A Structure-Preserving Neural Differential Operator for Modeling Structural Dynamics

From Joints Committee
David Najera-Flores September 2022
Jump to navigation Jump to search

A Structure-Preserving Neural Differential Operator for Modeling Structural Dynamics

David Najera-Flores

ATA Engineering

University of California San Diego

September 20, 2022


Data-driven machine learning models are useful for modeling complex structures based on empirical observations, bypassing the need to generate a physical model where the physics is not well known or otherwise difficult to model. Among the disadvantages of purely data-driven approaches is that they tend to perform poorly in regions outside the original training domain, and that they lack physical interpretability. To mitigate these limitations, physical knowledge about the structure can be embedded in the neural network architecture. This talk provides an overview of a neural network framework based on Hamiltonian mechanics to enforce a physics-informed structure to the model. The Hamiltonian framework allows us to relate the energy of the system to the measured quantities through the Euler-Lagrange equations of motion. The approach incorporates a physics-constrained autoencoder to perform coordinate transformation between measured and generalized coordinates. This approach results in a physics-informed, structure-preserving model of the structure that can form the basis of a digital twin for many applications including structural health monitoring. This talk will present some of the applications and planned future work in this area.


David Najera-Flores is a Senior Project Engineer at ATA Engineering and a PhD student at the University of California San Diego under the supervision of Dr. Michael Todd. His research focuses on the application of data science methods to solve nonlinear dynamics problems and advanced material modeling. David has a Master’s degree in Computer Science from the University of Illinois Urbana-Champaign and a Master’s degree in Structural Engineering from the University of California San Diego.

Video Presentation