利用遞迴式小波模糊類神經網路於電動轉向系統定位控制之研究;A Study of Position Control on Electrical Power Steering System using Recurrent Wavelet Fuzzy Neural Network

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Electrical Engineering > Electronic Thesis & Dissertation > Item 987654321/68985

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/68985

Title:	利用遞迴式小波模糊類神經網路於電動轉向系統定位控制之研究;A Study of Position Control on Electrical Power Steering System using Recurrent Wavelet Fuzzy Neural Network
Authors:	孫一イ凡;Sun,I-Fan
Contributors:	電機工程學系
Keywords:	六相永磁同步馬達;電動轉向系統;小波轉換;遞迴式模糊類神經網路;滑動模態控制器;李亞普諾夫穩定性;Six-phase permanent synchronous motor;electric power steering system;wavelet transform;recurrent fuzzy neural network;sliding-mode controller;Lyapunov stability
Date:	2015-08-24
Issue Date:	2015-09-23 14:51:23 (UTC+8)
Publisher:	國立中央大學
Abstract:	本文之研究目的為研製以數位訊號處理器為基礎之遞迴式小波模糊類神經網路之智慧型滑動模態控制，並應用於一基於六相永磁同步馬達之電動轉向系統，以期能改進其追隨效能與載具穩定性。首先，本研究將利用拉格朗日力學推導電動轉向系統的動態數學方程式。接著，以此方程式為基礎，設計一滑動模態控制器作為電動轉向系統之位置控制器。由於電動轉向系統是一個非線性與時變的系統，控制的準確性將深受整個電動轉向系統的參數變化、外力干擾與摩擦力…等不確定項的影響。因此在實際應用上，不確定項的上界難以精確取得，而間接導致滑動模態控制成效容易趨於保守，也容易造成其控制抖動之缺陷。有鑒於此，本研究提出了具有遞迴式小波模糊類神經網路作為不確定項估測器的智慧型滑動模態控制策略來改善此現象。其中，遞迴式小波模糊類神經網路能適時地估測當下因參數變化與外來干擾所產生之不確定項的大小，並加入強健控制器來消除近似誤差。其適應性線上學習法則則是藉由李亞普諾夫理論與泰勒展開式推導而得。最後，本研究以32 位元浮點運算數位訊號處理器完成所提出的電動轉向定位系統，且利用實驗結果來驗證所提出智慧型控制策略於電動轉向系統之定位成效與可行性。;The objective of this thesis is to develop a digital signal processor (DSP) based intelligent control of a six-phase permanent magnet synchronous motor (PMSM) drive system for electric power steering (EPS) system. First of all, the dynamic mathematical model of the EPS system is derived by Lagrangian dynamics. Since the EPS system is a nonlinear and time-varying system, the control accuracy is very sensitive to the parameter variations and external disturbances. Therefore, a sliding mode controller (SMC) is developed for the position control of the EPS system. However, the upper bound of the uncertainties is difficult to obtain in advance and the choice of high switching control gain in SMC may cause undesired chattering phenomenon. Hence, an intelligent SMC with a recurrent wavelet fuzzy neural network (ISMC-RWFNN) is proposed in this study, where the RWFNN is adopted as an uncertainty estimator to overcome the aforementioned disadvantage of SMC. Also, a robust compensator is employed to eliminate the estimation error. Furthermore, adaptive learning algorithms for the online training of the RWFNN are derived using the Lyapunov theorem and Taylor series. Finally, the proposed ISMC-RWFNN to control the six-phase PMSM drive system for the EPS system is implemented in a 32-bit floating-point digital signal processor (DSP), TMS320F28335, and the effectiveness is verified by some experiments.
Appears in Collections:	[Graduate Institute of Electrical Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	401	View/Open

社群 sharing

Loading...