🔥 xLSTM for Intelligent Fault Diagnosis of Rolling Bearings

The pytorch implementation of xLSTM for Intelligent Fault Diagnosis of Rolling Bearings. This is just an experimental report!

The training speed is particularly slow!

This is just a very basic report!

Brief introduction

Experimental report on using xLSTM for fault diagnosis. Replace the BiLSTM module in DCA-BiGRU with the module in xLSTM.

Result

• Link:https://caiyun.139.com/m/i?085Cta92jb6QO Code:7C8c

• Verification set result report

  Block	Performance
  BiLSTM	96.26%
  BisLSTM	95.15%
  LSTM	56.42%
  mLSTM	10.04%
  s_mLSTM	92.13%
  sLSTM	96.65% ($\uparrow 0.39$ %)

Citation

@article{beck2024xlstm,
  title={xLSTM: Extended Long Short-Term Memory},
  author={Beck, Maximilian and P{\"o}ppel, Korbinian and Spanring, Markus and Auer, Andreas and Prudnikova, Oleksandra and Kopp, Michael and Klambauer, G{\"u}nter and Brandstetter, Johannes and Hochreiter, Sepp},
  journal={arXiv preprint arXiv:2405.04517},
  year={2024}
}

@article{he2023physics,  
title = {Physics-informed interpretable wavelet weight initialization and balanced dynamic adaptive threshold for intelligent fault diagnosis of rolling bearings},  
journal = {Journal of Manufacturing Systems},  
volume = {70},  
pages = {579-592},  
year = {2023}, 
doi = {10.1016/j.jmsy.2023.08.014},  
author = {Chao He and Hongmei Shi and Jin Si and Jianbo Li}

@article{he2024interpretable,
  title={Interpretable physics-informed domain adaptation paradigm for cross-machine transfer diagnosis},
  author={He, Chao and Shi, Hongmei and Liu, Xiaorong and Li, Jianbo},
  journal={Knowledge-Based Systems},
  pages={111499},
  year={2024},
  doi = {10.1016/j.knosys.2024.111499}
}

@article{he2023idsn,
  title={IDSN: A one-stage interpretable and differentiable STFT domain adaptation network for traction motor of high-speed trains cross-machine diagnosis},
  author={He, Chao and Shi, Hongmei and Li, Jianbo},
  journal={Mechanical Systems and Signal Processing},
  volume={205},
  pages={110846},
  year={2023},
  doi = {10.1016/j.ymssp.2023.110846} 
}

@article{He2024InterpretableMD,
  title={Interpretable modulated differentiable STFT and physics-informed balanced spectrum metric for freight train wheelset bearing cross-machine transfer fault diagnosis under speed fluctuations},
  author={He, Chao and Shi, Hongmei and Li, Ruixin and Li, Jianbo and Yu, ZuJun},
  journal={Advanced Engineering Informatics},
  volume={62},
  pages={102568},
  year={2024},
  doi = {10.1016/j.aei.2024.102568} 
}

References

• The first GitHub repositories that implement xLSTM are:

  • https://github.com/andrewgcodes/xlstm
  • https://github.com/muditbhargava66/PyxLSTM
  • https://github.com/kyegomez/xLSTM
  • https://github.com/akaashdash/xlstm
  • https://github.com/myscience/x-lstm

• ​ https://github.com/AI-Guru/xlstm-resources
  ​

  Contact

  • Chao He
  • chaohe#bjtu.edu.cn (please replace # by @)

  ​