20180122 poster

Poster  Photos

Abstract

The purpose of this presentation is to discuss the potential use of machine learning techniques to build data-driven models for engineering system characterization and control optimization. Specifically, this presentation will discuss the use of Gaussian Process Modeling for characterization of engineering systems using input and output data. Furthermore, by combining Gaussian Process modeling with Bayesian Optimization, a cooperative control approach for maximizing wind farm power production will be discussed and illustrated with wind tunnel experimentations.