Optimized Power Quality Events Classifier
| Autor: | Dimitar Taskovski, Vladimir Dimchev, Marija Markovska, Bodan Velkovski |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
0209 industrial biotechnology
Computer science business.industry Feature extraction Pattern recognition 02 engineering and technology Random forest symbols.namesake 020901 industrial engineering & automation Additive white Gaussian noise 0202 electrical engineering electronic engineering information engineering symbols Power quality Classification methods 020201 artificial intelligence & image processing Artificial intelligence business Classifier (UML) Feature extraction algorithm |
| Zdroj: | 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe). |
| DOI: | 10.1109/eeeic.2019.8783267 |
| Popis: | In this paper optimized classifier for classification of different power quality (PQ) events is presented. Its implementation is performed in LabVIEW, using an efficient-wavelet based feature extraction algorithm and an optimized random forest (RF) classification method. It is able to classify twenty-one classes of single and combined PQ events. Its accuracy is tested and verified using signals from three different sources, including real PQ events, with and without presence of white Gaussian noise. The verification has shown that this classifier exhibits high classification accuracy, despite the fact that in the process of classification two classes obtained as combination of four disturbances are considered. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|