Monitoring a Reverse Osmosis Process with Kernel Principal Component Analysis: A Preliminary Approach

The water purification process is becoming increasingly important to ensure the continuity and quality of subsequent production processes, and it is particularly relevant in pharmaceutical contexts. However, in this context, the difficulties arising during the monitoring process are manifold. On the...

Full description

Saved in:
Bibliographic Details
Published inApplied sciences Vol. 11; no. 14; p. 6370
Main Authors Quatrini, Elena, Costantino, Francesco, Mba, David, Li, Xiaochuan, Gan, Tat-Hean
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.07.2021
Subjects
condition-based maintenance
Costs
Desalination
Discontinuity
Drinking water
Fault detection
Fault diagnosis
kernel principal component analysis
Linear programming
Monitoring
nonlinear system
Osmosis
Pharmaceutical industry
pharmaceutical process
Principal components analysis
Process parameters
Reverse osmosis
Solvents
Success
Water purification
Water treatment
Online AccessGet full text

Cover

More Information
Summary:The water purification process is becoming increasingly important to ensure the continuity and quality of subsequent production processes, and it is particularly relevant in pharmaceutical contexts. However, in this context, the difficulties arising during the monitoring process are manifold. On the one hand, the monitoring process reveals various discontinuities due to different characteristics of the input water. On the other hand, the monitoring process is discontinuous and random itself, thus not guaranteeing continuity of the parameters and hindering a straightforward analysis. Consequently, further research on water purification processes is paramount to identify the most suitable techniques able to guarantee good performance. Against this background, this paper proposes an application of kernel principal component analysis for fault detection in a process with the above-mentioned characteristics. Based on the temporal variability of the process, the paper suggests the use of past and future matrices as input for fault detection as an alternative to the original dataset. In this manner, the temporal correlation between process parameters and machine health is accounted for. The proposed approach confirms the possibility of obtaining very good monitoring results in the analyzed context.
ISSN:2076-3417
2076-3417
DOI:10.3390/app11146370