Machine learning for condition monitoring of technical assets and systemsModule description #41041 / Version 2
- 6 CP
- Oral exam
- Graded
- Winter and summer semester
- German
| Module / Version | #41041 / #2 |
|---|---|
| Validity | Since Winter semester 2024/25 |
| Available language(s) | German |
| Credit points | 6 |
| Person responsible for the module | Gühmann, Clemens |
| Grading | Graded |
| Exam format | Oral exam |
| Language(s) of instruction | German |
Affiliation
| Faculty | Fakultät IV |
|---|---|
| Institute | Institut für Energie und Automatisierungstechnik |
| Academic chair | 34311600 FG Elektronische Mess- und Diagnosetechnik |
Contact
| Office | EN 13 |
|---|---|
| Contact person | Gühmann, Clemens |
| E-mail address | clemens.guehmann@tu-berlin.de |
| Website | https://www.mdt.tu-berlin.de/menue/home/ |
Learning outcomes
After completing the module, students have in-depth knowledge in the area of condition monitoring for condition-based and predictive maintenance of technical plants and systems. Students will be able to detect anomalies in sensor data, classify errors found and carry out condition predictions. This includes the selection, independent and practical application as well as the scientifically based further development of suitable methods.
Content
The integrated course consists of lecture and exercise units. The lecture provides an introduction to the various maintenance strategies and their development. The role of data-driven methods of condition monitoring for condition-based and predictive maintenance of technical plants and systems is highlighted. Modern data-driven methods for fault detection, diagnosis and prognosis based on sensor data are learned in depth. In the exercise units, machine learning methods are applied to practical problems and solved with the help of Python.
Module components
Compulsory area
The following courses are mandatory for this module:
Workload and credit points
Maschinelles Lernen für die Zustandsüberwachung I (Integrated course)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
Maschinelles Lernen für die Zustandsüberwachung II (Integrated course)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance | 15 | 2 h | 30 h |
| Pre/post processing | 15 | 4 h | 60 h |
| 90 h | |||
The workload of the module adds up to 180 hours. The module therefore comprises 6 credit points.
Description of teaching and learning methods
The module contents are taught through an integrated course consisting of lecture and exercise parts. Weekly homework.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
Knowledge of the Python programming language.
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Oral exam |
| Language | German |
| Duration/Extent | 45 Minuten |
Duration of the module
The following number of semesters is estimated for taking and completing the module: 2 semester(s).
This module can be started in the following semesters: Winter and summer semester.
Maximum number of participants
The maximum capacity of participants is 35.
Registration procedures
The module starts in the winter semester.
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
unavailable
Recommended literature
- Bishop, C. M.: Pattern Recognition and Machine Learning, Information Science and Statistics (2006)
- Goodfellow, I.; Bengio, Y.; Courville, A.: Deep Learning. The MIT Press, 2016
- Hastie, Trevor; Tibshirani, Robert; Friedman, Jerome: The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition. Springer Series in Statistics (2009)
- Isermann, R.: Fault-Diagnosis Systems. An Introduction from Fault Detection to Fault Tolerance. Springer Verlag (2006)
- Korbicz, J.; Koscielny, J.M.; Kowalczuk, Z.; C holewa, W. (Eds.): Fault Diagnosis. Models, Artificial Intelligence, Application. Springer (2004)
- Raschka, S.; Mirjalili, Vahid: Machine Learning mit Python und Scikit-Learn und TensorFlow: Das umfassende Praxis-Handbuch für Data Science, Predictive Analytics und Deep Learning. Mittp (2017)
Assigned programs
This module version is used in the following programs:
| Program / program version | Semester(s) | Curriculum component |
|---|---|---|
| Automotive Systems Automotive Systems (M. Sc.) - StuPO 2017 | SS 2025 | Wahlpflichtbereich |
| WS 2025/26 | Wahlpflichtbereich | |
| SS 2026 | Wahlpflichtbereich | |
| WS 2026/27 | Wahlpflichtbereich |
Bauingenieurwesen (Master of Science) Computational Engineering Science (Informationstechnik im Maschinenwesen) (Master of Science) Computer Engineering (Master of Science) Computer Science (Informatik) (Master of Science) Elektrotechnik (Master of Science) Energie- und Verfahrenstechnik (Master of Science) Fahrzeugtechnik (Master of Science) Gebäudeenergiesysteme (Master of Science) Information Systems Management (Wirtschaftsinformatik) (Master of Science) Luft- und Raumfahrttechnik (Master of Science) Maschinenbau (Master of Science) Physikalische Ingenieurwissenschaft (Master of Science) Planung und Betrieb im Verkehrswesen (Master of Science) Process Energy and Environmental Systems Engineering (Master of Science) Produktionstechnik (Master of Science) Regenerative Energiesysteme (Master of Science) Scientific Computing (Master of Science) Statistic (Master of Science) Technomathematik (Master of Science) Wirtschaftsingenieurwesen (Master of Science)
Miscellaneous
Not specified