Application of PID Control Algorithm Based on Improved BP Neural Network to Turntable System

Abstract:

Aiming at the problem that traditional PID control algorithm is difficult to get ideal control effect, a PID control algorithm based on improved BP neural network is proposed to improve the performance of turntable system. According to the structure and characteristic of BP neural network, the construction of PID controller and the description of improved BP neural network algorithm are introduced at first. Then, on the basis of the least square method and neural network prediction model of controlled object, the weight adjustment algorithm of PID is improved by replacing the measured values of BP network with calculated forecast output. A mathematical model of turntable control system is established and simulated. Simulation results show that the improved BP neural network PID controller has good control performance, high tracking accuracy and strong system robustness, which can be better applied to turntable system.

• Periodical: Advanced Materials Research (Volumes 490-495)
• Pages: 191-194
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.490-495.191
• Online since: March 2012
• Authors: Yang Feng, Qing Jiu Xu
• Keywords: BP Neural Network (BPNN), Least-Square Method (LSM), PID Control, Turntable

References

[1] Yourui Huang and Liguo Qu: Research and Implement on PID Controller Parameters Tuning (Science press, China 2010), in Chinese.

[2] D.L. Yu, T.K. Chang and D.W. Yu: Control Engineering Practice. Vol. 4 (2007), p.1.

[3] G.D. Emilia, A. Marra and E. Natale: Robotics and Computer-Integrated Manufacturing. Vol. 23 (2007), p.170.

[4] G. Lera and M. Pinzolas: IEEE Transactions on Neural Networks, Vol. 5 (2002), p.410.

[5] A.J. Isaksson and S. F. Graebe : Automatica, Vol. 35 (1999), p.1121.

[6] A. Eleni and S. Haralambos: Computers and Chemical Engineering, Vol. 32 (2008), p.1225.