利用遞迴式模糊類神經小腦模型網路之錯誤容忍控制六相永磁同步馬達定位驅動系統;Recurrent Fuzzy Neural Cerebellar Model Articulation Network Fault-Tolerant Control of Six-Phase PMSM Position Servo Drive

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Electrical Engineering > Electronic Thesis & Dissertation > Item 987654321/65747

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/65747

Title:	利用遞迴式模糊類神經小腦模型網路之錯誤容忍控制六相永磁同步馬達定位驅動系統;Recurrent Fuzzy Neural Cerebellar Model Articulation Network Fault-Tolerant Control of Six-Phase PMSM Position Servo Drive
Authors:	楊凱木疌;Yang,Kai-jie
Contributors:	電機工程學系
Keywords:	六相永磁同步馬達;錯誤容忍控制;數位訊號處理器;遞迴式小腦模型網路;遞迴式模糊類神經網路;遞迴式模糊類神經小腦模型網路;Six-phase permanent synchronous motor;Fault-tolerant control;Digital signal processor;Recurrent fuzzy cerebellar model articulation network;Recurrent fuzzy neural network;Recurrent fuzzy neural cerebellar model articulation network
Date:	2014-07-25
Issue Date:	2014-10-15 17:09:23 (UTC+8)
Publisher:	國立中央大學
Abstract:	本論文的研究目的是研製以數位訊號處理器為基礎之遞迴式模糊類神經小腦模型網路之錯誤容忍控制六相永磁同步馬達定位驅動系統。首先，本研究將錯誤偵測以及錯誤容忍控制應用在六相永磁同步馬達定位驅動系統上。接著，將所設計好的理想轉矩控制器應用在定位系統控制上做馬達轉子機械位置命令的追隨。由於六相永磁同步馬達定位系統上所存在的不確定項是難以估計的，因此在實際應用上理想轉矩控制法則是難以獲得的。有鑒於此，本研究提出了遞迴式模糊類神經小腦模型網路來近似理想轉矩控制器，並加入補償控制器來消除近似誤差，另外一種方法則是採用遞迴式模糊類神經小腦模型網路作為估測器來估測計算轉矩控制法則的非線性項，並以強健控制器來補償其重建誤差。在遞迴式模糊類神經小腦模型網路的架構上分成兩個輸入維度，第一個輸入維度採用了小腦模型網路來提升其線上學習率以及網路區域化的學習能力。除此之外，輸入的第二維度採用了遞迴式模糊類神經網路，此方法除了提升網路歸納能力外更有效的減少記憶體使用需求。最後，本研究以32位元浮點運算數位訊號處理器完成了所提出的錯誤容忍控制定位驅動系統，且利用實驗結果來驗證所提出的遞迴式模糊類神經小腦模型網路錯誤容忍控制定位驅動系統的控制成效。;A DSP-based recurrent fuzzy neural cerebellar model articulation network (RFNCMAN) fault-tolerant control of a six-phase PMSM position servo drive system is proposed in this study. First, the fault detection and operating decision method of the six-phase PMSM position servo drive is developed. Then, an ideal computed torque controller is designed for the tracking of the rotor position reference command first. Since the uncertainties of the six-phase PMSM position servo drive system are difficult to know in advance, it is impossible to design an idea computed control law for practical application. Therefore, one method is that the RFNCMAN is proposed to mimic the ideal computed torque controller with a compensated controller to eliminate the approximation error. The other method is that the RFNCMAN is proposed to estimate a nonlinear equation included in the idea computed control law with a robust compensator designed to compensate the minimum reconstructed error. In the RFNCMAN, a recurrent fuzzy cerebellar model articulation network (RFCMAN) is adopted in the first dimension to enhance the online learning rate and localization learning capability. Moreover, a general recurrent fuzzy neural network (RFNN) is adopted in the second dimension to enhance the generalization performance and to reduce the required memory and rule numbers. Finally, the proposed fault-tolerant position control system is implemented in a 32-bit floating-point DSP. The effectiveness of the proposed RFNCMAN fault-tolerant control for the six-phase PMSM position servo drive system is verified by some experimental results.
Appears in Collections:	[Graduate Institute of Electrical Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	437	View/Open

社群 sharing

Loading...