將線性網絡應用于一類帶擾動的線性對象，提出了一種基于該線性網絡的自適應逆控制方案，該方案由辨識器、控制器和擾動消除器三部分構成，合理選擇三個線性網絡的輸入，通過辨識器的在線學習，同時更新控制器和擾動消除器的權值，文章研究了該方
案的收斂性和方案的跟蹤性。根據可變步長權值收斂條件，設計了輸入解相關變步長LMS算法調整辨識器權值方法。通過仿真研究了逆控制方法的有效性。
關鍵詞：線性網絡；LMS 算法；自適應逆控制
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)