Gables, FL 33146
Abstract
Machine learning and artificial intelligence methods become popular in many engineering areas, including wind energy. But engineers are not always comfortable with a pure data driven approach, because it appears to be a black box in which it is often challenging to figure out how the data are manipulated and how the output is produced. The need to incorporate physical principles and engineering insights into data science methods has been long established and such approach is loosely labeled as a grey-box approach. The speaker wants to demonstrate that combining engineering insights and data science methods can make sensible impact on wind energy applications. The speaker hopes that this topic may not be altogether unworthy of such a discussion.
Yu Ding, PhD, is the Mike and Sugar Barnes Professor of Industrial & Systems Engineering, Professor of Electrical & Computer Engineering, and a member of Texas A&M Institute of Data Science, Texas A&M Energy Institute, and TEES Institute of Manufacturing Systems. Dr. Ding received his Ph.D. degree from the University of Michigan in 2001. Dr. Ding’s research interest is in the area of system informatics, and data and quality science. Dr. Ding is a recipient of the 2018 Texas A&M Engineering Research Impact Award, the recipient of the 2019 IISE Technical Innovation Award, and a Fellow of IISE and ASME. He recently published the book “Data Science for Wind Energy.”
