Advanced

Multivariate statistical monitoring of continuous wastewater treatment plants

Aguado, D and Rosén, Christian LU (2008) In Engineering Applications of Artificial Intelligence 21(7). p.1080-1091
Abstract (Swedish)
Abstract in Undetermined

In this paper, different multivariate statistical approaches for analysing wastewater treatment process data are presented and compared. For this purpose, all the methods have been tested using one-year operational data in a simulation model benchmark. The general monitoring strategy adopted includes a screening stage to improve data quality, all adaptive model to detect and diagnose abnormal events, and two complementary tools for helping in the diagnosis of the faults. The first one is based oil the development of a local model that captures the most recent process behaviour and the second one oil the application of fuzzy c-means clustering to the scores of the monitoring model. The results have... (More)
Abstract in Undetermined

In this paper, different multivariate statistical approaches for analysing wastewater treatment process data are presented and compared. For this purpose, all the methods have been tested using one-year operational data in a simulation model benchmark. The general monitoring strategy adopted includes a screening stage to improve data quality, all adaptive model to detect and diagnose abnormal events, and two complementary tools for helping in the diagnosis of the faults. The first one is based oil the development of a local model that captures the most recent process behaviour and the second one oil the application of fuzzy c-means clustering to the scores of the monitoring model. The results have shown that simple scaling parameters adaptation is sufficient to obtain a model useful for monitoring the process during the whole period. Monitoring the deviations from the average daily behaviour showed clear detections of the disturbances in the Hotelling's T(2)-statistic and this feature was useful to determine different operational states (disturbances) in the process by clustering the PCA scores. On the other hand, the proposed procedure for isolation based on a local model improved the diagnosis results in terms of the responsible variables identified and the indication of the beginning of the fault. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Wastewater treatment, Principal component analysis (PCA), Monitoring, Clustering, Benchmark
in
Engineering Applications of Artificial Intelligence
volume
21
issue
7
pages
1080 - 1091
publisher
Engineering Applications of Artificial Intelligence
external identifiers
  • wos:000260748700011
  • scopus:52949138733
ISSN
1873-6769
DOI
10.1016/j.engappai.2007.08.004
language
English
LU publication?
yes
id
63ffefa0-4f9d-4fde-8079-070d0a890140 (old id 715397)
date added to LUP
2007-12-10 12:13:11
date last changed
2017-07-02 03:31:19
@article{63ffefa0-4f9d-4fde-8079-070d0a890140,
  abstract     = {<b>Abstract in Undetermined</b><br/><br>
In this paper, different multivariate statistical approaches for analysing wastewater treatment process data are presented and compared. For this purpose, all the methods have been tested using one-year operational data in a simulation model benchmark. The general monitoring strategy adopted includes a screening stage to improve data quality, all adaptive model to detect and diagnose abnormal events, and two complementary tools for helping in the diagnosis of the faults. The first one is based oil the development of a local model that captures the most recent process behaviour and the second one oil the application of fuzzy c-means clustering to the scores of the monitoring model. The results have shown that simple scaling parameters adaptation is sufficient to obtain a model useful for monitoring the process during the whole period. Monitoring the deviations from the average daily behaviour showed clear detections of the disturbances in the Hotelling's T(2)-statistic and this feature was useful to determine different operational states (disturbances) in the process by clustering the PCA scores. On the other hand, the proposed procedure for isolation based on a local model improved the diagnosis results in terms of the responsible variables identified and the indication of the beginning of the fault.},
  author       = {Aguado, D and Rosén, Christian},
  issn         = {1873-6769},
  keyword      = {Wastewater treatment,Principal component analysis (PCA),Monitoring,Clustering,Benchmark},
  language     = {eng},
  number       = {7},
  pages        = {1080--1091},
  publisher    = {Engineering Applications of Artificial Intelligence},
  series       = {Engineering Applications of Artificial Intelligence},
  title        = {Multivariate statistical monitoring of continuous wastewater treatment plants},
  url          = {http://dx.doi.org/10.1016/j.engappai.2007.08.004},
  volume       = {21},
  year         = {2008},
}