Spectral principal component analysis of dynamic process data

Abstract This article describes principal component analysis (PCA) of the power spectra of data from chemical processes. Spectral PCA can be applied to the measurements from a whole unit or plant because spectra are invariant to the phase lags caused by time delays and process dynamics. The same comment applies to PCA using autocovariance functions, which was also studied. Two case studies are presented. One was derived from simulation of a pulp process. The second was from a refinery involving 37 tags. In both cases, PCA clusters were observed which were characterised by distinct spectral features. Spectral PCA was compared with PCA using autocovariance functions. The performance was similar, and both offered an improvement over PCA using the time domain signals even when time shifting was used to align the phases.

[1]  J. E. Jackson,et al.  Control Procedures for Residuals Associated With Principal Component Analysis , 1979 .

[2]  P. Welch.  The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms , 1967 .

[3]  Tore Hägglund,et al.  A Control-Loop Performance Monitor , 1995 .

[4]  Brian Surgenor,et al.  Plant-Wide Feedback Control Performance Assessment using an Expert System Framework , 1995 .

[5]  Bhavik R. Bakshi,et al.  Representation of process trends—IV. Induction of real-time patterns from operating data for diagnosis and supervisory control , 1994 .

[6]  Svante Wold,et al.  Pattern recognition by means of disjoint principal components models , 1976, Pattern Recognit..

[7]  C. Posten,et al.  Supervision of bioprocesses using a dynamic time warping algorithm , 1996 .

[8]  A. Negiz,et al.  Statistical monitoring of multivariable dynamic processes with state-space models , 1997 .

[9]  Theodora Kourti,et al.  Multivariate SPC Methods for Process and Product Monitoring , 1996 .

[10]  Amir Wachs,et al.  Improved PCA methods for process disturbance and failure identification , 1999 .

[11]  G. D. Martin,et al.  Estimating control function benefits , 1991 .

[12]  Michael J. Piovoso,et al.  A multivariate statistical controller for on-line quality improvement , 1998 .

[13]  P. A. Taylor,et al.  Off-line diagnosis of deterministic faults in continuous dynamic multivariable processes using speech recognition methods , 1998 .

[14]  Michael J. Piovoso,et al.  PCA of Wavelet Transformed Process Data for Monitoring , 1997, Intell. Data Anal..

[15]  David M. Himmelblau,et al.  Sensor Fault Detection via Multiscale Analysis and Dynamic PCA , 1999 .

[16]  Catherine Porte,et al.  Automation and optimization of glycine synthesis , 1996 .

[17]  John F. MacGregor,et al.  Modeling of dynamic systems using latent variable and subspace methods , 2000 .

[18]  Barry M. Wise,et al.  The process chemometrics approach to process monitoring and fault detection , 1995 .

[19]  William H. Press,et al.  Numerical recipes , 1990 .

[20]  Ali Cinar,et al.  Monitoring of multivariable dynamic processes and sensor auditing , 1998 .

[21]  Tore Hägglund,et al.  Detection and Diagnosis of Oscillation in Control Loops , 1997 .

[22]  Bruce R. Kowalski,et al.  Detecting and Identifying Spectral Anomalies Using Wavelet Processing , 1998 .

[23]  J. Terrible,et al.  Consider using hydrogen plants to cogenerate power needs : Plant utilities , 1999 .

[24]  A. J. Morris,et al.  Monitoring the performance of the paper making process , 1999 .

[25]  Mary Beth Seasholtz,et al.  Making money with chemometrics , 1999 .

[26]  A. J. Collins,et al.  Introduction To Multivariate Analysis , 1981 .

[27]  Thomas E. Marlin,et al.  Multivariate statistical monitoring of process operating performance , 1991 .

[28]  B. Bakshi.  Multiscale PCA with application to multivariate statistical process monitoring , 1998 .

[29]  Barry Lennox,et al.  Fault detection in continuous processes using multivariate statistical methods , 2000, Int. J. Syst. Sci..

[30]  Raghunathan Rengaswamy,et al.  A syntactic pattern-recognition approach for process monitoring and fault diagnosis , 1995 .

[31]  Sirish L. Shah,et al.  Modeling and control of multivariable processes: Dynamic PLS approach , 1997 .

[32]  Kc Chow,et al.  Dynamic Principal Component Analysis Using Integral Transforms , 1998 .

[33]  M. Hoare,et al.  Near-infrared spectroscopy for bioprocess monitoring and control. , 1999, Biotechnology and bioengineering.

[34]  Nina F. Thornhill,et al.  Principal component analysis of spectra with application to acoustic emissions from mechanical equipment , 2002 .

[35]  Nina F. Thornhill,et al.  Detection of multiple oscillations in control loops , 2003 .

[36]  Peter A. Cook,et al.  Nonlinear dynamical systems , 1986 .

[37]  Christos Georgakis,et al.  Disturbance detection and isolation by dynamic principal component analysis , 1995 .

[38]  S. Qin,et al.  Selection of the Number of Principal Components: The Variance of the Reconstruction Error Criterion with a Comparison to Other Methods† , 1999 .

[39]  T. Harris.  Assessment of Control Loop Performance , 1989 .

[40]  Karl Johan Åström,et al.  Assessment of Achievable Performance of Simple Feedback Loops , 1988 .

[41]  Paul Geladi,et al.  Principal Component Analysis , 1987, Comprehensive Chemometrics.

[42]  Mark R. Riley,et al.  Simultaneous measurement of glucose and glutamine in insect cell culture media by near infrared spectroscopy. , 1997 .

[43]  Terje V. Karstang,et al.  Infrared spectroscopy and multivariate calibration used in quantitative analysis of additives in high-density polyethylene , 1992 .

[44]  A. J. Morris,et al.  Wavelets and non-linear principal components analysis for process monitoring , 1999 .