论文部分内容阅读
提出了延迟系统及延迟时间参数的神经网络辨识方法。改变神经网络输入样本区间，利用网络输出期望值与输出实际值之间的误差平方和产生的突变，可以辨识出非线性对象的延迟时间。将神经网络大延迟系统的辨识与基于模型补偿的控制策略相结合，可以用于具有变化参数或者不确定性延迟时间的大延迟系统的控制。仿真结果表明这种神经网络模型补偿延迟系统控制具有很好的控制效果，它是大延迟控制中克服延迟时间变化的很有希望的方法。
A neural network identification method of delay system and delay time parameters is proposed. By changing the input range of neural network, the delay of non-linear object can be identified by using the mutation sum of square error of the output value of the network and the output actual value. Combining the identification of a large delay system in a neural network with a control strategy based on model compensation can be used for the control of large delay systems with varying parameters or uncertain delay times. The simulation results show that this neural network model has good control effect in compensating for delay system control, and it is a promising method to overcome the variation of delay time in large delay control.