Data Science in EngineeringModule description #30855 / Version 4
- 3 CP
- Portfolio examination
- Graded
- Summer semester
- German
This module description is not valid in the current semester (Winter semester 2026/27).
Current version (v6)
| Module / Version | #30855 / #4 |
|---|---|
| Validity | Winter semester 2023/24 – Winter semester 2024/25 |
| Available language(s) | German |
| Credit points | 3 |
| Person responsible for the module | Repke, Jens-Uwe |
| Grading | Graded |
| Exam format | Portfolio examination |
| Language(s) of instruction | German |
Affiliation
| Faculty | Fakultät III |
|---|---|
| Institute | Institut für Prozess und Verfahrenstechnik |
| Academic chair | 33351500 FG Dynamik und Betrieb technischer Anlagen |
Contact
| Office | KWT 9 |
|---|---|
| Contact person | Hoffmann, Christian |
| E-mail address | lehre@dbta.tu-berlin.de |
| Website | https://www.tu.berlin/dbta/studium-lehre/lehrveranstaltungen-ii/data-science-in-process-engineering |
Learning outcomes
The students
- get an overview of modern methods of data science in engineering with a focus on chemical engineering
- know the basic methods of data pre-treatment, feature extraction and are able to apply them
- have an overview of methods for data-driven modeling, training methods of machine learning and can apply them independently to process engineering examples using freely available frameworks in Python.
- get an overview of modern methods of data science in engineering with a focus on chemical engineering
- know the basic methods of data pre-treatment, feature extraction and are able to apply them
- have an overview of methods for data-driven modeling, training methods of machine learning and can apply them independently to process engineering examples using freely available frameworks in Python.
Content
- Basics of data pre-treatment like multicollinearity, linear dependencies, imputation of missing values, anomaly detection, handling of outliers,
- feature selection and extraction methods using, for example, step-wise variable selection, Lasso, L1/L2 regularization, and PCA,
- supervised machine learning methods to solve regression problems
- nonlinear methods such as support vector regression, Gaussian process regression, and artificial neural networks,
- recurrent neural networks for dynamic, data-driven modeling.
All content will be explained using process engineering examples.
- feature selection and extraction methods using, for example, step-wise variable selection, Lasso, L1/L2 regularization, and PCA,
- supervised machine learning methods to solve regression problems
- nonlinear methods such as support vector regression, Gaussian process regression, and artificial neural networks,
- recurrent neural networks for dynamic, data-driven modeling.
All content will be explained using process engineering examples.
Module components
Compulsory area
The following courses are mandatory for this module:
| Courses | Type | Number | Frequency | Language | Hours per week | Course catalog |
|---|---|---|---|---|---|---|
| Data Science in Engineering | Integrated course | Summer semester | [de] | 2 | ISIS |
Workload and credit points
Data Science in Engineering (Integrated course)
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Attendance time | 15 | 2 h | 30 h |
| Pre- and postprocessing | 15 | 1 h | 15 h |
| 45 h | |||
Course-independent workload
| Workload description | Multiplier | Hours | Total |
|---|---|---|---|
| Exam preparation | 1 | 10 h | 10 h |
| Semester task | 1 | 35 h | 35 h |
| 45 h | |||
The workload of the module adds up to 90 hours. The module therefore comprises 3 credit points.
Description of teaching and learning methods
- the course takes place as a weekly online lecture with exercise units integrated into the lecture,
- Before the exercise units, the students are provided with corresponding application examples as computer-aided tasks for independent work and the results are discussed in small groups.
- Before the exercise units, the students are provided with corresponding application examples as computer-aided tasks for independent work and the results are discussed in small groups.
Requirements for participation and examination
Desirable prerequisites for participation in the courses:
- Analysis I und II sowie Lineare Algebra für Ingenieure
- Numerische Methoden für Ingenieure
- Grundlagen der Programmierung / Informatik für Ingenieure
- Numerische Methoden für Ingenieure
- Grundlagen der Programmierung / Informatik für Ingenieure
Mandatory requirements for the module examination registration:
This module has no examination requirements.
Completion of the module
| Grading | Graded |
|---|---|
| Exam format | Portfolio examination |
| Type of portfolio examination | 100 points in total |
| Language | German |
Test elements
| Name | Points/Weight | Category | Duration/Extent |
|---|---|---|---|
| Oral feedback | 20 | oral | |
| Programming project | 80 | practical |
Exam description
- Programming project (semester assignment),
- Oral feedback.
- Oral feedback.
Duration of the module
The following number of semesters is estimated for taking and completing the module: 1 semester(s).
This module can be started in the following semesters: Summer semester.
Maximum number of participants
This module is not limited to a number of students.
Registration procedures
Registration via MTS in MOSES
Recommended reading, lecture notes
Lecture notes
unavailable
Electronic lecture notes
available
Recommended literature
- Applied predictive modelling (Kjell Johnson und Max Kuhn)
- Elements of statistical learning (Jerome Friedman et al.)
- Introduction to statistical learning (Gareth James et al.)
Assigned programs
This module version is used in the following programs:
| Program / program version | Semester(s) | Curriculum component |
|---|---|---|
| Chemical Engineering MSc_ChemIng_2020 | WS 2023/24 | Wahlpflichtmodule › Technische Chemie |
| SS 2024 | Wahlpflichtmodule › Technische Chemie |
Miscellaneous
Not specified