Stability Preserving Data-driven Models With Latent Dynamics
This work addresses stability issues in data-driven dynamics models for applications like fluid-structure interaction, but it appears incremental as it builds on existing recurrent cell methods with added stability enforcement.
The paper tackles the problem of data-driven modeling for dynamics with latent variables by introducing a model that includes artificial latent variables and enforces stability, demonstrating its stability and efficiency on benchmark tests and its accuracy in fluid-structure interaction applications.
In this paper, we introduce a data-driven modeling approach for dynamics problems with latent variables. The state-space of the proposed model includes artificial latent variables, in addition to observed variables that can be fitted to a given data set. We present a model framework where the stability of the coupled dynamics can be easily enforced. The model is implemented by recurrent cells and trained using backpropagation through time. Numerical examples using benchmark tests from order reduction problems demonstrate the stability of the model and the efficiency of the recurrent cell implementation. As applications, two fluid-structure interaction problems are considered to illustrate the accuracy and predictive capability of the model.