Skip to main content
SpringerLink
Log in

Fault detection for centrifugal chillers using a Kernel Entropy Component Analysis (KECA) method

  • Research Article
  • Published:
Building Simulation Aims and scope Submit manuscript

Abstract

Fault detection is beneficial for chiller routine operation management in building automation systems. Considering the limitations of traditional principal component analysis (PCA) algorithm for chiller fault detection, a so-called kernel entropy component analysis (KECA) method has been developed and the development results are reported in this paper. Unlike traditional PCA, in KECA, the feature extraction or dimensionality reduction is implemented in a new space, called kernel feature space. The new space is nonlinearly related to the input space. The data set in the kernel feature space is projected onto a principal component subspace constructed by the feature space principal axes determined by the maximum Rényi entropy rather than the top eigenvalues. The proposed KECA is more suitable to deal with nonlinear process without Gaussian assumption. Using the available experimental data from ASHRAE RP-1043, seven typical chiller faults were tested by the proposed KECA method, and the results were compared to that of PCA. Two statistics, i.e. T2 and squared prediction error (SPE), were employed for fault detection monitoring. The fault detection results showed that the proposed KECA method had a better performance in terms of a higher detection accuracy in comparison to the traditional PCA. For the seven typical faults, the fault detection ratios were over 55%, even at their corresponding least severity level when using the proposed KECA based chiller fault detection method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Abbreviations

H :

Rényi quadratic entropy (bit)

p(·):

probability density function

V̂(p):

Rényi entropy estimate

φ(·):

kernel function

τss :

time window length (s)

Δt :

time interval (s)

δ2 :

confidence limit

D :

diagonal matrix storing the eigenvalues

E :

eigenvector matrix

I :

vector of ones

K :

kernel matrix

x :

vectors of variables

A/C:

air conditioning

CPV:

cumulative percent variance (%)

FDD:

fault detection and diagnosis

FDR:

fault detection ratio (%)

FAR:

false alarm ratio (%)

IAQ:

indoor air quality

KECA:

kernel entropy component analysis

PC:

principal component

PCA:

principal component analysis

SPE:

squared prediction error

SL:

severity level

RBF:

radial basis function

References

  • Ahmad MW, Mourshed M, Yuce B, Rezgui Y (2016). Computational intelligence techniques for HVAC systems: A review. Building Simulation, 9: 359–398.

    Article  Google Scholar 

  • Comstock MC, Braun JE, Bernhard R (1999). Development of analysis tools for the evaluation of fault detection and diagnostics in chillers. HL 99-20. Report #4036-3. Purdue University.

    Google Scholar 

  • Du Z, Jin X (2008). Multiple faults diagnosis for sensors in air handling unit using Fisher discriminant analysis. Energy Conversion and Management, 49: 3654–3665.

    Article  Google Scholar 

  • Du Z, Jin X, Wu L (2007). Fault detection and diagnosis based on improved PCA with JAA method in VAV systems. Building and Environment, 42: 3221–3232.

    Article  Google Scholar 

  • EMSD (2015). Hong Kong Energy End-use Data. Hong Kong Electrical & Mechanical Services Department.

    Google Scholar 

  • Fan C, Sun Y, Shan K, Xiao F, Wang J (2018). Discovering gradual patterns in building operations for improving building energy efficiency. Applied Energy, 224: 116–123.

    Article  Google Scholar 

  • Glass AS, Gruber P, Roos M, Todtli J (1995). Qualitative model-based fault detection in air-handling units. IEEE Control Systems Magazine, 15(4): 11-22.

    Google Scholar 

  • Gomez-Chova L, Jenssen R, Camps-Vails G (2011). Kernel Entropy component analysis in remote sensing data clustering. In: Proceedings of IEEE International Geoscience and Remote Sensing Symposium Vancouver, Canada.

    Google Scholar 

  • Gomez-Chova L, Jenssen R, Camps-Vails G (2012). Kernel entropy component analysis for remote sensing image clustering. IEEE Geoscience and Remote Sensing Letters, 9: 312–316.

    Article  Google Scholar 

  • Han H, Cao Z, Gu B, Ren N (2010). PCA-SVM-based automated fault detection and diagnosis (AFDD) for vapor-compression refrigeration systems. HVAC&R Research, 16: 295–313.

    Article  Google Scholar 

  • IEA (2018). The Future of Cooling. International Energy Agency. IEA (2019). The Future of Cooling in China, International Energy Agency.

    Google Scholar 

  • Jackett CJ, Turner PJ, Lovell JL, Williams RN (2011). Deconvolution of MODIS imagery using multiscale maximum entropy. Remote Sensing Letters, 2: 179–187.

    Article  Google Scholar 

  • Jenssen R (2010). Kernel entropy component analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32: 847–860.

    Article  Google Scholar 

  • Jenssen R, Eltoft T, Girolami M, Erdogmus D (2006). Kernel maximum entropy data transformation and an enhanced spectral clustering algorithm. In: Schölkopf B, Platt J, Hofmann T, Advances in Neural Information Processing Systems 19: Proceedings of the 2006 Conference. Cambridge, MA, USA: MIT Press.

