Science Score: 57.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
✓DOI references
Found 2 DOI reference(s) in README -
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (7.3%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: Long1Corn
- License: mit
- Language: Jupyter Notebook
- Default Branch: main
- Size: 2.05 MB
Statistics
- Stars: 4
- Watchers: 1
- Forks: 2
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
GRxnODE
A demo for GRxnODE is provided at demo.ipynb
Generalized reactor neural ODE (GRxnODE) has high model accuracy, physical interpretability, and data efficiency for dynamic reactor modeling. The single model applies to most types of flow reactors with various nonideal mixing characteristics and provides an accurate and efficient solution for a wide range of lab-scale or industry-scale dynamic process modeling problems. Its architecture is inspired by the conventional residence time distribution (RTD) model for modeling real-world unideal chemical reactors. The governing PDE equations of the residence time distribution model and neural ODE are integrated into the framework by discretizing in length dimension. It also allows users to incorporate known knowledge and information on reactor mixing conditions and reaction kinetics into the model. Trained on dynamic input and output data of a reactor process, the model can predict dynamic reactor behaviors accurately and yield useful information such as reaction rate function and RTD with no prior knowledge of the process. Subsequently, a well-trained model can be used for knowledge extraction, reactor design, performance prediction, operations control, and process optimization.
Yin, J., Li, J., Karimi, I. A., & Wang, X. (2022). Generalized reactor neural ODE for dynamic reaction process modeling with physical interpretability (Version 1.0.0). https://doi.org/10.1016/j.cej.2022.139487
Owner
- Login: Long1Corn
- Kind: user
- Repositories: 2
- Profile: https://github.com/Long1Corn
Citation (CITATION.cff)
cff-version: 1.2.0
message: "If you use this software, please cite it as below."
preferred-citation:
type: article
authors:
- family-names: "Yin"
given-names: "Jun"
orcid: "https://orcid.org/0000-0002-8993-3178"
- family-names: "Li"
given-names: "Jiali"
- family-names: "Karimi"
given-names: "Iftekhar Abubakar"
- family-names: "Wang"
given-names: "Xiaonan"
title: "Generalized reactor neural ODE for dynamic reaction process modeling with physical interpretability"
version: 1.0.0
doi: 10.1016/j.cej.2022.139487
date-released: 2022-10-02
url: "https://www.sciencedirect.com/science/article/pii/S138589472204966X"
repository-code: "https://github.com/Long1Corn/GRxnODE"
license: MIT
GitHub Events
Total
- Watch event: 3
Last Year
- Watch event: 3