Nonlinear On-line Process Monitoring and Fault Detection Based on Kernel ICA
- 1 December 2006
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (21511802) , 222-227
Abstract
In this paper, a novel nonlinear process monitoring and fault detection method based on kernel ICA is proposed. The Kernel ICA method is a two-phase algorithm, KPCA first spheres data and makes the data structure become as linearly separable as possible using an implicit nonlinear mapping determined by kernel. Then ICA seeks the projection directions in the KPCA whitened space, making the distribution of the projected data as non-gaussian as possible. The application to the FCCU simulated process indicates that the proposed process monitoring method based on Kernel ICA can effectively capture the nonlinear relationship in process variables. Its performance significantly outperforms monitoring method based on ICA or KPCA.Keywords
This publication has 16 references indexed in Scilit:
- Kernel ICA: An alternative formulation and its application to face recognitionPattern Recognition, 2005
- Statistical process monitoring with independent component analysisJournal of Process Control, 2004
- Nonlinear process monitoring using kernel principal component analysisChemical Engineering Science, 2004
- Recursive partial least squares algorithms for monitoring complex industrial processesControl Engineering Practice, 2003
- The application of principal component analysis and kernel density estimation to enhance process monitoringControl Engineering Practice, 2000
- Nonlinear Component Analysis as a Kernel Eigenvalue ProblemNeural Computation, 1998
- The process chemometrics approach to process monitoring and fault detectionJournal of Process Control, 1996
- Non-parametric confidence bounds for process performance monitoring chartsJournal of Process Control, 1996
- Disturbance detection and isolation by dynamic principal component analysisChemometrics and Intelligent Laboratory Systems, 1995
- Multivariate SPC Charts for Monitoring Batch ProcessesTechnometrics, 1995