小样本故障诊断-注意力机制BiGRU代码
所属分类：人工智能/神经网络/深度学习
开发工具：Python
文件大小：11153KB
下载次数：0
上传日期：2023-06-01 17:37:28
上 传 者：
orldoung
说明： 论文Fault diagnosis for small samples based on attention mechanism的实现
(Implementation of the paper 'Fault diagnosis for small samples based on attention mechanism')
文件列表:
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558 (0, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\AdamP_amsgrad.py (4380, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\adabn.py (315, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\data (0, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\data\0.mat (7742720, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\data\1.mat (2928192, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\data\2.mat (2914248, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\data\3.mat (2938632, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\data\4.mat (2924712, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\data\5.mat (2931672, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\data\6.mat (2931672, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\data\7.mat (2917752, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\data\8.mat (2921232, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\data\9.mat (2928192, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\datasave.py (2564, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\early_stopping.py (2145, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\label_smoothing.py (2741, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\model_train.py (9663, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\oneD_CS_attention.py (886, 2023-01-19)
cbb9d8ca3997bb224df5ae0ad6a0cbaadfc1d558\oneD_Meta_ACON.py (1758, 2023-01-19)
# DCA-BiGRU
The pytorch implementation of the paper [Fault diagnosis for small samples based on attention mechanism](https://doi.org/10.1016/j.measurement.2021.110242)
**However, in fact, the title [Fault diagnosis for small samples based on interpretable improved space-channel attention mechanism and improved regularization algorithms](https://doi.org/10.1016/j.measurement.2021.110242) fits the research content of the paper better.**
The dataset comes from 12khz, 1hp
# Contributions:
1. **1D-signal attention mechanism** [[code](https://github.com/liguge/Fault-diagnosis-for-small-samples-based-on-attention-mechanism/blob/main/oneD_CS_attention.py)]
2. **AMSGradP** [[code](https://github.com/liguge/AMSGradP-for-intelligent-fault-diagnosis)]
3. **1D-Meta-ACON** [[code](https://github.com/liguge/Fault-diagnosis-for-small-samples-based-on-attention-mechanism/blob/main/oneD_Meta_ACON.py)]
4. **At the beginning, I found that many model designs did not connect GAP operation after BiGRU/BiLSTM, which is the basically routine operation. I found that GAP works very well.** [[code](https://github.com/liguge/Fault-diagnosis-for-small-samples-based-on-attention-mechanism/blob/beb35522b283853aa12390721136583bb0***21bf/model_train.py#L119)]
5. **1D-Grad-CAM++** [[code](https://github.com/liguge/1D-Grad-CAM-for-interpretable-intelligent-fault-diagnosis)]
6. **AdaBN** [[code](https://github.com/liguge/Fault-diagnosis-for-small-samples-based-on-attention-mechanism/blob/main/adabn.py)]
# Attention Block(SCA)
# How does it work?
# If it is helpful for your research, please kindly cite this work:
```html
@article{ZHANG2022110242,
title = {Fault diagnosis for small samples based on attention mechanism},
journal = {Measurement},
volume = {187},
pages = {110242},
year = {2022},
issn = {0263-2241},
doi = {https://doi.org/10.1016/j.measurement.2021.110242 },
url = {https://www.sciencedirect.com/science/article/pii/S0263224121011507},
author = {Xin Zhang and Chao He and Yanping Lu and Biao Chen and Le Zhu and Li Zhang}
}
```
# Our other works
```html
@ARTICLE{9374403,
author={Luo, Hao and He, Chao and Zhou, Jianing and Zhang, Li},
journal={IEEE Access},
title={Rolling Bearing Sub-Health Recognition via Extreme Learning Machine Based on Deep Belief Network Optimized by Improved Fireworks},
year={2021},
volume={9},
number={},
pages={42013-42026},
doi={10.1109/ACCESS.2021.30***962},
url = {https://ieeexplore.ieee.org/document/9374403},
}
```
# Environment
pytorch == 1.10.0
python == 3.8
cuda == 10.2
# Contact
- **Chao He**
- **22110435#bjtu.edu.cn (please replace # by @)**
## Views
近期下载者：
相关文件：
收藏者：