基于模糊神经网络的多变量系统的解耦方法

Decoupling Control of a Multivariable System Based on Fuzzy Neural Network

针对多变量、强耦合、纯迟延系统,提出一种模糊神经网络的解耦方法,结合遗传算法、将多变量系统解耦成单变量系统。传统解耦方法对于非线性系统、变结构系统以及耦合关系和耦合强度随时间和负载变化的复杂系统经常无能为力,而这种综合了模糊逻辑和神经网络优势的解耦方法,由于具有非线性和自学习能力,使其解耦性能不受影响,弥补了传统解耦方法的缺陷,对复杂系统有着较好的解耦能力。且该方法不需要建立精确的数学模型,易于实现。文章最后通过仿真实验验证了该模型的解耦效果。

In this paper, to the problems of the multivariable variables, the strong coupling and the pure delay system, a method was proposed that could decouple a multivariable system into some single variable systems, based on the union of the genetic algorithm, fuzzy neural network. The traditional method had great difficulty in decoupling the nonlinear system, the variable structure system, the complex system with the coupling relationship or the changing coupling strength by the time and the load. However, this method that combines the advantages of fuzzy logic and neural network could make up the defects of the traditional decoupling method and had a good decoupling control performance in complex system, due to the non-linear and the self-learning ability. And this method was easy to implement without the precise mathematical model. Finally, the simulation results show that this method has a good decoupling control performance.