【摘要】 将基于Hopfield神经网络的线性系统参数辨识方案[1,2 ] 作了扩展 ,得出了在辨识神经网络输入为经传感器检测延迟的系统状态变量的情况下 ,其辨识输出趋于正确的充分条件。通过在鼠笼式电机传动系统参数辨识中应用的仿真结果 ,验证了该辨识方案的正确性。更多还原

【Abstract】 In this paper, the Hopfield Neural Network (HNN) based linear system parameters’identification scheme is extended, and the sufficient condition for correct HNN identification is derived under the assumption that HNN inputs are the detected system state variable signal delayed by sensors. The validity of the derived identify scheme is proved by the simulation results of HNN based asynchronous motor drive system parameters’ identification in consider of sensors’ characteristics.更多还原