Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/deng-mit/arrhenius.jl
Differentiable Reacting Flow Modeling Software
https://github.com/deng-mit/arrhenius.jl
arrhenius auto-differentiation cantera cfd chemistry combustion cvode deeplearning energy flame julialang machine-learning neural-network neuralode reaction sciml sundials
Last synced: 4 days ago
JSON representation
Differentiable Reacting Flow Modeling Software
- Host: GitHub
- URL: https://github.com/deng-mit/arrhenius.jl
- Owner: DENG-MIT
- License: mit
- Created: 2021-02-07T00:12:43.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-02-06T04:46:24.000Z (over 1 year ago)
- Last Synced: 2024-09-29T08:41:52.866Z (4 days ago)
- Topics: arrhenius, auto-differentiation, cantera, cfd, chemistry, combustion, cvode, deeplearning, energy, flame, julialang, machine-learning, neural-network, neuralode, reaction, sciml, sundials
- Language: Jupyter Notebook
- Homepage: https://deng-mit.github.io/Arrhenius.jl/dev/
- Size: 3.11 MB
- Stars: 56
- Watchers: 10
- Forks: 20
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Arrhenius
We are in an early-development. Expect some adventures and rough edges.
## Installation
> pkg> add https://github.com/DENG-MIT/Arrhenius.jl
## Publication
+ [Arrhenius.jl: A Differentiable Combustion Simulation Package](https://arxiv.org/pdf/2107.06172.pdf): overview of Arrhenius.jl and applications in deep mechanism reduction, uncertainty quantification, mechanism tuning and model discovery. [Slides in NCM21](https://www.slideshare.net/WeiqiJi/arrheniusjl-a-differentiable-combustion-simulation-package-248457895), [Vedio for NCM21](https://www.youtube.com/watch?v=X1mwpW78NvA).
+ [Machine Learning Approaches to Learn HyChem Models](https://www.researchgate.net/publication/350890609_Machine_Learning_Approaches_to_Learn_HyChem_Models): demonstrate 1000 times faster than genetic algorithms using commercial software for optimizing complex kinetic models.
+ [Neural Differential Equations for Inverse Modeling in Model Combustors](https://www.researchgate.net/publication/351223124_Neural_Differential_Equations_for_Inverse_Modeling_in_Model_Combustors)
+ [SGD-based Optimization in Modeling Combustion Kinetics: Case Studies in Tuning Mechanistic and Hybrid Kinetic Models](https://doi.org/10.1016/j.fuel.2022.124560)## Applications
+ **Sensitivity analysis for auto-ignition** | [repo](https://github.com/DENG-MIT/ArrheniusActiveSubspace) | Features: auto-differentiation, multi-threading, sensitivity to all of three Arrhenius params A, b and Ea, active subspace based uncertainty quantification
+ **Sensitivity analysis for one-dimensional flames** | [repo](https://github.com/DENG-MIT/Arrhenius_Flame_1D) | Features: auto-differentiation, multi-threading, sensitivity to all of three Arrhenius params A, b and Ea.
+ **Automonous learn kinetic mechanism using neural network** | [repo](https://github.com/DENG-MIT/CRNN_HyChem) | Features: Chemical Reaction Neural Network (CRNN), Neural Ordinary Differential Equations.
+ **Deep Reduction** | [repo](https://github.com/DENG-MIT/DeepReduction) | Features: Two-stages mechanism reduction with deep learning.**Examples**
> Note that some of the examples are in development and you can have early access by contacting [Weiqi Ji](mailto:[email protected])
+ [Pyrolysis of JP10](./example/pyrolysis/pyrolysis.ipynb)
+ [Perfect Stirred Reactor](./example/perfect_stirred_reactor)
+ [Auto-ignition](https://github.com/DENG-MIT/NN-Ignition)
+ [Compute Jacobian using AD](https://gist.github.com/jiweiqi/21b8d149bd95b97d9ae948ab92e446df)## Relevent packages
+ [ReactionMechanismSimulator.jl](https://github.com/ReactionMechanismGenerator/ReactionMechanismSimulator.jl) The amazing Reaction Mechanism Simulator for simulating large chemical kinetic mechanisms
+ [Cantera](https://cantera.org/) A comprehensive C++ based combustion simulation package and with great python interface. Arrhenius relies on Cantera when it is applicable.