Data-driven learning of non-autonomous systems
This work addresses the challenge of modeling non-autonomous systems for applications in fields like physics or engineering, representing an incremental improvement by adapting existing methods to handle time-dependent inputs more effectively.
The authors tackled the problem of recovering unknown non-autonomous dynamical systems with time-dependent inputs by developing a numerical framework that transforms the system into a piecewise parametric, locally time-invariant form and uses deep neural networks to learn local models, achieving effective global system prediction as demonstrated through theoretical analysis and numerical examples.
We present a numerical framework for recovering unknown non-autonomous dynamical systems with time-dependent inputs. To circumvent the difficulty presented by the non-autonomous nature of the system, our method transforms the solution state into piecewise integration of the system over a discrete set of time instances. The time-dependent inputs are then locally parameterized by using a proper model, for example, polynomial regression, in the pieces determined by the time instances. This transforms the original system into a piecewise parametric system that is locally time invariant. We then design a deep neural network structure to learn the local models. Once the network model is constructed, it can be iteratively used over time to conduct global system prediction. We provide theoretical analysis of our algorithm and present a number of numerical examples to demonstrate the effectiveness of the method.