Design and development of predictive maintenance in manufacturing equipment using machine learning methods
The digital transformation of production systems enables the production of large volumes of multivariate time series, which in turn facilitates the continuous monitoring of production assets. The modelling of multivariate time series can reveal the way parameters evolve as well as the influence amon...
| Κύριος συγγραφέας: | |
|---|---|
| Άλλοι συγγραφείς: | |
| Γλώσσα: | English |
| Έκδοση: |
2023
|
| Θέματα: | |
| Διαθέσιμο Online: | https://hdl.handle.net/10889/25409 |
| id |
nemertes-10889-25409 |
|---|---|
| record_format |
dspace |
| spelling |
nemertes-10889-254092023-07-07T03:54:33Z Design and development of predictive maintenance in manufacturing equipment using machine learning methods Σχεδιασμός και ανάπτυξη προγνωστικών αναλύσεων βιομηχανκού εξοπλισμού με χρήση μεθόδων μηχανικής μάθησης Μπαμπούλα, Ξανθή Bampoula, Xanthi Predictive maintenance Transformers Autoencoders Machine learning Προγνωστική συντήρηση Μετασχηματιστές Αυτοκωδικοποιητές Μηχανική μάθηση The digital transformation of production systems enables the production of large volumes of multivariate time series, which in turn facilitates the continuous monitoring of production assets. The modelling of multivariate time series can reveal the way parameters evolve as well as the influence amongst themselves. These data can be used in tandem with artificial intelligence methods to create insight upon the condition of production equipment, hence, potentially increasing the sustainability of existing production sites, by reducing waste and production downtime. In this context, LSTM-Autoencoders and a Transformer encoder are investigated in this study to enable predictive analytics through spatial and temporal time series forecasting. These neural networks are applied in combination upon a real-world dataset, targeting an efficient model for RUL estimation. The aforementioned methodology is implemented into a software prototype which is trained and tested in a real-world steel industry case. No sponsors Η Τέταρτη Βιομηχανική Επανάσταση οδήγησε στην αυτοματοποίηση και τον ψηφιακό μετασχηματισμό των συστημάτων παραγωγής επιτρέποντας την συνεχή παρακολούθηση των μηχανών μέσω αισθητήρων. Οι τεχνολογίες που επιτρέπουν τη διαχείριση και την επεξεργασία του τεράστιου όγκου δεδομένων αποτελούν κρίσιμα στοιχεία της εποχής μας. Μέθοδοι και δίκτυα τεχνητής νοημοσύνης, ειδικά Αυτοκωδικοποιητές σε συνδυασμό με Δίκτυα Μακράς Βραχύχρονης Μνήμης και Μετασχηματιστές, διερευνώνται σε αυτή τη εργασία για προγνωστική ανάλυση. Τέλος, στόχος είναι η ενίσχυση της παραγωγής με τη μείωση των βλαβών των μηχανών και του χρόνου διακοπής λειτουργίας με τη μείωση των περιττών συντηρήσεων. Η προτεινόμενη μεθοδολογία δοκιμάζεται σε ένα πραγματικό σύνολο δεδομένων προερχόμενο από μία βιομηχανία χάλυβα. 2023-07-06T14:00:48Z 2023-07-06T14:00:48Z 2023-07-05 https://hdl.handle.net/10889/25409 en None; None Attribution-NonCommercial-NoDerivs 3.0 United States http://creativecommons.org/licenses/by-nc-nd/3.0/us/ application/pdf |
| institution |
UPatras |
| collection |
Nemertes |
| language |
English |
| topic |
Predictive maintenance Transformers Autoencoders Machine learning Προγνωστική συντήρηση Μετασχηματιστές Αυτοκωδικοποιητές Μηχανική μάθηση |
| spellingShingle |
Predictive maintenance Transformers Autoencoders Machine learning Προγνωστική συντήρηση Μετασχηματιστές Αυτοκωδικοποιητές Μηχανική μάθηση Μπαμπούλα, Ξανθή Design and development of predictive maintenance in manufacturing equipment using machine learning methods |
| description |
The digital transformation of production systems enables the production of large volumes of multivariate time series, which in turn facilitates the continuous monitoring of production assets. The modelling of multivariate time series can reveal the way parameters evolve as well as the influence amongst themselves. These data can be used in tandem with artificial intelligence methods to create insight upon the condition of production equipment, hence, potentially increasing the sustainability of existing production sites, by reducing waste and production downtime. In this context, LSTM-Autoencoders and a Transformer encoder are investigated in this study to enable predictive analytics through spatial and temporal time series forecasting. These neural networks are applied in combination upon a real-world dataset, targeting an efficient model for RUL estimation. The aforementioned methodology is implemented into a software prototype which is trained and tested in a real-world steel industry case. |
| author2 |
Bampoula, Xanthi |
| author_facet |
Bampoula, Xanthi Μπαμπούλα, Ξανθή |
| author |
Μπαμπούλα, Ξανθή |
| author_sort |
Μπαμπούλα, Ξανθή |
| title |
Design and development of predictive maintenance in manufacturing equipment using machine learning methods |
| title_short |
Design and development of predictive maintenance in manufacturing equipment using machine learning methods |
| title_full |
Design and development of predictive maintenance in manufacturing equipment using machine learning methods |
| title_fullStr |
Design and development of predictive maintenance in manufacturing equipment using machine learning methods |
| title_full_unstemmed |
Design and development of predictive maintenance in manufacturing equipment using machine learning methods |
| title_sort |
design and development of predictive maintenance in manufacturing equipment using machine learning methods |
| publishDate |
2023 |
| url |
https://hdl.handle.net/10889/25409 |
| work_keys_str_mv |
AT mpampoulaxanthē designanddevelopmentofpredictivemaintenanceinmanufacturingequipmentusingmachinelearningmethods AT mpampoulaxanthē schediasmoskaianaptyxēprognōstikōnanalyseōnbiomēchankouexoplismoumechrēsēmethodōnmēchanikēsmathēsēs |
| _version_ |
1771297205339029504 |
