Novelty detection is the identification of abnormal system behaviour, in which a model of normality is constructed, with deviations from the model identified as “abnormal”. Complex high-integrity systems typically operate normally for the majority of their service lives, and so examples of abnormal data may be rare in comparison to the amount of available normal data. Given the complexity of such systems, the number of possible failure modes is large, many of which may not be characterised sufficiently to construct a. traditional multi-class classifier [22]. Thus, novelty detection is particularly suited to such cases, which allows previously-unseen or poorly-understood modes of failure to be correctly identified.
This chapter describes recent advances in the application of novelty detection techniques to the analysis of data from gas-turbine engines.Whole-engine vibration-based analysis will be illustrated, using data measured from casemounted sensors, followed by the application of similar techniques to the combustor component. In each case, the investigation described by this chapter shows how advances in prognostic condition monitoring are being made possible in a principled manner using novelty detection techniques.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Roberts S, Tarassenko L (1994) Neural Comput 6:270–284
Silverman BW (1986) Density estimation for statistics and data analysis. Chapman and Hall, London
Mayrose I, Friedman N, Pupko T (2005) A Gamma Mixture Model Better Accounts for Among Site Heterogeneity. Bioinformatics 21(2):151–158
Agusta Y, Dowe DL (2003) Unsupervised Learning of Gamma Mixture Models Using Minimum Message Length. Artificial intelligence and applications proceedings 403
Dempster AP, Laird NM, Rubin DB (1977) Maximum Likelihood from Incomplete Data via the EM Algorithm. J R Stat Soc Series B 39:1–38
Markou M, Singh S (2003) Novelty Detection: A Review. Signal Processing 83:2481–2497
Duda RO, Hart PE, Stork DG (2001) Pattern classification. Wiley, New York
Yeung DY, Ding Y (2002) Host-Based Intrusion Detection Using Dynamic and Static Behavioral Models. Pattern Recognit 36:229–243
Smyth P (1994) Markov Monitoring with Unknown States. IEEE J Sel Areas Commun 12(9):1600–1612
Quinn J, Williams CKI (2007) Known Unknowns: Novelty Detection in Condition Monitoring. Proceedings of 3rd Iberian conference on pattern recognition and image analysis, Lecture Notes in Computer Science, Springer
Markou M, Singh S (2006) A Neural Network-Based Novelty Detector for Image Sequence Analysis. IEEE Trans Pattern Anal Mach Intell 28(10):1664–1677
Ghahramani Z, Hinton GE (1998) Variational Learning for Switching State-Space Models. Neural Comput 12(4):963–996
McSharry PE, He T, Smith LA, Tarassenko L (2002) Linear and non-linear methods for automatic seizure detection in scalp electro-encephalogram recordings. Med Biol Eng Comput 40:447–461
Tax DMJ, Duin RPW (1998) Outlier detection using classifier instability. Advances in pattern recognition–the joint IAPR international workshops, Sydney, Australia, 593–601
Kohonen T (1982) Self-Organized Formation of Topologically Correct Feature Maps. Biol Cybern 43:59–69
Ypma A, Duin RPW (1998) Novelty Detection Using Self-Organising Maps. Prog Connect Based Inf Syst 2:1322–1325
Labib K, Vemuri R (2002) NSOM: A real-time network-based intrusion detection system using self-organizing maps. Networks security
Yin H, Allinson NM (2001) Self-organizing mixture networks for probability density estimation. IEEE Trans Neural Netw 12(2)
Vapnik V (2000) The nature of statistical learning theory. Second Edition. Springer, Berlin New York Heidelberg
Tax DMJ, Duin RPW (1999) Data Domain Description Using Support Vectors. Proceedings of ESAN99. Brussels:251–256
Scholkopf B, Williamson R, Smola AJ, Shawe-Taylor J, Platt J (2000) Support vector method for novelty detection. Advances in neural information processing systems 12, (NIPS99) Solla KMSA, Leen TK (eds.), MIT: 582–588
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, Oxford
Jennions IK (2006) Cross-platform challenges in engine health management. Proceesings of International Conference on Integrated Condition Monitoring, Anaheim, CA
Moya M, Hush D (1996) Neural Netw 9(3):463–474
Ritter G, Gallegos M (1997) Pattern Recogn Lett 18:525–539
Clifton DA, Bannister PR, Tarassenko L (2006) Learning shape for jet engine novelty detection. In: Wang J. et al. (eds.): Advances in neural networks III. Lecture Notes in Computer Science, Springer, Berlin Heidelberg New York, 3973:828–835
Sammon JW (1969) IEEE Trans Comput 18(5):401–409
DeRidder D, Duin RPW (1997) Pattern Recogn Lett
Lowe D, Tipping ME (1996) Neural Comput Appl 4:83–95
Tarassenko L (1998) A guide to neural computing applications. Arnold, UK
