A PyTorch framework for sensory signals in machinery fault diagnostics.
- numpy (>= 1.13.1)
- pytorch (>= 0.1.12.post2)
- data:
- .txt file for data: # signal_samples x # signal_length
- .txt file for label: # signal_samples x 1
- An example of fake dataset with 100 samples and labels are in toydata.
$ python run.py
- WDCNN from paper: A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals
- Ince's from paper: Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks
- 1DCNN from paper: Convolutional Neural Networks for Fault Diagnosis Using Rotating Speed Normalized Vibration (cite as)
@InProceedings{wei_conv_2019,
author="Wei, Dongdong
and Wang, KeSheng
and Heyns, Stephan
and Zuo, Ming J.",
title="Convolutional Neural Networks for Fault Diagnosis Using Rotating Speed Normalized Vibration",
booktitle="Advances in Condition Monitoring of Machinery in Non-Stationary Operations",
year="2019",
publisher="Springer International Publishing",
pages="67--76",
isbn="978-3-030-11220-2"
doi="10.1007/978-3-030-11220-2_8"
}
- LeNet5 for spectrogram of signals
- VGG forked from https://github.com/kuangliu/pytorch-cifar/blob/master/models/vgg.py