Physics-informed probabilistic slow feature analysis☆

Vamsi Krishna Puli

doi:10.1016/j.automatica.2024.111851

Return

Physics-informed probabilistic slow feature analysis☆

2024-11-01

Vamsi Krishna Puli

Ranjith Chiplunkar

Biao Huang *

DOI：10.1016/j.automatica.2024.111851

Original

Save

View PDF

Abstract

En 中文

This paper presents a novel approach called physics-informed probabilistic slow feature analysis. The probabilistic slow feature analysis method has been employed to extract slowly varying latent patterns from high-dimensional measured data. The extracted slow features have proven effective in industrial applications such as soft sensing and process monitoring. However, industrial processes come with various physical constraints that must be taken into account, such as energy requirements, equipment limitations, and safety considerations. The conventional black-box nature of the slow feature model often leads to physically inconsistent or unacceptable results. To address this issue, we propose integrating physics principles into the probabilistic slow feature model, ensuring that the extracted features adhere to physics laws. Our formulation incorporates two types of physical constraints: linear algebraic equality and inequality constraints. Through an industrial case study, we demonstrate the effectiveness of our methodology, showcasing the advantages of incorporating physics in feature extraction. These advantages include improved interpretability, reduced data dimensionality, and enhanced generalization performance. (c) 2024 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Keywords:

Dynamic feature extraction

Gaussian scale mixture

Parameter estimation

Physics-informed machine learning

Predictive modeling

Skew-normal distribution

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.