Guidelines for providing digital twins

Industrie 4.0 maps the digital twin as the Asset Administration Shell. To develop this digital twin, the Asset Administration Shell meta-model is used. A developer needs high-quality libraries in their programming languages to build the Asset Administration Shell in efficient and ergonomic way. The existing representations of the meta-model are inconvenient for moving from the specification to realizations in software development. This leads to many, often manual, re-implementations of the Asset Administration Shell in each programming language. We present an approach to automatically generate libraries based on the intermediate representation of the meta-model. The approach allows for practical and simple development process of Industrie 4.0 components, and scales across programming environments and future changes in the meta-model.

The concept of the Digital Twin (DT) and its implementation as Asset Administration Shell (AAS) is one of the key technologies for implementing Industry 4.0. By utilizing the AAS, use cases can be implemented with high interoperability. These use cases include optimizations and improvements of physical systems, like predictive maintenance or other artificial intelligence applications. For these use cases, historical data is key. However, there exists no guidance on how to handle historical data with the AAS. Furthermore, no integrated architecture exists that enables seamless storage and retrieval of historical data using the unified AAS meta-model and interface. Thus, we bridge this gap between use case and unified implementation by presenting multiple blueprints for data storage and retrieval motivated by use cases from Industry 4.0, healthcare, and civil construction. These data storage blueprints range from a mandatory change in the AAS infrastructure to augmentations of the existing AAS concepts. Furthermore, we showcase how the data model of the AAS can be utilized for a unified retrieval of historical data. In consequence, practitioners can quickly realize use cases that require historical data by tailoring and implementing the presented blueprints. Additionally, researchers can extend the presented guidance to further use cases, possibly from other domains.

Managing a product throughout its various lifecycle stages is essential for all stakeholders involved. Efficient management is supposed to streamline process, enhance product quality, increase customer satisfaction, and improve profitability. The current architecture faces challenges that impact trust among stakeholders because of its centralized architecture. This paper presents a blockchain-based solution to enhance trust and transparency in product lifecycle management. Using Asset Administration Shell (AAS) as a standardized digital representation, we model and share product digital twins via IPFS. The proposed architecture demonstrates how smart contracts and IPFS enable the creation, sharing, and traceability of digital twins throughout the product lifecycle, fostering collaboration among stakeholders. This is illustrated through the use case of an electric vehicle, where digital twins are created for critical components like the EV battery and tire and enabling tracking across different lifecycle stages. Additionally, we evaluate the implementation for scalability, latency, and cost efficiency.

Cities worldwide are rapidly integrating urban management information technology (IT) systems to address increasing urban challenges effectively. This paper examines the evolution of these systems, from the Ubiquitous City (U-City) to contemporary Smart Cities, and explores emerging technologies like the Metaverse and Digital Twin. Despite their growing relevance, there is ambiguity in their conceptual definitions and how they are applied interchangeably in urban management contexts. This study aims to clarify these technologies by analyzing U-City, Smart City, Metaverse, and Digital Twin within an Analysis Framework of Urban Management IT Systems. Our analysis reveals distinct roles and interconnections among these technologies. U-City initiated the development of essential IT infrastructure, laying the groundwork for subsequent systems. Smart City technology, leveraging the infrastructure provided by U-City, addresses real urban issues but lacks predictive capabilities for future challenges. In contrast, the Metaverse facilitates the simulation of urban changes and planning in a virtual environment, influencing real-world city development. Digital Twin technology enhances the operational efficiency of U-City and Smart City by simulating real-world data and optimizing urban management processes. The study highlights that while U-City and Smart City function in the tangible realm, Metaverse and Digital Twin operate in the virtual domain, yet they are closely integrated. Metaverse assists in urban planning through simulations that inform real-world Smart City designs, while Digital Twin optimizes real-time city operations and informs Metaverse simulations for future planning. The findings underscore the importance of understanding these technologies’ unique contributions and their interplay. Although current urban management IT systems have limitations, especially in technology classification and data accessibility, this research paves the way for future investigations. Further research should focus on refining the definitions and applications of Metaverse and Digital Twin, clarifying their relationships with Smart City and U-City, and addressing security and privacy concerns associated with these technologies.

