Abstract
Most industries face a growing challenge concerning data handling due to the large data storage capacity available today. In many cases, it is difficult to navigate through these amounts of data in search of relevant information. An important tool in this context is statistical process control (SPC), which enables the discovery of possible process drift or other problems as early as possible. In this work the potential of using near infrared (NIR) spectroscopy as a multifunction tool for SPC in the context of process monitoring has been investigated. Both principal component analysis (PCA) and partial least squares regression (PLS) are tested as tools for extracting useful information from NIR spectra. The two methods have been compared based on interpretation of score plots and explained variance. We have also tested classification tools for prediction of classes and various types of validation, since these data came from designed experiments. It has been demonstrated that PLS is a useful tool both for forward and backward predictions. Another topic considered is discovery of instrument drift and outlier detection. It has been demonstrated that PLS is a useful tool in both contexts. The robustness of PLS predictions has been investigated and it was found that PLS score plots can reveal useful information early in the process. This study was a feasibility study and the models can not be used directly in any large scale installations. This work has, however, demonstrated the usefulness of multivariate techniques in such processes and found a good basis for further model development.
© 2005 NIR Publications
PDF Article
More Like This
Cited By
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription