本研究目的在創建一個優化的同步磁阻馬達伺服驅動系統，通過使用具有智慧型步階回歸控制功能的多項式派翠模糊類神經網路來改變同步磁阻馬達固有的非線性和時變控制特性 本研究首先介紹了一個 ANSYS Maxwell-2D 動態模型，其中包含每安培最大扭矩控制的同步磁阻馬達伺服驅動器。建構查表法以組成有限元分析的結果，以生成每安培最大轉矩控制的直軸電流命令。隨後，本研究設計了一個步階回歸 控制系統來跟踪位置參考命令。在實際應用上步階回歸控制的設計非常複雜，因為事先無法獲得詳細的系統動態參數，包括同步磁阻馬達伺服驅動系統的不確定項 。因此這項研究明，多項式派翠模糊類神經網路可以作為理想步階回歸控制的近似優化來解決其現有的問題。此外，本研究修改了自適應補償器以主動調整多項式派翠模糊神經網路的潛在計算偏差。使用生成多項式派翠模糊類神經網路在線學習算法的李亞普諾夫穩定性方法可確保系統的漸近穩定性。最後，實驗提供了一些結果來驗證所提出的智慧型步階回歸多項式派翠模糊類神經網路控制的同步磁阻馬達伺服驅動器其有效性和強健性。;This study aims to create an optimized synchronous reluctance motor (SynRM) servo drive system to alter the inherent nonlinear and time-varying control characteristics of the SynRM by using an intelligent backstepping control polynomial Petri fuzzy neural network (IBSCPPFNN) that features an intelligent backstepping control. This study first introduces an ANSYS Maxwell-2D dynamic model that contains a maximum torque per ampere (MTPA) controlled SynRM servo drive. A lookup table (LUT) is built to compose of the finite element analysis (FEA) results to generate direct axis current command of the MTPA. Subsequently, this study designs a backstepping control (BSC) system to track the position reference command. Creating a working BSC for practical applications is quite complex because the detailed system dynamics, which includes the unpredictability of the SynRM servo drive system, is not available beforehand. Thus, this study suggests that a polynomial Petri fuzzy neural network (PPFNN) can act as a close substitute for the ideal BSC to resolve its existing complications. Furthermore, this study modifies an adaptive compensator to proactively adjust for the potential calculated deviance of the PPFNN. Asymptotical stability is assured by using the Lyapunov stability method, which generates the PPFNN’s online learning algorithms. Finally, some experimental results are provided to verify the effective and robust qualities of the suggested IBSCPPFNN controlled SynRM servo drive.
