Régulation directe par réseau neuronal appliquée aux systèmes de conditionnement d'air engendrant des économies d'énergie.

The direct neural control applied to energy-saving air conditioner systems.

Numéro : pap. C8-138

Auteurs : HSIEH C. H., CHEN Z. W., CHYR D. M., et al.

Résumé

An AC driver droved by an electrical inverter has been widely used to air conditioner systems for energy saving. But the AC driver will generate high heat dissipation and induce high operating temperature in low speed operation conditions. This will decrease the energy saving efficiency. The air conditioner compressors droved by a Brushless DC motor (BLDC motor) will improve the high heat generation problem in wide operation speed. The air conditioner with DC driver has better energy saving efficiency than that with a conventional AC driver. This study utilizes the direct neural control applied to an energy saving air conditioner system with DC driver. The proposed neural control system without reference model is based on the self-tuning control strategy, and the back propagation error is approximated by a linear combination of error and error’s differential, so that it is not necessary to built the neural emulator and estimate the Jacobian of plant. By this method, the convergent speed can be improved, and the speed performance of the BL motor with neural control system is better than that with a conventional PID control system. The simulation results reveal that the proposed control system is available to a DC air conditioner system with favor performance.

Documents disponibles

Format PDF

Pages : 6 p.

Disponible

  • Prix public

    20 €

  • Prix membre*

    15 €

* meilleur tarif applicable selon le type d'adhésion (voir le détail des avantages des adhésions individuelles et collectives)

Détails

  • Titre original : The direct neural control applied to energy-saving air conditioner systems.
  • Identifiant de la fiche : 30005389
  • Langues : Anglais
  • Source : ACRA2010. Asian conference on refrigeration and air conditioning: Tokyo, Japan, June 7-9, 2010.
  • Date d'édition : 07/06/2010

Liens


Voir d'autres communications du même compte rendu (107)
Voir le compte rendu de la conférence