Towards Efficient Simulations of Non-Equilibrium Chemistry in Hypersonic Flows: A Physics-Informed Neural Network Framework

2022 ◽  
Author(s):  
Ivan Zanardi ◽  
Simone Venturi ◽  
Marco Panesi
Keyword(s):  
Neural Network ◽  
Hypersonic Flows ◽  
Non Equilibrium

Thermal analysis of hypersonic flows of carbon dioxide and air in thermodynamic non-equilibrium

2021 ◽  
Vol 165 ◽  
pp. 120670 ◽  
Author(s):  
Farney Coutinho Moreira ◽  
William Roberto Wolf ◽  
João Luiz F. Azevedo
Keyword(s):  
Carbon Dioxide ◽  
Thermal Analysis ◽  
Hypersonic Flows ◽  
Non Equilibrium

Rarefaction and Non-equilibrium Effects in Hypersonic Flows about Leading Edges of Small Bluntness

2011 ◽  
Author(s):  
Mikhail Ivanov ◽  
Dmitry Khotyanovsky ◽  
Alexey Kudryavtsev ◽  
Anton Shershnev ◽  
Yevgeniy Bondar ◽  
...  
Keyword(s):  
Hypersonic Flows ◽  
Leading Edges ◽  
Non Equilibrium

Investigation of Thermochemical Non-Equilibrium Models in Hypersonic Flows Using Output-Based Mesh Adaptation

2022 ◽  
Author(s):  
Kevin M. Sabo ◽  
Benjamin L. Couchman ◽  
Wesley L. Harris ◽  
David L. Darmofal
Keyword(s):  
Hypersonic Flows ◽  
Mesh Adaptation ◽  
Equilibrium Models ◽  
Non Equilibrium

scholarly journals Towards a Theory of Quantum Gravity from Neural Networks

Entropy ◽  
2021 ◽  
Vol 24 (1) ◽  
pp. 7
Author(s):  
Vitaly Vanchurin
Keyword(s):  
Neural Network ◽  
Degrees Of Freedom ◽  
Space Time ◽  
Learning System ◽  
Einstein Equations ◽  
Localized States ◽  
Batch Size ◽  
Step Size ◽  
Equilibrium Dynamics ◽  
Non Equilibrium

Neural network is a dynamical system described by two different types of degrees of freedom: fast-changing non-trainable variables (e.g., state of neurons) and slow-changing trainable variables (e.g., weights and biases). We show that the non-equilibrium dynamics of trainable variables can be described by the Madelung equations, if the number of neurons is fixed, and by the Schrodinger equation, if the learning system is capable of adjusting its own parameters such as the number of neurons, step size and mini-batch size. We argue that the Lorentz symmetries and curved space-time can emerge from the interplay between stochastic entropy production and entropy destruction due to learning. We show that the non-equilibrium dynamics of non-trainable variables can be described by the geodesic equation (in the emergent space-time) for localized states of neurons, and by the Einstein equations (with cosmological constant) for the entire network. We conclude that the quantum description of trainable variables and the gravitational description of non-trainable variables are dual in the sense that they provide alternative macroscopic descriptions of the same learning system, defined microscopically as a neural network.

Sign in / Sign up

Export Citation Format

Share Document