An Investigation of the Negative Selection Algorithm for Fault Detection in Refrigeration Systems

Failure of refrigerated cabinets costs millions annually to supermarkets, and a large market exists for systems which can predict such failures. Previous work, now moving towards deployment, has used neural networks to predict volumes of alarms from refrigeration system controllers, and also to predict likely refrigerant gas loss. Here, we use in-cabinet temperature data, aiming to predict faults from the pattern of temperature over time. We argue that artificial immune systems (AIS) are particularly appropriate for this, and report a series of preliminary experiments which investigate parameter and strategy choices. We also investigate a ‘differential’ encoding scheme designed to highlight essential elements of in-cabinet temperature patterns. The results prove feasibility for AIS in this application, with good self-detection rates, and a promising fault-detection rate. The best configuration of those examined seems to be that which uses the novel differential encoding with r-bits matching.

[1]  Stephanie Forrest,et al.  A sense of self for Unix processes , 1996, Proceedings 1996 IEEE Symposium on Security and Privacy.

[2]  Teuvo Kohonen,et al.  Self-Organizing Maps, Second Edition , 1997, Springer Series in Information Sciences.

[3]  Dipankar Dasgupta,et al.  Tool Breakage Detection in Milling Operations using a Negative-Selection Algorithm , 1995 .

[4]  C. Janeway.  How the immune system recognizes invaders. , 1993, Scientific American.

[5]  Alan S. Perelson,et al.  Self-nonself discrimination in a computer , 1994, Proceedings of 1994 IEEE Computer Society Symposium on Research in Security and Privacy.

[6]  David Corne,et al.  Refrigerant Leak Prediction in Supermarkets using Evolved Neural Networks , 2002, SEAL.

[7]  D. Dasgupta,et al.  Immunity-based systems: a survey , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[8]  N. K. Jerne,et al.  The immune system. , 1973, Scientific American.

[9]  Dipankar Dasgupta,et al.  Novelty detection in time series data using ideas from immunology , 1996 .

[10]  Rogério de Lemos,et al.  Negative Selection: How to Generate Detectors , 2002 .

[11]  Jon Timmis,et al.  aiVIS - Artificial Immune Network Visualisation , 2001 .

[12]  Leandro Nunes de Castro,et al.  Artificial Immune Systems: A Novel Approach to Pattern Recognition , 2002 .

[13]  Jeffrey O. Kephart,et al.  A biologically inspired immune system for computers , 1994 .

[14]  David Corne,et al.  Predicting alarms in supermarket refrigeration systems using evolved neural networks and evolved rulesets , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).