A Novel Control Scheme Based on Improved RBF Neural Network

Abstract:

A novel control scheme based on an improved RBF neural network and PID control method is proposed. When used the RBF network in the PID controller, if RBF network provides the parameter to revise PID while it does not have training finished, the controller will oscillated or even to diverge. As the structure is more complex, and the adjustment speed is slower, the improvements are made to the standard RBF neural network trained algorithm. Uses the matrix operation substitute the iterative algorithm, may avoid the above question effectively. Finally, choosing a certain type of PID controller, the improved RBF neural network algorithm is used to design the control law for control command tracking, the simulation results show that the improved RBF neural network algorithm can avoid oscillated and diverge.

• Periodical: Applied Mechanics and Materials (Volumes 182-183)
• Pages: 1313-1317
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.182-183.1313
• Online since: June 2012
• Authors: Xiao Zhu Xie, Xing Lai Guan
• Keywords: Improved RBF Neural Network, PID Control, Weight Adjustment

References

[1] J. J. HOPFIELD Neural networks and physical systems with emergent collective computational abilities. Proc. NatL Acad. Sci. USA Vol. 79, pp.2554-2558, April 1982 Biophysics.

DOI: 10.1073/pnas.79.8.2554

[2] Lukaszyk, S. (2004) A new concept of probability metric and its applications in approximation of scattered data sets. Computational Mechanics, 33, 299-3004.

DOI: 10.1007/s00466-003-0532-2

[3] Liu Xiaojing, Yi Jianqiang, Zhao Dongbin, Wang Wei, A Kind of Nonlinear Adaptive Inverse Control System Based on RBF Networks [J]. Control and Desicion, Vol. 19, No. 10, October (2004).

DOI: 10.1109/acc.2005.1470363

[4] Buhmann, Martin D. (2003), Radial Basis Functions: Theory and Implementations, Cambridge University Press.

[5] Bennett, Stuart (1993). A history of control engineering, 1930-1955. IET. p. p.48.

[6] Ang, K.H., Chong, G.C.Y., and Li, Y. (2005). PID control system analysis, design, and technology, IEEE Trans Control Systems Tech, 13(4), pp.559-576.

DOI: 10.1109/tcst.2005.847331

[7] Shi Zhongke, Neural Network Control Theroy[C], Northwestern Polytechnical Publishing House, Xi'an, 1997. Figure 1 The structure of RBF neural network Figure 2 The flow chart of the standard BP neural network algorithm Figure 3 The structure of the PID controler Figure 4 The results of the adaptive controllers which designed by using RBF neural network Figure 5 The results of the adaptive controllers which designed by using non-training-type RBF neural network.

DOI: 10.7717/peerj-cs.1326/fig-3