Software Engineering for Machine Learning Applications in Manufacturing (SEML)

The tutorial ‘Software Engineering for Machine Learning Applications in Manufacturing (SEML)’ provides prospective engineers studying for a master's degree with a detailed insight to software engineering and machine learning. For an optimal combination of theory and practice, not only are different methods of machine learning taught in theory, but they are also implemented in a real practical project along a software development process. The practical project involves the development of an AI-based wear detection system for 3-axis milling machines using acceleration sensor data on the spindle.

Organizational

Event-type Tutorium (Master)
Cycle Winter semester
Time frame 4 Credit Points theory part (full time) and practical part (part time)
Language English
Dates The tutorial will take place during the 2026/2027 winter semester and consists of a theoretical and a practical component.

Theoretical part: November 2, 2026 – November 9, 2026 (6 days full-time)
Data collection: scheduled time slots November 23, 2026 – November 24, 2026, 12:30 PM – 4:00 PM
Practical component: November 9, 2026 – January 25, 2027 (part-time)
Exam: January 18, 2027, 10:00 a.m. – 10:30 a.m. (date and time subject to change)
Oral exam/final presentation: scheduled time slots January 25, 2027 – January 26, 2027, 12:30 PM – 4:30 PM (by appointment)
Lecturer Lukas Hammen M.Sc.
Florian Mitschke M.Sc.
Stefan Schulte M.Sc.
Kevin Zhao M.Sc.
Contact address
Contact person Lukas Hammen M.Sc.
Room L1|14 FlowFactory Seminarraum

Registration

Registration process Registration via contact person with waiting list

The number of participants is limited to 20 students. If you are interested, please send an email to first. As soon as you receive a positive response from the organizers by e-mail, you can register in TUCaN.

If you only register via TUCaN and are not registered at the department, your registration is considered invalid and will be removed from the TUCaN registration. If there are more registrations than the maximum number of participants, a selection will be made with regard to the order of registration.

TUCaN course: 16-09-4274-tt Tutorial Software Engineering for Machine Learning Applications in Manufacturing.
Participant numbers Maximum 20

Exam

Examination notes The exam of Winter Semester 2026/2027 will take place on Monday, 18.01.2027 from 10:00 – 10:30 am.
The oral exam and final presentation (60 min) will take place on scheduled time slots for each group by appointment January 25, 2027 – January 26, 2027, 12:30 PM – 4:30 PM.

No aids other than a document-proof blue or black pen are permitted for the examination. This also applies to calculators and drawing instruments such as a set square or ruler.

Please remember to bring a valid official photo ID.

Content

Aims The aim of the tutorial is to familiarize you with the methods of machine learning and professional software development in the context of production, both theoretically and practically. Using the example of the development process of a wear detection software solution based on acceleration sensor data on the spindle of 3-axis milling machines, you will apply the theoretical knowledge practically in the PTW FlowFactory.
Contents To this end, you will be able to:

1. explain and independently apply methods and instruments of professional software development:
  • Use of programming language Python
    • Fundamentals of object-oriented programming
    • Use of software tests for quality assurance
  • Use of the version management software Git
  • Use of Linux in development

2. explain methods and instruments of machine learning and apply them independently in the context of production:
  • dealing with established process models (CRISP-DM, etc.)
  • explain and select suitable machine learning approaches (regression, classification, etc.) for given use cases
  • explanation and selection of suitable deep learning approaches for given use cases
  • use of relevant Python libraries in the context of machine learning (NumPy, Pandas, scikit-learn, Keras)

3. develop and implement selected solutions for problems in the context of production together in a team

4. plan and operations conduct data acquisition

5. compile, present and critically evaluate the results in a clear manner
Previous knowledge / training Prior knowledge of programming with Python is required. Unfortunately, no basic course in programming with Python can be given during the tutorial. Lack of previous knowledge will lead to a higher familiarization effort for the programming tasks during the tutorial. References for familiarization with Python will be sent to the participants before the tutorial starts.
Note For the execution of the exercises in the theory part as well as the processing of the practical part, an own mobile PC/laptop is required.

Contact

  Name Working area(s) Contact
Lukas Hammen M.Sc.
CiP | Center for Industrial Productivity
+49 6151 8229-723
L1|01 225
Florian Mitschke M.Sc.
CiP | Center for Industrial Productivity
+49 6151 8229-641
L1|01 225
Stefan Schulte M.Sc.
CiP | Center for Industrial Productivity
+49 6151 8229-614
L1|01 225
Kevin Zhao M.Sc.
CiP | Center for Industrial Productivity
+49 6151 8229-615
L1|01 233