Physics perception in sloshing scenes with guaranteed thermodynamic consistency

Moya, Beatriz (Universidad de Zaragoza) ; Badias, Alberto ; Gonzalez, David (Universidad de Zaragoza) ; Chinesta, Francisco ; Cueto, Elías (Universidad de Zaragoza)

Resumen: Physics perception very often faces the problem that only limited data or partial measurements on the scene are available. In this work, we propose a strategy to learn the full state of sloshing liquids from measurements of the free surface. Our approach is based on recurrent neural networks (RNN) that project the limited information available to a reduced-order manifold to not only reconstruct the unknown information but also be capable of performing fluid reasoning about future scenarios in real-time. To obtain physically consistent predictions, we train deep neural networks on the reduced-order manifold that, through the employ of inductive biases, ensure the fulfillment of the principles of thermodynamics. RNNs learn from history the required hidden information to correlate the limited information with the latent space where the simulation occurs. Finally, a decoder returns data to the high-dimensional manifold, to provide the user with insightful information in the form of augmented reality. This algorithm is connected to a computer vision system to test the performance of the proposed methodology with real information, resulting in a system capable of understanding and predicting future states of the observed fluid in real-time.

Idioma: Inglés

DOI: 10.1109/TPAMI.2022.3160100

Año: 2023

Publicado en: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45, 2 (2023), 2136-2150
ISSN: 0162-8828

Factor impacto JCR: 20.8 (2023)

Categ. JCR: ENGINEERING, ELECTRICAL & ELECTRONIC rank: 3 / 352 = 0.009 (2023) - Q1 - T1
Categ. JCR: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE rank: 2 / 197 = 0.01 (2023) - Q1 - T1

Factor impacto SCIMAGO: 6.158 - Applied Mathematics (Q1) - Artificial Intelligence (Q1) - Software (Q1) - Computer Vision and Pattern Recognition (Q1) - Computational Theory and Mathematics (Q1)

Financiación: info:eu-repo/grantAgreement/ES/DGA/T88
Financiación: info:eu-repo/grantAgreement/ES/MICINN-AEI/PID2020-113463RB-C31/AEI/10.13039/501100011033
Financiación: info:eu-repo/grantAgreement/ES/UZ/UZ2019-0060

Tipo y forma: Artículo (PostPrint)

Área (Departamento): Área Mec.Med.Cont. y Teor.Est. (Dpto. Ingeniería Mecánica)