Identification and analysis based on genetic algorithm for proton exchange membrane fuel cell stack

Abstract

The temperature of proton exchange membrane fuel cell stack and the stoichiometric oxygen in cathode have relationship with the performance and life span of fuel cells closely. The thermal coefficients were taken as important factors affecting the temperature distribution of fuel cells and components. According to the experimental analysis, when the stoichiometric oxygen in cathode is greater than or equal to 1.8, the stack voltage loss is the least. A novel genetic algorithm was developed to identify and optimize the variables in dynamic thermal model of proton exchange membrane fuel cell stack, making the outputs of temperature model approximate to the actual temperature, and ensuring that the maximal error is less than 1 °C. At the same time, the optimum region of stoichiometric oxygen is obtained, which is in the range of 1.8–2.2 and accords with the experimental analysis results. The simulation and experimental results show the effectiveness of the proposed algorithm.

Keywords

proton exchange membrane fuel cell / genetic algorithm / temperature / thermal coefficient / stoichiometric oxygen

References

[1] RoweA, LiXian-guo. Mathematical modelling of proton membrane fuel cells [J]. Journal of Power Source, 2001, 102(1): 82-96

[2] YouLi-xin, LiuHong-tan. A two-phase flow and transport model for the cathode of PEM fuel cells [J]. International Journal of Heat and Mass Transfer, 2002, 45(11): 2277-2287

[3] BerningT, LuD M, DjilaiN. Three-dimensional computational analysis of transport phenomena in a PEM fuel cell [J]. Journal of Power Source, 2002, 106(2): 284-294

[4] LeeJ H, LalkT R, ApplebyA J. Modeling electrochemical performance in large scale proton exchange membrane fuel cell stacks [J]. Journal of Power Source, 1998, 70(2): 258-268

[5] JiangR Z, DerynC. Voltage-time behavior of a polymer electrolyte membrane fuel cell stack at constant current discharge [J]. Journal of Power Source, 2001, 92(2): 193-198

[6] HamelinJ, AgbossouK, LaperriereA, et al.. Dynamic behavior of a PEM fuel cell stack for stationary applications [J]. International Journal of Hydrogen Energy, 2001, 26(6): 625-629

[7] LeeJ H, LalkT R. Modeling fuel cell stack systems [J]. Journal of Power Sources, 1998, 73(2): 229-241

[8] WeiDongStudy of modeling and control of proton exchange membrane fuel cell stack[D], 2004, Shanghai, Department of Automation, Shanghai Jiaotong University

[9] WeiDong, ZhuXin-jian, CaoGuang-yi. Modeling based on improved genetic algorithm for temperature model of PEMFC stack [J]. Journal of Chemical Industry and Engineering, 2005, 156(13): 538-544(in Chinese)

[10] BergP, ÇaĝlarA, PromislowK, et al.. Electrical coupling in proton exchange membrane fuel cell stacks: Mathematical and computational modeling [J]. IMA Journal of Applied Mathematics, 2006, 71(2): 241-261

[11] ZhouMing, SunShu-dongThe theory and application of genetic algorithm [M], 1999, Beijing, National Defence Industry Press

[12] GoldbergD E. Real-coded genetic algorithm, virtual alphabets and blocking [J]. Complex Systems, 1991, 5(2): 139-167

[13] Yamamura M, Sotoh H, Kobayashi S. An analysis of crossover’s effect in genetic algorithms[C]// Proc 1st IEEE Conf on Evolutionary Computation. Orlando: IEEE, 1994: 613–618.

[14] SrinivasM. Adaptive probabilities of crossover and mutation in genetic algorithm[J]. IEEE Transaction on Systems, Man and Cybernetics, 1994, 24(4): 656-666

[15] FANG Kang-ling, GU Hai-chang, HUANG Wei-hua. A HGA based on the analysis of best value region and application to the fuzzy controller[C]// Proc of 2002 Internal Conf on Machine Learning and Cybernetics. Beijing: IEEE, 2002: 747–749.

[16] LiXiStudy of modeling and intelligent control strageties for proton exchange membrane fuel cell system[D], 2005, Shanghai, Department of Automation, Shanghai Jiaotong University

[17] PukrushpanJ T, StefanopoulouA G, PengH. Control of fuel cell breathing[J]. IEEE Control Systems Magazine, 2004, 24(2): 30-46