Performance Monitoring of the Refrigeration System with Minimum Set of Sensors

This paper describes a methodology for remote performance monitoring of retail refrigeration systems. The proposed framework starts with monitoring of the whole refrigeration circuit which allows detecting deviations from expected behavior caused by various faults and degradations. The subsequent diagnostics methods drill down deeper in the equipment hierarchy to more specifically determine root causes. An important feature of the proposed concept is that it does not require any additional sensors, and thus, the performance monitoring solution can be deployed at a low installation cost. Moreover only a minimum of contextual information is required, which also substantially reduces time and cost of the deployment process.

Authors:

• Radek Fisera
• Petr Stluka

Keywords:

• Condition monitoring
• energy baselining
• fault detection and diagnostics
• commercial refrigeration.

References:

[1] EPA, Supermarket Energy Use Profile, Environmental Protection
Agency, 2007.
[2] Dan W. Taylor, David W. Corne, David L. Taylor, and Jack Harkness,
Predicting Alarms in Supermarket Refrigeration Systems Using Evolved
Neural Networks and Evolved Rulesets, In the Proceedings of the World
Congress on Computational Intelligence (WCCI-2002), IEEE Press,
Honolulu, Hawaii, , 2002, pp. 1988-1993.
[3] Dan W. Taylor and David W. Corne, Refrigerant Leak Prediction in
Supermarkets Using Evolved Neural Networks, In the Proceedings of
the 4th Asia Pacific Conference on Simulated Evolution and Learning
(SEAL), Singapore, 2002.
[4] Abtar Singh, Paul Wickberg, Thomas J Mathews, and Neal Starling,
System for remote refrigeration monitoring and diagnostics, US Patent
7644591, 2010.
[5] William S. Cleveland, Robust Locally Weighted Regression and
Smoothing Scatterplots, Journal of the American Statistical Association,
vol. 74, pp. 829-836, 1979.
[6] William S. Cleveland and Susan J. Devlin, Locally Weighted
Regression: An Approach to Regression Analysis by Local Fitting,
Journal of the American Statistical Association, vol. 83, pp. 596-610,
1988.
[7] Trevor Hastie, Robert Tibshirani, and Jerome Friedman, The Elements
of Statistical Learning, Second Edition: Data Mining, Inference, and
Prediction, 2nd ed.: Springer, 2009.
[8] K. Marik, Z. Schindler, and P. Stluka, Decision support tools for
advanced energy management, Energy, vol. 33, pp. 858-873, 2008.
[9] Clive R. Loader, Bandwidth selection: classical or plug-in?, The Annals
of Statistics, vol. 27, pp. 415-438, 1999.
[10] Geoffrey S. Watson, Smooth regression analysis, Sankhya: The Indian
Journal of Statistic, vol. 26, pp. 359-372, 1964.
[11] E. A. Nadaraya, On estimating regression, Theory of Probability and its
Applications, vol. 9, pp. 141-142, 1964.
[12] J. Kukal, K. Macek, J. Rojicek, and J. Trojanova, From Symptoms to
Faults: Temporal Reasoning Methods, In the Proc. 2009 Int. Conference
on Adaptive and Intelligent Systems, Klagenfurt, Austria, 2009.
[13] Danfoss. (2009) Why Compressors Fail - Liquid Slugging. [Online].
http://www.ra.danfoss.com/TechnicalInfo/Approvals/Files/RAPIDFiles/
17/Article/LiquidSlugging/Why Compressors Fail Part 3-web.pdf.
[14] Dan W Taylor and David W Corne, An Investigation of the Negative
Selection Algorithm for Fault Detection in Refrigeration Systems, In the
Proceeding of Second International Conference on Artificial Immune
Systems (ICARIS), Edinburgh, UK, 2003, pp. 34-45.
[15] D. Ruppert and M.P.Wand, Multivariate Locally Weighted Least Square
Regression, The Annals of Statistics, vol. 22, pp. 1346-1370, 1994.