Summary information – BeverGreen significantly improves the energy and resource efficiency of the beverage industry through networking and the use of digital tools across the value chain. To this end, green digital product and process twins are being created for CO2-neutral transformation from the production process to reusable logistics. The development and use of digital twins (DT) and machine learning (ML) to increase transparency and reduce emissions will be demonstrated using exemplary application scenarios from the beverage industry. Building on the Da-Pro research project, the consortium of family and owner-managed companies from the German brewing industry, as well as solution and research partners from the fields of ML and DT, has been expanded to include the user Kontor N, two start-ups and the research partners Technical University Munich (TUM) and University of Applied Sciences Zwickau (WHZ) with regard to comprehensive circular value chains and expertise in domain-specific ontologies.
General information about the project
Project term:
01.05.2023 to 31.04.2026
Project lead:
Prof. Dr. Christoph Laroque
Sub-project lead WHZ
Cooperation partners:
Bitburger Braugruppe GmbH, Augustiner-Bräu Wagner KG, RapidMiner GmbH, Kontor N GmbH & Co. KG, RIF e. V., TU München, PRECOGIT GmbH, daibe UG
Project description
Rising energy and raw material costs, limited resources, climate change initiatives and new supply chain resilience requirements are driving a paradigm shift in manufacturing companies and even entire value networks. Digital technologies offer new ways to analyse energy and resource consumption and material cycles, and to derive data-driven improvements. The BeverGreen research project builds on this.
A support system will be developed to map existing data structures to application-specific ontologies that contain energy-relevant information and form the basis for green DCs. It will also form the basis for linking other internal and external data sets (e.g. life cycle assessment databases), e.g. on CO2 equivalents (CO2e). The core objective is to develop Green DCs in combination with ML that have a lighthouse character by identifying and realising energy and resource savings in exemplary application scenarios and serve the sustainable transformation of the beverage industry. The focus is on closed-loop applications in production and closed-loop value chains in the beverage and brewing industry.
Our contribution
Together with the TUM, the WHZ is developing a simulation model of a cross-sector value network in the beverage and brewing industry as an instrument for testing and evaluating solutions for the emerging digital twins (DT) and services. On the one hand, the simulation will serve for a complete evaluation of processes and systems on the basis of (historical) real data of the partners, and on the other hand, it will provide an instrument for targeted data generation and evaluation. Such a virtual instance of the value network of the beverage and brewing industry should also be available as a tool for data generation and knowledge discovery, for example providing data for determining the product carbon footprint along the supply chain.
The use of simulation as a virtual test system is proving to be profitable, as different scenarios can be tested in a risk-free, digital environment. Following the targeted data generation and knowledge discovery in the simulation data, the findings are incorporated into the resulting ontologies.
The WHZ researchers are also contributing their expertise in the field of backward simulation. The resulting simulation model will also be used to provide an IT service for coordinating the circular value chain via the cross-sector value creation network. This is linked to a sub-model of the emerging simulation model by considering the material flow starting from the last process stages and targets of the value chain. The backward simulation concretises the inversion of the flow logic including the implemented control and priority rules and the backward execution. The IT service is intended to contribute to demand-oriented cycle and replenishment planning on the basis of Green DT and to unlock the potential for improvement behind it.
