|
|
Personnel
>
Postgraduate Students
>
Abd Halim Shah Maulud
|
| Contact Details |
Abd Halim Shah Maulud
PhD Student
Ph: +61-2-9351 4337
Fax: +61-2-9351 2854
Email: halim@chem.eng.usyd.edu.au
Department of Chemical Engineering
University of Sydney
Sydney, NSW, 2006
|
 |
|
| Project |
Robust Nonlinear Multi-scale Techniques for Advanced Process Monitoring
|
Principal component analysis (PCA) has been sucessfully exploited in Multivariate Statistical
Process Control due to its capability of dimensionality reduction. Similarly, partial least
squares (PLS) is widely used when parameter estimation is required in multivariate
environments. Both these techniques assume the interactions between the process measurements
are linearly correlated. In most continous process plants, this assumption is valid as long
as the plant is operated within the steady state operation.
However, typical process plants are operated at different operating conditions and obviously
exhibit nonlinear correlations among the process measurements. Futhermore, process plant data
prones to outlier which degrades the PCA and PLS performances. In view to the nonllineraity
and outlier problems, advanced techniques of robust nonlinear multi-scale will be developed
for process monitoring.
|
|
|
|
This site is best viewed with version 5.0 browsers or above (IE & Netscape). www.pseonline.net |
|
Introduction to Process Control, Second Edition
Out Now!
|
