期刊
SUSTAINABILITY
卷 15, 期 11, 页码 -出版社
MDPI
DOI: 10.3390/su15118500
关键词
oxygen excess ratio; PID; fuzzy logic inference; neural network
In this paper, a nonlinear air supply system model integrated with the fuel cell stack voltage model is built. Conventional PID controls for the oxygen excess ratio are implemented, and fuzzy logic inference and neural network algorithm are integrated into the PID controller to tune the gain coefficients. Simulation results show that the fuzzy PID controller with seven subsets can improve the dynamic responses of the fuel cells in both constant and variable OER controls.
The hydrogen fuel cell is a quite promising green device, which could be applied in extensive fields. However, as a complex nonlinear system involving a number of subsystems, the fuel cell system requires multiple variables to be effectively controlled. Oxygen excess ratio (OER) is the key indicator to be controlled to avoid oxygen starvation, which may result in severe performance degradation and life shortage of the fuel cell stack. In this paper, a nonlinear air supply system model integrated with the fuel cell stack voltage model is first built, based on physical laws and empirical data; then, conventional proportional-integral-derivative (PID) controls for the oxygen excess ratio are implemented. On this basis, fuzzy logic inference and neural network algorithm are integrated into the conventional PID controller to tune the gain coefficients, respectively. The simulation results verify that the fuzzy PID controller with seven subsets could clearly improve the dynamic responses of the fuel cells in both constant and variable OER controls, with small overshoots and the fastest settling times of less than 0.2 s.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据