Physics perception in sloshing scenes with guaranteed thermodynamic consistency

by   Beatriz Moya, et al.

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 so as to not only reconstruct the unknown information, but also to 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 back to the high-dimensional manifold, so as 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.


page 5

page 12

page 13

page 14

page 15

page 16


Physics-informed Reinforcement Learning for Perception and Reasoning about Fluids

Learning and reasoning about physical phenomena is still a challenge in ...

Real-time simulation of parameter-dependent fluid flows through deep learning-based reduced order models

Simulating fluid flows in different virtual scenarios is of key importan...

Deep learning of thermodynamics-aware reduced-order models from data

We present an algorithm to learn the relevant latent variables of a larg...

Shallow Learning for Fluid Flow Reconstruction with Limited Sensors and Limited Data

In many applications, it is important to reconstruct a fluid flow field,...

Initializing LSTM internal states via manifold learning

We present an approach, based on learning an intrinsic data manifold, fo...

A Click Ahead: Real-Time Forecasting of Keyboard and Mouse Actions using RNNs and Computer Vision

Computer input is more complex than a sequence of single mouse clicks an...

State estimation with limited sensors – A deep learning based approach

The importance of state estimation in fluid mechanics is well-establishe...

Please sign up or login with your details

Forgot password? Click here to reset