No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
The digital twin paradigm for future NASA and U.S. air force vehicles
Abstract
Future generations of NASA and U.S. Air Force vehicles will require lighter mass while being subjected to higher loads and more extreme service conditions over longer time periods than the present generation. Current approaches for certification, fleet management and sustainment are largely based on statistical distributions of material properties, heuristic design philosophies, physical testing and assumed similitude between testing and operational conditions and will likely be unable to address these extreme requirements. To address the shortcomings of conventional approaches, a fundamental paradigm shift is needed. This paradigm shift, the Digital Twin, integrates ultra-high fidelity simulation with the vehicle's on-board integrated vehicle health management system, maintenance history and all available historical and fleet data to mirror the life of its flying twin and enable unprecedented levels of safety and reliability.
... To achieve the high demands on accuracy and throughput of (high-tech) engineering systems, precise, nonlinear (dynamical) models for accurate response prediction are required. Moreover, for digital twins [2], having an accurate model of a physical system is of high importance to enable, among others, structural health monitoring [3], model-based/predictive control, and path planning [4]. Typically, to model an engineering system, First Principles (FPs, e.g., physical laws) are uti-lized. ...
... In (1), we consider a second-order structure since it arises in many physical models, such as, e.g., in mechanics. 3 We care to stress that the method proposed here is generic since the proposed approach is also applicable if the dynamics is only described by the second equation in (1) (representing discretized first-order dynamics). Given the fact that the use cases in the paper are mechanical systems, but without loss of generality, we call x (1, p) k ∈ R n DoF and x (1,v) k ∈ R n DoF in (1) the position and velocity part of the state vector of the FP model. ...
... The augmentation to the FP vector field g is captured by l (1) w 1 :R 2n DoF +n ext +n u →R n DoF which is an NN parameterized by weights w 1 . Furthermore, the FP output equation h is augmented by l (3) w 3 :R 2n DoF +n ext →R n y , which is an NN parameterized by the weights w 3 . By adjusting the weights in the training phase (see Sect. 2.3 or [36,37] for a more detailed explanation), each NN is tuned such that it provides a mapping that improves the predictive capacity of the EA model. ...
Nonlinear dynamics models derived using First Principles (FPs) often suffer from limited accuracy in relation to the complex physical systems they represent. Therefore, model updating may be employed to improve the accuracy of the FP model. In this work, an AI-based updating methodology is proposed where an existing FP model is extended by introducing new states (to capture, e.g., unmodeled modes or parasitic degrees of freedom) using a subspace encoder, and capture their governing equations of motion using a Recurrent Neural Network (RNN). Additionally, the retained FP equations of motion are augmented by additional RNNs to capture unmodeled dynamics (e.g. nonlinearities) or improper parameter values. Simultaneously training all neural networks such that an output prediction error-based loss is minimized yields an Extension and Augmentation-based (EA) model that significantly decreases the prediction error with respect to the FP model. This methodology is applied on two use cases, one of which uses measurements performed on an industrial wire bonder. These use cases demonstrate that, also when changes are made to the FP parameters, excitation signals, and controllers, the EA model still shows significant improvement in prediction capability over the FP model. This shows that by using the FP model as a basis for model updating, the extrapolation capabilities of the resulting model are improved. Furthermore, the EA model updating method is compared with a similar, yet fully black-box, subspace-encoder network method (Beintema et al. Automatica 158:111210). The EA model is shown to outperform such purely data-based models in terms of accuracy, training efficiency, and extrapolation capabilities. Finally, in contrast to the (purely data-based) subspace-encoder network method, the EA model updating method enables updating of unstable open-loop systems by embedding stabilizing controllers in the FP model.
... Digital twin technology has emerged as a key paradigm for integrating real-time data with high-fidelity models of physical systems. A digital twin (DT) is generally defined as a digital model of a specific physical asset that remains in sync with the asset throughout its lifecycle [1,2]. In other words, a DT is a living model that is continuously updated to reflect changes in its physical counterpart. ...
... The concept of digital twins has evolved rapidly in recent years, finding applications in manufacturing, energy systems, healthcare, and urban infrastructure. Several survey papers and reviews (e.g., [1,3]) trace this evolution from its initial conceptualization to modern implementations. Here, we focus on the aspects most relevant to adaptive digital twins, particularly online model updating, data assimilation, and theoretical analyses of twin models. ...
... The term Digital Twin was popularized by NASA and the U.S. Air Force as part of vehicle health management for aerospace systems [1]. Glaessgen and Stargel [1] outlined the digital twin paradigm as a high-fidelity model synchronized with a physical asset, emphasizing its potential for life-cycle monitoring. ...
Digital twins are virtual representations of physical assets that remain continuously synchronized with their real-world counterparts. This paper focuses on \emph{adaptive digital twins}—models that incorporate online learning mechanisms to update their states and parameters in real time. We present a rigorous mathematical framework for adaptive digital twins, including formal definitions and data-driven update mechanisms. A theoretical convergence analysis establishes conditions under which the twin's state asymptotically tracks the physical system. We further explore theoretical performance limits, analyzing the effects of model uncertainties, noise, and computational constraints on accuracy. The paper follows academic best practices, providing detailed pseudocode for the adaptation algorithm, convergence proofs via Lyapunov stability theory, and supporting figures and tables. Our results show that, with proper design, adaptive digital twins can achieve stable and provably convergent tracking, ensuring reliable deployment in complex cyber-physical systems.
