Neuro-PID controller design for Networked Control Systems with non-linearity and random delays using Fisher information

Authors:
J. H. Zhang;H. Wang
Affiliations:
Beijing Key Laboratory of Industrial Process Measurement and Control New Technology and System, North China Electric Power University, Beijing, 102206, PR China.;Northeastern University, Shenyang, PR China/ Control Systems Centre, School of Electrical Engineering and Electronics, The University of Manchester, P.O. Box 88, Manchester, M60 1QD, UK
Venue:
International Journal of Systems, Control and Communications
Year:
2010

Citing 8
Cited 2

An observer-based compensator for distributed delays

Automatica (Journal of IFAC)
Stochastic analysis and control of real-time systems with random time delays

Automatica (Journal of IFAC)
Bounded Dynamic Stochastic Systems: Modelling and Control

Bounded Dynamic Stochastic Systems: Modelling and Control
An error-entropy minimization algorithm for supervised training ofnonlinear adaptive systems

IEEE Transactions on Signal Processing
PID controller design for output PDFs of stochastic systems using linear matrix inequalities

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Brief Stochastic optimal control and analysis of stability of networked control systems with long delay

Automatica (Journal of IFAC)
Technical Communique: Generalized discrete-time PI control of output PDFs using square root B-spline expansion

Automatica (Journal of IFAC)
Generalized information potential criterion for adaptive system training

IEEE Transactions on Neural Networks

On the effects of time delay variations in the design of networked control system

International Journal of Systems, Control and Communications
PI-PD controller for stable and unstable processes

International Journal of Systems, Control and Communications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a novel controller is proposed for Networked Control Systems (NCSs) with random delays and non-linearity using BP neural networks and Fisher information. The controller is designed by minimising the Fisher information of tracking error. The Fisher information is calculated based on estimated Probability Density Function (PDF) via the Parzen windowing technique. The convergent condition of the proposed control algorithm is given. A simulation example is given to show the effectiveness of the proposed algorithm.