Adaptive Backstepping Control Based upon DRFNN for RCRBV

Abstract:

For the nonliear and uncertainty parameters of the running driving component of Resonant cement-road breaking vehicle (RCRBV), the mathematic model of the speed Control is established, a adaptive backstepping control method based upon the dynamic recurrent fuzzy neural networks (DRFNN) is presented. The adaptive backstepping controlling arithmetic is designed firstly in transportational status without regard to the uncertain parameters. The convergence based on Lyapunov theory for the closed loop system is also analysised. secondly, the uncertain parameters of the Electro-hydraulic propotional system which affect the running speed controlling performances are defined as items to be estimated by DRFNN in breaking status to meet the high precision and stability requires, the parameter adjustment law is given based upon DRFNN. Finally, the results of the simulation show that the scheme is robust with respect to plant parameter variations and load disturbances.

• Periodical: Advanced Materials Research (Volumes 403-408)
• Pages: 5082-5087
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.403-408.5082
• Online since: November 2011
• Authors: Ping Jun Zhang, Xin Hua Jiang
• Keywords: Adaptive Backstepping Control, Dynamic Recurrent Fuzzy Neural Networks, Resonant Cement-Road Breaking Vehicle, Uncertainty

References

[1] XU Zhu-jie，LING Jian-ming，HUANG Qin-long . Research on Resonant Rubblized Effects of PCC Pavement [J]．China Journal of Highway and Transport, 2008, 21(5): 26-32.

[2] Zhong Tian-yu, Wang Qing-fen, Yao bing. DARC Based on Bi-directional Electro-hydraulic Proportional Tension Winch with Uncertain Factors[J]．Transactions of the Chinese Society For Agricultural Machinery，2007, 11(38): 144-148, 160.

[3] Wu Z J，Xie X J，Zhang S Y. The reduced order design of robust adaptive backstepping controller[J]．Acta Automatica Sinica，2005，3l(4)：543-548.

[4] Hsu C F, Lin C M, Lee T T. Wavelet adaptive backstepping control for a class of nonlinear systems[J]. IEEE Transactions on Neural Network, 2006, 17: 1175-1183.

DOI: 10.1109/tnn.2006.878122

[5] Farivar F, Shoorehdeli M A, Nekoui M A. Gaussian radial basis adaptive backstepping control for a class of nonlinear systems[ J]. Journal of Applied Sciences, 2009, 9(2): 248-257.

DOI: 10.3923/jas.2009.248.257

[6] Mao L P, Gong Y N, Sun W, et al. An adaptive control using recurrent fuzzy neural network[J]. ACTA Electronica Sinica, 2006, 24(12): 2285-2287.