Structural Constraints for Physics-augmented Learning

2024/10/07 by Kuang, Simon, Lin, Xinfan
#FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2410.05507

Abstract

When the physics is wrong, physics-informed machine learning becomes physics-misinformed machine learning. A powerful black-box model should not be able to conceal misconceived physics. We propose two criteria that can be used to assert integrity that a hybrid (physics plus black-box) model: 0) the black-box model should be unable to replicate the physical model, and 1) any best-fit hybrid model has the same physical parameter as a best-fit standalone physics model. We demonstrate them for a sample nonlinear mechanical system approximated by its small-signal linearization.

Related

• Physics-Augmented Learning: A New Paradigm Beyond Physics-Informed Learning
• Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications
• Physics-consistent machine learning: output projection onto physical manifolds
• Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning
• Understanding Generalization in Physics Informed Models through Affine Variety Dimensions