本論文於RT-Lab即時模擬系統環境下,建立一混合太陽能、風力、儲能系統及微渦輪機發電系統之微電網模型,並於微電網網外及網內不同匯流排上產生對稱三相短路故障,記錄微電網在不同負載量及發電量情況下,流經微電網主匯流排電流之小波能量,以作為自適應類神經模糊推論系統的訓練及測試資料,用於預測故障發生區域,再搭配小波轉換偵測微電網主匯流排電壓是否異常,作為靜態開關由併聯市電模式切換為孤島運轉模式的依據。自適應類神經模糊推論系統是使用 MATLAB 內建ANFIS Editor GUI,訓練完後提取隸屬函數參數,最後以Xilinx System Generator來實現自適應類神經模糊推論系統及小波分解之 FPGA 晶片硬體模擬。
This thesis develops a micro-grid simulation platform of hybrid solar PV, wind-turbine, storage system and micro-turbine generators using RT-Lab real-time digital simulator. The scenarios of three-phase balanced faults occurring at different buses are studied by considering different power generations and load levels. The wavelet energies at main bus are used for training adaptive network based fuzzy inference system (ANFIS), which is used to identify the faulted area. The parameters of ANFIS are obtained by MATLAB-based ANFIS Editor GUI. Using Xilinx System Generator, an FPGA-based static switch is developed using wavelet coefficients and ANFIS with fixed parameters attained from MATLAB.