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.
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.
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.
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.
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.
EMSD (2015). Hong Kong Energy End-use Data. Hong Kong Electrical & Mechanical Services Department.
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.
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.
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.
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.
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.
IEA (2018). The Future of Cooling. International Energy Agency. IEA (2019). The Future of Cooling in China, International Energy Agency.
Jackett CJ, Turner PJ, Lovell JL, Williams RN (2011). Deconvolution of MODIS imagery using multiscale maximum entropy. Remote Sensing Letters, 2: 179–187.
Jenssen R (2010). Kernel entropy component analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32: 847–860.
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.
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.
Jolliffe I (1986). Principal Component Analysis. New York: Springer.
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.
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.
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.
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.
MacGregor JF, Kourti T (1995). Statistical process control of multivariate processes. Control Engineering Practice, 3: 403–414.
Parzen E (1962). On estimation of a probability density function and mode. The Annals of Mathematical Statistics, 33: 1065–1076.
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.
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.
Shekar BH, Sharmila Kumari M, Mestetskiy LM, Dyshkant NF (2011). Face recognition using kernel entropy component analysis. Neurocomputing, 74: 1053–1057.
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.
Silverman BW (1986). Density Estimation for Statistics and Data Analysis. Boca Raton, FL, USA: Chapman & Hall/CRC.
Wang S, Xiao F (2004). Detection and diagnosis of AHU sensor faults using principal component analysis method. Energy Conversion and Management, 45: 2667–2686.
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.
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.
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.
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.
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.
Acknowledgements
The financial supports for the Natural Science Foundation of Zhejiang Province (Project No. LQ19E060007) are gratefully acknowledged.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
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
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12273-019-0598-1