CLC number: TM911.4
Online Access: 20141008
Received: 20140106
Revision Accepted: 20140507
Crosschecked: 20140929
Cited: 1
Clicked: 6677
Haibo Huo, Yi Ji, Xinjian Zhu, Xinghong Kuang, Yuqing Liu. Controloriented dynamic identification modeling of a planar SOFC stack based on genetic algorithmleast squares support vector regression[J]. Journal of Zhejiang University Science A, 2014, 15(10): 829839.
@article{title="Controloriented dynamic identification modeling of a planar SOFC stack based on genetic algorithmleast squares support vector regression",
author="Haibo Huo, Yi Ji, Xinjian Zhu, Xinghong Kuang, Yuqing Liu",
journal="Journal of Zhejiang University Science A",
volume="15",
number="10",
pages="829839",
year="2014",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.A1400011"
}
%0 Journal Article
%T Controloriented dynamic identification modeling of a planar SOFC stack based on genetic algorithmleast squares support vector regression
%A Haibo Huo
%A Yi Ji
%A Xinjian Zhu
%A Xinghong Kuang
%A Yuqing Liu
%J Journal of Zhejiang University SCIENCE A
%V 15
%N 10
%P 829839
%@ 1673565X
%D 2014
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.A1400011
TY  JOUR
T1  Controloriented dynamic identification modeling of a planar SOFC stack based on genetic algorithmleast squares support vector regression
A1  Haibo Huo
A1  Yi Ji
A1  Xinjian Zhu
A1  Xinghong Kuang
A1  Yuqing Liu
J0  Journal of Zhejiang University Science A
VL  15
IS  10
SP  829
EP  839
%@ 1673565X
Y1  2014
PB  Zhejiang University Press & Springer
ER 
DOI  10.1631/jzus.A1400011
Abstract: For predicting the voltage and temperature dynamics synchronously and designing a controller, a controloriented dynamic modeling study of the solid oxide fuel cell (SOFC) derived from physical conservation laws is reported, which considers both the electrochemical and thermal aspects of the SOFC. Here, the least squares support vector regression (LSSVR) is employed to model the nonlinear dynamic characteristics of the SOFC. In addition, a genetic algorithm (GA), through comparing a simulated annealing algorithm (SAA) with a 5fold crossvalidation (5FCV) method, is preferably chosen to optimize the LSSVR’s parameters. The validity of the proposed LSSVR with GA (GALSSVR) model is verified by comparing the results with those obtained from the physical model. Simulation studies further indicate that the GALSSVR model has a higher modeling accuracy than the LSSVR with SAA (SAALSSVR) and the LSSVR with 5FCV (5FCVLSSVR) models in predicting the voltage and temperature transient behaviors of the SOFC. Furthermore, the convergence speed of the GALSSVR model is relatively fast. The availability of this GALSSVR identification model can aid in evaluating the dynamic performance of the SOFC under different conditions and can be used for designing valid multivariable control schemes.
(1) All the gases are considered as ideal gases;
(2) The internal operating pressure is constant;
(3) Both anode and cathode channel exhaust gases pass through a single “choked” orifice;
(4) Temperature in the SOFC stack is uniform;
(5) The fuel and air temperatures at the exit of both channels are equal to the inside temperatures;
(6) Heat exchange between the stack and the ambient environment is not taken into account.
Item  Value 
Cell area (cm^{2})  100 
Electrode thickness (mm)  0.25 
Interconnector thickness (mm)  1.5 
Electrode density (g/cm^{3})  6.6 
Interconnector density (g/cm^{3})  6.11 
Fuel channel height (mm)  1 
Air channel height (mm)  1 
Item  Value 
N _{0}  384 
T _{in} (K)  973 
I _{rate} (A)  500 
E _{0} (V)  1.18 
K _{H2} (mol/(s·atm))  0.843 
K _{O2} (mol/(s·atm))  2.52 
K _{H2O} (mol/(s·atm))  0.281 
τ _{H2} (s)  26.1 
τ _{O2} (s)  2.91 
τ _{H2O} (s)  78.3 
r (Ω)  0.126 

5 

10 

−0.2418×10^{6} 

0.4 
Model type  MRE 

Stack voltage (V)  Operating temperature (K)  
GALSSVR  0.0935  0.1039 
SAALSSVR  0.1174  0.3149 
5FCVLSSVR  0.1432  0.4150 
Model type  RMSE 

Stack voltage (V)  Operating temperature (K)  
GALSSVR  0.7823  1.8641 
SAALSSVR  0.8952  3.6504 
5FCVLSSVR  10.4085  4.7680 
Model type  Prediction time (s) 

Stack voltage  Operating temperature  
GALSSVR  416.6730  133.3348 
SAALSSVR  370.8479  186.0621 
5FCVLSSVR  563.6533  518.5528 
Open peer comments: Debate/Discuss/Question/Opinion
<1>