How liguge/dlwcb works
DLWCB is a PyTorch rolling-bearing fault-diagnosis model. Its principal workflow loads labeled MATLAB signals, standardizes and splits them into batches, trains and evaluates a dual-branch Laplace-wavelet CNN/BiGRU classifier, and saves model weights. The repository also includes a separate model-definition file and validation-loss-based early stopping. Evidence is limited to the README and sampled Python files; the documented broader evaluation claims are not independently established by the code shown.
Main entry points: proposed_model.py Train and evaluate · gdatasave.py Load and split data · early_stopping.py Early stopping · laplacewave.py Laplace convolution
Components 11
Signal data
- Load and split data
gdatasave.py - Training batches
gdatasave.py - Test batches
gdatasave.py
Diagnosis model
- DLWCB classifier
proposed_model.py - Net definition
DLWCB.py - Laplace convolution
laplacewave.py
Training runtime
- Train and evaluate
proposed_model.py - Early stopping
early_stopping.py
Model artifacts
- Model weights
Other components
- Researcher
- Bearing MAT data
Connections 12
- Researcher → Bearing MAT data: provides signals
README.md - Bearing MAT data → Load and split data: loads MAT files
gdatasave.py - Load and split data → Training batches: builds batches
gdatasave.py - Load and split data → Test batches: builds batches
gdatasave.py - Training batches → Train and evaluate: trains on
proposed_model.py - Test batches → Train and evaluate: evaluates on
proposed_model.py - Train and evaluate → DLWCB classifier: runs forward
proposed_model.py - DLWCB classifier → Laplace convolution: uses filters
proposed_model.py - Net definition → Laplace convolution: uses filters
DLWCB.py - Train and evaluate → Early stopping: checks loss
proposed_model.py - Early stopping → Model weights: saves checkpoint
early_stopping.py - Train and evaluate → Model weights: saves weights
proposed_model.py