... Large complex systems are being fitted with appropriate sensors and actuators to enable this technology. Manufacturing is one of the early adopters of this technology, but DT are being successfully implemented in a variety of domains including production systems[1, 2], agricultural systems[3], utility systems [4], healthcare systems [5], and military systems [6]. While there are discussions on the use of digital twins in systems engineering [7], there is no course or textbook and few instructional materials are available outside of articles about the promise of the technology or a specific implementation. ...
... 5 Students will learn how C# is used within Unity and the resources available to them for writing code. 6 Physical Spaces Python Programming Electronics ...
... DT is a complex simulation built upon historical and real-time data designed to replicate the condition of a physical object (Glaessgen and Stargel, 2012). It is a digital representation of a physical product that mimics real-world behaviours by leveraging data from the physical system to its virtual counterpart. ...
In the transition towards Construction 5.0, intelligent systems, such as predictive Digital Twins (DTs), have emerged as a critical solution in infrastructure assets management. This is by leveraging advanced simulations and analytical methods for accurate asset condition prediction. However, while simulations are essential for enabling predictive DTs, existing literature often overlooks the role of pavement simulation within developed DTs. This paper systematically leverages the literature on Finite Element (FE) modelling for pavement performance prediction to assess the current state and practice of simulations, identifies trends in simulation integration, proposes advancements to enhance the incorporation of FE models within DTs, and proposes an architecture for the integration. Finally, the study concludes with a call for future research directions to address existing gaps, aiming to advance DTs for intelligent and sustainable pavement management.
... Tuegel et al. [1] presented a conceptual model using a digital twin to predict the aircrat's structural lie prediction and to assure the structural integrity in fight conditions. Later, in 2012, Glaessgen and Stargel [2] proposed a digital twin paradigm or the Α deterministic digital twin-based method or damage detection o composites subjected to impact loading: development, validation and time-eiciency improvement using a surrogate model 73 prediction o the health and the remaining lie o uture NASA and U.S air orce vehicles. Despite all o that, the digital twin technology is not mature enough or use in the aerospace industry and more development is required in several sectors such as data transmission, collection and processing, communication-interaction technology, modeling-simulation technology and sensing-measurement technology. ...
Both monolithic and sandwich composites are highly susceptible to impact loading. Despite of their inherent strength-to-weight ratio benefits, this vulnerability constitutes a major concern related to structural integrity. Although structures designed with fail-safe principles can withstand in theory partial system failure, the early detection of in-service damage is useful for supplementing regular inspections. The development and validation of a time-efficient predictive method for the localization and quantification of damage to composites can bring numerous benefits, such as rapid post-damage strength estimation. In the current study, a deterministic digital twin-based algorithm for the damage localization and quantification of a composite sandwich panel subjected to soft body impact is developed. The effectiveness and robustness of the developed algorithm are highlighted, whilst the time-efficiency of the algorithm is achieved using a kriging surrogate model.
... This advanced simulation capability not only reduces risks and downtime, but also allows warranty policies to be adjusted based on the actual conditions of use of the asset. As a result, more accurate and customized warranty coverage is offered, aligned with the life cycle and condition of each specific asset [13,14]. In this way, digital twins become a strategic tool that not only optimizes maintenance, but also adds value to the customer, improving the accuracy of warranty coverage and increasing the reliability and efficiency of assets during their life cycle [11]. ...
This research examines how Industry 4.0 technologies such as artificial intelligence (AI), the Internet of Things (IoT), and digital twins (DT) are used in the digital transformation process of warranty management. This research focuses on converting traditional warranty management practices from reactive systems to predictive and proactive ones, improving operational performance and customer experiences. Based on an already established eight-phase framework for warranty management, this paper reviews machine learning (ML), natural language processing (NLP), and predictive analytics, among other advanced technologies, to enhance warranty optimization processes. Best practices in the automotive sector, as well as in the railway and aeronautics industries, have experienced substantial achievements, including optimized resource utilization and savings, together with tailored services. This study describes the limitations of capital investments, labor training requirements, and data protection issues. Therefore, it suggests implementation sequencing and staff education approaches as solutions. In addition to the current evolution of Industry 4.0, this research's conclusion highlights how digital warranty management advancements optimize resources and reduce costs while adhering to international standards and ethical data practices.
... The NASA Definition. The NASA definition tends to lean heavily on multiphysics, multiscale, and probabilistic simulations [23,26], with special emphasis on aviation and aerospace applications such as the Space Launch System. As stated in the NASA DRAFT Modeling, Simulation, Information Technology & Processing Roadmap [23]: ...
While digital twin (DT) has made significant strides in recent years, much work remains to be done in the research community and in the industry to fully realize the benefits of DT. A group of 25 industry professionals, US federal government researchers, and academics came together from 11 different institutions and organizations to identify 14 key thrusts and 3 cross-cutting areas for further DT research and development (R&D). This article presents our vision for the future of DT R&D, provides historical context for DT’s birth and growth as a field, provides examples of DTs in use in industry and the lab, and discusses the current state of DT research. We hope that this article serves as a nucleation point for future R&D efforts and provides the community with shared vision and trajectory to collectively advance DT so that society can more rapidly see the benefits of DT.
