Abstract
Multivariate statistical process control (MSPC) can be applied for condition monitoring (CM) purposes. MSPC is implemented using a variety of techniques including neural networks (NNs). In situations when the number of process attributes is sufficiently large (e.g. 10 or more) concerns can arise with respect to training of NNs for pattern recognition. A classification method known as novelty detection (ND) can provide an effective alternative to conventional NN solutions that suffer from the above problem. Despite its great potential, ND is still unknown to the broad community of manufacturing engineers. This paper successfully demonstrates the ability of ND, using Gaussian mixture models, to notify operators of an end-milling process of the presence of faulty tool conditions. A significant achievement is that ND is used to identify abnormal time-series patterns as opposed to individual vectors of multiple simultaneous measurements related to abnormal conditions. Such patterns are found in windowed streams of signals related to 10 different process features (with an effective problem dimension of 140). The paper also investigates some of the issues related to implementation of ND for pattern recognition in condition monitoring .
Similar content being viewed by others
References
Grimmelius HT, Meiler PP, Mass HLMM, Bonnier B, Grevink JS, Kuilenburg RFV (1999) Three state-of-the-art methods for condition monitoring. IEEE Trans Ind Electron 46(2):407–416
Deming WE (1986) Out of the crisis. MIT Press, Cambridge, MA
Western Electric Company (1958) Statistical quality control handbook. Western Electric Company, New York
Zorriassatine F, Tannock JDT (1998) A review of neural networks for statistical process control. J Intell Manuf 9:209–224
Wierda SJ (1994) Multivariate statistical process control: recent results and directions for future research. Stat Neerlandica 48:147–168
Lowry CA, Montgomery DC (1995) A review of multivariate control charts. IIE Trans 27:800–810
Kourti T, MacGregor JF (1996) Multivariate SPC methods for process and product monitoring. J Qual Technol 28(4):409–428
Martin EB, Morris AJ, Kiparissides C (1999) Manufacturing performance enhancement through multivariate statistical process control. Annu Rev Control 23:35–44
Norvilas A, Negiz A, DeCicco J, Çinar A (2000) Intelligent process monitoring by interfacing knowledge-based systems and multivariate statistical monitoring. J Process Control 10:341–350
Wilson DJH, Irwin GW, Lightbody G (1997) Neural networks and multivariate SPC. Proceedings of the IEE/InstMC Colloquium on Fault diagnosis in Process Systems 97/174, London, April 1997, pp 15
Hotelling H (1947) Multivariate quality control – illustrated by the air testing of sample bombsights. In: Eisenhart C, Hastay MW, Wallis WA (eds) Techniques of statistical analysis. McGraw-Hill, New York, pp 11–184
Bakshi BR, Stephanopoulos G (1994) Representation of process trends III: multi-scale extraction of trends from process data. Comput Chem Eng 18:267–302
Cheung JT-Y, Stephanopoulos G (1990) Representation of process trends II: a formal representation framework. Comput Chem Eng 14:511–539
Cheung JT-Y, Stephanopoulos G (1990) Representation of process trends I: the problem of scale and qualitative scaling. Comput Chem Eng 14:511–539
Wong J, McDonald KA, Palazoglu A (1998) Classification of process trends based on fuzzified symbolic representation and hidden Markov models. J Process Control 8(5–6):395–408
Montgomery DC (1991) Design and analysis of experiments, 3rd edn. Wiley, New York
Taguchi G, Konishi S (1987) Taguchi methods, orthogonal arrays and linear graphs. American Supplier Institute, Dearborn, MI
Goldberg DE (1989) Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, Boston
Balazinski M, Czogala E, Jemielniak K, Leski J (2002) Tool condition monitoring using artificial intelligence methods. Eng Appl Artif Intell 15(1):73–80
Markou M, Singh S (2003) Novelty detection, a review part 1: statistical approaches. Signal Process 83:2481–2497
Markou M, Singh S (2003) Novelty detection, a review part 2: neural network based approaches. Signal Process 83:2499–2521
Taylor O, Addison D (2000) Novelty detection using neural network technology. Proceedings of COMADEM 2000, 13th International Congress on Condition Monitoring and Diagnostic Engineering Management, December 2000, Houston, TX, pp 731–743
Worden K, Manson G, Fieller NRJ (2000) Damage detection using outlier analysis. J Sound Vib 229(3):647–667
Worden K, Manson G, Allman D (2003) Experimental validation of a structural health monitoring methodology, part I: novelty detection on a laboratory structure. J Sound Vib 259(2):323–343
Worden K, Manson G, Allman D (2003) Experimental validation of a structural health monitoring methodology, part II: novelty detection on a Gnat aircraft. J Sound Vib 259(2):345–363
Zorriassatine F, O’Brien C, Tannock JDT (2003) Using novelty detection to identify abnormalities caused by mean shifts in bivariate processes. Comput Ind Eng 44(3):385–408
Bishop CM (1995) Neural networks for pattern recognition. Clarendon Press, Oxford
Parzen E (1962) On estimation of a probability density function and mode. Ann Math Stat 33:1065–1076
Travén HGC (1991) A neural network approach to statistical pattern classification by semiparametric estimation of probability density function. IEEE Trans Neural Netw 2:366–377
Martin EB, Morris AJ (1996) Non-parametric confidence bounds for process performance monitoring charts. J Process Control 6(6):349–358
Nabney I, Bishop C (1997) NETLAB Neural Network Software. Aston University, UK
Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via EM algorithm. J R Stat Soc B 39(1):1–38
Roberts S (1999) Novelty detection using extreme value statistics. IEE Proc Vis Image Signal Process 146(3):124–129
Hand D, Mannila H, Smyth P (2001) Principles of data mining. MIT Press, Cambridge, MA
Yeo SH, Khoo LP, Neo SS (2000) Tool condition monitoring using reflectance of chip surface and neural network. J Intell Manuf 11:507–514
Al-Habaibeh A, Zorriassatine F, Gindy N (2002) Comprehensive experimental evaluation of a systematic approach for cost effective and rapid design of condition monitoring systems using Taguchi’s method. J Mater Process Technol 124(3):372–383
Hagemann E (2003) Polyphase resampling part I: EETIMES Network. http://www.chipcenter.com/dsp/col001.html. Cited Dec 2003
MathWorks Incorporation (2001) MATLAB Signal Processing Toolbox. MathWorks Incorporation, Natick, MA
MacQueen JB (1967) Some methods for classification and analysis of multivariate observations. Proceedings of the 5th Berkeley Symposium on Mathematics and Statistical Probability 1, Berkeley, CA, 1967, pp 281–297
Bishop CM (1994) Novelty detection and neural network validation. IEE Proc Vis Image Signal Process 141(4):217–222
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zorriassatine, F., Al-Habaibeh, A., Parkin, R. et al. Novelty detection for practical pattern recognition in condition monitoring of multivariate processes: a case study. Int J Adv Manuf Technol 25, 954–963 (2005). https://doi.org/10.1007/s00170-004-2174-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-004-2174-8