本論文提出一只以數位訊號處理器為基礎之機率型模糊類神經網路智慧型控制器控制兩級交流-直流鋰錳電池充電器。此充電器前級為具有主動式功率因數修正之單相交流-直流升壓轉換器；後級為相移式全橋直流-直流降壓轉換器。此充電器將設計對於兩顆鋰錳電池組實現定電流充電以及定電壓充電之混合式充電策略。為了要改善輸出電壓在負載調節時的暫態響應，而機率型模糊類神經網路控制器取代傳統的比例積分控制器。此外，使用所提出之機率型模糊類神經網路控制器可明顯地改善電池組在定電流充電模式轉換定電壓充電模式瞬間的不連續充電電流以及充電電壓之問題。本文將詳細介紹機率型模糊類神經網路的架構以及線上學習法則，而所提之機率型模糊類神經網路控制器在實現混合式充電策略的控制性能將由實驗結果驗證。 A digital signal processor (DSP)-based probabilistic fuzzy neural network (PFNN) is proposed in this study to control a two-stage AC-DC charger. The input stage and output stage of the charger are AC-DC boost converter with power factor correction (PFC) and phase-shift full-bridge (PSFB) DC-DC converter. The designed charger adopts constant-current and constant-voltage (CC-CV) charging strategy to charge two Lithium-ion (Li-ion) battery packs. To improve the transient of voltage regulation during load variation, a PFNN controller is proposed to replace the traditional proportional-integral (PI) controller. Moreover, the discontinuous charging voltage and current during the transition between the CC and CV charging modes can also be reduced significantly using the proposed PFNN controller. The network structure and the online learning algorithms of the PFNN controller are introduced in detail. Furthermore, the control performances of the proposed PFNN control system for CC-CV charging are evaluated by some experimental results.
