Loading...
A one-class support vector machine for detecting valve stiction
O’Neill, Harrison Khalid, Yousaf Spink, Graham Thorpe, Patrick
O’Neill, Harrison
Khalid, Yousaf
Spink, Graham
Thorpe, Patrick
Advisors
Editors
Other Contributors
EPub Date
Publication Date
2023-08-10
Submitted Date
Collections
Files
Loading...
Article - VoR
Adobe PDF, 2.75 MB
Other Titles
Abstract
In industrial processes, control valve stiction is known to be one of the primary causes for poor control loop performance. Stiction introduces oscillatory behaviour in the process, leading to increased energy consumption, variations in product quality, shortened equipment lifespan and a reduction in overall plant profitability. Several detection algorithms using routine operating data have been developed over the last few decades. However, with the exception of a handful of recent publications, few attempts to apply classical supervised learning techniques have been published thus far. In this work, principal component analysis, linear discriminant analysis and a one-class support vector machine are trained to detect stiction using time series features as input. These features are extracted from the data using the tsfresh package for Python. The training data consists of simulated stiction examples generated using the XCH stiction model as well as other sources of oscillation. The classifier is subsequently benchmarked against closed-loop stiction data collected in an industrial setting, with performance exceeding that of existing methods.
Citation
O’Neill, H., Khalid, Y., Spink, G., & Thorpe, P. (2023). A one-class support vector machine for detecting valve stiction. Digital Chemical Engineering, 8, article-number 100116. https://doi.org/10.1016/j.dche.2023.100116
Publisher
Elsevier
Journal
Digital Chemical Engineering
Research Unit
DOI
10.1016/j.dche.2023.100116
PubMed ID
PubMed Central ID
Type
Article
Language
Description
Series/Report no.
ISSN
2772-5081