We use ResPSANet built by the PSA module. This network has the ability to extract multi-scale power disturbance abnormal waveform features, and has an attention mechanism that can select important scales for focused feature extraction.
- Use PAA for phase adaptive adjustment, which is implemented here using matlab;
- Use GAF to convert the data into two dimensions;
- Install the required libraries for python, you can view the requirement.txt file here;
- Create a folder Dataset in the same directory as main.py to store your data;
- Check whether the loaded data directory in main.py has the same name as the file you created;
- Modify the abnormal waveform category, which depends on the number of types of power disturbance abnormal waveform categories you need to identify.
- Run python main.py in the command line