Digital twins are a critical backbone technology for modern manufacturing and Industrie 4.0 (I4.0). The Asset Administration Shell (AAS) is becoming a popular foundation for modeling digital twins. Asset Administration Shells come in three successive levels of enhancement, also referred to as AAS (communication) types, though there is no common definition for these types. We conducted a systematic mapping study to find out how they are defined in the literature. As the analysis for type 2 AAS and type 3 AAS remains without direct results, we devised a novel classification schema from our findings via portfolio analysis. This schema can provide a foundation for the precise classification of AAS to guide researchers and practitioners in modeling digital twins.

Software infrastructure for ready-to-use, data analytics-based Digital Twins utilising the Asset Administration Shell

The article focuses on the project to develop a supply chain management information system using a digital twin for the maritime transport chain. Digital twins reflect real objects and processes in a virtual environment, which enables analysis, modelling and optimisation of supply chain operations. The author describes the main stages of the project, including requirements definition, system architecture development, implementation and testing. Particular attention is paid to the benefits of using digital twins in supply chain management, such as increased efficiency, reduced risk and improved forecasting. The results of the study show the potential of digital twins to optimise supply chain management and increase the competitiveness of companies. The article presents an approach to building a new model of interaction and systematic optimisation of business processes based on digital technologies at all stages of supply chain formation, which ensures the creation of a digital twin for the maritime transport chain. In order to improve supply chains, a digital twin has been proposed, which opens up great prospects for the management of logistics processes and the exchange of information between supply chain participants. This paper presents a framework for an integral Digital Supply Chain Twin (DSCT) capable of covering the entire transport chain. The proposed information system based on the use of the DSCT provides a number of improvements throughout the supply chain, as well as the ability to model and evaluate different scenarios for the supply chain. This creates opportunities to reduce the cost of organising and coordinating transport, improve the quality of transport and logistics services and make them more reliable by identifying potential problems at an early stage. The article analyses the main information technologies that facilitate the use of DSCT as a useful and reliable tool.

Autonomous Digital Process Twins (ADPTs) represent an advanced paradigm in intelligent computational systems that extends traditional digital twin frameworks by incorporating real-time analytics, artificial intelligence, and autonomous decisionmaking capabilities. Conventional digital twins are primarily designed for monitoring, visualization, and offline simulation; however, emerging complex environments require systems capable of adaptive reasoning and real-time optimization. This paper proposes a comprehensive software-centric architecture for an Autonomous Digital Process Twin that enables continuous synchronization between dynamic process models and intelligent decision engines. The proposed architecture integrates virtual process modeling, distributed real-time analytics, reinforcement learning-based decision intelligence, and simulation- driven control evaluation within a scalable computational framework. A mathematical formulation based on dynamic state-space modeling and Markov decision processes is introduced to support predictive reasoning and adaptive optimization. Extensive simulation experiments demonstrate improvements in decision accuracy, latency reduction, and scalability under high computational workloads. The results indicate that the architecture provides a robust foundation for next-generation intelligent systems capable of autonomous adaptation in complex digital environments. This research contributes to the advancement of intelligent digital twin ecosystems by emphasizing algorithmic autonomy, scalable architecture design, and realtime decision intelligence.

