基于神经网络直流无刷电机控制策略的研究-控制理论与控制工程专业论文.docxVIP

ABSTRACTIn ABSTRACT In recent years，advances in rare—earth permanent magnetic material，power devices， micro—processor,converter design technique and control theory have made BLDCM play a vital role in motion．contr01 applications．ttowever,the control performance of the BLDCM drive is still influence by uncertainties．which usually features parameter variations。 extemal load disturbances and nonlinear dynamics．To achieve higll．performance BLDCM drive，which has great ability of adaptation and better performance against disturbances，advanced control schemes have to be developed to deal with these uncertainties． This thesis，on the basis ofthe research 011 structure and learning algorithm ofneuraI network，a high．performance neuro-controller with simultaneous online identification and control iS proposed for controlling BLDCM．The dynamics of the motor are controlled using two difierent neural based identification and control schemes．as system iS in operation．In t11e first scheme．an aRempt iS made to control the rotor angular speed． utilizing a single three—hidden．1ayer network．the second scheme attempts to control the stator currents．This schemes incorporates three multilayered feedforward neural networks that are online trained，using the Levenburg-Marquardt training algorithm． The control ofthe direct and quadrature components ofthe stator current Can successfully traced trajectories after relatively short online training periods．The control strategy adapts to the uncertainties of the motor dynamics and their inherent nonlinearities． Promising simulation results have been observed when the neural controller iS trained in an environmem contaminated with noise． Keywords：Brushless DC Motor； Neuro—controller； Online training． II 第一章绪论第一章绪论 第一章绪论 第一章绪论 1．1研究背景 直流无刷电动机具有结构简单、体积小、重量轻、效率高、功率因数高、转矩i 重量比高、转动惯量低、易于散热、易于维护保养等优点，因而应用范围极为广泛， 尤其是在要求高控制精度和高可靠性的场合，如航空、航天、数控机床、机器人等 方面获得广泛的应用。 直流无刷电动机的本体是永磁同步电机【”，它由稀士永磁材料来产生磁场，是 永磁电机家族中的重要～员。自二十世纪八十年代以来，各国相应的研究机构及著 名的电气公司竞相把稀土永磁