一种基于I/O数据的多模型建模方法

I/O data-based multiple-model modeling method

针对复杂非线性系统,提出了一种基于I/O数据的多模型建模方法.首先,利用模糊划分对输入数据进行在线聚类;然后,采用最小二乘法在每一个聚类点处建立一个局部模型,并利用新获得的I/O数据对局部模型的参数进行更新.该方法借鉴模糊模型中空间划分的思想,将模糊空间划分与多模型建模相结合,利用即时I/O数据对局部模型的数量以及每一个局部模型的参数进行在线更新,从而实现对复杂非线性系统的在线建模.仿真实验证明了该方法的有效性.

A multiple-model modeling method based on the I/O data is suggested for the complex nonlinear system. Firstly, fuzzy partition was employed to on-line clustering of the I/O data. Then, the least-squares （LS） algorithm was used to construct the local model for each clustering, and the parameters of each local model were updated according to the new data. The proposed algorithm takes advantage of space decomposition of the fuzzy model, combines the fuzzy partition and multiple-model modeling, and updates on-line the number of the local model and the parameter of each, so as to realize the on-line modeling for the complex nonlinear system. Simulation result shows the effectiveness of this method.