Abstract
Latent variable (LV) models have been widely used in multivariate statistical process monitoring. However, whatever deviation from nominal operating condition is detected, an alarm is triggered based on classical monitoring methods. Consequently, they cannot distinguish real faults incurring dynamics anomalies from normal deviations in operating conditions. In this chapter, a new process monitoring strategy based on slow feature analysis (SFA) is proposed for the concurrent monitoring of operating point deviations and process dynamics anomalies. Slow features as LVs are developed to describe slowly varying dynamics, yielding improved physical interpretation. In addition to classical statistics for monitoring deviation from design conditions, two novel indices are proposed to detect anomalies in process dynamics through the slowness of LVs. The proposed approach can distinguish whether normal changes in operating conditions or real faults occur. Two case studies show the validity of the SFA-based process monitoring approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Available at http://web.mit.edu/braatzgroup/TE_process.zip.
References
MacGregor JF, Cinar A (2012) Monitoring, fault diagnosis, fault-tolerant control and optimization: data driven methods. Comput Chem Eng 47:111–120
Jackson JE (1980) Principal components and factor analysis: part I-principal components. J Qual Technol 12:201–213
Jackson JE, Mudholkar GS (1979) Control procedures for residuals associated with principal component analysis. Technometrics 21:341–349
Kano M, Tanaka S, Hasebe S et al (2003) Monitoring independent components for fault detection. AIChE J 49:969–976
Lee JM, Yoo C, Lee IB (2004) Statistical process monitoring with independent component analysis. J Process Control 14:467–485
Lee JM, Qin SJ, Lee IB (2006) Fault detection and diagnosis based on modified independent component analysis. AIChE J 52:3501–3514
Qin SJ, Zheng Y (2013) Quality-relevant and process-relevant fault monitoring with concurrent projection to latent structures. AIChE J 59:496–504
Ku W, Storer RH, Georgakis C (1995) Disturbance detection and isolation by dynamic principal component analysis. Chemometr Intell Lab Syst 30:179–196
Chen J, Liu KC (2002) On-line batch process monitoring using dynamic PCA and dynamic PLS models. Chem Eng Sci 57:63–75
Shang C, Huang X, Suykens JAK et al (2015) Enhancing dynamic soft sensors based on DPLS: a temporal smoothness regularization approach. J Process Control 28:17–26
Lee JM, Yoo C, Lee IB (2004) Statistical monitoring of dynamic processes based on dynamic independent component analysis. Chem Eng Sci 59:2995–3006
Negiz A, Cinar A (1997) PLS, balanced, and canonical variate realization techniques for identifying VARMA models in state space. Chemometr Intell Lab Syst 38:209–221
Dunia R, Qin SJ (1998) Subspace approach to multidimensional fault identification and reconstruction. AIChE J 44:1813–1831
Negiz A, Cinar A (1997) Statistical monitoring of multivariable dynamic processes with state-space models. AIChE J 43:2002–2020
Russell EL, Chiang LH, Braatz RD (2000) Fault detection in industrial processes using canonical variate analysis and dynamic principal component analysis. Chemometr Intell Lab Syst 51:81–93
Wiskott L, Sejnowski TJ (2002) Slow feature analysis: unsupervised learning of invariances. Neural Comput 14:715–770
Berkes P, Wiskott L (2005) Slow feature analysis yields a rich repertoire of complex cell properties. J Vis 5:9–9
Körding KP, Kayser C, Einhäuser W et al (2004) How are complex cell properties adapted to the statistics of natural stimuli? J Neurophysiol 91:206–212
Blaschke T, Zito T, Wiskott L (2007) Independent slow feature analysis and nonlinear blind source separation. Neural Comput 19:994–1021
Sprekeler H, Zito T, Wiskott L (2014) An extension of slow feature analysis for nonlinear blind source separation. J Mach Learn Res 15:921–947
Zhang Z, Tao D (2012) Slow feature analysis for human action recognition. IEEE Trans Pattern Anal Mach Intell 34:436–450
Wu C, Du B, Zhang L (2014) Slow feature analysis for change detection in multispectral imagery. IEEE Trans Geosci Remote Sens 52:2858–2874
Zhang L, Wu C, Du B (2014) Automatic radiometric normalization for multitemporal remote sensing imagery with iterative slow feature analysis. IEEE Trans Geosci Remote Sens 52:6141–6155
Casella G, Berger RL (2002) Statistical inference, vol 2. Duxbury, Pacific Grove
Golub GH, Van Loan CF (2012) Matrix computations, vol 3. JHU Press, Baltimore
Hyvärinen A, Oja E (2000) Independent component analysis: algorithms and applications. Neural Netw 13:411–430
Turner R, Sahani M (2007) A maximum-likelihood interpretation for slow feature analysis. Neural Comput 19:1022–1038
Blaschke T, Berkes P, Wiskott L What is the relation between slow feature analysis and independent component analysis? Neural Comput 18:2495–2508
Li G, Qin SJ, Ji Y et al (2010) Reconstruction based fault prognosis for continuous processes. Control Eng Pract 18:1211–1219
Yoon S, MacGregor JF (2001) Fault diagnosis with multivariate statistical models. Part I: using steady state fault signatures. J Process Control 11:387–400
Downs JJ, Vogel EF (1993) A plant-wide industrial process control problem. Comput Chem Eng 17:245–255
Chiang LH, Braatz RD, Russell EL (2001) Fault detection and diagnosis in industrial systems. Springer, New York
Yin S, Ding SX, Haghani A et al (2012) A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process. J Process Control 22:1567–1581
Lyman PR, Georgakis C (1995) Plant-wide control of the Tennessee Eastman problem. Comput Chem Eng 19:321–331
Shang C, Yang F, Gao X et al (2015) Concurrent monitoring of operating condition deviations and process dynamics anomalies with slow feature analysis. AIChE J 61:3666–3682
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix A: Proof of Theorem 2.1
In order to calculate the value of \(\varDelta (\cdot )\), we need to first normalize \(x_{ {j}}\) to unit variance:
Then the its value of \(\varDelta \) can be calculated as:
Notice that \(\varvec{\varOmega }=\text {diag}\left\{ \omega _1, \ldots , \omega _{m(d+1)} \right\} = \text {diag}\left\{ \varDelta (s_1), \ldots , \varDelta (s_{m(d+1)}) \right\} \). Therefore (2.48) can be further decomposed as:
where \(\alpha _i=r_{ji}^2 / \sum _i r_{ji}^2\) and \(\sum _i \alpha _i=1\). This completes the proof.
Appendix B: Proof of Theorem 2.2
If k satisfy \(\varDelta (s_k) > \varDelta (x_{ {j}})\), then we have:
This completes the proof.
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Shang, C. (2018). Monitoring of Operating Condition and Process Dynamics with Slow Feature Analysis. In: Dynamic Modeling of Complex Industrial Processes: Data-driven Methods and Application Research. Springer Theses. Springer, Singapore. https://doi.org/10.1007/978-981-10-6677-1_2
Download citation
DOI: https://doi.org/10.1007/978-981-10-6677-1_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-6676-4
Online ISBN: 978-981-10-6677-1
eBook Packages: EngineeringEngineering (R0)