基于系统辨识的PEMFC温度非线性建模与预测

针对质子交换膜燃料电池(PEMFC)等一类具有严重非线性的复杂被控对象，提出一种基于模糊模型的模糊预测算法，并对PEMFC系统进行建模。在建模过程中，采用离线学习和在线修正辨识出对象的模糊模型。其中，模型的参数通过模糊聚类初始化和离线反向传播算法进行学习，必要时可通过在线调整后件参数，以使得模型的预测精度能满足实时控制的需要。仿真和实验结果表明了该模糊辨识建模方法具有建模简单、模型精度高等优点，亦证明了该算法的有效性和优越性。

Nonlinear Temperature Modeling and Prediction of PEMFC Based on System Identification

A nonlinear predictive control algorithm based on fuzzy model was presented for a family of complex systems with severe nonlinearity such as of Proton exchange membrane fuel cell (PEMFC). In order to implement nonlinear predictive control of the plant, the fuzzy model was identified by offline learning and online rectified. The model parameters were initialized by fuzzy clustering, and off-line learned using back-propagation algorithm. If necessary, it can be rectified on-line to improve the predictive precision in real-time control process. The simulation results demonstrate the effectiveness and advantages of this approach. We find the modeling method is simple and accurate. It is applicable for studying model and controlling of PEMFC control system.