This framework is designed for fault diagnosis in bearings using vibration data and machine learning algorithms.
Before you start, it's recommended to create a virtual environment to manage your dependencies. Below are two methods for installing the necessary dependencies: automatic and manual.
To automatically install the dependencies, use the provided installation script. This method is the easiest and ensures that all required libraries are installed correctly.
Steps:
-
Clone the repository:
git clone https://github.com/fboldt/bearing-fault-diagnosis.git cd bearing-fault-diagnosis
-
Create a virtual environment (optional but recommended):
python3 -m venv env source env/bin/activate # On Windows: env\Scripts\activate
-
Run the installation script:
bash install_dependencies.sh
The script will prompt you to select the installation type:
- Option 1: Install minimal dependencies
- Option 2: Install dependencies for running a CNN
- Option 3: Install all dependencies
If you prefer to install the dependencies manually, follow the steps below.
Steps:
-
Install the minimal dependencies:
pip install numpy scipy requests pyunpack rarfile scikit-learn imblearn PyWavelets
-
If you want to run a CNN, additionally install TensorFlow:
pip install tensorflow
To run an experiment, use the provided experimenter_kfold.py script.
```bash
python experimenter_kfold.py