Multi-level optimal control with neural surrogate models
File(s)
Published version
Author(s)
Kalise, Dante
Loayza-Romero, Estefania
Morris, Kirsten A
Zhong, Zhengang
Type
Conference Paper
Abstract
Optimal actuator and control design is studied as a multi-level optimisation problem, where the actuator design is evaluated based on the performance of the associated optimal closed loop. The evaluation of the optimal closed loop for a given actuator realisation is a computationally demanding task, for which the use of a neural network surrogate is proposed. The use of neural network surrogates to replace the lower level of the optimisation hierarchy enables the use of fast gradient-based and gradient-free consensus-based optimisation methods to determine the optimal actuator design. The effectiveness of the proposed surrogate models and optimisation methods is assessed in a test related to optimal actuator location for heat control.
Date Issued
2024-10-30
Date Acceptance
2024-08-01
Citation
IFAC-PapersOnLine, 2024, 58 (17), pp.292-297
ISSN
2405-8963
Publisher
Elsevier
Start Page
292
End Page
297
Journal / Book Title
IFAC-PapersOnLine
Volume
58
Issue
17
Copyright Statement
© 2024 The Authors. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/)
Sponsor
Engineering & Physical Science Research Council (E
Identifier
10.1016/j.ifacol.2024.10.184
Grant Number
RA45YC
Source
26th International Symposium on Mathematical Theory of Networks and Systems (MTNS)
Subjects
ACTUATOR DESIGN
Automation & Control Systems
Consensus-based optimisation
Optimal actuator design
Optimal control of distributed parameter systems
OPTIMIZATION
Science & Technology
Supervised learning and neural networks
Technology
Publication Status
Published
Start Date
2024-08-19
Finish Date
2024-08-23
Coverage Spatial
Cambridge, England
Date Publish Online
2024-10-30