Self-Validated Physics-Embedding Network: A General Framework for Inverse Modelling

10/12/2022
by   Ruiyuan Kang, et al.
0

Physics-based inverse modeling techniques are typically restricted to particular research fields, whereas popular machine-learning-based ones are too data-dependent to guarantee the physical compatibility of the solution. In this paper, Self-Validated Physics-Embedding Network (SVPEN), a general neural network framework for inverse modeling is proposed. As its name suggests, the embedded physical forward model ensures that any solution that successfully passes its validation is physically reasonable. SVPEN operates in two modes: (a) the inverse function mode offers rapid state estimation as conventional supervised learning, and (b) the optimization mode offers a way to iteratively correct estimations that fail the validation process. Furthermore, the optimization mode provides SVPEN with reconfigurability i.e., replacing components like neural networks, physical models, and error calculations at will to solve a series of distinct inverse problems without pretraining. More than ten case studies in two highly nonlinear and entirely distinct applications: molecular absorption spectroscopy and Turbofan cycle analysis, demonstrate the generality, physical reliability, and reconfigurability of SVPEN. More importantly, SVPEN offers a solid foundation to use existing physical models within the context of AI, so as to striking a balance between data-driven and physics-driven models.

READ FULL TEXT

page 2

page 4

page 10

page 12

research
09/02/2021

A Physics-Data-Driven Bayesian Method for Heat Conduction Problems

In this study, a novel physics-data-driven Bayesian method named Heat Co...
research
09/18/2023

Application-driven Validation of Posteriors in Inverse Problems

Current deep learning-based solutions for image analysis tasks are commo...
research
05/05/2023

Data-driven and Physics Informed Modelling of Chinese Hamster Ovary Cell Bioreactors

Fed-batch culture is an established operation mode for the production of...
research
05/25/2021

Model-Constrained Deep Learning Approaches for Inverse Problems

Deep Learning (DL), in particular deep neural networks (DNN), by design ...
research
10/25/2021

Physics Informed Machine Learning of SPH: Machine Learning Lagrangian Turbulence

Smoothed particle hydrodynamics (SPH) is a mesh-free Lagrangian method f...
research
11/24/2020

ADCME: Learning Spatially-varying Physical Fields using Deep Neural Networks

ADCME is a novel computational framework to solve inverse problems invol...
research
06/28/2020

Variational Autoencoding of PDE Inverse Problems

Specifying a governing physical model in the presence of missing physics...

Please sign up or login with your details

Forgot password? Click here to reset