本文建構一以三相三臂變流器為電路架構之主動式電力濾波器，以補償市電因非線性負載所引起的諧波電流，使得市電電流可補償為正弦波波形，而為提升諧波補償成效與改善非線性負載變動時直流鏈電壓的暫態響應，本文提出一非對稱歸屬函數之遞迴式機率模糊類神經網路控制器取代傳統的比例積分控制器。另一方面，本論文亦建構一以三相四臂變流器為電路架構之主動式電力濾波器，以補償市電因三相不平衡負載所引起的三相不平衡電流，使得市電電流可補償為三相平衡電流且抑制中性線電流，此外，為提升不平衡補償效果與改善三相不平衡負載變動時直流鏈電壓的暫態響應，亦提出一派翠機率模糊類神經網路控制器取代比例積分控制器。再者，本文將分別詳細介紹所提出之二種新式智慧型控制器的網路架構與線上學習法則，並且分別證明其收斂性。最後，本研究利用Texas Instruments TMS320F28335數位訊號處理器完成所提出的主動式電力濾波器，並且利用實驗結果證明主動式電力濾波器結合所提出之智慧型控制之補償成效及可行性。;A three-phase three-arm active power filter (APF) is proposed to compensate harmonic current under nonlinear load conditions in grid-connected operation in this study. In order to improve the regulation control of the DC-link voltage in the shunt APF under the variation of nonlinear load and to compensate the currents harmonic effectively, a novel recurrent probabilistic fuzzy neural network with an asymmetric membership function(RPFNN-AMF) controller is proposed to replace traditional proportional-integral (PI) controller. Moreover, a three-phase four-arm inverter-based active power filter is also proposed to compensate three-phase unbalanced currents under unbalanced load conditions in grid-connected operation in this study. Furthermore, to improve the regulation control of the DC-link voltage in the APF under the variation of three-phase unbalanced load and to compensate the three-phase unbalanced currents effectively, a novel Petri probabilistic fuzzy neural network (PPFNN) controller is proposed to replace traditional PI controller. In addition, the network structure, online learning algorithms and convergence analysis of the proposed two intelligent controllers are represented respectively in detail. Finally, the proposed two intelligent controllers to control the APF are implemented by the control platform using the Texas Instruments digital signal processor (DSP) TMS320F28335, and the effectiveness and the feasibility are verified by some experimental results.
