Fault Detection via Occupation Kernel Principal Component Analysis

Morrison, Zachary; Russo, Benjamin P.; Lian, Yingzhao; Kamalapurkar, Rushikesh

doi:10.1109/lcsys.2023.3287568

Fault Detection via Occupation Kernel Principal Component Analysis

Journal Article · Tue Jun 20 00:00:00 EDT 2023 · IEEE Control Systems Letters

DOI:https://doi.org/10.1109/lcsys.2023.3287568· OSTI ID:2000314

^[1]; ^[2]; ^[3]; ^[1]

Oklahoma State Univ., Stillwater, OK (United States)
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)

Reliable operation of automatic systems is heavily dependent on the ability to detect faults in the underlying dynamics. While traditional model-based methods have been widely used for fault detection, data-driven approaches have garnered increasing attention due to their ease of deployment and minimal need for expert knowledge. In this letter, we present a novel principal component analysis (PCA) method that uses occupation kernels. Occupation kernels result in feature maps that are tailored to the measured data, have inherent noise-robustness due to the use of integration, and can utilize irregularly sampled system trajectories of variable lengths for PCA. The occupation kernel PCA method is used to develop a reconstruction error approach to fault detection and its efficacy is validated using numerical simulations.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE Office of Science (SC)

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 2000314

Journal Information:: IEEE Control Systems Letters, Journal Name: IEEE Control Systems Letters Journal Issue: 7 Vol. 7; ISSN 2475-1456

Publisher:: IEEECopyright Statement

Country of Publication:: United States

Language:: English

References (15)

Analytical and knowledge-based redundancy for fault diagnosis in process plants Fathi, Zohreh; Ramirez, W. Fred; Korbicz, Jozef AIChE Journal, Vol. 39, Issue 1 https://doi.org/10.1002/aic.690390107	journal	January 1993
Observer-based fault detection and isolation: Robustness and applications Patton, R. J.; Chen, J. Control Engineering Practice, Vol. 5, Issue 5 https://doi.org/10.1016/S0967-0661(97)00049-X	journal	May 1997
Gear-box fault detection using time-frequency based methods Odgaard, Peter Fogh; Stoustrup, Jakob Annual Reviews in Control, Vol. 40 https://doi.org/10.1016/j.arcontrol.2015.09.004	journal	January 2015
Fault detection and identification of nonlinear processes based on kernel PCA Choi, Sang Wook; Lee, Changkyu; Lee, Jong-Min Chemometrics and Intelligent Laboratory Systems, Vol. 75, Issue 1 https://doi.org/10.1016/j.chemolab.2004.05.001	journal	January 2005
Fault detection of batch processes based on multivariate functional kernel principal component analysis Wang, Huangang; Yao, Ma Chemometrics and Intelligent Laboratory Systems, Vol. 149 https://doi.org/10.1016/j.chemolab.2015.09.018	journal	December 2015
Comparison of advanced set-based fault detection methods with classical data-driven and observer-based methods for uncertain nonlinear processes Mu, Bowen; Yang, Xuejiao; Scott, Joseph K. Computers & Chemical Engineering, Vol. 166 https://doi.org/10.1016/j.compchemeng.2022.107975	journal	October 2022
Fault detection based on Kernel Principal Component Analysis Nguyen, Viet Ha; Golinval, Jean-Claude Engineering Structures, Vol. 32, Issue 11 https://doi.org/10.1016/j.engstruct.2010.08.012	journal	November 2010
Kernel PCA-based GLRT for nonlinear fault detection of chemical processes Mansouri, Majdi; Nounou, Mohamed; Nounou, Hazem Journal of Loss Prevention in the Process Industries, Vol. 40 https://doi.org/10.1016/j.jlp.2016.01.011	journal	March 2016
Kernel PCA for novelty detection Hoffmann, Heiko Pattern Recognition, Vol. 40, Issue 3 https://doi.org/10.1016/j.patcog.2006.07.009	journal	March 2007
Multiple Sclerosis Detection Based on Biorthogonal Wavelet Transform, RBF Kernel Principal Component Analysis, and Logistic Regression Wang, Shui-Hua; Zhan, Tian-Ming; Chen, Yi IEEE Access, Vol. 4 https://doi.org/10.1109/ACCESS.2016.2620996	journal	January 2016
Occupation Kernels and Densely Defined Liouville Operators for System Identification Rosenfeld, Joel A.; Kamalapurkar, Rushikesh; Russo, Benjamin 2019 IEEE 58th Conference on Decision and Control (CDC) https://doi.org/10.1109/CDC40024.2019.9029337	conference	December 2019
Detecting Anomaly in Chemical Sensors via L1-Kernel-Based Principal Component Analysis Pan, Hongyi; Badawi, Diaa; Bassi, Ishaan IEEE Sensors Letters, Vol. 6, Issue 10 https://doi.org/10.1109/LSENS.2022.3209102	journal	October 2022
Trajectory-Based Anomalous Event Detection Piciarelli, C.; Micheloni, C.; Foresti, G. L. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 18, Issue 11 https://doi.org/10.1109/TCSVT.2008.2005599	journal	November 2008
Nonlinear Component Analysis as a Kernel Eigenvalue Problem Schölkopf, Bernhard; Smola, Alexander; Müller, Klaus-Robert Neural Computation, Vol. 10, Issue 5 https://doi.org/10.1162/089976698300017467	journal	July 1998
Data-driven Fault Detection and Diagnosis for Complex Industrial Processes Qin, S. Joe IFAC Proceedings Volumes, Vol. 42, Issue 8 https://doi.org/10.3182/20090630-4-ES-2003.00184	journal	January 2009

Similar Records

Motion tomography via occupation kernels

Journal Article · Fri Dec 31 23:00:00 EST 2021 · Journal of Computational Dynamics · OSTI ID:1842593

Incipient Fault Detection and Isolation of Field Devices in Nuclear Power Systems Using Principal Component Analysis

Journal Article · Wed Nov 14 23:00:00 EST 2001 · Nuclear Technology · OSTI ID:20826709

Kernel Near Principal Component Analysis

Technical Report · Mon Jul 01 00:00:00 EDT 2002 · OSTI ID:810934

Related Subjects

42 ENGINEERING
Dynamical systems
Eigenvalues and eigenfunctions
Fault detection
Hilbert space
Kernel
Principal component analysis
Trajectory

Fault Detection via Occupation Kernel Principal Component Analysis

Citation Formats

References (15)

Similar Records

Related Subjects