Abstract
Accurate and rapid fault detection based on the data from industry process is very important for the process control. This paper introduces a new multivariate statistical process control approach for fault detection using kernel method based manifold learning algorithm combining T 2 statistic. The proposed approach is effective in the fault detection, which has two stages. Stage I: a kernel method based locally linear embedding is employed to extract the nonlinear features, preserve local structure and reduce dimensionality of the multivariate input data, and a new low-dimensional embedding method is developed to solve the ”out-of-sample” problem. Stage II: the fault detection is performed by T 2 statistic with control limits derived from the eigen-analysis of the kernel matrix in the Hilbert feature space. In this study, the method is applied for the fault detection of the benchmark Tennessee Eastman (TE) challenge process. The proposed method has been compared with conventional methods in terms of performances such as detection accuracy, detection delay and false alarm rate. It is demonstrated that the proposed method outperformed the others in fault detection on TE process.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Montgomery, D.C.: Introduction to Statistical Quality Control. John Wiley & Sons (2005)
Yang, K., Trewn, J.: Multivariate Statistical Methods in Quality Management. McGraw-Hill Professional (2004)
Chiang, L.H., Russell, E.L., Braatz, R.D.: Fault Detection and Diagnosis in Industrial Systems. Springer (2001)
Russell, E.L., Chiang, L.H., Braatz, R.D.: Fault detection in industrial processes using canonical variate analysis and dynamic principal component analysis. Chemometrics and Intelligent Laboratory Systems 51(1), 81–93 (2000)
Jia, F., Martin, E.B., Morris, A.J.: Nonlinear principal components analysis with application to process fault detection. Journal of Systems Science 31(5), 1473–1487 (2001)
Dong, D., McAvoy, T.J.: Nonlinear principal component analysis based on principal curves and neural networks. Computers and Chemical Engineering 20(1), 65–78 (1996)
Schölkpof, B., Smola, A., Müller, K.-R.: Nonlinear Component Analysis as a Kernel Eigenvalue Problem. Neural Computation 10(5), 1299–1319 (1998)
Mahadevan, S., Shah, S.L.: Fault detection and diagnosis in process data using one-class support vector machines. Journal of Process Control 19(10), 1627–1639 (2009)
Tenenbaum, J.B., Silva, V., Langford, J.C.: A Global Geometric Framework for Nonlinear Dimensionality Reduction. Science 290, 2319–2323 (2000)
Roweis, S.T., Saul, L.K.: Nonlinear Dimensionality Reduction by Locally Linear Embedding, vol. 290, pp. 2323–2326 (2000)
Belkin, M., Niyogi, P.: Laplacian Eigenmaps for Dimensionality Reduction and Data Representation. Neural Computation 15, 1373–1396 (2003)
Weinberger, K.Q., Saul, L.K.: An Introduction to Nonlinear Dimensionality Reduction by Maximum Variance Unfolding. In: Proceedings of the 27th National Conference on Artificial Intelligence, pp. 1683–1686. AAAI Press (2001)
Elgammal, A.M., Lee, C.S.: Separating style and content on a nonlinear manifold. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern, pp. 478–485. IEEE Press (2004)
Mekuz, N., Bauckhage, C., Tsotsos, J.K.: Face recognition with weighted locally linear embedding. In: Proceedings of The Second Canadian Conference on Computer and Robot Vision, pp. 290–296. IEEE Press (2005)
Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press (2004)
Choi, H., Choi, S.: Robust Kernel Isomap. Pattern Recognition 40(3), 853–862 (2007)
Yu, X., Wang, X., Liu, B.: Supervised kernel neighborhood preserving projections for radar target recognition. Signal Processing 88(9), 2335–2339 (2008)
Saul, L.K., Roweis, S.T.: Think globally, fit locally: unsupervised learning of low dimensional manifolds. The Journal of Machine Learning Research 4, 119–155 (2003)
Downs, J.J., Vogel, E.F.: A Plant-wide Industrial Process Control Problem. Computers & Chemical Engineering 17(3), 245–255 (1993)
Schölkopf, B., Platt, J., Shawe-Taylor, J., Smola, A., Williamson, R.: Estimating the support of a high-dimensional distribution. Nerual Computation 13(7), 1443–1471 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cheng, J., Guo, Yn. (2013). Kernel Based Manifold Learning for Complex Industry Fault Detection. In: Yin, H., et al. Intelligent Data Engineering and Automated Learning – IDEAL 2013. IDEAL 2013. Lecture Notes in Computer Science, vol 8206. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41278-3_48
Download citation
DOI: https://doi.org/10.1007/978-3-642-41278-3_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41277-6
Online ISBN: 978-3-642-41278-3
eBook Packages: Computer ScienceComputer Science (R0)