A Real-Time Novelty Recognition Framework Based on Machine Learning for Fault Detection
New technologies are developed inside today’s companies with the ascent of Industry 4.0 paradigm; Artificial Intelligence applied to Predictive Maintenance is one of these, helping factories automate their systems in detecting anomalies. The deviation of statistical features from standard operating...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/16/2/61 |
| _version_ | 1797622864694738944 |
|---|---|
| author | Umberto Albertin Giuseppe Pedone Matilde Brossa Giovanni Squillero Marcello Chiaberge |
| author_facet | Umberto Albertin Giuseppe Pedone Matilde Brossa Giovanni Squillero Marcello Chiaberge |
| author_sort | Umberto Albertin |
| collection | DOAJ |
| description | New technologies are developed inside today’s companies with the ascent of Industry 4.0 paradigm; Artificial Intelligence applied to Predictive Maintenance is one of these, helping factories automate their systems in detecting anomalies. The deviation of statistical features from standard operating conditions computed on collected data is a common investigation technique that companies use. The information loss due to transformation from raw data to extracted features is a problem of this approach. Furthermore, a common Predictive Maintenance framework requires historical data about failures that often do not exist, neglecting the possibility of applying it. This paper uses Artificial Intelligence as Machine Learning models to recognize when something changes in the data’s behavior collected up to that moment, also helping companies to gather a preliminary dataset for future Predictive Maintenance implementation. The aim concerns a framework in which several sensors are used to collect data by adopting a sensor fusion approach. The architecture is composed of an optimized software system able to enhance the computation scalability and the response time regarding novelty detection. This article analyzes the proposed architecture, then explains a proof-of-concept development using a digital model; finally, two real cases are studied to show how the framework behaves in a real environment. The analysis done in this paper has an application-oriented approach; hence a company can directly use the framework in its systems. |
| first_indexed | 2024-03-11T09:17:17Z |
| format | Article |
| id | doaj.art-bb5bbb5d00cc4c8484621f462cda4b9f |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-11T09:17:17Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-bb5bbb5d00cc4c8484621f462cda4b9f2023-11-16T18:37:11ZengMDPI AGAlgorithms1999-48932023-01-011626110.3390/a16020061A Real-Time Novelty Recognition Framework Based on Machine Learning for Fault DetectionUmberto Albertin0Giuseppe Pedone1Matilde Brossa2Giovanni Squillero3Marcello Chiaberge4Department of Electronics and Telecommunications, Politecnico di Torino, Corso Duca degli Abruzzi, 24, 10129 Torino, ItalyDepartment of Control and Computer Engineering, Politecnico di Torino, Corso Duca degli Abruzzi, 24, 10129 Torino, ItalyResearch and Development Department, Spea Spa, Via Torino, 16, 10088 Volpiano, ItalyDepartment of Control and Computer Engineering, Politecnico di Torino, Corso Duca degli Abruzzi, 24, 10129 Torino, ItalyDepartment of Electronics and Telecommunications, Politecnico di Torino, Corso Duca degli Abruzzi, 24, 10129 Torino, ItalyNew technologies are developed inside today’s companies with the ascent of Industry 4.0 paradigm; Artificial Intelligence applied to Predictive Maintenance is one of these, helping factories automate their systems in detecting anomalies. The deviation of statistical features from standard operating conditions computed on collected data is a common investigation technique that companies use. The information loss due to transformation from raw data to extracted features is a problem of this approach. Furthermore, a common Predictive Maintenance framework requires historical data about failures that often do not exist, neglecting the possibility of applying it. This paper uses Artificial Intelligence as Machine Learning models to recognize when something changes in the data’s behavior collected up to that moment, also helping companies to gather a preliminary dataset for future Predictive Maintenance implementation. The aim concerns a framework in which several sensors are used to collect data by adopting a sensor fusion approach. The architecture is composed of an optimized software system able to enhance the computation scalability and the response time regarding novelty detection. This article analyzes the proposed architecture, then explains a proof-of-concept development using a digital model; finally, two real cases are studied to show how the framework behaves in a real environment. The analysis done in this paper has an application-oriented approach; hence a company can directly use the framework in its systems.https://www.mdpi.com/1999-4893/16/2/61predictive maintenanceprognosticnovelty detectionmachine learningfault detectionanomaly detection |
| spellingShingle | Umberto Albertin Giuseppe Pedone Matilde Brossa Giovanni Squillero Marcello Chiaberge A Real-Time Novelty Recognition Framework Based on Machine Learning for Fault Detection Algorithms predictive maintenance prognostic novelty detection machine learning fault detection anomaly detection |
| title | A Real-Time Novelty Recognition Framework Based on Machine Learning for Fault Detection |
| title_full | A Real-Time Novelty Recognition Framework Based on Machine Learning for Fault Detection |
| title_fullStr | A Real-Time Novelty Recognition Framework Based on Machine Learning for Fault Detection |
| title_full_unstemmed | A Real-Time Novelty Recognition Framework Based on Machine Learning for Fault Detection |
| title_short | A Real-Time Novelty Recognition Framework Based on Machine Learning for Fault Detection |
| title_sort | real time novelty recognition framework based on machine learning for fault detection |
| topic | predictive maintenance prognostic novelty detection machine learning fault detection anomaly detection |
| url | https://www.mdpi.com/1999-4893/16/2/61 |
| work_keys_str_mv | AT umbertoalbertin arealtimenoveltyrecognitionframeworkbasedonmachinelearningforfaultdetection AT giuseppepedone arealtimenoveltyrecognitionframeworkbasedonmachinelearningforfaultdetection AT matildebrossa arealtimenoveltyrecognitionframeworkbasedonmachinelearningforfaultdetection AT giovannisquillero arealtimenoveltyrecognitionframeworkbasedonmachinelearningforfaultdetection AT marcellochiaberge arealtimenoveltyrecognitionframeworkbasedonmachinelearningforfaultdetection AT umbertoalbertin realtimenoveltyrecognitionframeworkbasedonmachinelearningforfaultdetection AT giuseppepedone realtimenoveltyrecognitionframeworkbasedonmachinelearningforfaultdetection AT matildebrossa realtimenoveltyrecognitionframeworkbasedonmachinelearningforfaultdetection AT giovannisquillero realtimenoveltyrecognitionframeworkbasedonmachinelearningforfaultdetection AT marcellochiaberge realtimenoveltyrecognitionframeworkbasedonmachinelearningforfaultdetection |