AI based System of Systems Lifecycle Management of Digital Threads

Technological advancements have led to the transition of manufacturing industries to Smart Manufacturing and Industry 4.0. Promising concepts such as Digital Twin and Digital Thread could help speed up the transition. One benefit of using digital twins is to enable continuity of lifecycle information. However, currently, most digital-twin implementations focus on modeling a particular lifecycle stage of a physical element in “silos”. This makes companies missing out on up to 65% of possible value of digital twin investments. This also results in it challenging to incorporate diverse data streams from different lifecycle stages. Digital thread has been used to represent information flow along the product lifecycle. Using information across product lifecycle stages will facilitate interoperability and reusability of digital twins. Because data from each lifecycle stage could be accessed and managed systematically, this will ensure the value and the credibility of the digital twin. A lot of confusion still remains in industry about what are digital twin and digital thread as well as their relationships. Using lifecycle data from a digital thread for digital twin implementation is complex because of the heterogeneity of standards and technologies involved. In this paper, we provide definitions of both digital twin and digital thread; we highlight the benefit of using them for interoperability and reusability of a digital twin for product lifecycle management and analysis; we propose a methodology for implementing digital twins using lifecycle data supported by a digital thread. Finally, we showcase the proposed methodology by providing an example of integrating digital twins with a digital thread.

We present a structural digital twin system based on component-based parametric reduced order modeling using Reduced Basis Finite Element Analysis (RB-FEA) framework. This enables fast, detailed, and holistic modeling of large-scale structures, such as floating and fixed production and drilling platforms, and crucially, the digital twin's parametric nature and fast solve time enables the system to be connected seamlessly with inspection and sensor data. We demonstrate RB-FEA based structural digital twins, and capabilities for connecting them to sensor data and data science methods to increase predictive power and engineering insight. We show how the digital twin is a key enabler for a Digital Thread – a data-driven architecture that links together information generated from across the product lifecycle. Inspection data, such as thickness measurements, can be directly mapped into the structural digital twin. Sensor data, such as motion and strain can be transformed into loading data, e.g. to estimate sea-states and calculate stress and fatigue accumulation based on actual conditions, or to "tune" model parameters to match data-based measurements, such as mode shapes and frequencies. This enables continuous tracking of the asset and assessment of its current state, based on quantitative and detailed structural analysis, at any time. Ultimately the structural digital twin provides an interpretation layer for integration of monitoring and inspection data, leading to a fully automated digital thread. We present a framework, based on a cloud-based simulation platform and Python-based scripting, to automate the workflows listed above. Digital twin provides a single source of truth about asset condition and allows data driven communication and decision taking between multiple stakeholders – operators, contractors, regulators, etc. We will show examples of real-world applications of RB-FEA digital twin for FPSO and Jacket platforms and development work for digital thread with emphasis on data driven value creation along the entire life cycle of the asset. The Reduced Basis FEA based structural digital twin is a key enabler of data driven digital thread in addition to sensor frameworks and data science systems. RB-FEA provides fast, parametric, and physics-based analysis providing a transparent interpretation layer for data obtained from other systems. It provides a key element allowing knowledge management along asset lifecycle – from concept to decommissioning. High fidelity, physics based global simulations, such as RB-FEA digital twins, are a key enabler for effective digital transformation of industrial operations. They enable real-time insights into asset performance that are otherwise unattainable, providing tools for Asset Integrity Management, Risk Based Inspection, Automation and Optimization of Operations as well as enabling full digital thread enhancing Safety and CAPEX and OPEX.

