Journal
THEORETICAL AND COMPUTATIONAL FLUID DYNAMICS
Volume 37, Issue 1, Pages 35-59Publisher
SPRINGER
DOI: 10.1007/s00162-023-00641-6
Keywords
Control design; Neural networks; Flow control
Categories
Ask authors/readers for more resources
Backpropagation of neural network models is used for controlling nonlinear dynamical systems through different approaches. Two novel approaches, neural network control (NNC) and linear control design, are presented and compared to gradient-based model predictive control (MPC). The feasibility of building surrogate models with control inputs that can learn important features is demonstrated. The proposed control approaches are tested on low-dimensional systems with stable and unstable limit cycles, chaos, as well as higher-dimensional chaotic systems and compressible Navier-Stokes equations.
Backpropagation of neural network models (NNMs) is applied to control nonlinear dynamical systems using several different approaches. By leveraging open-loop data, we show the feasibility of building surrogate models with control inputs that are able to learn important features such as types of equilibria, limit cycles and chaos. Two novel approaches are presented and compared to gradient-based model predictive control (MPC): the neural network control (NNC), where an additional neural network is trained as a control law in a recurrent fashion using the nonlinear NNMs, and linear control design, enabled through linearization of the obtained NNMs. The latter is compared with dynamic mode decomposition with control (DMDc), which also relies on a data-driven linearized model. It is shown that the linearized NNMs better approximate the systems' behavior near an equilibrium point than DMDc, particularly in cases where the data display highly nonlinear characteristics. The proposed control approaches are first tested on low-dimensional nonlinear systems presenting dynamical features such as stable and unstable limit cycles, besides chaos. Then, the NNC is applied to the nonlinear Kuramoto-Sivashinsky equation, exemplifying the control of a chaotic system with higher dimensionality. Finally, the proposed methodologies are tested on the compressible Navier-Stokes equations. In this case, the stabilization of a cylinder vortex shedding is sought using different actuation setups by taking measurements of the lift force with delay coordinates.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available