基于混合学习算法的模糊神经网络控制系统  

A Fuzzy Neural Network Control System Based on Hybrid Learning Algorithms

作　　者：刘美俊[1] 

机构地区：[1]厦门理工学院电子与电气工程系,福建厦门361024

出　　处：《厦门理工学院学报》2009年第1期36-41,共6页Journal of Xiamen University of Technology

基　　金：福建省教育厅A类科技项目(JA08218)

摘　　要：针对复杂非线性系统在控制过程中的不确定性及参数的时变性,设计了一种模糊神经自适应预测控制系统,通过误差补偿以提高预测控制的精度;对模糊神经网络(FNN)的学习算法进行了研究,利用遗传算法的全局搜索能力对FNN控制器参数进行离线优化,并对遗传操作进行了改进,使其最终搜索到全局最优或近似全局最优的附近,再利用BP算法的局部搜索能力和对对象的适应能力,进一步对参数进行在线调整.从而使系统具有更高的学习精度和更快的收敛速度,所得的FNN具有良好的泛化性能.仿真结果证明了本方法的有效性.For a class of complex nonlinear system with uncertainty and time-varying parameters in the process control, an adaptive predictive control system based on fuzzy neural network has been developed. Using the error-compensation , the accuracy of the system is improved; and researching the algorithms of fuzzy neural network（ FNN）, an optimal or suboptimal spot is found by the optimization of fuzzy network＇s parameters using the global searching ability of genetic algorithms. The BP algorithms ability of local searching and adaptation to object is used to adjust the parameters further. So the system owns greater precision and better convergent speed, and the FNN obtained has excellent performance of generalization. A simulation example demonstrates the efficiency of the method.

关 键 词：模糊控制 神经网络 混合算法 自适应预测控制 仿真 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]