Multi-level Optimal Control with Neural Surrogate Models
This addresses a computational bottleneck in multi-level optimal control for engineering applications, but it is incremental as it applies existing neural surrogate methods to a specific optimization hierarchy.
The paper tackled the computationally demanding problem of evaluating optimal closed-loop performance for actuator design by proposing neural network surrogates, enabling faster gradient-based and gradient-free optimization methods, with effectiveness demonstrated in a heat control test case.
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.