... Biofeedback systems and virtual coaching functionalities embedded within Digital Health Twins contribute to behavior modification and lifestyle optimization through responsive, real-time interaction. Biofeedback systems within DHTs collect and analyze data on physiological signals such as heart rate variability, skin conductance, respiration rate, and muscle activity to provide users with immediate insights into their physical or emotional states (Glaessgen & Stargel, 2012). These systems support selfregulation strategies by helping individuals recognize and manage stress, fatigue, or poor posture, especially in occupational and rehabilitative settings (Sun et al., 2022). ...
Digital Health Twins (DHTs) represent a groundbreaking advancement in personalized and predictive healthcare, functioning as real-time, data-driven digital replicas of individual patients. By integrating continuous physiological, behavioral, and contextual data from sources such as wearable devices, biosensors, electronic health records (EHRs), and mobile health platforms, DHTs simulate the progression of health conditions, predict outcomes, and enable individualized care planning. This systematic literature review investigates the current landscape of DHT development and implementation with a specific focus on their clinical, technological, ethical, and organizational dimensions. The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, ensuring transparency, reproducibility, and methodological rigor. A total of 72 peer-reviewed journal articles published between 2010 and 2022 were selected from five major databases, representing diverse disciplines including biomedical engineering, health informatics, artificial intelligence, and occupational health. The findings indicate that DHTs are being widely utilized for early detection of chronic diseases, personalized risk profiling, and virtual treatment simulations, particularly in specialties such as cardiology, oncology, and neurology. In parallel, DHTs are enabling a new era of personal health management through real-time biofeedback, digital coaching, and self-monitoring tools that empower individuals to make data-informed lifestyle decisions. The review also reveals emerging applications of DHTs in corporate health and workforce wellbeing, where they support occupational health surveillance, wellness program optimization, and predictive modeling of employee engagement and absenteeism. This review not only consolidates current knowledge across multiple sectors but also identifies critical research and policy gaps, highlighting the need for robust ethical frameworks, standardized interoperability protocols, and inclusive governance mechanisms to ensure the equitable and responsible implementation of DHTs across healthcare ecosystems.
... Digital twins are one of the foundational pillars of modern engineering and scientific applications. [31][32][33][34] They provide a framework for system design, analysis, and operation. 35 The digital twin of a physical system is a dynamic virtual model consisting of real-time data, simulations, and predictive analytics to offer a representation of system behaviors. ...
This paper discusses the NVIDIA Omniverse platform for visualizing and integrating digital twins of fusion power plants, focusing on enhancing the design, simulation, and operational workflows of complex fusion systems. As global fusion projects such as ITER, STEP, and CFETR move toward realizing practical fusion energy, sophisticated tools to model, simulate, and optimize such systems become increasingly critical. Digital twins are virtual replicas of physical systems that act as a “single source of truth” by integrating scientific analysis, engineering design, and real-time data integration. This paper outlines the workflow for creating and visualizing a digital twin of a tokamak, demonstrating the integration of computer-aided design models, simulation data, and material properties into Omniverse. It also provides a view of extending Omniverse with real-time data visualization, Python scripting, and generative AI in applications that make the digital twin even more functional and interactive, allowing seamless collaboration across teams and stakeholders. The interoperability challenges that limit the adoption of Omniverse in fusion research are also discussed. In conclusion, the paper outlines how Omniverse can create a comprehensive, immersive, and interactive environment that optimizes the design and operation of a fusion power plant. In the future, this approach may extend to developing more efficient and reliable fusion energy systems.
... The concept of a digital twin has evolved significantly over the years. Initially defined by NASA and the Air Force Research Laboratory [1,2] for predicting the health of aircraft [3] to more recent and comprehensive definitions. These now include refined digital descriptions of product entities and incorporate simulation experiments based on digital models [4][5][6] . ...
With advancement in digitalization and simulation technology, digital twin (DT) technology has emerged as a focal point of research in various industries. In response to the demands for high-quality and efficient wireless communication, it is crucial to conduct an in-depth study of core aspects and key technologies of digital twin technology. This will facilitate a better understanding and exploration of the future development direction of related digital simulation technology within the communication field. This paper provides a systematic summary and analysis of the concept of digital twins, their key technologies, and the current research landscape. Additionally, it explores the research and application fields, as well as the development prospects of digital twin technology in communications. The paper also examines diverse applications of digital twin technology in future 6th generation (6G) networks, including an end-to-end digital twin network architecture framework for non-terrestrial networks (NTNs) in the context of 6G. Finally, it discusses the challenges and opportunities for the widespread implementation of digital twins in future wireless communication networks.
... This technology has been successfully applied not only in organizing technological processes in industrial enterprises, but also in the development of spacecraft simulators. By 2010, the concept officially acquired a name of a digital twin during a NASA project to create digital simulators for spacecraft [19]. A digital twin is a virtual copy of a real-world object, process, or system that reflects its dynamic functionality based on input data and artificial intelligence technologies. ...
The article presents a literature review on the application of digital twin technology in healthcare administration over the past decade. This review examines the potential applications of digital twins at different levels of healthcare management. The formation and global development of digital twin technology are discussed. Examples of the use of digital twins in the management of healthcare institutions and healthcare processes are specified, and their advantages and future prospects are analyzed.
... • подключенные данные: информационные связи, объединяющие физический и виртуальный продукты, обеспечивая постоянный обмен данными между ними. [10] Ключевыми особенностями этого подхода являются: • интеграция физических моделей: использование наиболее точных физических моделей для описания поведения объекта; ...
