Projektseminar
| Credits | 10 SWS, 10 ECTS |
| Contact | Gregor Döhner and Axel Zimmermann |
| Sessions | Tuesday and Thursday, lecture and hands-on 13:30-15:00 for 4 weeks, then independent project phase |
| Rooms | MW 1701 and 1702 (lecture and hands-on) |
| Type | introductory seminar |
|---|---|
| Term | Wintersemester 2024/25 |
| Language of instruction | English |
Admission information
See TUMonline
Note: Note: Application with CV and proof of performance. Admission to the course takes place after an interview (in groups).
Note: Note: Application with CV and proof of performance. Admission to the course takes place after an interview (in groups).
Objectives
After successfully completing the module, students will have knowledge of the theory of thermoacoustics, fundamental expertise in the field of data science and machine learning as well as advanced skills in using Python. They will also be trained to work in a project group.
Description
Students are introduced to the basics of flame modeling in order to then design software packages for modeling (partly) turbulent combustion processes on their own. First, the underlying physics and current modeling strategies are discussed. Then, current models from the field of machine learning are explained and implemented.
Python is used as the programming environment.
At the beginning of the project seminar, the following theoretical focal points will be covered:
(1) Relevance of combustion
(2) Basics of combustion
(3) Fundamentals of acoustics
(4) Basics of thermoacoustics
(5) Basics of machine learning
(6) Advanced machine learning methods
At the same time, the students are familiarized with Python through coding sessions and thus acquire the basics of this programming language in small practical tasks.
This is followed by work in small project groups and the students develop a solution strategy for their task on their own responsibility. The results are documented in a clearly commented Python code and a written report (10 pages).
Python is used as the programming environment.
At the beginning of the project seminar, the following theoretical focal points will be covered:
(1) Relevance of combustion
(2) Basics of combustion
(3) Fundamentals of acoustics
(4) Basics of thermoacoustics
(5) Basics of machine learning
(6) Advanced machine learning methods
At the same time, the students are familiarized with Python through coding sessions and thus acquire the basics of this programming language in small practical tasks.
This is followed by work in small project groups and the students develop a solution strategy for their task on their own responsibility. The results are documented in a clearly commented Python code and a written report (10 pages).