Modification of Neuron PID Control in Case of Improper Learning Factors

Some modifications of conventional neuron proportional-integral-differential controller (NPID) are presented in this paper to prevent its slow dynamic response and loss of control in case of improper learning factors. The quasi-step signal replaces the step signal as the reference signal to improve the dynamic characteristics. The control output of NPID is modified every step by multiplying a penalty factor called senior teacher signal to suppress further the overshoot and compress the settling time. The steady-state error from the modified NPID (MNPID) is reduced or removed by adjusting dynamically reference input signal while excluding the pseudo steady state. Lots of simulation experiments are done to prove the stability and convergence of the MNPID control algorithm.

[1]  Pyung Hun Chang,et al.  A Systematic Method for Gain Selection of Robust PID Control for Nonlinear Plants of Second-Order Controller Canonical Form , 2009, IEEE Trans. Control. Syst. Technol..

[2]  Aidan O'Dwyer.  PI and PID controller tuning rule design for processes with delay, to achieve constant gain and phase margins for all values of delay , 2001 .

[3]  D. Seborg,et al.  PI/PID controller design based on direct synthesis and disturbance rejection , 2002 .

[4]  J. G. Ziegler,et al.  Optimum Settings for Automatic Controllers , 1942, Journal of Fluids Engineering.

[5]  Serdar Ethem Hamamci.  Stabilization using fractional-order PI and PID controllers , 2007 .

[6]  George K. I. Mann,et al.  Time-domain based design and analysis of new PID tuning rules , 2001 .

[7]  R.C. Schaefer,et al.  Tuning a PID controller for a digital excitation control system , 2005, IEEE Transactions on Industry Applications.

[8]  Huaguang Zhang,et al.  Global Asymptotic Stability of Reaction–Diffusion Cohen–Grossberg Neural Networks With Continuously Distributed Delays , 2010, IEEE Transactions on Neural Networks.

[9]  Achiel Van Cauwenberghe,et al.  PID gradient algorithm for neural network based generalised nonlinear PID controller , 2000 .

[10]  A. Godhwani,et al.  A digital excitation control system for use on brushless excited synchronous generators , 1996 .

[11]  I-Lung Chien,et al.  Consider IMC Tuning to Improve Controller Performance , 1990 .

[12]  Yai Zhang,et al.  Updating learning rates for backpropagation network , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[13]  Yaonan Wang,et al.  Composite feedforward-feedback controller for generator excitation system , 2008 .