The concept of a digital twin (hereafter referred to as DT) is discussed as a complex cyber-physical system that represents a virtual representation of physical objects, processes, or systems. A retrospective analysis of the evolution of this technology is conducted, starting from its origins in NASA’s practice and culminating in contemporary conceptual approaches, such as the product life cycle model proposed by Michael Grieves and the multi-physics models developed by Glassgen. Unlike simple modeling, a DT ensures dynamic correspondence between the virtual and physical entities through continuous data exchange and feedback. Key methodological aspects of creating and operating a DT are identified, including issues related to the integration of heterogeneous data, the selection of appropriate models, and ensuring interoperability. A critical analysis of the advantages and limitations of this technology is provided, taking into account considerations regarding the need for validation and the limitations associated with the availability and quality of data. The prospects for further development of DT are discussed, particularly the integration with artificial intelligence technologies and big data analytics to address complex tasks related to sustainable development and the minimization of anthropogenic impact on the environment, including aspects of pollution monitoring and natural resource management. It is specifically emphasized that, unlike a simple database, a DT possesses an operational model that enables the interpretation and use of data to solve specific tasks.
... The concept of digital twins, first proposed by Dr. Michael Grieves in 2003 during the Product Lifecycle Management (PLM) Executive Course at the University of Michigan, encompasses three main components: physical space, products in virtual space, and the bidirectional data connection between physical and virtual spaces [221,222]. Digital twins leverage physical experiments and integrate multidisciplinary, multi-physical quantities, multi-scale, and multi-probability simulation processes based on physical simulation models, sensor signals, and other data [223,224]. This integration enables comprehensive mapping in virtual space, reflecting the full lifecycle process of the corresponding physical equipment. ...
Laser cladding with wire feeding is an advanced surface modification technology that has seen significant growth in recent decades, attributed to its high deposition rate, efficient material utilization, strong metallurgical bonding, low dilution ratio, and minimal heat-affected zone. Despite these advantages, the thermo-physical-metallurgical mechanisms underlying the laser cladding process are intricate, making it challenging to discern the potential relationships among materials, design, process, and performance using only traditional expertise or conventional expert systems. This paper provides a comprehensive review of recent advancements in the field, focusing on process development, parameter optimization, numerical simulation–based fundamental studies, real-time sensing, and quality control of laser cladding with cold- and hot-wire feeding techniques. Key developments in multi-physics modeling of the laser wire cladding process are summarized, highlighting the understanding of heat transfer, mass transport in the molten pool, and the structural mechanical behavior of clad components, which are influenced by rapid local melting and subsequent solidification, as well as critical metallurgical transformations within the metal microstructure of clads. Additionally, the paper discusses sensor selection and feature extraction for real-time monitoring of clad surface profiles and the detection of volumetric defects, which can significantly impact clad quality. The integration of multi-sensor fusion with machine learning is proposed as a promising direction for developing intelligent online quality monitoring systems for laser cladding, offering improved reliability and accuracy in predicting key quality attributes. This approach could also facilitate adaptive process control, ensuring desired quality levels are maintained despite variations in material properties, component design, and process variables. Furthermore, the concept of a digital twin for the laser wire cladding system is introduced, aiming to provide interactive feedback among materials, design, process, and performance. This virtual reality system, which combines experimental measurements with numerical simulations, has the potential to enhance the product development process by providing a comprehensive understanding of the system’s behavior.
... Digital Twins (DTs) have emerged as a key technology that enables real-time monitoring and optimization of complex systems, referred to as the Actual Twin (AT). Glaessgen and Stargel [6] defined a DT as a multiscale and dynamic representation of a complex system whose functions are to mirror the life of its corresponding AT. As such, the synchronization between the DT and its AT is fundamental and is achieved through the automated integration of real-time data from the AT. ...
Despite the indisputable benefits of Continuous Integration (CI) pipelines (or builds), CI still presents significant challenges regarding long durations, failures, and flakiness. Prior studies addressed CI challenges in isolation, yet these issues are interrelated and require a holistic approach for effective optimization. To bridge this gap, this paper proposes a novel idea of developing Digital Twins (DTs) of build processes to enable global and continuous improvement. To support such an idea, we introduce the CI Build process Digital Twin (CBDT) framework as a minimum viable product. This framework offers digital shadowing functionalities, including real-time build data acquisition and continuous monitoring of build process performance metrics. Furthermore, we discuss guidelines and challenges in the practical implementation of CBDTs, including (1) modeling different aspects of the build process using Machine Learning, (2) exploring what-if scenarios based on historical patterns, and (3) implementing prescriptive services such as automated failure and performance repair to continuously improve build processes.
... Based on real-time monitoring and data analysis, DTs technology significantly improved production efficiency and product quality. In 2012, NASA redefined the concept of DTs as highly accurate simulations that integrate multiphysics and multiscale modeling with probabilistic methods [30] . These DTs provide real-time reflections of their physical counterparts by using historical data, real-time sensor inputs, and detailed physical models to ensure high fidelity and timely updates. ...
