受益于RBF神经网络在函数逼近和学习局部变化方面具有良好的性能，使用与

Benefiting from the good performance of RBF neural network in function approximation and learning of local changes, the use of the function coefficient matrix related to the operating point enables the RBF-ARX model to effectively reflect the dynamic characteristics of the nonlinear system at each operating point.

Benefiting from the good performance of RBF neural network in function approximation and learning local variation, the use of function coefficient matrix related to the working point enables the RBF-ARX model to effectively reflect the dynamic characteristics of nonlinear systems at each work point.

Thanks to the good performance of RBF neural network in function approximation and learning local variation, the RBF-ARX model can effectively reflect the dynamic characteristics of the nonlinear system at each working point by using the function coefficient matrix related to the working point.<br>