Systems engineering is a transdisciplinary scientific and applied direction that combines the principles of a systems approach, methods, tools and standards that provide an integrated methodology and relevant technologies for the design and development of complex systems, their comprehensive analysis and verification, efficient and safe use. The modern approach to systems engineering is characterized by an accentuated modeling of systems throughout their life cycle with the ultimate goal of creating their digital twins. It is called model-based systems engineering (MBSE). Consistent integration of MBSE with software engineering leads to the formation of the MBSSE (Model-Based Systems and Software Engineering) direction. This textbook is devoted to this area, the main objective of which is to study the conceptual and scientific-methodological foundations of MBSE and MBSSE, models and methods of life cycle management of systems and software, basic standards of systems engineering, study and mastery of the UML and SysML systems modeling languages and the corresponding modeling tools, study of requirements engineering methods and development of a description of the system architecture, familiarization with the concept of digital twins and their role in MBSE, study of the MBSSE reference model and its relationship with the process standards of systems engineering, study of the methodological aspects of the system and software integration process. The final chapter of the textbook is devoted to the study of the mathematical foundations of systems engineering. The main aspects of the mathematical theory of systems by A. Wayne Wymore, which became an important stimulus for the development of the model-oriented approach in systems engineering, and modern research, including the apparatus of finite automata by David Harel, the formalism of modeling of discrete systems DEVS, research into category theory as a formal mathematical basis for model-based system design are considered. The authors recommend this course as a basic course for training IT professionals.

Smart Manufacturing advances have recently emerged, focused on the integration of Digital Thread (DTh) and Digital Twin (DT). DTh-DT has been explored in additive manufacturing, aircraft production, and weapons. However, there is still an area of opportunity to explore DTh-DT in collaborative manufacturing cells, layouts, and specifically, in the creation of a system to make an intelligent robotic cell. This work provides a novel approach of a DTh-DT developed to function within a manufacturing robotic cell. A discrete event simulation (DES) was created with open-source programming software, representing the cell. Information is collected from the physical process and sent to a cloud service. The DES request the data from the cloud is executed and the results are received by a database, which works with a Server (Ignition 8.0). The Server receives data and displays results, working as the link between the DT and the Product Lifecycle. This work presents a quick look at a DTh applied to a robotic cell, an approach to a DT, and the use of different types of communications and platforms. The potential benefits of applying this type of configuration in an Industry 4.0 environment are described and critically reviewed.

The application of digital twins is increasing in several fields. Mirroring the current state of the asset and making predictions of the future state are the main purposes of digital twins. Inside the German Aerospace Center (DLR), an internal project is set up to find methods, technologies and processes for digital twins. Several institutes are contributing to the project, including institutes in the IT domain like the Institute of Software Methods for Product Virtualization or the Institute for Software Technology on one side, and the aviation engineering domain on the other side, e.g. the Institute of Flight Systems, the Institute of Composite Structures and Adaptive Systems and the Institute of Maintenance, Repair and Overhaul. In order to demonstrate the capabilities and identify new development opportunities of digital twins, three different use cases are defined. These use cases include the virtual product house, the virtual engine and the research aircraft. For the research aircraft use case, the digital twin can be seen as a research tool within the organization. The research questions of the project are addressing several information technology related issues like data formats, data sizes, data storage concepts, provenance, and security. Additionally, the project addresses the definitions of the digital twin, the digital thread, and the application layer as well as a common digital twin vision. The next steps in the project are the implementation and demonstration of first prototypes for the individual use cases. This paper gives an overview over the project results and the developments for digital twins. The aim is to digitally map aircraft and their components with all their characteristics and relevant data.

This paper presents a digital twin prototype of the PiCar-X by Sunfounder based on the middleware Robot Operating System (ROS), Docker, and the ARCHES Digital Twin Framework, which provides tools to exchange data between a physical and digital twin. The digital twin prototype can be used to explore our implementation and test all software functions without needing to use the physical PiCar-X. The actual hardware is replaced with emulators or a simulation, and the interfaces are virtualized. The embedded control system operating the physical PiCar-X and the digital twin prototype are identical. Our goal is to provide researchers and practitioners with an affordable and straightforward example to explore how the concepts physical twin, digital model, digital template, digital thread, digital shadow, digital twin, and digital twin prototype can be implemented. These concepts were originally used for development, testing, monitoring, and operating an underwater network of ocean observation systems in the project ARCHES (Autonomous Robotic Networks to help Human Societies).

A model-based approach to large-scale distributed system architecting is suggested, which is based on the use of dynamic digital twins. This approach can be considered as an integration of known paradigms, such as digital twins, evolutionary architecture and agile architecture. It can also be considered as one of the possible realizations of the digital thread paradigm. As part of this approach, a three-level digital thread reference architecture is suggested, which includes the following levels: (i) digital thread support level; (ii) agile architecture support level; (iii) digital shadow support level. This approach has been used in the development of a number of real systems, and has shown its effectiveness in supporting system agility at the exploitation and modernization stages. The proposed approach is focused on building digital twin-based systems. This article may be interesting for specialists engaged in research and development in the domain of IoT- and IIoT-based information systems, primarily architects.