The concept of Industry 4.0 uses cyber-physical systems and the Internet of Things to create "smart factories" that enable automated and connected production. However, the complex and diverse nature of cyber-physical systems makes them vulnerable to physical threats, where any fault in their physical components can lead to serious consequences, from financial losses to human safety. To reduce the risk of such failures, it is essential to have techniques in place to monitor the condition of these physical components closely. In recent years, data-driven predictive maintenance methods have become common due to the growth in data and advancements in machine learning. This thesis focuses on fault diagnosis, a key part of predictive maintenance, which aims to detect and identify faults in physical components. Incorporating advanced techniques, including machine learning algorithms and sensor data analysis, enhanced fault diagnosis systems' accuracy and efficiency. However, several real-world barriers challenge the effectiveness of these techniques. This research is structured around three primary objectives. The first objective aims to establish an efficient fault diagnosis system that is highly sensitive to fault occurrences while being resilient to uncertainties such as variability in fault patterns and data imbalance. To address variability in fault patterns, we developed a multi-step approach integrating clustering techniques and an adaptive neuro-fuzzy inference system, which significantly improved diagnosis robustness even under noisy conditions. For imbalanced datasets, a two-step method was introduced, combining permutation entropy for fault detection and envelope analysis for fault isolation. This approach was enhanced by an automatic frequency band selection method leveraging wavelet transform and statistical criteria, resulting in high fault diagnosis accuracy and reliability, even with limited labeled faulty data. The second objective focuses on developing fault diagnosis systems that can maintain high performance despite domain shifts and limited training data in both source and target domains. To address the challenge of domain shifts, a transfer learning technique was introduced, and a systematic literature review was conducted. This study bridges a technical gap by providing a comprehensive taxonomy, state-of-the-art methods, and insights into the challenges of applying transfer learning to predictive maintenance. Additionally, a conceptual framework was proposed to explore scenarios for transferring diagnostic knowledge from different source domains to target domains with insufficient training datasets. In a subsequent study, a new diagnostic framework was developed using digital twins and partial transfer learning to address the lack of real training datasets in both source and target domains as well as label space inconsistencies between them. The framework includes a general approach for developing digital twins of real machines to generate synthetic diagnostic data as source domain data. Furthermore, by incorporating a deep learning network and a double-layer attention mechanism, a partial transfer learning diagnostic model was developed to transfer diagnostic knowledge from the digital twin to the real target domain despite label space inconsistencies. The proposed framework was validated through an industrial case study involving rolling bearings in rotating equipment. The third objective focuses on developing an efficient fault diagnosis system capable of maintaining reliability under unseen and evolving working conditions. To achieve this, a novel self-adaptive fault diagnosis system was proposed, incorporating the MAPE-K loop, a domain generalization network model, and digital twin technologies. This self-adaptive fault diagnosis system leverages the MAPE-K loop to adapt in real time to evolving working conditions. Digital twins were employed to continuously generate data aligned with the real system’s operational context, enabling accurate fault diagnosis in dynamic environments. The domain generalization network model enhances generalization to unseen target working conditions by addressing overfitting and feature loss through multi-domain data augmentation, adversarial learning, and domain discrepancy modules. Validation using multiple rotating machinery datasets demonstrated that the developed fault diagnosis system outperformed state-of-the-art methods across various scenarios. In summary, this dissertation proposes a comprehensive and practical approach to addressing variability in fault patterns, imbalance datasets, data scarcity, domain shifts, and unseen and evolving working conditions challenges in existing fault diagnosis systems.

A future-oriented approach is the application of Digital Twins for process development, optimization and finally during manufacturing. Digital Twins are detailed virtual representations of bioprocesses with predictive capabilities. In biotechnology, Digital Twins can be used to monitor processes and to provide data for process control and optimization. Central and crucial components of Digital Twins are mathematical process models, which are capable to describe and predict cultivations with high fidelity. Detailed mechanistic models in particular are suitable for both use in Digital Twins and for the development of process control strategies.In this chapter the requirements that process models must fulfil in order to be used for process optimization and finally in Digital Twins will be described. Different types of models, including mechanistic as well as compartmentalized models, are outlined and their application in Digital Twins and for process optimization is explained. Finally, a structured, compartmentalized process model, which was specifically designed for process optimization and has already been used in Digital Twins, is highlighted.

