Predictive control of a direct internal reforming SOFC using a self recurrent wavelet network model  

作　　者：Jun LI Nan GAO Guang-yi CAO Heng-yong TU Ming-ruo HU Xin-jian ZHU Jian LI 

机构地区：[1]Institute of Fuel Cell, Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China [2]Department of Mathematics, Shanghai University, Shanghai 200444, China [3]College of Materials Science and Engineering, Huazhong University of Seience and Technology, Wuhan 430074, China

出　　处：《Journal of Zhejiang University-Science A(Applied Physics & Engineering)》2010年第1期61-70,共10页浙江大学学报（英文版）A辑（应用物理与工程）

基　　金：supported by the National High-Tech Research and Devel-opment Program (863) of China (No. 2006AA05Z148);the Shanghai Municipal Natural Science Foundation, China (No. 08ZR1409800)

摘　　要：In this paper,an application of a nonlinear predictive controller based on a self recurrent wavelet network (SRWN) model for a direct internal reforming solid oxide fuel cell (DIR-SOFC) is presented. As operating temperature and fuel utilization are two important parameters,the SOFC is identified using an SRWN with inlet fuel flow rate,inlet air flow rate and current as inputs,and temperature and fuel utilization as outputs. To improve the operating performance of the DIR-SOFC and guarantee proper operating conditions,the nonlinear predictive control is implemented using the off-line trained and on-line modified SRWN model,to manipulate the inlet flow rates to keep the temperature and the fuel utilization at desired levels. Simulation results show satisfactory predictive accuracy of the SRWN model,and demonstrate the excellence of the SRWN-based predictive controller for the DIR-SOFC.In this paper, an application of a nonlinear predictive controller based on a self recurrent wavelet network （SRWN） model for a direct internal reforming solid oxide fuel cell （DIR-SOFC） is presented. As operating temperature and fuel utilization are two important parameters, the SOFC is identified using an SRWN with inlet fuel flow rate, inlet air flow rate and current as inputs, and temperature and fuel utilization as outputs. To improve the operating performance of the DIR-SOFC and guarantee proper operating conditions, the nonlinear predictive control is implemented using the off-line trained and on-line modified SRWN model, to manipulate the inlet flow rates to keep the temperature and the fuel utilization at desired levels. Simulation results show satisfactory predictive accuracy of the SRWN model, and demonstrate the excellence of the SRWN-based predictive controller for the DIR-SOFC.

关 键 词：Direct internal reforming （DIR） Solid oxide fuel cell （SOFC） Predictive control Self recurrent wavelet network （SRWN） 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TM911.4[自动化与计算机技术—控制科学与工程]