Real-time power quality disturbance classification using convolutional neural networks
There is a growing interest in disturbance monitoring to maintain power quality. This paper developed a real-time power quality disturbance (PQD) detection system using convolutional neural networks (CNN) due to its fast and accurate feature extraction and classification. First, 29 classes of power...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Book Chapter |
| Language: | en en |
| Published: |
Springer
2020
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/84768/2/Paper_191_rev3.pdf http://irep.iium.edu.my/84768/1/Acceptance%20Letter_DrTeddy_IIUM.pdf http://irep.iium.edu.my/84768/ https://im3f2020.ump.edu.my/index.php/en/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | There is a growing interest in disturbance monitoring to maintain power quality. This paper developed a real-time power quality disturbance (PQD) detection system using convolutional neural networks (CNN) due to its fast and accurate feature extraction and classification. First, 29 classes of power quality disturbance were synthetically generated around 5000 samples for each type. Second, an efficient CNN structure was developed to extract unique features. Next, the output of CNNs was then inputted into a fully connected layer with softmax and classification layer to act as the classifier for 29 classes of PQD signals. Our proposed algorithm was then trained using 80% of the synthetic signals, while 20% of the synthetic signals were used for testing. Experimental results showed that the proposed algorithm produced a good result with the classification accuracy of 97.52% trained using 100 epochs. Furthermore, it requires only 80.96 μs to detect each 16ms segment of PQD signals. |
|---|