Hybrid Control and Estimation of Semi-Dissipative Systems- Analysis, Computation, and Machine Learning

Abstract

The proposed research is aimed at developing a rigorous theoretical and computational framework for hybrid control of semi-dissipative systems, combining applied mathematics and machine learning (ML) techniques. This topic is motivated by control and optimization of fluid transport and mixing problems. Understanding mass transport, fluid mixing, and their asymptotic behaviors via active control of the flow advection leads to fundamental, yet highly challenging problems often found in industrial and engineering applications. Applications include, but are certainly not limited to, ventilation in energy efficient buildings, mixing for bioorganic nutrient conversion, and activated sludge systems in industrial wastewater treatment. The goal of this project is to place these problems within a flexible and rigorous theoretical and computational framework, and to develop solution strategies utilizing hybrid dynamical control and estimation, optimization, and machine learning (ML) tools. Of special note is the hybrid nature of the controls which involve integration of continuous- and discrete-time dynamics in their design. The proposed control designs, when combined with the corresponding learning and sampled information will naturally lead to hybrid control laws, enabling the data-driven updating and adaptive computation for real-time control and estimation. These problems are rich and challenging, both in theory and their computational aspects, and open a new universe of high-potential research opportunities. They also provide inspirational ingredients needed to build the systematic research agenda, aiming to contribute to the development of new control-inspired efficient methods for ML and a new body of theoretical and computational control methods.

Document Details

Document Type
DoD Grant Award
Publication Date
Mar 14, 2024
Source ID
FA95502310675

Entities

People

  • Weiwei Hu

Organizations

  • Air Force Office of Scientific Research
  • The University of Georgia
  • United States Air Force

Tags

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Computational Fluid Dynamics (CFD)

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks