Dynamic Classifier Auditing by Unsupervised Anomaly Detection Methods: An Application in Packaging Industry Predictive Maintenance
Predictive maintenance in manufacturing industry applications is a challenging research field. Packaging machines are widely used in a large number of logistic companies’ warehouses and must be working uninterruptedly. Traditionally, preventive maintenance strategies have been carried out to improve...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/882 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589223006306304 |
|---|---|
| author | Fernando Mateo Joan Vila-Francés Emilio Soria-Olivas Marcelino Martínez-Sober Juan Gómez-Sanchis Antonio José Serrano-López |
| author_facet | Fernando Mateo Joan Vila-Francés Emilio Soria-Olivas Marcelino Martínez-Sober Juan Gómez-Sanchis Antonio José Serrano-López |
| author_sort | Fernando Mateo |
| collection | DOAJ |
| description | Predictive maintenance in manufacturing industry applications is a challenging research field. Packaging machines are widely used in a large number of logistic companies’ warehouses and must be working uninterruptedly. Traditionally, preventive maintenance strategies have been carried out to improve the performance of these machines. However, these kinds of policies do not take into account the information provided by the sensors implemented in the machines. This paper presents an expert system for the automatic estimation of work orders to implement predictive maintenance policies for packaging machines. The central innovation lies in a two-stage process: a classifier generates a binary decision on whether a machine requires maintenance, and an unsupervised anomaly detection module subsequently audits the classifier’s probabilistic output to refine and interpret its predictions. By leveraging the classifier to condense sensor data and applying anomaly detection to its output, the system optimizes the decision reliability. Three anomaly detection methods were evaluated: One-Class Support Vector Machine (OCSVM), Minimum Covariance Determinant (MCD), and a majority (hard) voting ensemble of the two. All anomaly detection methods improved the baseline classifier’s performance, with the majority voting ensemble achieving the highest F1 score. |
| format | Article |
| id | doaj-art-dfc93e022e1448f5ae7354e89a40c326 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-dfc93e022e1448f5ae7354e89a40c3262025-01-24T13:21:11ZengMDPI AGApplied Sciences2076-34172025-01-0115288210.3390/app15020882Dynamic Classifier Auditing by Unsupervised Anomaly Detection Methods: An Application in Packaging Industry Predictive MaintenanceFernando Mateo0Joan Vila-Francés1Emilio Soria-Olivas2Marcelino Martínez-Sober3Juan Gómez-Sanchis4Antonio José Serrano-López5Departamento de Ingeniería Electrónica, Escola Tècnica Superior d’Enginyería (ETSE), Avenida de la Universidad, 46100 Burjassot, SpainDepartamento de Ingeniería Electrónica, Escola Tècnica Superior d’Enginyería (ETSE), Avenida de la Universidad, 46100 Burjassot, SpainDepartamento de Ingeniería Electrónica, Escola Tècnica Superior d’Enginyería (ETSE), Avenida de la Universidad, 46100 Burjassot, SpainDepartamento de Ingeniería Electrónica, Escola Tècnica Superior d’Enginyería (ETSE), Avenida de la Universidad, 46100 Burjassot, SpainDepartamento de Ingeniería Electrónica, Escola Tècnica Superior d’Enginyería (ETSE), Avenida de la Universidad, 46100 Burjassot, SpainDepartamento de Ingeniería Electrónica, Escola Tècnica Superior d’Enginyería (ETSE), Avenida de la Universidad, 46100 Burjassot, SpainPredictive maintenance in manufacturing industry applications is a challenging research field. Packaging machines are widely used in a large number of logistic companies’ warehouses and must be working uninterruptedly. Traditionally, preventive maintenance strategies have been carried out to improve the performance of these machines. However, these kinds of policies do not take into account the information provided by the sensors implemented in the machines. This paper presents an expert system for the automatic estimation of work orders to implement predictive maintenance policies for packaging machines. The central innovation lies in a two-stage process: a classifier generates a binary decision on whether a machine requires maintenance, and an unsupervised anomaly detection module subsequently audits the classifier’s probabilistic output to refine and interpret its predictions. By leveraging the classifier to condense sensor data and applying anomaly detection to its output, the system optimizes the decision reliability. Three anomaly detection methods were evaluated: One-Class Support Vector Machine (OCSVM), Minimum Covariance Determinant (MCD), and a majority (hard) voting ensemble of the two. All anomaly detection methods improved the baseline classifier’s performance, with the majority voting ensemble achieving the highest F1 score.https://www.mdpi.com/2076-3417/15/2/882predictive maintenanceanomaly detectionclassifier auditingpackaging industrymanufacturing systems |
| spellingShingle | Fernando Mateo Joan Vila-Francés Emilio Soria-Olivas Marcelino Martínez-Sober Juan Gómez-Sanchis Antonio José Serrano-López Dynamic Classifier Auditing by Unsupervised Anomaly Detection Methods: An Application in Packaging Industry Predictive Maintenance Applied Sciences predictive maintenance anomaly detection classifier auditing packaging industry manufacturing systems |
| title | Dynamic Classifier Auditing by Unsupervised Anomaly Detection Methods: An Application in Packaging Industry Predictive Maintenance |
| title_full | Dynamic Classifier Auditing by Unsupervised Anomaly Detection Methods: An Application in Packaging Industry Predictive Maintenance |
| title_fullStr | Dynamic Classifier Auditing by Unsupervised Anomaly Detection Methods: An Application in Packaging Industry Predictive Maintenance |
| title_full_unstemmed | Dynamic Classifier Auditing by Unsupervised Anomaly Detection Methods: An Application in Packaging Industry Predictive Maintenance |
| title_short | Dynamic Classifier Auditing by Unsupervised Anomaly Detection Methods: An Application in Packaging Industry Predictive Maintenance |
| title_sort | dynamic classifier auditing by unsupervised anomaly detection methods an application in packaging industry predictive maintenance |
| topic | predictive maintenance anomaly detection classifier auditing packaging industry manufacturing systems |
| url | https://www.mdpi.com/2076-3417/15/2/882 |
| work_keys_str_mv | AT fernandomateo dynamicclassifierauditingbyunsupervisedanomalydetectionmethodsanapplicationinpackagingindustrypredictivemaintenance AT joanvilafrances dynamicclassifierauditingbyunsupervisedanomalydetectionmethodsanapplicationinpackagingindustrypredictivemaintenance AT emiliosoriaolivas dynamicclassifierauditingbyunsupervisedanomalydetectionmethodsanapplicationinpackagingindustrypredictivemaintenance AT marcelinomartinezsober dynamicclassifierauditingbyunsupervisedanomalydetectionmethodsanapplicationinpackagingindustrypredictivemaintenance AT juangomezsanchis dynamicclassifierauditingbyunsupervisedanomalydetectionmethodsanapplicationinpackagingindustrypredictivemaintenance AT antoniojoseserranolopez dynamicclassifierauditingbyunsupervisedanomalydetectionmethodsanapplicationinpackagingindustrypredictivemaintenance |