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

Research output: Journal article publicationJournal articleAcademic researchpeer-review

86 Citations (Scopus)


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 (εsc), 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 real-time 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.
Original languageEnglish
Pages (from-to)560-572
Number of pages13
JournalApplied Thermal Engineering
Issue number1-2
Publication statusPublished - 1 Jan 2013


  • Centrifugal chiller
  • EWMA control chart
  • Fault detection
  • Fault diagnosis
  • Support vector regression

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Industrial and Manufacturing Engineering

Cite this