质子交换膜燃料电池的神经网络建模与控制

该文从设计质子交换膜燃料电池（PEMFC）控制方案的角度出发，首先提出了采用Elman动态神经网络对PEMFC系统进行建模的新方法，以实验中采样到的PEMFC系统的工作温度输入输出数据训练网络，并采用动态反向传播学习算法根据误差不断调整网络参数直至达到要求精度；Elman神经网络辨识可使辨识过程简化并提高了辨识精度。然后在此基础上设计了自适应模糊神经网络控制器。最后的仿真实验以Elman神经网络模型为参考模型，使用自适应神经网络控制算法控制PEMFC的工作温度，取得了较好的控制效果。结果显示所设计的控制系统适合于控制PEMFC这样一类复杂非线性系统。

Modeling and Control of Elman Neural Network for PEMFC

To design a control strategy suitable for controlling operation temperature of hydrogen/air proton exchange membrane fuel cells(PEMFC),a novel neural network modeling method is presented in this paper.The method develops an Elman neural network identification model of PEMFC based on the input-output sampled data.Elman neural network modeling can offer the advantage that the identification process is simple and costs less time.And then,an adaptive fuzzy neural network control algorithm is also designed.Finally using the Elman neural network model of PEMFC,the simulation results of the control algorithm are presented.The results show the effectiveness of the proposed modeling and control strategy for PEMFC.