[其它]Modeling a PEMFC by a support vector machine

Abstract {sN"(H4$  
This paper reports a modeling study of proton exchange membrane fuel cell (PEMFC) performance by using a support vector machine (SVM). l_FGZ!7  
A PEMFC is a nonlinear, multi-variable system that is hard to model by conventional methods. As regards the SVM, it has a superior capability for  SVP:D3)  
generalization, and this capability is independent on the dimensionality of the input data. These two merits combine to make it a powerful tool to 5?u[XAE  
predict how a PEMFC will behave under different operating conditions. Herein a SVM model of a PEMFC system is built, optimized and tested. kL{;.WsB  
First, the model is determined with selected experimental data, and then it is used to predict PEMFC performance. It is shown that the model can s
B}]yw  
make the prediction in 10 ms with the squared correlation coefficient as high as 99.7%. Therefore, the proposed black-box SVM PEMFC model 7-iIay1h"  
applies to the simulation, real-time control and monitoring of a fuel cell’s performance. (4~WWU (iT  
© 2006 Elsevier B.V. All rights reserved. ka7uK][  
Keywords: Fuel c .. )jW(6  
2V#6q,2  

未注册仅能浏览部分内容，查看全部内容及附件请先 登录 或 注册