Loading...
Loading...

Go to the content (press return)

Diagnosis of fluid leaks in pipelines using dynamic PCA?

Author
Santos, I.; López, F.; Puig, V.
Type of activity
Journal article
Journal
IFAC-PapersOnLine
Date of publication
2018-01-01
Volume
51
Number
24
First page
373
Last page
380
DOI
https://doi.org/10.1016/j.ifacol.2018.09.604 Open in new window
Repository
http://hdl.handle.net/2117/130091 Open in new window
URL
https://www.sciencedirect.com/science/article/pii/S2405896318323164?via%3Dihub Open in new window
Abstract
In this paper, a data-driven system based on PCA is described to detect and quantify fluid leaks in an experimental pipeline. A dynamic PCA implementation (DPCA) was used to capture the process dynamics because the system variables are time-correlated. To detect leaks online, the Hotelling’s T2 statistic and the squared prediction error (SPE) were used as residuals, which are compared against statistically defined thresholds from a set of training data. To determine the number of delays to be ...
Citation
Santos, I.; López, F.; Puig, V. Diagnosis of fluid leaks in pipelines using dynamic PCA?. "IFAC-PapersOnLine", 1 Gener 2018, vol. 51, núm. 24, p. 373-380.
Keywords
Data-driven fault detection, Fault diagnosis, Fluid leaks, Pipelines, Principal component analysis
Group of research
CS2AC-UPC - Supervision, Safety and Automatic Control
SAC - Advanced Control Systems

Participants