Abstract
Dynamic principal component analysis (DPCA) and its nonlinear extension, dynamic kernel principal component analysis (DKPCA), are widely used in the monitoring of dynamic multivariate processes. In traditional DPCA and DKPCA, extended vectors through concatenating current process data point and a certain number of previous process data points are utilized for feature extraction. The dynamic relations among different variables are fixed in the extended vectors, i.e. the adoption of the dynamic information is not adaptively learned from raw process data. Although DKPCA utilizes a kernel function to handle dynamic and (or) nonlinear information, the prefixed kernel function and the associated parameters cannot be most effective for characterizing the dynamic relations among different process variables. To address these problems, this paper proposes a novel nonlinear dynamic method, called dynamic neural orthogonal mapping (DNOM), which consists of data dynamic extension, a nonlinear feedforward neural network, and an orthogonal mapping matrix. Through backpropagation and Eigen decomposition (ED) technique, DNOM can be optimized to extract key low-dimensional features from original high-dimensional data. The advantages of DNOM are demonstrated by both theoretical analysis and extensive experimental results on the Tennessee Eastman (TE) benchmark process. The results on the TE benchmark process show the superiority of DNOM in terms of missed detection rate and false alarm rate. The source codes of DNOM can be found in https://github.com/htz-ecust/DNOM.
Similar content being viewed by others
Notes
For simplicity, assume that the mapped data need not be centered. In this case, DKPCA can be viewed as a Karhunen–Loeve (K–L) transformation in the feature space. Actually, all calculations can be reformulated to deal with centering [17].
This dynamic process is modified from a simple multivariate process in [21] to contain serial correlations.
the agitation speed was not included because it was not manipulated.
References
Qin SJ (2012) Survey on data-driven industrial process monitoring and diagnosis. Ann Rev Control 36(2):220
MacGregor J, Cinar A (2012) Monitoring, fault diagnosis, fault-tolerant control and optimization: data driven methods. Comput Chem Eng 47:111–120
Yin S, Ding SX, Haghani A, Hao H, Zhang P (2012) A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark tennessee eastman process. J Process Control 22(9):1567–1581
Ge ZQ, Song ZH, Gao F (2013) Review of recent research on data-based process monitoring. Ind Eng Chem Res 52(10):3543–3562
Feital T, Kruger U, Dutra J, Dutra JC, Lima EL (2013) Modeling and performance monitoring of multivariate multimodal processes. AIChE J 59(5):1557–1569
Liu Y, Liu B, Zhao X, Xie M (2018) A mixture of variational canonical correlation analysis for nonlinear and quality-relevant process monitoring. IEEE Trans Ind Electron 65(8):6478–6486
Askarian M, Escudero G, Graells M, Zarghami R, Jalali-Farahani F, Mostoufi N (2016) Fault diagnosis of chemical processes with incomplete observations: a comparative study. Comput Chem Eng 84:104–116
He Z, Wu J, Han N (2020) Flexible robust principal component analysis. Int J Mach Learn Cybern 11(3):603–613
Rato TJ, Blue J, Pinaton J, Reis MS (2017) Translation-invariant multiscale energy-based PCA for monitoring batch processes in semiconductor manufacturing. IEEE Trans Autom Sci Eng 14(2):894–904
Li G, Qin SJ, Zhou D (2014) A new method of dynamic latent-variable modeling for process monitoring. IEEE Trans Ind Electron 61(11):6438–6445
Ku W, Storer RH, Georgakis C (1995) Disturbance detection and isolation by dynamic principal component analysis. Chemom Intell Lab Syst 30(1):179–196. https://doi.org/10.1016/0169-7439(95)00076-3
Li W, Qin S (2001) Consistent dynamic PCA based on errors-in-variables subspace identification. J Process Control 11(6):661–678
Negiz A, Clinar A (1997) Statistical monitoring of multivariable dynamic processes with state-space models. AIChE J 43(8):2002–2020
Wen Q, Ge Z, Song Z (2012) Data-based linear gaussian state-space model for dynamic process monitoring. AIChE J 58(12):3763–3776
Choi SW, Lee I-B (2004) Nonlinear dynamic process monitoring based on dynamic kernel PCA. Chem Eng Sci 59(24):5897–5908
Vito ED, Umanità V, Villa S (2013) An extension of mercer theorem to matrix-valued measurable kernels. Appl Comput Harmonic Anal 34(3):339–351
Zhao H, Yuen PC, Kwok JT (2006) A novel incremental principal component analysis and its application for face recognition. IEEE Trans Syst Man Cybern Part B (Cybern) 36(4):873–886
Wanto A, Windarto AP, Hartama D, Parlina I (2017) Use of binary sigmoid function and linear identity in artificial neural networks for forecasting population density. Int J Inf Syst Technol 1(1):43–54
Li Y, Fu Y, Li H, Zhang S (2009) The improved training algorithm of back propagation neural network with self-adaptive learning rate. In: Proceedings of the international conference on computational intelligence and natural computin, vol 1. pp 73–76. https://doi.org/10.1109/CINC.2009.111
Kendall DG (1989) A survey of the statistical theory of shape. Stat Sci 4(2):87–99
Jiang X, Zhao H, Leung H (2017) Fault detection and diagnosis in chemical processes using sparse principal component selection. J Chem Eng Jpn 50:31–44
Samuel RT, Cao Y (2016) Nonlinear process fault detection and identification using kernel PCA and kernel density estimation. Syst Sci Control Eng 4(1):165–174
Chiang LH, Braatz RD, Russell EL (2001) Fault detection and diagnosis in industrial systems. Springer Science & Business Media, Berlin
Lyman P, Georgakis C (1995) Plant-wide control of the tennessee eastman problem. Comput Chem Eng 19(3):321–331
Soltanalian M, Stoica P (2012) Computational design of sequences with good correlation properties. IEEE Trans Signal Process 60(5):2180–2193
Hardle W, Simar L (2007) Applied multivariate statistical analysis. Prentice Hall, Upper Saddle River
Ten Berge JMF (1977) Orthogonal procrustes rotation for two or more matrices. Psychometrika 42(2):267–276
Acknowledgements
This research is sponsored by National Natural Science Foundation of China (61375007) and Basic Research Programs of Science and Technology Commission Foundation of Shanghai (15JC1400600).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Theorem 3
[27] Reduced Rank Procrustes Rotation. Let M and N be two matrices. Consider the constrained minimization problem
Suppose the singular value decomposition (SVD) of \(M^{T}N\) is \(PDQ^{T}\), then \({\hat{H}}=PQ^{T}\).
Rights and permissions
About this article
Cite this article
Hu, Z., Peng, J. & Zhao, H. Dynamic neural orthogonal mapping for fault detection. Int. J. Mach. Learn. & Cyber. 12, 1501–1516 (2021). https://doi.org/10.1007/s13042-020-01250-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-020-01250-z