Partager

Détection statistique des anomalies et méthode de diagnostic pour les refroidisseurs centrifuges fondées sur des tableaux de suivi des moyennes mobiles pondérées de façon exponentielle et sur la régression des vecteurs de support.

A statistical fault detection and diagnosis method for centrifugal chillers based on exponentially-weighted moving average control charts and support vector regression.

Auteurs : ZHAO Y., WANG S., XIAO F.

Type d'article : Article

Résumé

This paper presents a new fault detection and diagnosis (FDD) method for centrifugal chillers of building air-conditioning systems. Firstly, the Support Vector Regression (SVR) is adopted to develop the reference PI models. A new PI, namely the heat transfer efficiency of the sub-cooling section ( epsilon (sc)), is proposed to improve the FDD performance. Secondly, the Exponentially-Weighted Moving Average (EWMA) control charts are introduced to detect faults in a statistical way to improve the ratios of correctly detected points. Thirdly, when faults are detected, diagnosis follows which is based on a proposed FDD rule table. Six typical chiller component faults are concerned in this paper. This method is validated using the realtime experimental data from the ASHRAE RP-1043. Test results show that the combined use of SVR and EWMA can achieve the best performance. Results also show that significant improvements are achieved compared with a commonly used method using Multiple Linear Regression (MLR) and t-statistic.

Détails

  • Titre original : A statistical fault detection and diagnosis method for centrifugal chillers based on exponentially-weighted moving average control charts and support vector regression.
  • Identifiant de la fiche : 30006882
  • Langues : Anglais
  • Source : Applied Thermal Engineering - vol. 51 - n. 1-2
  • Date d'édition : 03/2013
  • DOI : http://dx.doi.org/10.1016/j.applthermaleng.2012.09.030

Liens


Voir d'autres articles du même numéro (26)
Voir la source

Indexation