journal article·2008-05

Dynamic temperature modeling of an SOFC using least squares support vector machines

Ying-Wei Kang, Jun Li, Guang-Yi Cao, Heng-Yong Tu, Jian Li, Jie Yang

Journal of Power Sources· Volume 179· Issue 2
Publisher page

Abstract

Cell temperature control plays a crucial role in SOFC operation. In order to design effective temperature control strategies by model-based control methods, a dynamic temperature model of an SOFC is presented in this paper using least squares support vector machines (LS-SVMs). The nonlinear temperature dynamics of the SOFC is represented by a nonlinear autoregressive with exogenous inputs (NARXs) model that is implemented using an LS-SVM regression model. Issues concerning the development of the LS-SVM temperature model are discussed in detail, including variable selection, training set construction and tuning of the LS-SVM parameters (usually referred to as hyperparameters). Comprehensive validation tests demonstrate that the developed LS-SVM model is sufficiently accurate to be used independently from the SOFC process, emulating its temperature response from the only process input information over a relatively wide operating range. The powerful ability of the LS-SVM temperature model benefits from the approaches of constructing the training set and tuning hyperparameters automatically by the genetic algorithm (GA), besides the modeling method itself. The proposed LS-SVM temperature model can be conveniently employed to design temperature control strategies of the SOFC.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Advanced Control Systems Optimization · Fault Detection and Control Systems · Advancements in Solid Oxide Fuel Cells

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (34)

Show source-provided references
1. 2003 · 14
2. Aguiar · J. Power Sources · 2005 · 147 · 13610.1016/j.jpowsour.2005.01.017 ↗
3. Stiller · J. Power Sources · 2006 · 158 · 30310.1016/j.jpowsour.2005.09.010 ↗
4. Achenbach · J. Power Sources · 1994 · 49 · 33310.1016/0378-7753(93)01833-4 ↗
5. Hall · IEEE Trans. Energy Conv. · 1999 · 14 · 74910.1109/60.790946 ↗
6. Aguiar · J. Power Sources · 2004 · 138 · 12010.1016/j.jpowsour.2004.06.040 ↗
7. Xi · J. Power Sources · 2007 · 165 · 25310.1016/j.jpowsour.2006.12.009 ↗
8. Seborg · 2004
9. Ljung · 1999
10. Shen · Simulat. Model. Pract. Theor. · 2002 · 10 · 10910.1016/S1569-190X(02)00064-3 ↗
11. Jurado · J. Power Sources · 2006 · 154 · 14510.1016/j.jpowsour.2005.04.005 ↗
12. Jurado · J. Power Sources · 2006 · 158 · 24510.1016/j.jpowsour.2005.08.041 ↗
13. Yang · J. Power Sources · 2007 · 166 · 35410.1016/j.jpowsour.2007.01.062 ↗
14. Suykens · Neural Process. Lett. · 1999 · 9 · 29310.1023/A:1018628609742 ↗
15. Suykens · Neural Netw. · 2001 · 14 · 2310.1016/S0893-6080(00)00077-0 ↗
16. Viaene · Int. J. Intell. Syst. · 2001 · 16 · 102310.1002/int.1047 ↗
17. Vong · Eng. Appl. Artif. Intell. · 2006 · 19 · 27710.1016/j.engappai.2005.09.001 ↗
18. Huo · J. Power Sources · 2006 · 162 · 122010.1016/j.jpowsour.2006.07.031 ↗
19. Holland · 1975
20. Goldberg · 1989
21. Larminie · 2000
22. Suykens · Eur. J. Contr. (Special Issue on fundamental issues in control) · 2001 · 7 · 311
23. Duan · Neurocomputing · 2003 · 51 · 4110.1016/S0925-2312(02)00601-X ↗
24. Ferguson · J. Power Sources · 1996 · 58 · 10910.1016/0378-7753(95)02269-4 ↗
25. Zhang · J. Power Sources · 2006 · 160 · 25810.1016/j.jpowsour.2006.01.024 ↗
26. A. Selimovic, Doctoral Thesis, Lund University, Sweden, 2002.
27. Mathews · 2003
28. Narendra · IEEE Trans. Neural Netw. · 1990 · 1 · 410.1109/72.80202 ↗
29. Lukas · IEEE Trans. Energy Conv. · 1999 · 14 · 165110.1109/60.815119 ↗
30. Kandepu · Energy · 2007 · 32 · 40610.1016/j.energy.2006.07.034 ↗
31. Murshed · J. Power Sources · 2007 · 163 · 83010.1016/j.jpowsour.2006.09.080 ↗
32. Yakabe · J. Power Sources · 2001 · 102 · 14410.1016/S0378-7753(01)00792-3 ↗
33. Campanari · J. Power Sources · 2004 · 132 · 11310.1016/j.jpowsour.2004.01.043 ↗
34. Costamagna · J. Electrochem. Soc. · 1998 · 145 · 399510.1149/1.1838904 ↗