Embodied artificial intelligence (AI) is reshaping the landscape of intelligent robotic systems, particularly by providing many realistic solutions to execute actions in complex and dynamic environments. However, Embodied AI requires a huge data generation for training and evaluation to ensure safe interaction with physical environments. Therefore, it is necessary to build a cost-effective simulated environment that can provide enough data for training and optimization from the physical characteristics, object properties, and interactions. Digital twins (DTs) are vital issues in Industry 5.0, which enable real-time monitoring, simulation, and optimization of physical processes by mirroring the state and action of their real-world counterparts. This review explores how integrating DTs with Embodied AI can bridge the sim-to-real gap by transforming virtual environments into dynamic and data-rich platforms. The integration of DTs offers real-time monitoring and virtual simulations, enabling Embodied AI agents to train and adapt in virtual environments before deployment in real-world scenarios. In this review, the main challenges and the novel perspective of the future development of integrating DTs and Embodied AI are discussed. To the best of our knowledge, this is the first work to comprehensively review the synergies between DTs and Embodied AI.
... Different definitions were introduced of DTs. DTs are complex simulations built upon historical and real-time data designed to replicate the condition of a physical object [102]. They are also defined as a representation of a physical product that utilises data from the physical element or system to mimic real-world behaviour in the corresponding virtual counterpart [103]. ...
With the movement of the construction industry towards Construction 5.0, Digital Twin (DT) has emerged in recent years as a pivotal and comprehensive management tool for predictive strategies for infrastructure assets. However, its effective adoption and conceptual implementation remain limited in this domain. Current review works focused on applications and potentials of DT in general infrastructures. This review focuses on interpreting DT’s conceptual foundation in the flexible pavement asset context, including core components, considerations, and methodologies. Existing pavement DT implementations are evaluated to uncover their strengths, limitations, and potential for improvement. Based on a systematic review, this study proposes a comprehensive cognitive DT framework for pavement management. It explores the extent of enhanced decision-making and a large-scale collaborative DT environment. This study also identifies current and emerging challenges and enablers, as well as highlights future research directions to advance DT implementation and support its alignment with the transformative goals of Construction 5.0.
... Michael Grieves przedstawił jego koncepcję na konferencji związanej z inteligentnymi systemami wytwórczymi w branży lotniczej. Agencja NASA zaproponowała w 2012 r. następującą definicję [6,7]: "Bliźniak cyfrowy to zintegrowana, wielofizyczna, wieloskalowa, probabilistyczna symulacja złożonego produktu, która stosuje najlepszy z dostępnych modeli fizycznych, dane z sensorów w czasie rzeczywistym, dane historyczne itp., aby odzwierciedlić funkcjonowanie odpowiadającego mu bliźniaka". W oryginalnej koncepcji bliźniaka cyfrowego M. Grieves zwrócił uwagę na fundamentalne znaczenie wzajemnego przepływu informacji między bliźniakami i oddziaływania cyfrowej repliki na układ fizyczny w czasie rzeczywistym. ...
This paper presents the concept of a matrix digital shadow of an IoT sensor network. The differences between digital twin and digital shadow are discussed and the choice of the sensor network shadow concept is justified. A matrix description of such a network is presented and the concept of εk − neighborhood of sensor is introduced. Formulas for linear models of plus and star εk − neighborhoods are provided. Selected examples show the possibility of detecting and eliminating some security threats to sensor networks.
... The concept of a Digital Twin was first introduced by Grieves in 2003 in the context of Product Lifecycle Management (PLM) [15]. A DT is defined as a virtual representation of a physical object or system that integrates real-time data, simulation models, and analytics to replicate the dynamic behavior of its physical counterpart [16]. Unlike traditional monitoring systems, DT enables real-time synchronization between the physical and digital domains, allowing for proactive optimization, predictive maintenance, and enhanced decision-making [17]. ...
This paper introduces an intelligent optimization framework that integrates Digital Twin (DT) technology, deep learning, and a tailored Multi-Restart Bayesian Optimization with Random Initialization (MRBORI) to enhance parameter control and yield in semiconductor manufacturing. The proposed framework synergizes XGBoost-based feature selection, which identifies critical parameters in high-dimensional spaces, with a custom deep learning surrogate model that captures complex nonlinear interactions. Building on these insights, the MRBORI strategy leverages multiple optimization restarts, each initialized randomly, to mitigate local minima risks and systematically explore broad parameter spaces. Experimental validation using real-world data from an epitaxial silicon carbide (Epi SiC) process demonstrates notably tighter thickness control and improved yield compared to traditional methods. By unifying DT-driven real-time insights with advanced machine learning and multi-restart optimization, this framework offers a robust and precise solution for tackling the complexities of modern semiconductor manufacturing.
... The second approach is fully autonomous control, or the typical closed-loop control system, where control systems are integrated into the digital twin to automate responses such as optional parameter adjustment and maintenance actions (Glaessgen and Stargel, 2012). Fully autonomous control can be difficult to achieve for non-trivial real-world systems, often lacks generalizability, and may be dangerous if applied in the wrong contexts (Huang et al., 2023). ...
As next-generation scientific instruments and simulations generate ever larger datasets, there is a growing need for high-performance computing (HPC) techniques that can provide timely and accurate analysis. With artificial intelligence (AI) and hardware breakthroughs at the forefront in recent years, interest in using this technology to perform decision-making tasks with continuously evolving real-world datasets has increased. Digital twinning is one method in which virtual replicas of real-world objects are modeled, updated, and interpreted to perform such tasks. However, the interface between AI techniques, digital twins (DT), and HPC technologies has yet to be thoroughly investigated despite the natural synergies between them. This paper explores the interface between digital twins, scientific computing, and machine learning (ML) by presenting a consistent definition for the digital twin, performing a systematic analysis of the literature to build a taxonomy of ML-enhanced digital twins, and discussing case studies from various scientific domains. We identify several promising future research directions, including hybrid assimilation frameworks and physics-informed techniques for improved accuracy. Through this comprehensive analysis, we aim to highlight both the current state-of-the-art and critical paths forward in this rapidly evolving field.
