利用遞迴小波模糊類神經網路於永磁輔助同步磁阻馬達位置驅動系統之智慧型步階回歸控制;Intelligent Backstepping Control of Permanent Magnet Assisted Synchronous Reluctance Motor Position Servo Drive with Recurrent Wavelet Fuzzy Neural Network

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Electrical Engineering > Electronic Thesis & Dissertation > Item 987654321/93389

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/93389

Title:	利用遞迴小波模糊類神經網路於永磁輔助同步磁阻馬達位置驅動系統之智慧型步階回歸控制;Intelligent Backstepping Control of Permanent Magnet Assisted Synchronous Reluctance Motor Position Servo Drive with Recurrent Wavelet Fuzzy Neural Network
Authors:	簡佑宸;Chien, Yu-Chen
Contributors:	電機工程學系
Keywords:	永磁輔助同步磁阻馬達;每安培最大轉矩;有限元素分析;步階回歸控制;遞迴小波模糊類神經網路;permanent magnet assisted synchronous reluctance motor (PMASynRM);maximum torque per ampere (MTPA);finite element analysis (FEA);backstepping control (BSC);intelligent backstepping control recurrent wavelet fuzzy neural network (IBSCRWFNN)
Date:	2023-08-03
Issue Date:	2024-09-19 16:57:00 (UTC+8)
Publisher:	國立中央大學
Abstract:	本研究的目標是開發一種用於永磁輔助同步磁阻電機(PMASynRM)的智慧型伺服驅動系統，該系統能夠適應電機的非線性和時變控制要求。為此，提出了一種具有智慧型步階回歸控制的遞迴小波模糊神經網路(RWFNN)。首先，引入ANSYS Maxwell-2D動態模型來控制PMASynRM驅動器的最大每安培扭矩(MTPA)。根據有限元分析(FEA)結果創建查找表(LUT)，以確定 MTPA內的當前指令角。接下來，開發了基於步階回歸(BSC)的系統來跟踪位置命令。然而，由於事先無法獲得不確定性訊息，為PMASynRM位置伺服驅動系統的實際應用設計有效的BSC具有挑戰性。因此，本研究提出了一種 RWFNN 來近似 BSC，並減輕了與使用傳統 BSC 相關的上述困難。改進的自適應補償器被添加到 RWFNN 以解決潛在的近似誤差。為保證RWFNN的穩定性，採用Lyapunov穩定性方法生成RWFNN的在線學習算法並保證漸近穩定性。實驗結果證明了所提出的 IBSCRWFNN 控制的 PMASynRM 驅動器的有效性和強健性。最後，本研究採用32位元浮點運算數位訊號處理器TMS320F28075，以實現所提出的智慧型控制於永磁輔助同步磁阻馬達驅動系統中。;The goal of this study is to develop an intelligent servo drive system for a permanent magnet assisted synchronous reluctance motor (PMASynRM) that can adapt to the motor′s nonlinear and time-varying control requirements. To achieve this, a recurrent wavelet fuzzy neural network (RWFNN) with intelligent backstepping control is proposed. First, an ANSYS Maxwell-2D dy-namic model is introduced to control the maximum torque per ampere (MTPA) of the PMASynRM servo drive. A lookup table (LUT) is created based on finite element analysis (FEA) results to determine the current angle of command within the MTPA. Next, a system based on backstepping control (BSC) is developed to track the position reference. However, designing an effective BSC for practical applications of the PMASynRM position servo drive system is chal-lenging due to the unavailability of uncertainty information in advance. Therefore, this study proposes an RWFNN to approximate the BSC and alleviate the above difficulties associated with using a traditional BSC. An improved adaptive compensator is added to the RWFNN to address potential approximation errors. To ensure the stability of the RWFNN, the Lyapunov stability method is used to generate the RWFNN′s online learning algorithms and guarantee asymptotic stability. Experimental results demonstrate the effectiveness and robustness of the proposed in-telligent backstepping control recurrent wavelet fuzzy neural network (IBSCRWFNN) controlled PMASynRM servo drive. Finally, the intelligent control system and the vector mechanism for the PMASynRM drive are successfully implemented utilizing the TMS320F28075, a 32-bit floating point digital signal processor (DSP)
Appears in Collections:	[Graduate Institute of Electrical Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	16	View/Open

社群 sharing

Loading...