Share

IIR document

On-line training modelling and control using neural network, for pressure refrigeration systems.

Author(s) : TUMIALAN J. A. B., HERNANDEZ O. S. M., BANDARRA FILHO E. P., et al.

Summary

This work uses the neural network (NN) technique to model and control an experimental vapour compression refrigeration system set up, using two manipulated variables (compressor rotation and expansion valve electronically actuated). It used a dynamic perception multilayer NN, with the NN delayed, and a back propagation algorithm with sigmoid actuation fraction. To model the system and a neural prediction with correction, MISO type control. The paper describes training techniques used using single and simultaneous controlled variables inputs. The NN technique used shows good dynamic stability, short time actuation and easy to implement.

Available documents

Format PDF

Pages: ICR07-B2-946

Available

  • Public price

    20 €

  • Member price*

    Free

* Best rate depending on membership category (see the detailed benefits of individual and corporate memberships).

Details

  • Original title: On-line training modelling and control using neural network, for pressure refrigeration systems.
  • Record ID : 2008-0113
  • Languages: English
  • Source: ICR 2007. Refrigeration Creates the Future. Proceedings of the 22nd IIR International Congress of Refrigeration.
  • Publication date: 2007/07/21

Links


See other articles from the proceedings (839)
See the conference proceedings

Indexing