    Google Scholar 

  • Jiang Q, Yan X, Lv Z, Guo M (2013). Fault detection in nonlinear chemical processes based on kernel entropy component analysis and angular structure. Korean Journal of Chemical Engineering, 30: 1181–1186.

    Article  Google Scholar 

  • Jolliffe I (1986). Principal Component Analysis. New York: Springer.

    Book  MATH  Google Scholar 

  • Katipamula S, Brambley MR (2005a). Methods for fault detection, diagnostics, and prognostics for building systems—A review, part I. HVAC&R Research, 11: 3–25.

    Article  Google Scholar 

  • Katipamula S, Brambley MR (2005b). Review article: methods for fault detection, diagnostics, and prognostics for building systems—A review, part II. HVAC&R Research, 11: 169–187.

    Article  Google Scholar 

  • Li S, Wen J (2014). A model-based fault detection and diagnostic methodology based on PCA method and wavelet transform. Energy and Buildings, 68: 63–71.

    Article  Google Scholar 

  • Li G, Hu Y, Chen H, Shen L, Li H, Hu M, Liu J, Sun K (2016). An improved fault detection method for incipient centrifugal chiller faults using the PCA-R-SVDD algorithm. Energy and Buildings, 116: 104–113.

    Article  Google Scholar 

  • MacGregor JF, Kourti T (1995). Statistical process control of multivariate processes. Control Engineering Practice, 3: 403–414.

    Article  Google Scholar 

  • Parzen E (1962). On estimation of a probability density function and mode. The Annals of Mathematical Statistics, 33: 1065–1076.

    Article  MathSciNet  MATH  Google Scholar 

  • Rényi A (1961). On measures of entropy and information. In: Proceedings of the 4th Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Contributions to the Theory of Statistics.

    Google Scholar 

  • Ruan X, Wang S (2017). Face recognition based on weighted multi-resolution kernel entropy component analysis. In: Proceedings of the Chinese Control and Decision Conference (CCDC), Chongqing, China.

    Google Scholar 

  • Shekar BH, Sharmila Kumari M, Mestetskiy LM, Dyshkant NF (2011). Face recognition using kernel entropy component analysis. Neurocomputing, 74: 1053–1057.

    Article  Google Scholar 

  • Sheng J, Dong S, Liu Z, Gao H (2016). Fault feature extraction method based on local mean decomposition Shannon entropy and improved kernel principal component analysis model. Advances in Mechanical Engineering, 8: https://doi.org/10.1177/1687814016661087.

    Article  Google Scholar 

  • Silverman BW (1986). Density Estimation for Statistics and Data Analysis. Boca Raton, FL, USA: Chapman & Hall/CRC.

    Book  MATH  Google Scholar 

  • Wang S, Xiao F (2004). Detection and diagnosis of AHU sensor faults using principal component analysis method. Energy Conversion and Management, 45: 2667–2686.

    Article  Google Scholar 

  • Wang Z, Wang L, Liang K, Tan Y (2018). Enhanced chiller fault detection using Bayesian network and principal component analysis. Applied Thermal Engineering, 141: 898–905.

    Article  Google Scholar 

  • Yuan Z, He Y, Yuan L, Cheng Z (2017). A diagnostics method for analog circuits based on improved kernel entropy component analysis. Journal of Electronic Testing, 33: 697–707.

    Article  Google Scholar 

  • Zhao Y, Wang S, Xiao F (2013). Pattern recognition-based chillers fault detection method using Support Vector Data Description (SVDD). Applied Energy, 112: 1041–1048.

    Article  Google Scholar 

  • Zhao Y, Li T, Thang X, Thang C (2019). Artificial intelligence-based fault detection and diagnosis methods for building energy systems: Advantages, challenges and the future. Renewable and Sustainable Energy Reviews, 109: 85–101.

    Article  Google Scholar 

  • Zhou H, Shi T, Liao G, Xuan J, Su L, He Z, Lai W (2017). Using supervised kernel entropy component analysis for fault diagnosis of rolling bearings. Journal of Vibration and Control, 23: 2167–2178.

    Article  Google Scholar 

Download references

Acknowledgements

The financial supports for the Natural Science Foundation of Zhejiang Province (Project No. LQ19E060007) are gratefully acknowledged.

Author information

Authors and Affiliations

  1. School of Automation (School of Artificial Intelligence), Hangzhou Dianzi University, Hangzhou, China

    Yudong Xia, Qiang Ding & Aipeng Jiang

  2. Institute of Refrigeration and Cryogenics, Zhejiang University, Hangzhou, China

    Yudong Xia

  3. School of Environment & Architecture, University of Shanghai for Science & Technology, Shanghai, China

    Zhao Li

Authors
  1. Yudong Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qiang Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Aipeng Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qiang Ding.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xia, Y., Ding, Q., Li, Z. et al. Fault detection for centrifugal chillers using a Kernel Entropy Component Analysis (KECA) method. Build. Simul. 14, 53–61 (2021). https://doi.org/10.1007/s12273-019-0598-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12273-019-0598-1

Keywords

Search

Navigation