基于一种FGA-ANFIS技术的DMFC温度建模和控制  

Temperature modeling and control of DMFC based on FGA-ANFIS technology

作　　者：戚志东[1] 朱新坚[2] 

机构地区：[1]南京理工大学自动化学院,江苏南京210094 [2]上海交通大学燃料电池研究所,上海200030

出　　处：《控制理论与应用》2008年第4期738-742,共5页Control Theory & Applications

基　　金：国家863项目资助(2002AA517020).

摘　　要：为了提高直接甲醇燃料电池(DMFC)的发电性能,采用自适应神经模糊推理技术(FGA-ANFIS)对电池的工作温度进行建模与控制.首先,基于实验的输入输出数据建立了DMFC电堆温度的自适应神经模糊辨识模型,避开了DMFC电堆的内部复杂性.然后,将训练好的网络模型作为DMFC控制系统的参考模型,采用一种改进的模糊遗传算法对神经模糊控制器的参数和模糊规则进行自适应调整.最后,通过仿真,将所提出的算法与非线性PID和传统模糊算法进行比较,结果表明所设计的神经模糊控制器具有较好的性能.To improve the performance of a direct methanol fuel cell （DMFC）, the adaptive neural fuzzy inference （FGA-ANFIS） technology is applied to the modeling and control of a DMFC temperature system. First, an adaptive neural fuzzy inference system （ANFIS） identification model of DMFC stack temperature is developed based on the input-output sampled data, getting around the internal complexity of DMFC stack. Then, taking the well-trained network model as the reference model of the control system of DMFC stack, we use a novel fuzzy genetic algorithm （FGA） for adaptively adjusting the parameters and fuzzy rules of a neural fuzzy controller. Simulation results demonstrate better performance of this neural fuzzy controller in comparison with those of the nonlinear PID and traditional fuzzy algorithm.

关 键 词：直接甲醇燃料电池 自适应神经模糊推理系统 模糊遗传算法 

分 类 号：TM911.4[电气工程—电力电子与电力传动]