Fault Detection and Location by Static Switch in Microgrids Using Wavelet Transform and Taguchi-based Artificial Neural Network
| Autor: | Mark Tristan Angelo Morena Cabatac, 崔思安 |
|---|---|
| Rok vydání: | 2018 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 106 This study presents a fault detection, classification and localization using the multiresolution analysis (MRA) of the discrete wavelet transform (DWT) and a Taguchi-based artificial neural network (ANN). The difference of wavelet energies of the three-phase fault voltages, three-phase fault currents and the wavelet energy of the ground fault current are utilized as inputs to the neural network. The wavelet energies are obtained from the local fault signals at the static switch located at the secondary side of the main transformer in the microgrid. The neural network identifies the faulty phase and the location of the fault. The neural network determines the control action (open or close) of the static switch when both the fault location and phase are identified. The proposed method is implemented in Renesas RX62T microcontroller. The microcontroller is then implemented in a Chip-in-the-loop with a real-time digital simulator. The DWT is also implemented using a 50-kVA static switch hardware. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|