| Zugriffsnummer | 46640 |
| Dokumenttyp | Zeitschriftenartikel |
| Peer Review | mit Peer Review |
| Sprache | Englisch |
| Titel | Influence of synchronization within a sensor network on machine learning results |
| Autor(in); Institution |
Dorst, Tanja; ZeMA - Center for Mechatronics and Automation Technology gGmbH, Saarbrücken, GERMANY
Robin, Yannick; Lab for Measurement Technology, Department of Mechatronics, Saarland University, Saarbrücken, GERMANY
Eichstädt, Sascha; PSt, Präsidialer Stab, PTB-Berlin
Schütze, Andreas; ZeMA - Center for Mechatronics and Automation Technology gGmbH, Saarbrücken, GERMANY; Lab for Measurement Technology, Department of Mechatronics, Saarland University, Saarbrücken, GERMANY
Schneider, Tizian; ZeMA - Center for Mechatronics and Automation Technology gGmbH, Saarbrücken, GERMANY; Lab for Measurement Technology, Department of Mechatronics, Saarland University, Saarbrücken, GERMANY
|
| Quelle/Jahr | Journal of Sensors and Sensor Systems: 10 (2021), 2, 233 - 245 |
| ISSN | 2194-8771 (PRINT) ; 2194-878X (ONLINE) |
| DOI | |
| Verlag | Göttingen: Copernicus |
| Freie Schlagworte | sensor network ; uncertainty ; condition monitoring ; synchronisation |
| Zusammenfassung | Process sensor data allow for not only the control of industrial processes but also an assessment of plant conditions to detect fault conditions and wear by using sensor fusion and machine learning (ML). A fundamental problem is the data quality, which is limited, inter alia, by time synchronization problems. To examine the influence of time synchronization within a distributed sensor system on the prediction performance, a test bed for end-of-line tests, lifetime prediction, and condition monitoring of electromechanical cylinders is considered. The test bed drives the cylinder in a periodic cycle at maximum load, a 1 s period at constant drive speed is used to predict the remaining useful lifetime (RUL). The various sensors for vibration, force, etc. integrated into the test bed are sampled at rates between 10 kHz and 1 MHz. The sensor data are used to train a classification ML model to predict the RUL with a resolution of 1 % based on feature extraction, feature selection, and linear discriminant analysis (LDA) projection. In this contribution, artificial time shifts of up to 50 ms between individual sensors' cycles are introduced, and their influence on the performance of the RUL prediction is investigated. While the ML model achieves good results if no time shifts are introduced, we observed that applying the model trained with unmodified data only to data sets with time shifts results in very poor performance of the RUL prediction even for small time shifts of 0.1 ms. To achieve an acceptable performance also for time-shifted data and thus achieve a more robust model for application, different approaches were investigated. One approach is based on a modified feature extraction approach excluding the phase values after Fourier transformation; a second is based on extending the training data set by including artificially time-shifted data. This latter approach is thus similar to data augmentation used to improve training of neural networks. |
| Kostenfreier Zugang | Open Access Gold |
| Rechteinformation | CC BY 4.0 ; Creative Commons Attribution 4.0 License |
| Themenbereich der Metrologie | Mathematik und metrologische Informationstechnik |
| Forschungsprojekt | 17IND12: Met4FoF: Metrology for the Factory of the Future |
| Förderinformationen (1) |
Förderername: European Commission (EC)
Förderer ID: 0000 0001 2242 8989 Förderer ID Typ: ISNI Förderprogramm: EMPIR 2017 Industry Titel der Förderung: 17IND12: Met4FoF: Metrology for the Factory of the Future Förderungsnummer: 17IND12 |