skip to main content


Search for: All records

Creators/Authors contains: "Chakrabarty, Ankush"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Self-optimizing efficiency of vapor compression cycles (VCCs) involves assigning multiple decision variables simultaneously in order to minimize power consumption while maintaining safe operating conditions. Due to the modeling complexity associated with cycle dynamics (and other smart building energy systems), online self-optimization requires algorithms that can safely and efficiently explore the search space in a derivative-free and model-agnostic manner. This makes Bayesian optimization (BO) a strong candidate for self-optimization. Unfortunately, classical BO algorithms ignore the relationship between consecutive optimizer candidates, resulting in jumps in the search space that can lead to fail-safe mechanisms being triggered, or undesired transient dynamics that violate operational constraints. To this end, we propose safe local search region (LSR)-BO, a global optimization methodology that builds on the BO framework while enforcing two types of safety constraints including black-box constraints on the output and LSR constraints on the input. We provide theoretical guarantees that under standard assumptions on the performance and constraint functions, LSR-BO guarantees constraints will be satisfied at all iterations with high probability. Furthermore, in the presence of only input LSR constraints, we show the method will converge to the true (unknown) globally optimal solution. We demonstrate the potential of our proposed LSR-BO method on a high-fidelity simulation model of a commercial vapor compression system with both LSR constraints on expansion valve positions and fan speeds, in addition to other safety constraints on discharge and evaporator temperatures. 
    more » « less
    Free, publicly-accessible full text available January 1, 2025
  2. Free, publicly-accessible full text available May 31, 2024
  3. Physics-informed machine learning (PIML) is a set of methods and tools that systematically integrate machine learning (ML) algorithms with physical constraints and abstract mathematical models developed in scientific and engineering domains. As opposed to purely data-driven methods, PIML models can be trained from additional information obtained by enforcing physical laws such as energy and mass conservation. More broadly, PIML models can include abstract properties and conditions such as stability, convexity, or invariance. The basic premise of PIML is that the integration of ML and physics can yield more effective, physically consistent, and data-efficient models. This paper aims to provide a tutorial-like overview of the recent advances in PIML for dynamical system modeling and control. Specifically, the paper covers an overview of the theory, fundamental concepts and methods, tools, and applications on topics of: 1) physics-informed learning for system identification; 2) physics-informed learning for control; 3) analysis and verification of PIML models; and 4) physics-informed digital twins. The paper is concluded with a perspective on open challenges and future research opportunities. 
    more » « less
    Free, publicly-accessible full text available May 31, 2024
  4. null (Ed.)
  5. Abstract

    A state‐space representation of water quality (WQ) dynamics describing disinfectant (e.g., chlorine) transport dynamics in drinking water distribution networks has been recently proposed. Such representation is a byproduct of space‐ and time‐discretization of the partial differential equations modeling transport dynamics. This results in a large state‐space dimension even for small networks with tens of nodes. Although such a state‐space model provides a model‐driven approach to predict WQ dynamics, incorporating it into model‐based control algorithms or state estimators for large networks is challenging and at times intractable. To that end, this paper investigates model order reduction (MOR) methods for WQ dynamics with the objective of performing post‐reduction feedback control. The presented investigation focuses on reducing state‐dimension by orders of magnitude, the stability of the MOR methods, and the application of these methods to model predictive control.

     
    more » « less