2512101 – Seminar: From Physical Models to Digital Twins: A Data-Driven Simulation Workshop (Master)

General Information

Important Information
This seminar focuses on the data-driven discovery of simulation models in industrial settings, providing a hands-on approach to understanding and optimizing production processes.
Students will start by designing and constructing production lines using Lego Spike and similar modular systems. This activity will include developing comprehensive data-capturing pipelines to collect detailed event-logging raw data from their production lines.
Next, the seminar will explore advanced techniques for transforming this raw data into simulation models, e.g., Petri nets. Participants will learn and apply data-driven model extraction methods, such as process mining to extract workflow processes; statistical methods to fit probability distributions and analyse trends and machine learning algorithms to model complex behaviours within the production process. Through these techniques, students will extract simulation models that reflect the real-world dynamics of their production lines. The seminar will then guide participants on how to validate the extracted simulation models to ensure their accuracy.
By the end of the seminar, students will be equipped with the skills to build model production lines, collect event logging data from them, transform event log data into actionable simulation models and use these models to drive efficiency and innovation in industrial production settings.

General

Language
English
Copyright
All rights reserved

Availability

Access
Unlimited
Admittance
You have to request for membership to access this course. Please describe your interest for becoming member in the message form. You will be notified as soon as an administrator has accepted or declined your request.
Registration Period
Unlimited

Personal Data Visible to Course Administrators

Data Types of the Personal Profile
Username
First Name
Last Name
E-Mail
Matriculation number

Additional Information

Object-ID
3567127