基于局部递归线性NF模型智能非线性识别系统设计

Intelligent Non-Linear Modeling of an Industrial Winding Process Using Recurrent Neuro-Fuzzy Networks

摘要:

主要研究了智能非线性识别技术在绕组建模中的设计;首先分析了模糊神经(NF)建模的相关属性,针对绕组建模系统所需要的控制性能,为了改善其控制性能,实现可靠的容错系统,提出一种新的基于模糊神经网络NF的模拟模型,将该模型应用到基于递归的局部线性模糊神经网络(RLLNF),该网络通过局部的线性模型树(LOLIMOT)训练,设计出一种改进的基于树的增量学习算法;最后设置时间间隔在220 s和225 s之间的实际的绕组过程,通过仿真实验结果表明,将提出的NF模型与其他已知智能算法,即多层感知器(MLP)等进行比较,所设计的系统更具有可行性与高效性。

Abstract:

This study deals with the neuro-fuzzy (NF) modeling of a real industrial winding process in which the acquired NF model can be exploited to improve control performance and achieve a robust fault-tolerant system. A new simulator model is proposed for a winding process using non-linear identification based on a recurrent local linear neuro-fuzzy (RLLNF) network trained by local linear model tree (LOLIMOT), which is an incremental tree-based learning algorithm. The proposed NF models are compared with other known intelligent identifiers, namely multilayer perceptron (MLP) and radial basis function (RBF). Experimental results show the effectiveness of our proposed NF modeling approach.