A novel Artificial Immune System for fault behavior detection

Research highlights? Fault detection problem is addressed via the Natural Killer immune cells mechanisms. ? The Natural Killer immune cells mechanisms inspired an Artificial Immune System. ? The difference between normal and harmful activities generates an alarm scheme. ? The DAMADICS benchmark is used to compare the proposed methodology to other ones. This paper presents an error detection methodology to enable fault detection inspired on recent immune theory. The fault detection problem is a challenging problem due to processes increasing complexity and agility necessary to avoid malfunction or accidents. The key challenge is determining the difference between normal and potential harmful activities. A promising solution is emerging in the form of Artificial Immune System (AIS). In this article, Natural Killer (NK) immune cells mechanisms inspired an AIS. The AIS proposed uses recent biological mechanism such as: NK activation and education machinery. DAMADICS benchmark was applied to compare the proposed AIS performance to others fault detection algorithms. The results show that the novel approach developed provides better detection rate and false alarms tradeoff when compared to other methods in literature.

[1]  E. Tomasello,et al.  Natural killer cells: detectors of stress. , 2008, The international journal of biochemistry & cell biology.

[2]  R. Vance,et al.  Self-tolerance of natural killer cells , 2006, Nature Reviews Immunology.

[3]  van der,et al.  Proceedings of the 2012 winter simulation conference , 2001, WSC 2008.

[4]  Tommy W. S. Chow,et al.  Induction machine fault detection using clone selection programming , 2009, Expert Syst. Appl..

[5]  R. Vance,et al.  Regulation of the natural killer cell receptor repertoire. , 2001, Annual review of immunology.

[6]  Jun He,et al.  A hybrid artificial immune system and Self Organising Map for network intrusion detection , 2008, Inf. Sci..

[7]  Eric Vivier,et al.  Functions of natural killer cells , 2008, Nature Immunology.

[8]  Thomas Stützle,et al.  Design and analysis of stochastic local search for the multiobjective traveling salesman problem , 2009, Comput. Oper. Res..

[9]  Yi Zhi Zhao,et al.  A structured methodology for the development of anticipative event management systems with self-recovery capability , 2004, 30th Annual Conference of IEEE Industrial Electronics Society, 2004. IECON 2004.

[10]  Thomas Parisini,et al.  Model-free actuator fault detection using a spectral estimation approach: the case of the DAMADICS benchmark problem , 2003 .

[11]  R. Ulevitch,et al.  Triad3A, an E3 ubiquitin-protein ligase regulating Toll-like receptors , 2004, Nature Immunology.

[12]  Jack P. C. Kleijnen.  Design of experiments: overview , 2008, WSC 2008.

[13]  Leandro Nunes de Castro,et al.  Fundamentals of Natural Computing - Basic Concepts, Algorithms, and Applications , 2006, Chapman and Hall / CRC computer and information science series.

[14]  João Miguel da Costa Sousa,et al.  An architecture for fault detection and isolation based on fuzzy methods , 2009, Expert Syst. Appl..

[15]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[16]  Jian-Da Wu,et al.  An expert system for fault diagnosis in internal combustion engines using wavelet packet transform and neural network , 2009, Expert Syst. Appl..

[17]  B. Suarez-Alvarez,et al.  The NKG2D receptor: sensing stressed cells. , 2008, Trends in molecular medicine.

[18]  K. I. Ramachandran,et al.  Vibration-based fault diagnosis of spur bevel gear box using fuzzy technique , 2009, Expert Syst. Appl..

[19]  Xin Yao,et al.  Special Issue on "Nature Inspired Problem-Solving" , 2008, Inf. Sci..

[20]  Frederico G. Guimarães,et al.  Design of mixed H2/Hinfinity control systems using algorithms inspired by the immune system , 2007, Inf. Sci..

[21]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[22]  Lewis L Lanier,et al.  Up on the tightrope: natural killer cell activation and inhibition , 2008, Nature Immunology.

[23]  Fernando José Von Zuben,et al.  BAIS: A Bayesian Artificial Immune System for the effective handling of building blocks , 2009, Inf. Sci..

[24]  Zhou Ji,et al.  V-detector: An efficient negative selection algorithm with "probably adequate" detector coverage , 2009, Inf. Sci..