Hands-on labs for the Innovative Industrieproduktions module — applying data science and simulation methods to real production data from a Learning Factory environment.
| # | Lab | Topic | Folder |
|---|---|---|---|
| 1 | Data Preparation | Cleaning, merging, and exploring production data with Pandas | labs/01_data_preparation |
| 2 | Regression Modeling | Building and evaluating a Decision Tree model to predict production durations | labs/02_regression |
| 3 | Process Mining | Discovering process flows and comparing planned vs. actual execution with pm4py | labs/03_process_mining |
| 5 | Discrete Event Simulation | Simulating a manufacturing flow shop with setup times and queues using SimPy | labs/05_simulation |
The labs 1 and 2 follow the CRISP-DM methodology and build on each other — data preparation produces the dataset used by a regression. The labs 3 - 5 are based on the previous learnings and extend the scope.
- Introduction to data analysis
- Big data processes and statistical foundations
- Big data methods and technologies
- Technological innovations as drivers of Industry 4.0
- Cyber-physical systems and decentralized control structures in digital value networks
- Applications and potential of big data and cloud computing
- Work and education in the age of digitalization
- Production systems and value networks of the future (Smart Factory)
Upon successful completion, students will be able to
- understand the role of process thinking in logistics and supply chain management, and identify key characteristics of processes.
- distinguish IT systems for modeling and supporting operational processes, and describe the potential of digitalization through digital twin concepts.
- name and characterize the different phases of the industrial revolution.
- identify societal developments and implications for the workplace resulting from digitalization and Industry 4.0.
- describe technological developments and innovations driving Industry 4.0, and apply the opportunities created by digitalization to develop innovative business models.
- recognize the potential of decentralized control structures in digital value networks enabled by digitalization, and describe cyber-physical systems, their functionality, and their significance for real-time control of industrial production.
- present the implications and potential of digitalization for industrial processes and production in a structured manner.
- demonstrate the improved analytical capabilities through big data applications in business practice, and explain the significance of cloud computing in an industrial context.
- describe the impact of digitalization on the design of future production systems and value networks, and explain the connections to other societal domains such as education and research.
- Bauernhansel, T. / Hompel, M. ten / Vogel-Heuser, B. (Hrsg.) (2014): Industrie 4.0 in Produktion, Automatisierung und Logistik. Springer Vieweg, Wiesbaden.
- Disselkamp, M. (2012): Innovationsmanagement. Instrumente und Methoden zur Umsetzung im Unternehmen. 2. Auflage, Springer Gabler, Wiesbaden.
- Fost, M. (2014): E-Commerce-Strategien für produzierende Unternehmen. Springer Gabler, Wiesbaden.
- Hausladen, I. (2014): IT-gestützte Logistik. Systeme, Prozesse, Anwendungen. 2. Auflage, Springer Gabler, Wiesbaden.
- Schenk, M. (Hrsg.) (2015): Produktion und Logistik mit Zukunft. Digital Engineering and Operation. Springer Vieweg, Wiesbaden.
- Wolf-Kluthausen, H. (Hrsg.) (2016): Jahrbuch Logistik 2016. free beratung GmbH, Korschenbroich.