B样条基函数模糊神经网络控制系统及其混合学习算法  

A Control System with Fuzzy B-spline Neural Networks and Its Hybrid Training Algorithm

作　　者：程启明[1] 王勇浩[2] 

机构地区：[1]上海电力学院信控系,上海200090 [2]上海理工大学光电学院,上海200090

出　　处：《动力工程》2005年第4期528-532,共5页Power Engineering

基　　金：上海市教委发展基金(020K02)

摘　　要：介绍了一种基于模糊B样条基函数神经网络的控制器,该控制器将模糊控制的定性知识表达能力、神经网络的定量学习能力和B样条基函数优异的局部控制性能相结合,采用B样条基函数作为模糊隶属函数。还提出了模糊神经网络控制器的混合学习算法,即先采用免疫遗传算法离线优化,再采用BP梯度算法在线调整。对锅炉主蒸汽温度控制的仿真结果表明了此法的可行性和有效性。A novel controller based on the fuzzy B-spline neural network is being presented, which combines the advantages of qualitative defining capability of fuzzy logic, quantitative learning ability of neural networks and excellent local controlling ability of B-spline basis functions, which are being used as membership of fuzzy functions. Simultaneously, a hybrid learning algorithm of the controller is proposed as well, in which immune genetic algorithm is used offline first for optimizing, followed by online adjustment with BP algorithm. Simulation results of a boier＇s fresh steam temperature control shows the method to be feasible and effective. Figs 4 and refs 3.

关 键 词：自动控制技术 智能控制 B样条基函数模糊神经网络 混合学习算法 主蒸汽温度 

分 类 号：TP273.5[自动化与计算机技术—检测技术与自动化装置]