Competitive Decentralized Autonomous Neural Net Controllers

  • Takehiro Ohba
  • Masaru Ishida
Conference paper


A simple and effective method is proposed for controlling a system consists of small processes. Each process is controlled by a decentralized autonomous neural network controller. These controllers compete with each other in order to increase their performances. As a result of the competition, the performance of whole system is kept at a suboptimal level. A control of example system consist of lots of processes is performed.


Performance Index Control Result Preference Factor Small Process Model Reference Adaptive Control 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Lin Shi and Sunil K. Singh (2003) Decentralized adaptive controller design for large scale systems with higher order interconnections. IEEE Trans. Autom. Contr. 37:1106–1118MathSciNetCrossRefGoogle Scholar
  2. [2]
    Wen Changyun and Y. C. Soh (1999) Decentralized Model Reference Adaptive Control Without Restriction on Subsystem Relative Degrees. IEEE Trans. Autom. Contr. 44: 1464–1469MathSciNetCrossRefGoogle Scholar
  3. [3]
    Jain Sandeep and F. Khorrami (1997) Decentralized adaptive output feedback design for large-scale nonlinear systems. IEEE Trans. Autom. Contr. 42:729–735CrossRefGoogle Scholar
  4. [4]
    Chen, Chyi-Tsong and Yen Jia-Hwang (1998) Multivariable process control using decentralized single neural controllers. J. of Chem. Eng. of Japan 31:14–20CrossRefGoogle Scholar
  5. [5]
    Nardi, F., Hovakimyan, N. and Calise A J. (2001) Decentralized control of large-scale systems using single Hidden layer neural networks. Proceedings of the American Control Conference 4:3122–3127Google Scholar
  6. [6]
    Lewin D.R. and A. Parag (2003) A constrained genetic algorithm for decentralized control system structure selection and optimization. Automatica 39:1801–1807MathSciNetCrossRefGoogle Scholar
  7. [7]
    Ohba, T. and M. Ishida (1998) Application of a Neural Network to Evaluation of Interactions in a MIMO Process. A.I.Ch.E. Journal 44:2018–2024Google Scholar

Copyright information

© Springer-Verlag/Wien 2005

Authors and Affiliations

  • Takehiro Ohba
    • 1
  • Masaru Ishida
    • 1
  1. 1.Chemical Resources LaboratoryTokyo Institute of TechnologyYokohamaJapan

Personalised recommendations