Intelligent Self-Adaptive Control Method Based on RBFNN and its Application in Hydraulic Control

Abstract:

We proposed an intelligent self-adaptive control method based on RBFNN in this paper, dynamic identification model of nonlinear control system is built based on radial basis neural network, mixed intelligent method of dynamic self-adaptive internal model control is developed by adjusting online for nonlinear control system. We applied the intelligent self-adaptive control method to nonlinear hydraulic control, simulation shows the dynamic characteristic is greatly improved by the intelligent control strategy for nonlinear control system, good tracking and control effect is reached in condition of high frequency response, and the intelligent control method has higher precision, smaller overshoot and stronger robustness compared with common PID control, BPNN control and fuzzy control. It provides a new control method for nonlinear control system.

• Periodical: Advanced Materials Research (Volumes 1030-1032)
• Pages: 1488-1492
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1030-1032.1488
• Online since: September 2014
• Authors: Hao Zhang*, Ya Jie Zhang, Yan Gu Zhang
• Keywords: Mixed Intelligent Method, Nonlinear Control System, Radial Basis Neural Network, Self-Adaptive Internal Control

References

[1] Hong Yu, Zheng-jin Feng and Xu-yong Wang: Journal of Zhejiang University - Science A Vol. 5(11)(2009), pp.1413-1417.

[2] Miao-Lei Zhou, Yan-tao Tian, Wei Gao and Zhi-gang Yang: Journal of Central South University of Technology Vol. 14(6)(2007), pp.832-837.

[3] Wei-Jie Mao and Yuan-Yuan Zhang: Lecture Notes in Computer Science, Intelligent Robotics and Applications Vol. 5314(2008), pp.401-409.

[4] Jun Gu, James Taylor and Derek Seward: Journal of Control Theory and Applications Vol. 5(4)(2009), pp.391-396.

[5] Y. Wan: Advanced Materials Research Vol. 580(2012), pp.12-15.

[6] J. S. Guo: Research on artificial neural Networks (ANN) for water quality assessment and Simulation (Chongqing university, Chongqing 2002).

[7] Y. Wan: 2009 ETP/IITA World Congress in Applied Computing, Computer Science, and Computer Engineering /(ACC2009) Vol. 2009, pp.176-179.

[8] Qing-hua He, Peng Hao and Da-qing Zhang: Journal of Central South University of Technology Vol. 15(3)(2008), pp.382-386.

[9] Kasprzyczak, Leszek; Macha, Ewald: Mechanical Systems and Signal Processing Vol. 22(6)(2009), pp.1274-1288.

[10] ShengWei Mei, XiaoYang Gui, Chen Shen and Qiang Lu: Science in China Series E: Technological Sciences Vol. 50(5)(2007), pp.618-635.

[11] Yi. He: The Identification Modeling and Control of Nonlinear System Based on SVM (Tianjin University, Tianjin2006).

[12] Zhong Liang JI: Control Method on VCM Production Process Based on SVM (Dalian University of Technology, Dalin 2005).