A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes
Many classical multivariate statistical process monitoring (MSPM) techniques assume normal distribution of the data and independence of the samples. Very often, these assumptions do not hold for real industrial chemical processes, where multiple plant operating modes lead to multiple nominal operati...
| Autores principales: | , , , , |
|---|---|
| Formato: | JOUR |
| Materias: | |
| Acceso en línea: | http://hdl.handle.net/20.500.12110/paper_00981354_v34_n2_p223_Maestri |
| Aporte de: |
| id |
todo:paper_00981354_v34_n2_p223_Maestri |
|---|---|
| record_format |
dspace |
| spelling |
todo:paper_00981354_v34_n2_p223_Maestri2023-10-03T14:56:55Z A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes Maestri, M. Farall, A. Groisman, P. Cassanello, M. Horowitz, G. Fault detection Multiple operating modes Multivariate statistical process monitoring Alarm rate Clustering techniques False alarms Industrial installations Industrial processs Methanol plants Multiple operations Multivariate statistical process monitoring Nominal operations Operating modes Realistic simulation Robust clustering Steady-state operation Tennessee Eastman process Chemical detection Cluster analysis Covariance matrix Inspection equipment Methanol Multivariant analysis Normal distribution Process monitoring Statistical process control Fault detection Many classical multivariate statistical process monitoring (MSPM) techniques assume normal distribution of the data and independence of the samples. Very often, these assumptions do not hold for real industrial chemical processes, where multiple plant operating modes lead to multiple nominal operation regions. MSPM techniques that do not take account of this fact show increased false alarm and missing alarm rates. In this work, a simple fault detection tool based on a robust clustering technique is implemented to detect abnormal situations in an industrial installation with multiple operation modes. The tool is applied to three case studies: (i) a two-dimensional toy example, (ii) a realistic simulation usually used as a benchmark example, known as the Tennessee-Eastman Process, and (iii) real data from a methanol plant. The clustering technique on which the tool relies assumes that the observations come from multiple populations with a common covariance matrix (i.e., the same underlying physical relations). The clustering technique is also capable of coping with a certain percentage of outliers, thus avoiding the need of extensive preprocessing of the data. Moreover, improvements in detection capacity are found when comparing the results to those obtained with standard methodologies. Hence, the feasibility of implementing fault detection tools based on this technique in the field of chemical industrial processes is discussed. © 2009 Elsevier Ltd. All rights reserved. Fil:Maestri, M. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Groisman, P. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Cassanello, M. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Horowitz, G. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. JOUR info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by/2.5/ar http://hdl.handle.net/20.500.12110/paper_00981354_v34_n2_p223_Maestri |
| institution |
Universidad de Buenos Aires |
| institution_str |
I-28 |
| repository_str |
R-134 |
| collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
| topic |
Fault detection Multiple operating modes Multivariate statistical process monitoring Alarm rate Clustering techniques False alarms Industrial installations Industrial processs Methanol plants Multiple operations Multivariate statistical process monitoring Nominal operations Operating modes Realistic simulation Robust clustering Steady-state operation Tennessee Eastman process Chemical detection Cluster analysis Covariance matrix Inspection equipment Methanol Multivariant analysis Normal distribution Process monitoring Statistical process control Fault detection |
| spellingShingle |
Fault detection Multiple operating modes Multivariate statistical process monitoring Alarm rate Clustering techniques False alarms Industrial installations Industrial processs Methanol plants Multiple operations Multivariate statistical process monitoring Nominal operations Operating modes Realistic simulation Robust clustering Steady-state operation Tennessee Eastman process Chemical detection Cluster analysis Covariance matrix Inspection equipment Methanol Multivariant analysis Normal distribution Process monitoring Statistical process control Fault detection Maestri, M. Farall, A. Groisman, P. Cassanello, M. Horowitz, G. A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes |
| topic_facet |
Fault detection Multiple operating modes Multivariate statistical process monitoring Alarm rate Clustering techniques False alarms Industrial installations Industrial processs Methanol plants Multiple operations Multivariate statistical process monitoring Nominal operations Operating modes Realistic simulation Robust clustering Steady-state operation Tennessee Eastman process Chemical detection Cluster analysis Covariance matrix Inspection equipment Methanol Multivariant analysis Normal distribution Process monitoring Statistical process control Fault detection |
| description |
Many classical multivariate statistical process monitoring (MSPM) techniques assume normal distribution of the data and independence of the samples. Very often, these assumptions do not hold for real industrial chemical processes, where multiple plant operating modes lead to multiple nominal operation regions. MSPM techniques that do not take account of this fact show increased false alarm and missing alarm rates. In this work, a simple fault detection tool based on a robust clustering technique is implemented to detect abnormal situations in an industrial installation with multiple operation modes. The tool is applied to three case studies: (i) a two-dimensional toy example, (ii) a realistic simulation usually used as a benchmark example, known as the Tennessee-Eastman Process, and (iii) real data from a methanol plant. The clustering technique on which the tool relies assumes that the observations come from multiple populations with a common covariance matrix (i.e., the same underlying physical relations). The clustering technique is also capable of coping with a certain percentage of outliers, thus avoiding the need of extensive preprocessing of the data. Moreover, improvements in detection capacity are found when comparing the results to those obtained with standard methodologies. Hence, the feasibility of implementing fault detection tools based on this technique in the field of chemical industrial processes is discussed. © 2009 Elsevier Ltd. All rights reserved. |
| format |
JOUR |
| author |
Maestri, M. Farall, A. Groisman, P. Cassanello, M. Horowitz, G. |
| author_facet |
Maestri, M. Farall, A. Groisman, P. Cassanello, M. Horowitz, G. |
| author_sort |
Maestri, M. |
| title |
A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes |
| title_short |
A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes |
| title_full |
A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes |
| title_fullStr |
A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes |
| title_full_unstemmed |
A robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes |
| title_sort |
robust clustering method for detection of abnormal situations in a process with multiple steady-state operation modes |
| url |
http://hdl.handle.net/20.500.12110/paper_00981354_v34_n2_p223_Maestri |
| work_keys_str_mv |
AT maestrim arobustclusteringmethodfordetectionofabnormalsituationsinaprocesswithmultiplesteadystateoperationmodes AT faralla arobustclusteringmethodfordetectionofabnormalsituationsinaprocesswithmultiplesteadystateoperationmodes AT groismanp arobustclusteringmethodfordetectionofabnormalsituationsinaprocesswithmultiplesteadystateoperationmodes AT cassanellom arobustclusteringmethodfordetectionofabnormalsituationsinaprocesswithmultiplesteadystateoperationmodes AT horowitzg arobustclusteringmethodfordetectionofabnormalsituationsinaprocesswithmultiplesteadystateoperationmodes AT maestrim robustclusteringmethodfordetectionofabnormalsituationsinaprocesswithmultiplesteadystateoperationmodes AT faralla robustclusteringmethodfordetectionofabnormalsituationsinaprocesswithmultiplesteadystateoperationmodes AT groismanp robustclusteringmethodfordetectionofabnormalsituationsinaprocesswithmultiplesteadystateoperationmodes AT cassanellom robustclusteringmethodfordetectionofabnormalsituationsinaprocesswithmultiplesteadystateoperationmodes AT horowitzg robustclusteringmethodfordetectionofabnormalsituationsinaprocesswithmultiplesteadystateoperationmodes |
| _version_ |
1807314772067090432 |