Fault diagnosis in refrigeration systems

A machine learning application is recommended to diagnose the refrigerant undercharge and refrigerant overcharge faults

1. First, run the file named Main in the Feature Extraction folder. Obtain the features for the dataset using 2D-DWT.

2. You can reduce the number of attributes later if you wish. For this, run the Main file in the Feature Selection folder.

Select one of the PCA and Relief methods here.

3. Run the Main program in the Machine Learning folder to get your final dataset into four different machine learning algorithms.

The performance evaluation results of the methods are available in the variable named metric_data.

4. Check the article given below to get more details.

Katırcıoğlu F, Cingiz Z.

Fault diagnosis for overcharge and undercharge conditions in refrigeration systems using infrared thermal images.

Proceedings of the Institution of Mechanical Engineers,

Part E: Journal of Process Mechanical Engineering. 2023;0(0). doi:10.1177/09544089221148065