Zhuang Hong
State Key Laboratory of Industrial Control Technology, Department of Control Science and Engineering, Zhejiang University, Zhejiang, Hangzhou, 310027, China
Lu Jian-Gang
State Key Laboratory of Industrial Control Technology, Department of Control Science and Engineering, Zhejiang University, Zhejiang, Hangzhou, 310027, China
Yang Qin-Min
State Key Laboratory of Industrial Control Technology, Department of Control Science and Engineering, Zhejiang University, Zhejiang, Hangzhou, 310027, China
Wang Xue-Fei
State Key Laboratory of Industrial Control Technology, Department of Control Science and Engineering, Zhejiang University, Zhejiang, Hangzhou, 310027, China
Chen Jin-Shui
State Key Laboratory of Industrial Control Technology, Department of Control Science and Engineering, Zhejiang University, Zhejiang, Hangzhou, 310027, China
ABSTRACT
This study focuses on the control problem of hydrogen production via autothermal reforming of methanol. To deal with uncertain system dynamics and external disturbance, an improved adaptive neural network controller is designed to regulate hydrogen flow rate by manipulating methanol flow rate. Theoretical derivation and analysis demonstrate its adaptability to model mismatch and external disturbance. Furthermore, a variable ratio controller law is employed as the reforming temperature controller to achieve steady reforming temperature by adjusting the reforming air flow rate. Finally, the effectiveness of the entire system is testified by experimental means.
PDF References Citation
How to cite this article
Zhuang Hong, Lu Jian-Gang, Yang Qin-Min, Wang Xue-Fei and Chen Jin-Shui, 2013. Adaptive Neural Network Control of Hydrogen Production via Autothermal Reforming
of Methanol. Information Technology Journal, 12: 6992-6997.
DOI: 10.3923/itj.2013.6992.6997
URL: https://scialert.net/abstract/?doi=itj.2013.6992.6997
DOI: 10.3923/itj.2013.6992.6997
URL: https://scialert.net/abstract/?doi=itj.2013.6992.6997
REFERENCES
- Chen, F.C. and C.C. Liu, 1994. Adaptively controlling nonlinear continuous-time systems using multilayer neural networks. IEEE Trans. Automatic Control, 39: 1306-1310.
Direct Link - Hu, Y., D.J. Chmielewski and D. Papadias, 2008. Autothermal reforming of gasoline for fuel cell applications: Controller design and analysis. J. Power Sources, 182: 298-306.
CrossRef - Hu, Y. and D.J. Chmielewski, 2009. Nonlinear multivariable predictive control of an autothermal reforming reactor for fuel cell applications. Proceedings of the American Control Conference, June 10-12, 2009, St. Louis, MO, America, pp: 10-12.
CrossRef - Huang, S., K.K. Tan and T.H. Lee, 2004. An improvement on stable adaptive control for a class of nonlinear systems. IEEE Trans. Automat. Contr., 49: 1398-1403.
CrossRef - Kolavennu, P.K., S. Palanki, D.A. Cartes and J.C. Telotte, 2008. Adaptive controller for tracking power profile in a fuel cell powered automobile. J. Process Contr., 18: 558-567.
CrossRef - Lindstrom, B. and L.J. Pettersson, 2003. Development of a methanol fuelled reformer for fuel cell applications. J. Power Sources, 118: 71-78.
CrossRef - Mu, X., L. Pan, N. Liu, C. Zhang, S. Li, G. Sun and S. Wang, 2007. Autothermal reforming of methanol in a mini-reactor for a miniature fuel cell. Int. J. Hydrogen Energy, 32: 3327-3334.
CrossRef - Tornambe, A., 1992. High-gain observers for non-linear systems. Int. J. Syst. Sci., 23: 1475-1489.
CrossRef - Zheng, J.F., Q.M. Yang, J.G. Lu and Y.X. Sun, 2012. Adaptive control design for hydrogen production via autothermal reforming of methanol. Adv. Mater. Res., 418: 377-382.
Direct Link