Digital twins are a virtual representation of a production system synchronized between the virtual and the real system, able to run different analytics based on sensed data and connected smart devices, optimized real-time communication protocols, and mathematical models. Industry 4.0 manufacturing paradigms exploit these features to forecast and optimize the behavior of the production system at each life cycle phase in real-time. Keeping interoperability and modularity at the core, VirMan project aims at the development of structural and functional semantic-based information models in order to build a digital twin for the virtual plant, assets or manufacturing process. Further tasks equip it with novel and real-time connectivity infrastructure and connected smart devices, setting up the data storage and processing environment, developing optimized artificial intelligence modules to analyze a large amount of data and developing advanced plant monitoring and predictive maintenance functionality, and visualization modules for reporting, real-time monitoring, and warning. The project outcomes include interoperable software and hardware modules for digital twin of a manufacturing plant based on ISA 95 and Industry 4.0 standards. TUK develops data-driven control, condition-monitoring and predictive maintenance algorithms in a use-case with the large water production enterprise Brandenburger Ustromquelle.

The objective of this project is to create a solution based on the digital twin of manufacturing environments in which the efficiency and quality of production will increase thanks to the information provided by rich production-related sensor data and geospatially enriched contextual data, AI-supported analytics and advanced monitoring/visualization.
In the scope of the project, different ontologies from different studies/domains will be merged, enriched according to needs of the industrial partners of the project by addition of classes about specific tools and machineries, production processes, raw material semi-product and products, creating a knowledge graph and the meta-model of the manufacturing plants. This meta-model will close the gap between raw data and expert knowledge, needed also for the AI models developed.

Predictive maintenance is a crucial process in manufacturing because both unexpected failures and too frequent maintenance are very costly in means of time and money. On the other hand, quality control is the process for ensuring customers get products free of defects and meet their requirements. The innovation will be developing self-service models and algorithms to predict defects by analysing the comprehensive data collected during production, called predictive maintenance. Using different state-of-the-art algorithms to leverage the large amount of data collected, new modules will be developed to predict maintenance cost and time of the machines, increasing the performance and accuracy of the results and products.

A big data platform, implemented with open and free software models will make it possible to develop modules and interoperable solutions, to ingest, synchronize, process and store the data. This data will be used for the services and visualization models, which will be merged in a single user interface between the digital twin and the end users, in form of a dashboard. The dashboard will show in real-time to providing 3D visualizations of factory, reports and daily results.

• Development of structural and functional model of the Digital Twin (DT) of a plant, implementing a comprehensive state of the art manufacturing ontology and knowledge graph.
• Development of self-learning AI models and algorithms to analyse comprehensive data about the machineries and increasing the performance and accuracy of the results continuously by learning from the data produced daily.
• Development of advanced Plant Monitoring and 3D visualisations of factory, augmented by analysis results and real time production data, closing the gap in the value chain, by providing interoperable, cost-effective module for presenting the analysis results and insights to the users.
• Development of a smart gateway that will meet challenges like heterogeneity, existence of static and mobile nodes at the same time, transmission of data to the required distances, security and efficiency.

• Smart Manufacturing
• Predictive Maintenance
• Digital Twins
• Big Data Visualisations

May 2021 - April 2023

• Ximaj IT-Solutions (Germany)
• sysGen (Germany)
• Accuro (Spain)
• Starflow (Spain)
• ForteArGe (Turkey)
• Karel (Turkey)
• EBP (Turkey)

Prof. Dr.-Ing. Naim Bajcinca
Gottlieb-Daimler-Str. 42
67663, Kaiserslautern
+49 (0)631/205-3230
naim.bajcinca(at)mv.uni-kl.de