B样条基函数模糊神经网络控制系统及其混合学习算法

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。图4参3

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

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.