摘要
利用神经网络具有逼近任意复杂非线性函数的能力 ,以甲醇浓度为神经网络辨识模型的输入量 ,电池电压 /电流密度为输出量 ,利用 10 0 0组实验数据 ,建立了DMFC电堆的神经网络模型。然后 ,基于电特性的输入输出关系设计了一个模糊控制器 ,且利用模糊控制器的输入输出样本训练神经网络。仿真结果表明 ,所设计的神经网络模糊控制器具有自学习、自适应等优点 ,达到了在线控制的目的。
Neural network is able approaching to any complicated non-linear function. By using this feature of neural network, neural network model of DMFC electric pile is established based on 1000 sets of experimental data with the concentration of methanol as input of neural network recognition and cell voltage/current density as output. Then a fuzzy controller is designed based on relationship of input vs. output of electric characteristics. The neural network is trained from the samples of input and output of the fuzzy controller. The result of simulation shows that this neural network fuzzy controller features self-learning and self-adaptive capabilities, and the purpose of on-line control is accomplished.
出处
《自动化仪表》
CAS
北大核心
2004年第7期46-49,共4页
Process Automation Instrumentation
基金
国家 8 63计划资助项目 (编号 :2 0 0 2AA51 70 2 0 )