Design of Networked Control Systems Based on Single-Neuron PID


Article Preview

With the development of control theory and communication technology, networked control systems have got more and more attention. The traditional PID controller is no longer suitable to meet performance requirements of time-delay control systems. And communication network is introduced into control systems that makes systems arise some problems, such as time delays, data dropout and so on. These problems affect the control performance badly. A model based on the single-neuron PID controller for networked control systems is proposed to improve the control performance. The design method for controller is based on neural network, traditional PID controller and Smith predictive control. The simulation results represent the model we proposed has better control performance.



Advanced Materials Research (Volumes 219-220)

Edited by:

Helen Zhang, Gang Shen and David Jin






Y. X. Jin et al., "Design of Networked Control Systems Based on Single-Neuron PID", Advanced Materials Research, Vols. 219-220, pp. 1101-1104, 2011

Online since:

March 2011




[1] NILSSON J., BERNHARDSSON B., WITTENMARK B.: Stochasticanalysis and control of real-time systems with random time delays, [J], Automatica, 1998, 34, (1), p.57–64.

DOI: 10.1016/s0005-1098(97)00170-2

[2] Hu, S.S., and Zhu, Q.X.: Stochastic optimal control and analysis of stability of networked control systems with long delay, [J], Automatica, 2003, 39, p.1877–1884.

DOI: 10.1016/s0005-1098(03)00196-1

[3] Liu, G.P., Mu, J.X., and Rees, D.: Networked predictive control of systems with random network transmission delay-a polynomial approach, [C]. Proc. IFAC World Congress, (2005).

DOI: 10.3182/20050703-6-cz-1902.00909

[4] Kim, D.K., Park, P.G., and Ko, J.W.: Output-feedback H1 control of systems over communication networks using a deterministic switching system approach, [J], Automatica, 2004, 40, p.1205–1212.

DOI: 10.1016/j.automatica.2004.01.024

In order to see related information, you need to Login.