摘要
针对熔融碳酸盐燃料电池 ( MCFC)电堆系统难以建模以及已建立的模型过于复杂 ,难以满足工程上对 MCFC系统控制设计特别是实时控制需要的情况 ,绕开 MCFC的内部复杂性 ,提出利用神经网络可以逼近任意复杂非线性函数的性能 ,将神经网络辨识方法应用到 MCFC这种高度非线性系统的建模中 .以燃料气和氧化剂气体的流速为输入量 ,MCFC电堆的温度响应为输出量 ,根据输入输出数据用神经网络辨识建立 MCFC电堆系统的温度模型 ,给出了辨识系统的结构及改进 BP算法 .仿真结果证明了这种方法的可行性 ,所建立的模型精度较高 ,使得设计
Modeling Molten Carbonate Fuel Cells(MCFC) is very difficult and the models existed are too complicated to be used as a model for controller design, especially for on line controlling. This paper tries to avoid the internal complexes of MCFC. It set up a temperature model of MCFC using neural networks identification technology, the flow rate of fuel gas and oxidant gas as the input and the temperature response of MCFC stack as the output. The structure and the novel BP algorithm of neural networks identification system were given. The validity and accuracy of the modeling were proved by the simulation results . The neural networks modeling makes it possible to design an online controller of MCFC.
出处
《上海交通大学学报》
EI
CAS
CSCD
北大核心
2002年第8期1184-1186,共3页
Journal of Shanghai Jiaotong University
基金
上海市科技发展基金资助项目 (993 0 12 0 13 )