Nabney I (2002) Netlab: algorithms for pattern recognition. Springer, Berlin Heidelberg New York
Clifton DA, Bannister PR, Tarassenko L (2007) Visualisation of jet engine vibration characteristics for novelty detection. Proceedings of NCAF, London, UK
Nairac A, Townsend N, Carr R, King S, Cowley P, Tarassenko L (1999) Integr Comput-Aided Eng 6(1):53–65
Clifton DA, Bannister PR, Tarassenko L (2006) Application of an intuitive novelty metric for jet engine condition monitoring. In: Ali M, Dapoigny R (eds) Advances in applied artificial intelligence. Lecture Notes in Artificial Intelligence. Springer, Berlin Heidelberg New York 4031:1149–1158
Clifton DA, Bannister PR, Tarassenko L (2007) A framework for novelty detection in jet engine vibration data. In: Garibaldi L, Surace S, Holford K (eds) Key engineering materials 347:305–312
Clifton DA, Bannister PR, Tarassenko L (2007) Novelty detection in large-vehicle turbochargers. In: Okuno HG, Ali M (eds) New trends in applied artificial intelligence. Lecture Notes in Computer Science, Springer, Berlin Heidelberg New York, 4750
Hayton P, Scholkopf B, Tarassenko L, Anuzis P (2000) Support vector novelty detection applied to jet engine vibration spectra. Proceedings of Neural Information Processing Systems
Wang L, Yin H (2004) Wavelet analysis in novelty detection for combustion image data. Proceedings of 10th CACSC, Liverpool, UK
Clifton LA, Yin H, Zhang Y (2006) Support vector machine in novelty detection for multi-channel combustion data. Proceedings of 3rd International Symposium on Neural Networks
Nairac A, Corbett-Clark T, Ripley R, Townsend N, Tarassenko L (1997) Choosing an appropriate model for novelty detection. Proceedings of IEE 5th International Conference on Artificial Neural Networks
Tax D, Duin R (1999) Pattern Recogn Lett 20:1191–1199
Schölkopf B, Platt J, Shawe-Taylor J, Smola AJ, Williamson RC (2001) Neural Comput 13(7):1443–1471
Bishop CM (1994) Novelty detection and neural network validation. Proceedings of IEE Conference on Vision and Image Signal Processing
Zadrozny B, Elkan C (2002) Transforming classifier scores into accurate multiclass probability estimates. Pro. ACM SIGKDD 694–699
Roberts SJ (1999) Proc IEE 146(3)
Roberts SJ (2000) Proc IEE Sci Meas Technol 147(6)
Medova EA, Kriacou MN (2001) Extremes in operational risk management. Technical report, Centre for Financial Research, Cambridge, U.K.
Fisher RA, Tippett LHC (1928) Proc Camb Philos Soc 24
Coles S (2001) An introduction to statistical modelling of extreme values. Springer, Berlin Heidelberg New York
Embrechts P, Kluppelberg C, Mikosch T (1997) Modelling extremal events. Springer, Berlin Heidelberg New York
Rolls-Royce PLC (1996) The jet engine. Renault Printing, UK
Hayton P, Utete S, Tarassenko L (2003) QUOTE project technical report. University of Oxford, UK
Clifton DA (2005) Condition monitoring of gas-turbine engines. Transfer report. Department of Engineering Science, University of Oxford, UK
Bannister PR, Clifton DA, Tarassenko L (2007) Visualization of multi-channel sensor data from aero jet engines for condition monitoring and novelty detection. Proceedings of NCAF, Liverpool, UK
Khanna VK (2001) A study of the dynamics of laminar and turbulent fully and partially premixed flames. Virginia Polytechnic Institute and State University
Lieuwen TC (1999) Investigation of combustion instability mechanisms in premixed gas turbines. Georgia Institute of Technology
Ng WB, Syed KJ, Zhang Y (2005) Flame dynamics and structures in an industrial-scale gas turbine combustor. Experimental Thermal and Fluid Science 29:715–723
Daubechies I (1988) Orthonormal bases of compactly supported wavelets. Communications on Pure and Applied Mathematics 41:909–996
Mallat SG (1989) A theory for multiresolution signal decomposition. IEEE Trans. Pattern Analysis and Machine Intelligence 11(7):674–693
Guo H, Crossman JA, Murphey YL, Coleman M (2000) IEEE Trans Vehicular Technol 49(5):1650–1662
Clifton LA, Yin H, Clifton DA, Zhang Y (2007) Combined support vector novelty detection for multi-channel combustion data. Proceedings of IEEE ICNSC
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Clifton, D.A., Clifton, L.A., Bannister, P.R., Tarassenko, L. (2008). Automated Novelty Detection in Industrial Systems. In: Liu, Y., Sun, A., Loh, H.T., Lu, W.F., Lim, EP. (eds) Advances of Computational Intelligence in Industrial Systems. Studies in Computational Intelligence, vol 116. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-78297-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-540-78297-1_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-78296-4
Online ISBN: 978-3-540-78297-1
eBook Packages: EngineeringEngineering (R0)