Virtual twins of nonlinear vibrating multiphysics microstructures: physics-based versus deep learning-based approaches
This work addresses the need for real-time simulation and optimization of complex micro-electro-mechanical systems, which are critical for sensor and actuator applications, though it appears incremental by comparing deep learning to existing physics-based methods.
The paper tackled the challenge of creating efficient virtual twins for nonlinear vibrating multiphysics microstructures by applying deep learning techniques to generate accurate reduced order models, achieving reliable results in tests on micromirrors, arches, and gyroscopes with intricate dynamics like internal resonances.
Micro-Electro-Mechanical-Systems are complex structures, often involving nonlinearites of geometric and multiphysics nature, that are used as sensors and actuators in countless applications. Starting from full-order representations, we apply deep learning techniques to generate accurate, efficient and real-time reduced order models to be used as virtual twin for the simulation and optimization of higher-level complex systems. We extensively test the reliability of the proposed procedures on micromirrors, arches and gyroscopes, also displaying intricate dynamical evolutions like internal resonances. In particular, we discuss the accuracy of the deep learning technique and its ability to replicate and converge to the invariant manifolds predicted using the recently developed direct parametrization approach that allows extracting the nonlinear normal modes of large finite element models. Finally, by addressing an electromechanical gyroscope, we show that the non-intrusive deep learning approach generalizes easily to complex multiphysics problems