Abstract
The goal of this work is the development of a suitable monitoring module, which is to be the first module of an integrated fault detection and control system for the SHARON process. To model the process properly, different PCA models are tested. As a first step, PCA is used in an iterative manner to exclude data not considered to represent normal operational conditions and process behaviour from the original data set. To improve the performance of the identified model, it is decided to account for dynamics in the SHARON process by means of auto-regressive exogenous (ARX) structuring of data before the identification. A fruitful replacement of missing values for this purpose is done by means of a static PCA model. It is shown that the different criteria used in model selection lead to the same DPCA model. In this paper all steps of the monitoring module design are explained and the performance of different models is analyzed.
Original language | English |
---|---|
Pages (from-to) | 1297-1302 |
Number of pages | 6 |
Journal | Computer Aided Chemical Engineering |
Volume | 20 |
Issue number | C |
DOIs | |
State | Published - 2005 |
Externally published | Yes |
Funding
This work was supported by the Institute for Encouragement of Innovation by means of Science and Technology in Flanders (IWT), the Visiting Postdoctoral Fellowship of the Fund for Scientific Research-Flanders (FWO) and the ICON Project No. EVK1-CT2000-054.
Keywords
- Dynamics PCA
- environmental biotechnology
- fault detection
- statistical monitoring
- wastewater treatment