Control Simulation Study Based on Recurrent Generalized Congruence Neural Network

Abstract:

In order to meet the real-time demand of neural network control system, the structure and algorithm of self-tuning PID control system based on recurrent generalized congruence neural network(RGCNN) with fast convergence are presented, in which the improved recurrent generalized congruence neural network is adopted for identifier, and the single generalized congruence neuron with three inputs is used as controller. The simulation results of nonlinear dynamical control system show that the proposed RGCNN control system responses quickly and is stable, i.e., the proposed control system based on RGCNN is effective and feasible.

• Periodical: Advanced Materials Research (Volumes 383-390)
• Pages: 5691-5696
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.383-390.5691
• Online since: November 2011
• Authors: Tian Yun Yan
• Keywords: BP, Control Simulation, Neural Network (NN), Recurrent Generalized Congruence

References

[1] Ying SHEN, Cuifang ZHANG, Model reference adaptive control based on BP neural networks, Journal of Southwest Jiaotong University, 2001, vol. 36, no. 5, pp.553-556.

[2] P.S. SASTRY, G. SANTHARAM, K.P. UNNIKRISHNAN, Memory neuron networks for identification and control of dynamical systems, IEEE Transactions on Neural Networks, 1994, vol. 5, no. 2, pp.306-319.

DOI: 10.1109/72.279193

[3] K.K. Tan, S. Zhao, S. Huang, Iterative reference adjustment for high-precision and repetitive motion control applications, IEEE Transactions on Control Systems Technology, 2005, vol. 13, no. 1, pp.85-97.

DOI: 10.1109/tcst.2004.838549

[4] Tianyun Yan, Hefei Ling, Shurong Zou, A novel recurrent generalized congruence neural network for dynamical system identification, Proceeding of the 3rd International Conference on Natural Computation and the 4th International Conference on Fuzzy Systems and Knowledge Discovery, China, 2007, vol. 1, pp.39-43.

DOI: 10.1109/icnc.2007.122