Online Condition Monitoring of Industrial Loads Using AutoGMM and Decision Trees
Condition monitoring and fault management approaches can help with timely maintenance planning, assure industry-wide continuous production, and enhance both performance and safety in complex industrial operations. At the moment, data-driven approaches for condition monitoring and fault detection are...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/11/12/1082 |
| _version_ | 1827574271564578816 |
|---|---|
| author | Elia Brescia Patrizia Vergallo Pietro Serafino Massimo Tipaldi Davide Cascella Giuseppe Leonardo Cascella Francesca Romano Andrea Polichetti |
| author_facet | Elia Brescia Patrizia Vergallo Pietro Serafino Massimo Tipaldi Davide Cascella Giuseppe Leonardo Cascella Francesca Romano Andrea Polichetti |
| author_sort | Elia Brescia |
| collection | DOAJ |
| description | Condition monitoring and fault management approaches can help with timely maintenance planning, assure industry-wide continuous production, and enhance both performance and safety in complex industrial operations. At the moment, data-driven approaches for condition monitoring and fault detection are the most attractive being conceived, developed, and applied with less of a need for sophisticated expertise and detailed knowledge of the addressed plant. Among them, Gaussian mixture model (GMM) methods can offer some advantages. However, conventional GMM solutions need the number of Gaussian components to be defined in advance and suffer from the inability to detect new types of faults and identify new operating modes. To address these issues, this paper presents a novel data-driven method, based on automated GMM (AutoGMM) and decision trees (DTree), for the online condition monitoring of electrical industrial loads. By leveraging the benefits of the AutoGMM and the DTree, after the training phase, the proposed approach allows the clustering and time allocation of nominal operating conditions, the identification of both already-classified and new anomalous conditions, and the acknowledgment of new operating modes of the monitored industrial asset. The proposed method, implemented on a commercial cloud-computing platform, is validated on a real industrial plant with electrical loads, characterized by a daily periodic working cycle, by using active power consumption data. |
| first_indexed | 2024-03-08T20:34:48Z |
| format | Article |
| id | doaj.art-6af1835f7deb4ebab65e3d230759c375 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-08T20:34:48Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-6af1835f7deb4ebab65e3d230759c3752023-12-22T14:22:00ZengMDPI AGMachines2075-17022023-12-011112108210.3390/machines11121082Online Condition Monitoring of Industrial Loads Using AutoGMM and Decision TreesElia Brescia0Patrizia Vergallo1Pietro Serafino2Massimo Tipaldi3Davide Cascella4Giuseppe Leonardo Cascella5Francesca Romano6Andrea Polichetti7Department of Electrical and Information Engineering, Polytechnic University of Bari, 70125 Bari, ItalyDepartment of Electrical and Information Engineering, Polytechnic University of Bari, 70125 Bari, ItalyIdea75 S.r.l., 70121 Bari, ItalyDepartment of Electrical and Information Engineering, Polytechnic University of Bari, 70125 Bari, ItalyIdea75 S.r.l., 70121 Bari, ItalyDepartment of Electrical and Information Engineering, Polytechnic University of Bari, 70125 Bari, ItalyLinks Management & Technology Spa, 70121 Bari, ItalyFree Energy Saving S.r.l., 04100 Latina, ItalyCondition monitoring and fault management approaches can help with timely maintenance planning, assure industry-wide continuous production, and enhance both performance and safety in complex industrial operations. At the moment, data-driven approaches for condition monitoring and fault detection are the most attractive being conceived, developed, and applied with less of a need for sophisticated expertise and detailed knowledge of the addressed plant. Among them, Gaussian mixture model (GMM) methods can offer some advantages. However, conventional GMM solutions need the number of Gaussian components to be defined in advance and suffer from the inability to detect new types of faults and identify new operating modes. To address these issues, this paper presents a novel data-driven method, based on automated GMM (AutoGMM) and decision trees (DTree), for the online condition monitoring of electrical industrial loads. By leveraging the benefits of the AutoGMM and the DTree, after the training phase, the proposed approach allows the clustering and time allocation of nominal operating conditions, the identification of both already-classified and new anomalous conditions, and the acknowledgment of new operating modes of the monitored industrial asset. The proposed method, implemented on a commercial cloud-computing platform, is validated on a real industrial plant with electrical loads, characterized by a daily periodic working cycle, by using active power consumption data.https://www.mdpi.com/2075-1702/11/12/1082anomaly and novelty detectionautomated Gaussian mixture modeldecision treeselectrical industrial loadsGaussian mixture modelonline condition monitoring |
| spellingShingle | Elia Brescia Patrizia Vergallo Pietro Serafino Massimo Tipaldi Davide Cascella Giuseppe Leonardo Cascella Francesca Romano Andrea Polichetti Online Condition Monitoring of Industrial Loads Using AutoGMM and Decision Trees Machines anomaly and novelty detection automated Gaussian mixture model decision trees electrical industrial loads Gaussian mixture model online condition monitoring |
| title | Online Condition Monitoring of Industrial Loads Using AutoGMM and Decision Trees |
| title_full | Online Condition Monitoring of Industrial Loads Using AutoGMM and Decision Trees |
| title_fullStr | Online Condition Monitoring of Industrial Loads Using AutoGMM and Decision Trees |
| title_full_unstemmed | Online Condition Monitoring of Industrial Loads Using AutoGMM and Decision Trees |
| title_short | Online Condition Monitoring of Industrial Loads Using AutoGMM and Decision Trees |
| title_sort | online condition monitoring of industrial loads using autogmm and decision trees |
| topic | anomaly and novelty detection automated Gaussian mixture model decision trees electrical industrial loads Gaussian mixture model online condition monitoring |
| url | https://www.mdpi.com/2075-1702/11/12/1082 |
| work_keys_str_mv | AT eliabrescia onlineconditionmonitoringofindustrialloadsusingautogmmanddecisiontrees AT patriziavergallo onlineconditionmonitoringofindustrialloadsusingautogmmanddecisiontrees AT pietroserafino onlineconditionmonitoringofindustrialloadsusingautogmmanddecisiontrees AT massimotipaldi onlineconditionmonitoringofindustrialloadsusingautogmmanddecisiontrees AT davidecascella onlineconditionmonitoringofindustrialloadsusingautogmmanddecisiontrees AT giuseppeleonardocascella onlineconditionmonitoringofindustrialloadsusingautogmmanddecisiontrees AT francescaromano onlineconditionmonitoringofindustrialloadsusingautogmmanddecisiontrees AT andreapolichetti onlineconditionmonitoringofindustrialloadsusingautogmmanddecisiontrees |