The shift towards product personalization is the main enabler behind Industry 4.0 and drives the need to deploy flexible and reconfigurable assembly systems. This paper investigates the use of Digital Twins (DT) for enabling system flexibility and reconfigurability through various functionalities, leading to an overall resilience in the system. The suggested DT infrastructure involves two main components: a) Virtual representation of the shop floor, combining multiple sensor data and CAD models and b) Real-time multi-robot behaviour control. The communication layer between the physical and the virtual agents in the level of Digital Twin is realised through the ROS framework. The integration of the DT in an overall production system with various components (like planning systems) is realised through the Asset Administration Shell (AAS) and custom ROS-AAS connectors responsible for translating data between the two formats. Finally, an orchestration system (referred as Station Controller) that is responsible for dispatching planned tasks to the assigned resources has been implemented. The developed infrastructure is validated through a case study inspired by the consumer electronics industry focusing on the assembly of two different products, a trimmer head, and a monitor cover. Nevertheless, the proposed solution has been designed to be easily applicable to any similar scenario.

The keyword “human digital twin” has received considerable attention in recent years, and information technology has been developed in healthcare and sports training systems to guide human behavior to a better state. In contrast, from optimizing the production and maintenance processes of industrial products, which is the origin of the term “digital twin,” intelligent robot systems can be interpreted as a mainstream of digital twin. In other words, assistive robots that support humans in their daily lives and improve their life behavior require the integration of human digital twin and conventional object digital twin. However, integrating these two digital twins is not easy from the viewpoint of system integration. In addition, it is necessary to encourage humans to change their behavior to provide users with subjective and immersive experiences rather than simply displaying numerical information. This study reviews the current status and limitations of these digital twin technologies and proposes the concept of a virtual reality (VR) digital twin that integrates digital twins and VR toward assistive robotic systems. This will expand the experience of both humans and robots and open the way to the realization of robots that can better support our daily lives.

This article explores the concept of digital twins and reasons why manufacturers prefer digital replicas of products, machines, processes, or even entire factories. A digital twin models the robotic line with such high fidelity that the engineer can do all this in the virtual world. Digital twins are the foundation of tomorrow’s smarter workplace. A factory’s digital twin must be robust enough to capture those changes, plus all relevant data from each operation. Smart factories, such as GE’s Brilliant Factory and Siemens’ competing Industrie 4.0, need both types of digital twins—product and process—to work. Digital product models contain each component that goes into a product, from screws and welds to plastic shapes and machined metals. Digital twins also support greater automation. As artificial intelligence (AI) systems learn more about specific machines, they will use their digital twins to help engineers run plants more efficiently. AI can analyze it to see if a screw is loose or a bearing is starting to fail. The better the AI knows the machine, the more accurately it can predict when that failure is likely to happen.

Models and P4R asset description for digital twin-based advanced planning and scheduling using cyber-physical integration for resilient production operation

The wiring harness is one of the most expensive components of the automobile. It is still a custom-made product despite the high-volume production in the automotive industry. However, various trends, such as increasing fragility of supply chains and functional safety demands for autonomous driving are demanding the automation of the value creation processes. But in mass customisation, automation needs the digitalisation of all information flows. Machines and processes must be able to automatically gather all required information. In the wiring harness industry, much of the information has been geared toward processing by humans and has hardly been digitised at all. One of the foundations for Industry 4.0-oriented automation is ergo the existence of complete digital information of each wiring harness. A digital twin of the wiring harness is required. The Asset Administration Shell (AAS) is the technical concept for transparently interoperating with the digital twin. The project “Asset Administration Shell for the Wiring Harness” or in German (Verwaltungsschale für den Leitungssatz - VWS4LS) creates the first complete digital description of the wiring harness based on the AAS. As a result, all actors in the value network can access complete and consistent data (“single point of truth”), enrich it, and control its application through authorisations. To achieve this goal, a consortium from all levels of the value network was assembled for VWS4LS starting with the OEM, through the suppliers at the various levels of the value chain, and to the software suppliers and machine manufacturers. This publication presents the project and its initial results.