Content
This module offers a hands-on introduction to data management, digital twins, and machine learning in an engineering context. It focuses on the role of data as a foundation for informed decision-making and innovative product development. Students are introduced to the concept of digital twin models and how real-world data can be integrated into system simulations. In parallel, the module covers essential principles of research data management, with particular emphasis on the FAIR data principles. Building on this foundation, students explore core machine learning concepts and understand how optimization techniques are used in both the design and training of learning models. Practical programming exercises and real-world case studies are used throughout to deepen the understanding of data-driven modeling and prediction.
Learning Objectives
By the end of the module, students will have a solid understanding of how data supports engineering development and system design. They will be able to explain the purpose and structure of digital twins, apply key principles of research data management, and evaluate the quality and reusability of data. In addition, they will gain fundamental knowledge of supervised and unsupervised machine learning techniques as well as theoretical and algorithmic optimization methods used in model training. Students will be equipped with practical programming skills that enable them to independently analyze engineering data and apply machine learning methods to solve real technical problems.
Course Structure
Aimed at Master’s students, this module combines theoretical input with a strong emphasis on practical application. Teaching is delivered through lectures and hands-on programming exercises, where students work with real datasets and engineering challenges. The course content is structured to move from data fundamentals toward increasingly complex machine learning applications, with a focus on applied problem-solving. Students will gain experience in developing basic data workflows, training ML models, and using visualization techniques. The module concludes with a 90-minute written exam assessing both theoretical knowledge and practical application.
Leistungsumfang: 5LP
Register for the event on StudIP.
Ansprechperson
