本論文提出一配電型靜態同步補償器來改善非線性與線性負載造成之電流諧波與功率因數等電力品質問題。另一方面，由於功率流進或流出配電型靜態同步補償器之直流鏈側的電容，會造成直流鏈電壓的波動。因此，配電型靜態同步補償器之直流鏈電壓控制在負載變動情況下尤其重要。本論文為了改善電力品質與有效地維持直流鏈電壓在非線性與線性負載變動情況下，提出一新式非對稱補償模糊類神經網路(CFNN-AMF)控制器取代傳統比例積分(PI)控制器。本論文所提出的非對稱補償模糊類神經網路(CFNN-AMF)，其補償層參數整合了CFNN模糊系統中的悲觀與樂觀運算。並且，在歸屬函數層的維度採用非對稱(AMF)的方式以優化模糊規則與提升網路學習能力的最佳化。此外，本論文將詳細介紹CFNN-AMF的網路架構與線上學習法則。最後，以實驗結果驗證使用CFNN-AMF之配電型靜態同步補償器在非線性與線性負載變動情況下改善電力品質與維持直流鏈電壓之有效性與可行性。;A distribution static compensator (DSTATCOM) is proposed to improve power quality, including the grid current harmonic and power factor, resulted from the nonlinear and linear loads. On the other hands, since the instantaneous power following into or out of the DC-link capacitor on the DC side of the DSTATCOM, a sudden load change may cause a serious DC-link voltage fluctuation across the dc capacitor. Hence, the DC-link voltage regulation control of the DSTATCOM is important especially under load variation. In this study, to improve the power quality and keep the DC-link voltage of the DSTATCOM constant under variation of nonlinear and linear loads effectively, the traditional proportional-integral (PI) controller is substituted with a novel online trained compensatory neural fuzzy network with an asymmetric membership function (CFNN-AMF) controller. In the proposed CFNN-AMF, the compensatory parameter to integrate pessimistic and optimistic operations of fuzzy systems is embedded in the CFNN. Moreover, the dimensions of the Gaussian membership functions are directly extended to AMFs for the optimization of the fuzzy rules and the upgrade of learning ability of the networks. Furthermore, the network structure and online learning algorithms of the proposed CFNN-AMF are introduced in detail. Finally, the effectiveness and feasibility of the DSTATCOM using the proposed CFNN-AMF controller for the improvement of power quality and maintaining the constant DC-link voltage under nonlinear and linear load change have been demonstrated by some experimental results.
