Build Proton Exchange Membrane Fuel Cell Model Based on ANN

With the development of human society, it is extremely urgent to solve the energy shortage. Proton exchange membrane fuel cell (PEMFC) as a new form of energy has been highlighted for special atlention, the study of the PEMFC is mainly about theoretical model and experimental study. Theoretical model can reflect the PEMFC output characteristics, and often used to design battery and analyze operating performance. In fact, the theoretical model was built to describe its mechanism by assuming ideal conditions, with a certain degree of regularity but not accurate enough. Experimental study is not typical because of its limited sample size. In this paper a new model based on artificial neural network (ANN) was developed combined with experimental data and improved theoretical models. Validation results show that the model can combine theoretical analysis with experimental data effectively. The artificial neural network model can be used to forecast the PEMFC performance.