本論文提出兩種併網型太陽光電系統於故障期間之實虛功智慧型控制法，此二智慧型控制法皆同時符合再生能源併網低電壓穿越規範與變流器之最大電流限制。所提之二智慧型控制器分別為機率小波模糊類神經網路控制器，以及非對稱歸屬函數之TSK型機率模糊類神經網路控制器。論文中將詳細介紹兩種智慧型控制器的架構與線上學習法則，並證明其收斂性分析。當併網型太陽光電系統發生電壓故障時，控制器會依據低壓穿越規範所規範的虛功補償參考值，調整注入市電系統之虛功量，並能使太陽光電系統所產生的實功與注入市電的實功維持平衡。此外，本研究還提出兩種雙模式控制策略可於故障期間消除直流鏈電壓的波動。還有，在故障期間，注入市電系統電流大小加入了最大電流限制以降低過電流發生的風險。最後展示一些實驗結果以驗證所提方法之成效。 Two active and reactive power control schemes using intelligent control for grid-connected three-phase photovoltaic (PV) system during grid faults are proposed in this study. The control schemes are based on a ratio between active and reactive power which meet the low voltage ride through (LVRT) regulations and inverter maximum current limit simultaneously. Moreover, two intelligent controls based on probabilistic wavelet fuzzy neural network (PWFNN) and Takagi-Sugeno-Kang type probabilistic fuzzy neural network with asymmetric membership function (TSKPFNN-AMF) are developed to control the reactive power injected into the grid and balance the active power between the power generated by the PV and the power delivered into the grid under grid faults. The intelligent controllers regulate the value of reactive power to a new reference value which complies with the requirements of LVRT under grid faults. Furthermore, two dual-mode operation control strategies, which can eliminate the fluctuation of DC-link bus voltage under grid faults, are also discussed. In addition, to reduce the risk of over-current during the LVRT operation, a current limit is predefined in current injection. Finally, some experimental results are presented in order to validate the effectiveness of the proposed control.