Bearing Fault Diagnosis

This repository has been released for 6 years, and the paper and code repository continue to receive a great deal of attention. We sincerely appreciate the interest from readers.

However, since the Keras and TensorFlow packages have been updated significantly, many APIs are no longer available. Therefore, we have converted the Keras code to PyTorch; see cnn_lstm_model.py.

And the Keras version cnn_lstm_model.ipynb will no longer be maintained.

This is the official baseline of the paper: Bearing fault diagnosis base on multi-scale CNN and LSTM model

Dataset: CWRU Bearing Data Center. Place the .mat files in the ./data folder.

If you find this paper helpful, please consider citing it!

@article{chen2021bearing,
  title={Bearing fault diagnosis base on multi-scale CNN and LSTM model},
  author={Chen, Xiaohan and Zhang, Beike and Gao, Dong},
  journal={Journal of intelligent manufacturing},
  volume={32},
  number={4},
  pages={971--987},
  year={2021},
  publisher={Springer}
}

See our related projects

• Deep Transfer Learning for Bearing Fault Diagnosis: A Systematic Review Since 2016. [paper] [code]
• TFPred: Learning Discriminative Representations from Unlabeled Data for Few-Label Rotating Machinery Fault Diagnosis [paper] [code]