... However, there are some popular definitions, such as the one proposed by Glaessgen and Stargel: "an integrated multiscale, multi-physics probabilistic simulation of a complex product that uses the best available physical model and sensing information to mirror the information of its physical twin. " (Glaessgen & Stargel 2012). ...
Structural health monitoring (SHM) is the most direct and advanced method for understanding the evolution laws of structures and ensuring structural safety. The essence of SHM lies in diagnosing structural health by analyzing monitoring data. Since the introduction of machine learning paradigm for SHM, using machine learning methods to analyze the monitoring data, identify, and evaluate structural health status has become a prominent research topic in this field. For complex bridge structures, diagnosing structural health based on highly incomplete monitoring data presents an inherent high-dimensional problem. Machine learning methods are particularly well-suited for addressing these issues due to their capabilities in effective feature extraction, efficient optimization, and robust scalability. This article provides a brief review of the developments in machine learning-based structural health diagnosis, including data cleaning, structural modal parameters estimation, structural damage identification, digital twin technology, and structural reliability assessment. Additionally, the paper discusses related open questions and potential directions for future research.
Digital twin technology is shaking things up in the manufacturing world by creating realtime virtual copies of physical assets. But as this technology evolves, keeping these systems safe and secure is more important than ever. Digital twins work by constantly exchanging data between the real world and their virtual counterparts, which makes them a target for cyberattacks. If these attacks succeed, they can throw off the accuracy of the virtual models and disrupt manufacturing processes. This research looks into security automation solutions specifically for digital twin systems in manufacturing settings, prioritizing monitoring and defending against new cyber threats. We’re suggesting automated security tools that use anomaly detection algorithms to keep an eye on the data flowing into digital twins, allowing us to spot and react to any unusual or harmful activities in real-time. Plus, we’re introducing automated lockdown features that protect the digital twin environment by isolating any compromised components to stop further damage. The goal of this framework is to boost the security, accuracy, and reliability of digital twin systems, ensuring these innovative technologies can be used safely and effectively in critical manufacturing operations. This paper dives into the design, implementation, and challenges of securing digital twins in the manufacturing space and adds to the ongoing push to weave security automation into the Industry 4.0 framework.
Reinforcement learning-based methods are gaining popularity in energy management strategy (EMS) for hybrid electric vehicles (HEVs). Most of the literature in this area focuses on pure simulation with limited scenarios, while real-time control through embedded implementation is still limited. In this paper, based on the basic DQN algorithm, design of mode transition control strategy, parameterized functions, and directed Wasserstein distance, the embedded scenario-adaptive D4QN-EMS to control series-parallel multi-speed (SPMS) HEVs is established. MIL and HIL tests on the strategy using standard driving cycles and nine driving cycles representing characteristics of various Chinese cities are conducted. The results show that the proposed EMS can adaptively update the strategy according to the characteristic of actual driving scenarios without frequent mode switching, demonstrating excellent performance in both transient performance and fuel economy of the SPMS HEV. Across all test scenarios, the average total fuel consumption of the A-D4QN-EMS (4.52 L/100 km) improved by 9.73%, 4.21%, and 2.43% compared to the RB-EL (4.96 L/100 km), RB-PL (4.71 L/100 km), and D4QN (4.63 L/100 km) strategies, respectively.
The human-centered technology in smart manufacturing has been considered as the new generation technology to serve intelligent, green manufacturing systems, also known as human-cyber-physical systems. The human digital twin strategy provides a manufacturing system with cutting-edge technology to achieve human–machine interaction in real time and unmanned work environment for the safety consideration. This chapter comprehensively describes the essential role of humans in manufacturing activities and systematically reviews the research advances on human digital twins. Addressing the issues of safety, human–machine–environment interaction, and health monitoring in the manufacturing process, a human skeleton digital twin framework is proposed for the human behaviors-oriented in the manufacturing process based on predictive modeling technologies. The feasibility and effectiveness of the proposed framework are verified by using a medical image-based human lumbar spine model during manufacturing process, which exhibits how the human–machine dynamic interactions work in the manufacturing process and how the biomechanical features of human skeleton are detected in real-time during the manufacturing process. Several proposals on model construction, data collection, and production service, are present for addressing the issues and challenges in the human digital twin.
Emerging technologies seem to bring out unprecedented forms of human alienation, from the general issue of what we may define as engineered humans to the particular issue of what we may define as predicted humans. First, I shall reflect upon the way in which our language increasingly changes when we address our relationship with emerging technologies. More precisely, the change of our language shows a kind of optimisation that is taken to the extreme, starting with the optimisation of humans’ performances: the more engineered humans are (in that they identify their purpose not with feeling good, for instance, but with performing in faster and more profitable ways), the better they are (in that they measure themselves not against typically human values, such as feeling good, for instance, but against typically engineering values, such as efficiency). But a remarkable paradox emerges: the more humans work on optimising themselves, the more they (paradoxically) work on moving optimisation from themselves, i.e. their capabilities as autonomous humans (starting with self-perception and self-mastery), to technologies, i.e. ways of engineering, specifically automating, themselves. Second, I shall reflect upon the technological prediction of humans’ future as what may be thought of as the most extreme way to engineer them. Even though the cradle of Western culture, from scripture to mythology, continuously stresses that knowledge can be dangerous, specifically for humans, the history of Western culture coincides with the increasing effort to make knowledge the primary objective of human activities, from philosophy itself to science and technology. More precisely, the more technology develops, the more its primary objective is knowing our future, i.e. predicting our future, from our bodies’ performances to our minds’ performances. Are humans still free to determine their own future even surprisingly, i.e. against all odds?
