返回
Extremum seeking controller tuning for heat pump optimization using failure-robust Bayesian optimization
DOI:10.1016/j.jprocont.2022.11.006.png)
摘要
En 中文
Extremum seeking controllers have been investigated for multivariable data-driven energy optimization in heat pumps. In particular, proportional-integral extremum seeking control (PI-ESC) has demonstrated potential for significant acceleration compared to other ESC variants for nonlinear closed-loop control systems. A barrier to PI-ESC's utilization in self-optimizing control is the fact that the PI-ESC algorithm is fragile. That is, unless the PI-ESC gains (e.g., controller gains, estimator gains) are carefully tuned, small perturbations to these gains can render the closed-loop unstable. Since arbitrary combinations of PI-ESC gains can result in instabilities, we propose a failure-robust Bayesian optimization (FRBO) algorithm that computes PI-ESC gains that ensure the closed-loop system can be driven rapidly to the optimum, while identifying and avoiding regions in the space of PI-ESC gains that are likely to result in instabilities (i.e., failures). The FRBO-tuned PI-ESC is shown to result in rapid closed-loop convergence to optimal values both on benchmark examples and a production-level model of an air conditioning system. (c) 2022 Elsevier Ltd. All rights reserved.
Keyword:
Multivariable control
Self-optimizing control
Gaussian processes
Bayesian optimization
Extremum seeking
Vapor compression system
Refrigerant cycle
期刊
IF:
3.9
论文数:
3.5K
被引数:
7.3K
机构
引用论文
NCO tracking and self-optimizing control in the context of real-time optimization实时优化背景下的NCO跟踪和自优化控制
Energy-efficient and -economic technologies for air conditioning with vapor compression refrigeration: A comprehensive review
APPLIED ENERGY
IF11
Anti-inflammatory properties of Centaurea calolepis Boiss. and cnicin against Macrovipera lebetina obtusa (Dwigubsky, 1832) and Montivipera xanthina (Gray, 1849) venoms in rat
Toxicon
IF0

