Influence of synchronization within a sensor  network on machine learning results

Dorst, Tanja; Robin, Yannick; Eichstädt, Sascha; Schütze, Andreas; Schneider, Tizian

doi:https://doi.org/10.5194/jsss-10-233-2021

Articles | Volume 10, issue 2

https://doi.org/10.5194/jsss-10-233-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/jsss-10-233-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 10, issue 2

Regular research article

|

24 Aug 2021

Regular research article |

| 24 Aug 2021

Influence of synchronization within a sensor network on machine learning results

Tanja Dorst, Yannick Robin, Sascha Eichstädt, Andreas Schütze, and Tizian Schneider

Data sets

Sensor data set of 3 electromechanical cylinder at ZeMA testbed (2kHz) T. Dorst https://doi.org/10.5281/zenodo.3929385

Model code and software

Automated ML Toolbox for Cyclic Sensor Data T. Dorst, Y. Robin, T. Schneider, and A. Schütze https://github.com/ZeMA-gGmbH/LMT-ML-Toolbox

Short summary

Synchronization problems within distributed sensor networks are a major challenge in the field of Industry 4.0. In this paper, artificially generated time shifts between sensor data and their influence on remaining useful lifetime prediction of electromechanical cylinders are investigated. It is shown that time shifts within sensor data lead to poor remaining useful lifetime predictions. However, this prediction can be significantly improved using various methods as shown in this contribution.