本文用具紧支集的尺度函数之张量乘积构成人工神经网络的基函数, 再由这个小波神经网络辨识静态与动态的离散线性系统, 并且证明了依所给的方法产生的模型是收敛的.最后,用 一个仿真例子,说明如何实现算法及算法的效果.

In this paper, the tensor product of a scale function with compact support set is introduced to be used a base function for a artificial neural network. Based on the wavelet neural network static and dynamic, discrete-time, nonlinear systems are identified and it is proved that the identification error converge to zero according to the given law. Finally, a numerical simulation example is presented to illustrate the presented algorithm and the effectiveness of the method.