Research Team Supply Chain Digitalization
Digitalization is ubiquitous, and thus supply chains are thoroughly disrupted by its emerging phenomena, such as Industrie 4.0 and Big Data. Within the first research area of Supply Chain Digitalization, the chair wants to meet the challenges that come with it, identify, and exploit opportunities that arise. To achieve this, the chair conducts research on emerging trends such as Supply Chain Performance Measurement, Production Planning under Industrie 4.0 and Predictive Maintenance and investigates how supply chain digitalization can facilitate through the means of Computational Intelligence and Supply Chain Analytics.
The research team Supply Chain Digitalization (fLTR):
- Raquel Mello, M.Sc. (firstname.lastname@example.org).
- Frauke Hellweg, M.Sc. (email@example.com).
- Kevin Wesendrup, M.Sc. (firstname.lastname@example.org).
- Dennis Horskemper, M.Sc. (email@example.com).
- Sandra Lechtenberg, M.Sc. (firstname.lastname@example.org).
- Lucas Stampe, M.Sc. (email@example.com).
- Predictive Maintenance, Prognostics and Health Management
- Supply Chain Analytics, Machine Learning for Transport Planning
- Optimization and Analytics, Automated Design of Optimizers for Supply Chain Planning
- Performance Measurement Sytems, Performance Measures
- Supply Chain Risk Management
Teaching of WT 2021/22
- BA-PS Advanced Service Parts Forecasting
Spare parts are characterized by sporadic and intermittent demands that make prediction difficult. Although many algorithms, from exponential smoothing to Croston's method, have been researched, often only the simplest methods are used in practice. Besides the complexity of accurate algorithms, the implementation and embedding in a wide enterprise landscape is a major difficulty. Furthermore, new potentials arise from artificial intelligence methods and new data sources (e.g. sensors). This project seminar deals with the development of a future concept for spare parts forecasting, which can exploit the unused potentials, taking into account the numerous difficulties of spare parts demand forecasting.
- MA-PS Predictive Maintenance for AIOps
The emergence of digitalization results in the need for IT operations to become more flexible and adapt to new infrastructure. AIOps (Artificial Intelligence for IT Operations) are a new approach to IT operations considering big data and machine learning as its central components. A reliably working infrastructure is essential for a successful application of AIOps. Hence, this project seminar focuses on the idea to apply predictive maintenance to IT infrastructure. The project is conducted in cooperations with IQ-optimize.
MA-PS Data Analytics for Supply Chain Performance Measurement
Today’s business environment requires supply chains to be proactive rather than reactive, demanding a new approach for supply chain performance measurement systems (SCPMS) which includes data analytics. This project seminar addresses the topic of data analytics-driven SCPMS (DA-SCPMS) focusing on forecast scenarios for supporting both the identification and management of complex and uncertain decision-making. Students collaborating with this seminar are expected to design and implement a DA-SCPMS prototype in the context of forecast scenarios in cooperation with thyssenkrupp Materials Services GmbH.
- MA-CS Supply Chain Analytics
Due to emerging technologies, storing and processing more data than ever before becomes possible. Hence, (big) data analytics gains currency over various industries. Supply Chain Management also starts to apply data analytics to gain new insights, adapt processes or even optimize the supply chain. However, implementing analytics is not an easy endeavour and various challenges need to be tackled before reaping the expected benefits.
This seminar will look into supply chain analytics (SCA) and discuss it from various views. Topics both include application cases of SCA and issues surrounding the implementation process such as necessary capabilities.
Teaching of ST 2021
- BA-VM-WI Digitale Supply Chains
Digitalization is omni-present and especially supply chains are disrupted by emerging phenomenons like industry 4.0 or big data. This specialization module will focus on the challenges and resulting chances of digital supply chains.
- MA-PS Return-Flow-of-Goods Process Analysis @ CLAAS
Global return parts logistics is often an intransparent and highly complex process as is the case with CLAAS. Our partners at CLAAS would therefore like to gain a clearer picture of their return parts logistics processes. Thus, in this project seminar, first the as-is situation should be mapped on the basis of existing data and expert knowledge. Subsequently, possible optimization potentials should be identified to envision a to-be process.
- MA-PS Data Analytics Driven Forecasting @ Warsteiner
The demand behaviour in beer industry is highly influenced by various internal and external factors so that demand forecasting solely based on historical sales data does not produce satisfying results. Hence, Warsteiner would like to work with you to improve their demand forecasts. The goal will be to not only to explore suitable input factors, select the best algorithm and implement it but also to sum it up in a new forecasting concept for Warsteiner’s products.
- MA-CS Predictive Maintenance
With emerging modern technology, machines become more complex and the costs for maintaining these systems increase manifold. Therefore, companies choose a Predictive Maintenance (PdM) strategy that reduces costs, by only maintaining systems when necessary. In this conventional seminar, you will explore the different steps of Predictive Maintenance, gain insights into state-of-the-art research by writing your seminar thesis, and apply your acquired knowledge within practical case studies.
We offer various topics in the areas of our past theses, which can be seen here:
- Frauke Hellweg. Examples:
Developing a Maturity Model for Digital Supply Chains,
- Dennis Horstkemper
- Sandra Lechtenberg. Examples: Minimizing empty runs by including backloads in the dynamic environment of a freight exchange
- Raquel Mello
- Kevin Wesendrup. Example: Improving Production Planning and Control through Predictive Maintenance – An Expert Interview Study
- Lucas Stampe
If you are interested in one of these areas, you can write a mail to the corresponding person, and we will work out a topic together!
- Hellweg, F., Lechtenberg, S., Hellingrath, B., & Thomé, A. M. T. (2021). Literature Review on Maturity Models for Digital Supply Chains. Brazilian Journal of Operations & Production Management. (Accepted)
- Wagner, C., & Hellingrath, B. (2021). Supporting the Implementation of Predictive Maintenance — a Process Reference Model. International Journal of Prognostics and Health Management, Vol. 12(002).
- Wesendrup, K., & Hellingrath, B. (2020). A Process-based Review of Post-Prognostics Decision-Making. In Proceedings of the 5th European Conference of the PHM Society, Virtual.
- Mello, R., Hellingrath, B., & Martins, R. (2019). Big Data Analytics in Supply Chain Performance Measurement Systems. In Proceedings of the 26th International Annual European Operations Management Association Conference, Helsinki, Finland.