Wiener模型的集成辨识方法

Integrated Identification Method for Wiener Model

对一类石油化工生产过程中的Ｗｉｅｎｅｒ模型辨识问题，提出了一种稳态与动态相结合的集成辨识方法．利用稳态信息获取稳态模型的强一致性估计，通过神经网络逼近得到非线性增益的逆函数．然后利用系统的动态信息辨识Ｗｉｅｎｅｒ模型的线性系统的参数，并得到一致性估计．仿真结果表明了该方法的有效性和实用性．

In accordance with a class of Wiener model in petroleum chemical engineering,an identification method for Wiener model is put forward.In this method,the steadystate model a system is obtained from its steadystate data.The inverse function of nonlinear gain is get by using neural network.The nonlinearity of the system can be eliminated by the inverse function,so Wiener model becomes a pure linear model.The linear parameters of the model can be gained according to the dynamic data of the system.The effectiveness and practicality of this method is demonstrated by the simulation results of examples.