Identifying Benchmarks for Failure Prediction in Industry 4.0
Industry 4.0 is characterized by the availability of sensors to operate the so-called intelligent factory. Predictive maintenance, in particular, failure prediction, is an important issue to cut the costs associated with production breaks. We studied more than 40 publications on predictive maintenan...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Informatics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9709/8/4/68 |
| _version_ | 1797503626663428096 |
|---|---|
| author | Mouhamadou Saliou Diallo Sid Ahmed Mokeddem Agnès Braud Gabriel Frey Nicolas Lachiche |
| author_facet | Mouhamadou Saliou Diallo Sid Ahmed Mokeddem Agnès Braud Gabriel Frey Nicolas Lachiche |
| author_sort | Mouhamadou Saliou Diallo |
| collection | DOAJ |
| description | Industry 4.0 is characterized by the availability of sensors to operate the so-called intelligent factory. Predictive maintenance, in particular, failure prediction, is an important issue to cut the costs associated with production breaks. We studied more than 40 publications on predictive maintenance. We point out that they focus on various machine learning algorithms rather than on the selection of suitable datasets. In fact, most publications consider a single, usually non-public, benchmark. More benchmarks are needed to design and test the generality of the proposed approaches. This paper is the first to define the requirements on these benchmarks. It highlights that there are only two benchmarks that can be used for supervised learning among the six publicly available ones we found in the literature. We also illustrate how such a benchmark can be used with deep learning to successfully train and evaluate a failure prediction model. We raise several perspectives for research. |
| first_indexed | 2024-03-10T03:53:23Z |
| format | Article |
| id | doaj.art-226a58cb9e5040fdac9f13ffc681b5e1 |
| institution | Directory Open Access Journal |
| issn | 2227-9709 |
| language | English |
| last_indexed | 2024-03-10T03:53:23Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Informatics |
| spelling | doaj.art-226a58cb9e5040fdac9f13ffc681b5e12023-11-23T08:50:56ZengMDPI AGInformatics2227-97092021-09-01846810.3390/informatics8040068Identifying Benchmarks for Failure Prediction in Industry 4.0Mouhamadou Saliou Diallo0Sid Ahmed Mokeddem1Agnès Braud2Gabriel Frey3Nicolas Lachiche4ICube, University of Strasbourg, 300 Bd Sébastien Brant, 67400 Illkirch-Graffenstaden, FranceICube, University of Strasbourg, 300 Bd Sébastien Brant, 67400 Illkirch-Graffenstaden, FranceICube, University of Strasbourg, 300 Bd Sébastien Brant, 67400 Illkirch-Graffenstaden, FranceICube, University of Strasbourg, 300 Bd Sébastien Brant, 67400 Illkirch-Graffenstaden, FranceICube, University of Strasbourg, 300 Bd Sébastien Brant, 67400 Illkirch-Graffenstaden, FranceIndustry 4.0 is characterized by the availability of sensors to operate the so-called intelligent factory. Predictive maintenance, in particular, failure prediction, is an important issue to cut the costs associated with production breaks. We studied more than 40 publications on predictive maintenance. We point out that they focus on various machine learning algorithms rather than on the selection of suitable datasets. In fact, most publications consider a single, usually non-public, benchmark. More benchmarks are needed to design and test the generality of the proposed approaches. This paper is the first to define the requirements on these benchmarks. It highlights that there are only two benchmarks that can be used for supervised learning among the six publicly available ones we found in the literature. We also illustrate how such a benchmark can be used with deep learning to successfully train and evaluate a failure prediction model. We raise several perspectives for research.https://www.mdpi.com/2227-9709/8/4/68Industry 4.0predictive maintenancedata miningfailure predictiondata collectionevaluation methodology |
| spellingShingle | Mouhamadou Saliou Diallo Sid Ahmed Mokeddem Agnès Braud Gabriel Frey Nicolas Lachiche Identifying Benchmarks for Failure Prediction in Industry 4.0 Informatics Industry 4.0 predictive maintenance data mining failure prediction data collection evaluation methodology |
| title | Identifying Benchmarks for Failure Prediction in Industry 4.0 |
| title_full | Identifying Benchmarks for Failure Prediction in Industry 4.0 |
| title_fullStr | Identifying Benchmarks for Failure Prediction in Industry 4.0 |
| title_full_unstemmed | Identifying Benchmarks for Failure Prediction in Industry 4.0 |
| title_short | Identifying Benchmarks for Failure Prediction in Industry 4.0 |
| title_sort | identifying benchmarks for failure prediction in industry 4 0 |
| topic | Industry 4.0 predictive maintenance data mining failure prediction data collection evaluation methodology |
| url | https://www.mdpi.com/2227-9709/8/4/68 |
| work_keys_str_mv | AT mouhamadousalioudiallo identifyingbenchmarksforfailurepredictioninindustry40 AT sidahmedmokeddem identifyingbenchmarksforfailurepredictioninindustry40 AT agnesbraud identifyingbenchmarksforfailurepredictioninindustry40 AT gabrielfrey identifyingbenchmarksforfailurepredictioninindustry40 AT nicolaslachiche identifyingbenchmarksforfailurepredictioninindustry40 |