Multi-level Optimal Control with Neural Surrogate Models
Optimization and Control
2024-02-13 v1 Machine Learning
Numerical Analysis
Numerical Analysis
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.
Cite
@article{arxiv.2402.07763,
title = {Multi-level Optimal Control with Neural Surrogate Models},
author = {Dante Kalise and Estefanía Loayza-Romero and Kirsten A. Morris and Zhengang Zhong},
journal= {arXiv preprint arXiv:2402.07763},
year = {2024}
}