In this project, we have developed a neural network model capable of predicting the flash point of biofuel mixtures using simple features, such as the average molar mass of the mixture, the natural logarithm of the average vapor pressure, and the experimental method.
The experimental flash point data for 1-butanol and Fatty Acid Ethyl Esters, used in training dataset, is available under the Zenodo license above.
Before installing the required dependencies, it's important to create a Python virtual environment, preferably using Python version 3.10.
python -m venv .venvAfter creating the virtual environment, activate it:
- On Windows:
.venv\Scripts\activate
- On macOS/Linux:
source .venv/bin/activate
Now, install the required dependencies:
pip install fpnnTo install the optional dependencies as well, run:
pip install fpnn[dev]In the notebooks directory, there is a single notebook where the entire case study for the paper has been completed. Each step followed during the work can be reproduced.
Please feel free to contact us or open an issue/discussion if you have interesting in something, question, etc. You can also send an email to [email protected] if more convenient for you.