本論文的研究目的是研製以數位訊號處理器為基礎之智慧型控制六相永磁同步馬達驅動系統，其應用在電動轉向系統上。由於電動轉向系統是一個非線性與時變的系統，控制的準確性對於整個電動轉向系統的參數變化、外力干擾與摩擦力相當敏感。然而電動轉向系統的穩定性是目前最重要的發展議題，因此本論文提出兩種智慧型控制系統，一個是具有線上調整學習速率的改良型差分演化演算法之非對稱歸屬函數之小波模糊類神經網路控制器，另一個是智慧型二階滑動模態控制器，利用非對稱歸屬函數之小波模糊類經網路的線上學習能力與快速收斂的特性來估測電動轉向系統的不確定項，以達到電動轉向系統所需求高的控制性能。最後以DSP(TMS320F28335)實現六相永磁同步馬達驅動系統，並且以實驗結果來驗證所提出的智慧型控制器之可行性。 The purpose of this thesis is to develop a digital signal processor (DSP) based intelligent control of six-phase permanent magnet synchronous motor (PMSM) drive system for electric power steering (EPS) system. Due to the EPS system is a nonlinear and time-varying system, the control accuracy is very sensitive to the parameter variations and external disturbances. Since the stability of EPS system is the most important issue, two intelligent control systems are proposed in this thesis. First, an improved differential evolution wavelet fuzzy neural network with asymmetric membership function (IDE WFNN-AMF) is proposed, in which the learning rates of IDE WFNN-AMF are adapted online. Then, an intelligent two-order sliding-mode controller (I2OSMC) is proposed, in which the uncertainties of the EPS system is estimated using the WFNN-AMF with online learning and fast convergence capabilities. The above two intelligent controllers can achieve the required high control performance of the EPS system. Finally, the six-phase PMSM drive system is implemented by the DSP TMS320F28335, and some experimental results are illustrated to verify the validity of the proposed intelligent controllers.
