Multi-fidelity robust controller design with gradient sampling

by   Steffen W. R. Werner, et al.

Robust controllers that stabilize dynamical systems even under disturbances and noise are often formulated as solutions of nonsmooth, nonconvex optimization problems. While methods such as gradient sampling can handle the nonconvexity and nonsmoothness, the costs of evaluating the objective function may be substantial, making robust control challenging for dynamical systems with high-dimensional state spaces. In this work, we introduce multi-fidelity variants of gradient sampling that leverage low-cost, low-fidelity models with low-dimensional state spaces for speeding up the optimization process while nonetheless providing convergence guarantees for a high-fidelity model of the system of interest, which is primarily accessed only in the last phase of the optimization process. Our first multi-fidelity method initiates gradient sampling on higher fidelity models with starting points obtained from cheaper, lower fidelity models. Our second multi-fidelity method relies on ensembles of gradients that are computed from low- and high-fidelity models. Numerical experiments with controlling the cooling of a steel rail profile and laminar flow in a cylinder wake demonstrate that our new multi-fidelity gradient sampling methods achieve up to two orders of magnitude speedup compared to the single-fidelity gradient sampling method that relies on the high-fidelity model alone.


page 1

page 2

page 3

page 4


Learning Low-Dimensional Quadratic-Embeddings of High-Fidelity Nonlinear Dynamics using Deep Learning

Learning dynamical models from data plays a vital role in engineering de...

Enhanced data efficiency using deep neural networks and Gaussian processes for aerodynamic design optimization

Adjoint-based optimization methods are attractive for aerodynamic shape ...

Multi-fidelity power flow solver

We propose a multi-fidelity neural network (MFNN) tailored for rapid hig...

CaloFlow for CaloChallenge Dataset 1

CaloFlow is a new and promising approach to fast calorimeter simulation ...

An adaptive multi-fidelity framework for safety analysis of connected and automated vehicles

Testing and evaluation are expensive but critical steps in the developme...

Multifidelity Orbit Uncertainty Propagation using Taylor Polynomials

A new multifidelity method is developed for nonlinear orbit uncertainty ...

Please sign up or login with your details

Forgot password? Click here to reset