To keep pace with growing system complexity, Digital Engineering (DE) Model Based Systems Engineering (MBSE) capabilities must be expanded. A digital thread based approach is required to holistically evaluate measures of effectiveness/performance for missions. This paper describes the approach taken to connect requirements, SysML‐based architecture, and analytical Modeling and Simulation (M&S) yielding an interdisciplinary digital thread supporting mission analysis. The analysis was conducted in support of a multi‐domain (land, air, sea, and space) multi‐platform mission to detect, track, and engage the enemy. The approach used commercially available tools, strategically connected to establish an Authoritative Source of Truth (ASOT) for each piece of data, and gain insights about the System of Systems (SoS) beyond that which the component models could provide on their own. The results of these efforts produced a multipurpose SoS MBSE toolset enabling semi‐automated trade study analysis, while more importantly serving as a basis from which to expand systems engineering activities during subsequent phases of the systems' lifecycle. This paper concludes by identifying further opportunities for MBSE research and development to expand the developed capability.

Dynamically updated digital twin for prognostics and health management: Application in permanent magnet synchronous motor

Generation and sharing of data have always been critical within the Architecture, Engineering, Construction and Operation (AECO) sector due to its fragmentation and it is well recognized that this led to an inefficient and poor integration of processes along the building lifecycle. Despite the introduction of Building Information Modelling (BIM) that enhances interoperability many issues related to the management of information evolution still persist. Management of vast amount of data is complex especially in change management process during construction phase when a real-time processing, integration and immediate feedback are usually necessary. In order to exploit the potential of digital technologies for process efficiency improvement linking directly to BIM models and defining BIM processes is necessary. Product Life-cycle Management (PLM) and Model-Based Systems Engineering (MBSE), commonly applied to other engineering fields, embody the key approach to complex construction management and model-based information use. The challenge is not only to support the various phases of the building’s life cycle, but also to capture its multidisciplinary nature which has led to the creation of various frameworks. To this aim, “digital twin” with its dynamic digital representation of the physical system continuously updated with latter’s performance, maintenance and health status data can represent a valuable tool. However, current MBSE digital twins face the following challenges: specific domains applications, unrelated modelling theories, different semantic models and uncommon storage representations. All these issues led to seamless integration across disciplines during the whole lifecycle. MBSE toolchain is an emerging technique in the area of systems engineering which is expected to become a next generation approach for supporting complex Cyber-Physical System (CPS) development as the integration system of systems. This paper proposes a framework for development of digital twin integration based on MBSE toolchain technique, providing a semantic integration among layers such as social (integration of stakeholders’ views), process (integration of management models for process control and monitoring), technical (integration of domain specific model for predictive co- simulation), information (integration of data, model and tool operations). The framework has two main purposes: to support toolchain development with a Model Based System Engineering approach; to promote interoperability of the whole developed toolchain through a service-oriented approach where services are provided to the other components by application components, through a communication protocol over a network.

