论文部分内容阅读
提出了一种基于神经网络的参数辨识方法,该方法与传统的参数辨识方法有着本质的不同。它充分地利用了神经网络对任意非线性函数的逼近能力,并将其与传统的基于阶跃响应的辨识方法结合起来。对方法的原理及其相关的神经网络算法做了具体的阐述并给出了仿真实例,结果表明方法是可行的,并可由此看出,神经网络用于工程实际的广阔前景。
A parameter identification method based on neural network is proposed, which is different from the traditional parameter identification method. It makes full use of the ability of neural network to approximate any nonlinear function, and combines it with the traditional identification method based on step response. The principle of the method and its related neural network algorithm are described in detail and the simulation examples are given. The results show that the method is feasible and it can be seen that the neural network is applied to the broad prospect of engineering practice.