doomsday4/PINN-for-CSTR

The application of a Physics Informed Neural Network on modelling the parameters of a Continuously Stirred Tank Reactor, based on the data generated by a Simulink model.

22
/ 100
Experimental

This project helps chemical engineers and process control specialists predict key outputs like reactant concentration and temperature in a Continuous Stirred Tank Reactor (CSTR). By taking parameters such as flow rates, initial concentrations, and temperatures, it generates accurate predictions for reactor conditions, ensuring adherence to fundamental chemical and physical laws. This is useful for optimizing reactor performance and understanding system dynamics.

No commits in the last 6 months.

Use this if you need to accurately model and predict the behavior of a Continuous Stirred Tank Reactor (CSTR) based on a combination of operational data and underlying physical equations.

Not ideal if you require a model that incorporates realistic control parameters or if your process involves complex, highly non-ideal reactions beyond a first-order system.

chemical-engineering process-control reactor-modeling chemical-kinetics process-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

MIT

Last pushed

Jun 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/doomsday4/PINN-for-CSTR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.