基于線性網(wǎng)絡(luò)的一類(lèi)帶擾動(dòng)線性對(duì)象的逆控制研究

將線性網(wǎng)絡(luò)應(yīng)用于一類(lèi)帶擾動(dòng)的線性對(duì)象，提出了一種基于該線性網(wǎng)絡(luò)的自適應(yīng)逆控制方案，該方案由辨識(shí)器、控制器和擾動(dòng)消除器三部分構(gòu)成，合理選擇三個(gè)線性網(wǎng)絡(luò)的輸入，通過(guò)辨識(shí)器的在線學(xué)習(xí)，同時(shí)更新控制器和擾動(dòng)消除器的權(quán)值，文章研究了該方
案的收斂性和方案的跟蹤性。根據(jù)可變步長(zhǎng)權(quán)值收斂條件，設(shè)計(jì)了輸入解相關(guān)變步長(zhǎng)LMS算法調(diào)整辨識(shí)器權(quán)值方法。通過(guò)仿真研究了逆控制方法的有效性。
關(guān)鍵詞：線性網(wǎng)絡(luò)；LMS 算法；自適應(yīng)逆控制
Abstract：The linear neural network is applied of a class linear plant with Disturbance, and a
LNN-based adaptive inverse control scheme is presented. The control scheme is composed of
three parts: identifier, controller and disturbance canceller. Three LLN’s respectively selected
inputs are so reasonable that when on-line training is only in the identifier, three networks’ weight values are updated at the same time. The scheme’s weight convergence is expatiated, and a desired reference can be tracked by the plant output. In according to the weight convergence condition of the variable step size least mean square algorithm, a new input-decorrelated variable step size least mean square algorithm is presented to make the scheme be applied in practice. A simulation examples are also presented to evaluate the scheme.
Key words：Linear Neural Network(LNN); Least Mean Square(LMS) Algorithm; Adaptive
Inverse Control(AIC)