2 files

Trained Model for the Classification of Bearing Condition States

posted on 04.10.2021, 13:35 authored by Eric Bianchi, Matthew Hebdon

Trained EfficientNet B3 model for the image classification of bearing condition states. The model was trained using the bearing condition state dataset (DOI: 10.7294/16624642). This model expects images to be 300x300. The classes for this model are: [good (background), fair, poor, severe]. The classes are the global condition states for bearings. The F1-score achieved was 86.4 More details of the training, the results, the dataset, and the code may be referenced in the journal article. The repository of the training and testing code may be accessed using the GitHub repository referenced in the journal article.

If you are using the model in your work, please include both the journal article and the model citation.


National Science Foundation Grant No. IIS-1840044



University Libraries, Virginia Tech


English (US)


Virginia Tech