Predictive Maintenance
The participants learn to independently explore and understand a given topic and present it to the other participants in a concise and coherent way.
| Intended Participants | Bachelor students / Master students |
| Instructors | Myra Spiliopoulou, Benjamin Noack |
| SWS | 2 |
| Credits | 5 (Bachelor) / 6 (Master) |
| Languages | English / German |
| Prerequisites |
basics of linear algebra and calculus,
ideally some knowledge of signal processing and data analysis |
| Kick-Off | see elearning |
Course Description
Predictive maintenance has become a key element in modern industrial processes for ensuring optimal equipment utilization and minimizing downtimes.It demands data engineering and learning methods for the detection of operational anomalies, for the estimation of the remaining useful life of a machine or component, for the forecasting of disruptive events in an industrial process etc. This module builds on data processing methods and intelligent technologies. We are going to discuss extensions for anomaly detection, prediction and estimation on timestamped data.
In this seminar, the participants will learn about
- challenges and methods for data acquisition in industrial processing
- data analysis tool in predictive maintenance
- process modeling, fault detection, and state prediction
Each seminar assignment will encompass collecting, reading, commenting and comparing scientific publications in a predictive maintenance topic. The assignments for bachelor students will be smaller.
Registration
elearning (please register in elearing for kickoff meeting)
Seminar topics will be assigned in the kick-off meeting.
For any additional questions regarding the project or for any issues with registration, please email
or