In the realm of proactive medical care, digital twin technology is rising to the forefront as a paradigm shift due to the combination of customised healthcare, 6G connectivity, and artificial intelligence (AI). This study investigates AI-driven, 6G-powered healthcare digital twin technology, focusing on patient-centric monitoring and predictive analytics. It must clearly outline the research objectives, such as real-time health data integration, adaptive decision-making, and improved treatment personalization. The proposed methodology should describe the use of 6G-enabled ultra-reliable low-latency communication, AI models for digital twin construction, and secure data management frameworks. Improved diagnostic accuracy, fast response time to clinical emergencies, and improved resource allocation in healthcare systems were main outcomes that are presented in this abstract. The technical contributions of this work with the integration of AI, 6G, and digital twin technologies are highlighted in the end of this study, and this may support the next-generation intelligent healthcare solutions. For self-learning healthcare digital twin, a model that leverages 6G-enabled medical informatics, real-time data streams, and artificial intelligence (AI) analytics is presented in this study. This presented model may support in clinical diagnosis, and classifying damages earlier. A real-time updated digital copy of the patient was created by the suggested method by integrating multimodal data from various sources including imaging, vital signs, consumer electronic devices such as smartwatches, wearable sensor metrics, and electronic health records (EHRs). The patient physiological patterns and previous injury profiles are constantly learnt by the integration of digital twin and deep learning (DL) algorithms. This integration is effective in predicting the occurrence, kind, and severity of injuries and internal trauma, falls, cardiovascular events, and neurodegenerative insults. The digital twin and healthcare providers are connected seamlessly with 6G communication infrastructure, guaranteeing ultra-low latency and great dependability. This allows for pre-hospital and critical care settings to implement instantaneous feedback loops, as well as for remote diagnostics and adaptive clinical decision-making. From home health monitoring solutions to smartphones and wearables, consumer electronics are ubiquitous and serve as common data collectors, greatly increase access and enabling the instant collection of accurate data using a digital twin. To keep data private while training AI models on dispersed healthcare data, the architecture offers federated learning. Based on severity level, the injury types are classified by a multi-layered decision engine, and this may promote a customized, context-aware responses like alerting emergency teams, modifying treatment regimens, or demanding robotic surgical support. The AI-driven, 6G-powered healthcare digital twin revolutionizes the diagnosis of injury, and it establish a path for a precise, preventive, and predictive medicine. Furthermore, scaling efficiencies were reduced by 95.81%, while reaction times decreased to 96.88%, resulting in significant gains. This technology is particularly helpful for populations who are elderly, at risk, or located far away, as it decreases reaction time, reduces diagnostic error, and provides scalable, continuous care.

Digital Thread and Twin for Systems Engineering: Design to Retirement

The Digital Thread is a system that connects different phases of the product lifecycle and the related data across one or more companies in the supply chain. This work aims to develop a graph data model of the Digital Thread, in the context of the vision of polyglot persistence, that interconnects the different phases of the lifecycle and their corresponding data models, processes, and IT systems. This work proposes a Digital Thread Graph that integrates a Digital Model and a derived Digital Twin, using object and relation attributes for view creation and filtering while minimizing redundancy.

The move towards advanced manufacturing and Industry 4.0 is fed by increased demand for speeding up innovation, increasing flexibility, improving maintenance, and becoming more customized while saving on the total cost of operations. This is accompanied by increased dependence on virtual product and process development, data‐driven processes, and product knowledge. Other characteristics, affecting modern design, include big data intelligence in product, process, and maintenance. New technologies that empower data analytics include added manufacturing, flexible manufacturing, robotics, sensor technology, smart value/supply chains, and industrial information backbones. This paper is about surrogate models, also called digital twins, that provide an important complementary capacity to physical assets. Digital twins capture past, present, and predicted behavior of physical assets. Digital twin models are updated periodically to represent the current state of physical assets. This distinguishes digital twins from conventional simulations in that sensor data can continuously feed them. The type of curated information on the state of physical asset's history depends on how digital twins are used. For example, if a digital twin is used for fault classification, the history captured is operational data from equipment in healthy and faulty states. We provide here a review of digital twins, with an emphasis on Industry 4.0 applications.

In Formula 1 racing, aerodynamic efficiency is a critical determinant of car performance, influencing factors like drag reduction, downforce, and stability. This paper reviews the computational tools and algorithms used to analyze aerodynamic data, focusing on prominent software such as ANSYS, OpenFOAM, and STAR-CCM+, alongside emerging technologies like machine learning and digital twins. By synthesizing findings from multiple studies, this review provides insights into the effectiveness of these tools in optimizing Formula 1 car design and performance. Furthermore, it highlights current challenges, such as computational costs and real-time data integration, and discusses future directions in aerodynamic analysis that could enhance competitive advantages. The paper concludes with an evaluation of the potential for continued innovation in aerodynamic simulation tools, machine learning algorithms, and decision support systems to revolutionize the motorsports industry. Keywords—Formula 1, Aerodynamics, CFD, ANSYS, STAR- CCM+, OpenFOAM, Machine Learning, Digital Twin, Decision Support Systems (DSS), Drag Reduction, Downforce Optimization, Computational