The tissue paper converting system involves critical stages, including unwinding, embossing, folding, stacking, cutting, and packaging. Despite its maturity, challenges such as production interruptions during roll changes, equipment coordination issues, and unstable packaging speeds persist, affecting overall efficiency. While existing methods like fast roll change mechanisms and automated speed regulation systems have improved individual equipment performance, they fall short in achieving system-wide optimization. This paper proposes a digital-twin-based framework for the tissue paper converting system. High-precision simulation models are developed for key equipment, including the base paper roll stand, folding machine, paper stacker, and packaging machine, enabling real-time system monitoring and prediction. Key performance indicators such as base paper availability, folding speed, stacking status, and packaging progress are effectively predicted, preventing interruptions and reducing downtime. The proposed framework was validated in a real-world application at a Chinese paper manufacturing company. Results show that it increases machine runtime by 3 h per day, improving production efficiency by 15%. This leads to an additional daily output of 35,000 packs, contributing approximately CNY 85,000 in revenue growth. Additionally, the system helps prevent 300 kg of base paper waste daily, saving CNY 600 in manufacturing costs per day.
Circular factories must ensure the functionality and reliability of used components for recombination with other components or subsystems from the same or different product generations. This paper presents a data-driven decision-making framework integrating the Functional Behavior Model and System Reliability Model within a Digital Twin. Data from physical testing is continuously incorporated, simulating recombination scenarios and guiding decision-making on component reprocessing. An angle grinder is used as a case study for demonstration. The proposed framework enhances sustainability and supports the use of reprocessed components in products designed for primary markets.
The rapid expansion of cloud computing has raised concerns about its environmental impact, particularly its carbon footprint. Sustainable IT operations focus on minimizing energy consumption and greenhouse gas emissions while maintaining performance and scalability. This paper explores strategies for measuring, optimizing, and reducing the carbon footprint of cloud infrastructure. It discusses key metrics such as Power Usage Effectiveness (PUE), Carbon Usage Effectiveness (CUE), and Energy Reuse Effectiveness (ERE) to assess sustainability. Optimization techniques, including workload distribution, renewable energy integration, and AI-driven resource allocation, are examined. Furthermore, policy frameworks, green data center designs, and industry best practices are analyzed to promote energy-efficient cloud operations. The findings highlight the importance of balancing sustainability with operational efficiency, fostering a greener digital economy.
The rapid evolution of Hybrid IT infrastructure-integrating on-premises, cloud, and edge computing-demands innovative approaches for efficient management, performance optimization, and predictive maintenance. Digital Twins, virtual replicas of physical and digital assets, offer a transformative solution by enabling real-time monitoring, simulation-based analysis, and predictive insights. This paper explores the development and implementation of Digital Twins for Hybrid IT environments, focusing on key aspects such as predictive maintenance, simulation environments, and performance testing strategies. Predictive maintenance powered by Digital Twins leverages AI-driven analytics to anticipate system failures, optimize resource allocation, and reduce downtime. Simulation environments enable organizations to model complex IT ecosystems, assess architectural changes, and enhance scalability without disrupting live operations. Furthermore, advanced performance testing strategies using Digital Twins facilitate stress testing, failure prediction, and optimization of workloads under varying conditions. By integrating Digital Twins into Hybrid IT management, enterprises can achieve proactive decision-making, enhanced system reliability, and cost efficiency. This paper also highlights real-world implementations, best practices, and future trends in leveraging Digital Twin technology to drive the next generation of IT infrastructure management.
Başta savunma sanayii olmak üzere birçok alanda kullanılan dijital ikiz teknolojisi, son yıllarda afet yönetiminde de kullanılmaktadır. Yerel yönetimler tarafından dijital ikiz teknolojisinin verileri afet öncesi gerçekçi bir şekilde uygulandığı zaman, kaynak planlamasından kaçak yapı denetimine kadar birçok boyutta kent analizlerini inceleyebilecektir. Dijital ikiz ile yapılan bu hazırlık çalışmaları afet sırasında ve sonrasında yerel yönetimlerin olaylara karşı hızlı müdahale etmesini ve verimli sonuçlar almasını sağlayacaktır. Bu çalışma, literatür taramasıyla, yapılan çalışmalardan bir derleme çalışması olarak yapılmıştır. Çalışmada, Japonya'daki yerel yönetimlerin dijital ikiz teknolojisini kullanarak afet yönetiminde nasıl bir rol oynadığı incelenmiştir. Çalışmada, Japonya’nın örnek olarak seçilmesinin nedeni, ülkenin afet yönetimi alanında dünya çapında en gelişmiş dijital ikiz sistemlerinden birine sahip olmasıdır. Çalışmada; akademik literatür, resmi belgeleri, yerel yönetimlerin afet politikalarına ilişkin raporlar ve teknoloji kullanımına dair ikincil veriler analiz edilmiş ve yerel yönetimlerin teknolojiyi nasıl benimsediğini anlamayı amaçlamıştır. Dijital ikiz teknolojisinin, afetleri önlemede dayanıklı ve akıllı bir kentin kurulmasında etkisini belirlemek amacı doğrultusunda Japonya'daki dijital ikiz uygulama örnekleri incelenmiştir. Doğal afetlerin olumsuz etkilerini en aza indirebilme konusunda dijital ikiz teknolojisinin faydalarının ve uygulamalarının deprem ile yaşayan ve bu afet durumunu başarı ile yöneten Japonya örneği temelinde araştırılması, çalışmanın özgün bir yapıda olmasını sağlamıştır. Bu çalışma sonucunda Japonya’nın depremlere karşı dijital ikiz teknolojisini başarılı bir şekilde uyguladığı görülmüştür.
In precision cardiology, virtual replicas (VRs) hold promise for predicting arrhythmias by leveraging patient-specific data and biophysics knowledge. A crucial first step is creating VRs of cardiac tissue based on retrospective patient data. However, VRs aim to replicate biopotential conduction directly, whereas only non-invasive methods are feasible for clinical use on real organs and tissues. This discrepancy challenges our understanding of VR applicability limits. This study aims to enhance the mathematical template of VR by developing an in vitro validation complement. We performed a frame-by-frame comparison of in vitro optical mapping of biopotential conduction with VR predictions. Patient-specific self-organized tissue samples from human induced pluripotent stem cell-derived cardiomyocytes (CMs) with diffuse fibrosis were utilized as VR prototypes. High-resolution optical mapping recordings (Δx = 117 ± 4 μm, Δt = 7.69 ms) and immunostaining were used to reproduce fibrotic samples of linear size 7.5 mm. We applied data-driven Bayesian optimization of the Cellular Potts model (CPM) to study wave propagation at the subcellular level. The modified CPM accurately reflected the “perinatal window” until the 20th day of differentiation, affecting CMs’ self-organization. The percolation threshold of virtual conductive pathways reached 0.26 (0.27 ± 0.03 of CMs in vitro), yielding a spatial correlation of amplitude maps with Pearson's coefficients of 0.83 ± 0.02. As a proof-of-concept, we demonstrated that CPM-enhanced VR could predict wavefront trajectories in optical mapping recordings, showing that approximating fibrosis distribution is crucial for improving VR prediction accuracy.
The chapter explores the convergence of Internet of Things (IoT) and Digital Twins, two transformative technologies that are reshaping industries across the globe. IoT, with its ability to connect devices and collect vast amounts of data, is revolutionizing how we interact with our environment. Digital Twins, on the other hand, offer a virtual representation of physical assets, enabling simulation, monitoring, and optimization in real-time. By combining these technologies, organizations can create powerful ecosystems where physical and digital worlds merge seamlessly. The chapter discusses the fundamentals of IoT and Digital Twins, their individual impacts on various industries, and the synergies that arise when they are integrated. It also delves into case studies and future trends, illustrating how this integration is driving innovation and efficiency in fields such as manufacturing, healthcare, and smart cities.
Digital Twin (DT) technology has been employed as an innovator prototype in all industries; it adds to the creation of a virtual picture of physical facilities, processes and systems. This concept which evolved from the engineering areas and the manufacturing industries has extended to other fields of operation like manufacturing, health, transport, and agricultural and urban development fields. Real-time data, stream acquisition, modeling and simulation, operation optimization, decision-making improvement, analytics, and DTs allow businesses to achieve better insight. Next generation DT means next generation DT is an innovation of DT. This paper provides brief description on what DT technology is and the DT technology of the next generation, the elements of the DT at the center and how DT works. Furthermore, we consider the problems, prospects, and tendencies of the application of DTs. Hence, the paper presents a focus on the DT enabled machine learning architecture, security concerns and remedies. To justify that DT are useful for designing the future of interconnected data driven systems, examples of articles and industry are presented.
Local Digital Twins (LDTs) appear as a novel approach within the fourth industrial revolution for advancing governance and citizen participation, exploring new ways and providing new opportunities in sensing data, understanding complex phenomena and forecasting the future. The idea of LDTs, that is the application of digital twin technology in a municipality, region or even country level, promises new services and digital means for citizens, in an effort to tackle most of the problems and provide new services to all aspects of life. Within this context, the present chapter analyses the notion, the possibilities, and the state-of-the-art applications of the LDT concept, and then focuses on the possible future developments of this novel technical and societal approach. In this direction, the chapter presents what can be achieved through the convolution of LDTs with breakthrough developments in emerging technologies such as Artificial Intelligence, Machine Learning and the Internet of Things (IoT), which ultimately result in the development of new applications and services for the intelligent city and the region of tomorrow.
Reengineering of the aircraft structural life prediction process to fully exploit advances in very high performance digital computing is proposed. The proposed process utilizes an ultrahigh fidelity model of individual aircraft by tail number, a Digital Twin, to integrate computation of structural deflections and temperatures in response to flight conditions, with resulting local damage and material state evolution. A conceptual model of how the Digital Twin can be used for predicting the life of aircraft structure and assuring its structural integrity is presented. The technical challenges to developing and deploying a Digital Twin are discussed in detail.