Deep learning-driven digital twin system for pedestrian tracking and evacuation load assessment in public spaces

Digital twin (DT) systems, which involve creating virtual replicas of physical objects or systems, have the potential to transform healthcare by offering personalised and predictive models that grant deeper insight into a patient's condition. This review explores current concepts in DT systems for musculoskeletal (MSK) applications through an overview of the key components, technologies, clinical uses, challenges, and future directions that define this rapidly growing field. DT systems leverage computational models such as multibody dynamics and finite element analysis to simulate the mechanical behaviour of MSK structures, while integration with wearable technologies allows real-time monitoring and feedback, facilitating preventive measures, and adaptive care strategies. Early applications of DT systems to MSK include optimising the monitoring of exercise and rehabilitation, analysing joint mechanics for personalised surgical techniques, and predicting post-operative outcomes. While still under development, these advancements promise to revolutionise MSK care by improving surgical planning, reducing complications, and personalising patient rehabilitation strategies. Integrating advanced machine learning algorithms can enhance the predictive abilities of DTs and provide a better understanding of disease processes through explainable artificial intelligence (AI). Despite their potential, DT systems face significant challenges. These include integrating multi-modal data, modelling ageing and damage, efficiently using computational resources and developing clinically accurate and impactful models. Addressing these challenges will require multidisciplinary collaboration. Furthermore, guaranteeing patient privacy and protection against bias is extremely important, as is navigating regulatory requirements for clinical adoption. DT systems present a significant opportunity to improve patient care, made possible by recent technological advancements in several fields, including wearable sensors, computational modelling of biological structures, and AI. As these technologies continue to mature and their integration is streamlined, DT systems may fast-track medical innovation, ushering in a new era of rapid improvement of treatment outcomes and broadening the scope of preventive medicine. Level of Evidence: Level V.

New technologies enable the creation of digital twin systems (DTS) combining continuous data collection from children’s home and artificial intelligence (AI)-based recommendations to adapt their care in real time. The objective was to assess whether children and adolescents with asthma would be ready to use such DTS. A mixed-method study was conducted with 104 asthma patients aged 8 to 17 years. The potential advantages and disadvantages associated with AI and the use of DTS were collected in semi-structured interviews. Children were then asked whether they would agree to use a DTS for the daily management of their asthma. The strength of their decision was assessed as well as the factors determining their choice. The main advantages of DTS identified by children were the possibility to be (i) supported in managing their asthma (ii) from home and (iii) in real time. Technical issues and the risk of loss of humanity were the main drawbacks reported. Half of the children (56%) were willing to use a DTS for the daily management of their asthma if it was as effective as current care, and up to 93% if it was more effective. Those with the best computer skills were more likely to choose the DTS, while those who placed a high value on the physician–patient relationship were less likely to do so. Conclusions: The majority of children were ready to use a DTS for the management of their asthma, particularly if it was more effective than current care. The results of this study support the development of DTS for childhood asthma and the evaluation of their effectiveness in clinical trials.What is Known:• New technologies enable the creation of digital twin systems (DTS) for children with asthma.• Acceptance of these DTSs by children with asthma is unknown.What is New:• Half of the children (56%) were willing to use a DTS for the daily management of their asthma if it was as effective as current care, and up to 93% if it was more effective.•Children identified the ability to be supported from home and in real time as the main benefits of DTS.Supplementary InformationThe online version contains supplementary material available at 10.1007/s00431-022-04754-8.

Objectives/Scope A digital twin is a virtual representation of a real-world system used to digitally model performance, identify inefficiencies, and design solutions to improve its physical counterpart. With the success of digital twin systems in various scenarios, the digital twin system of gas station is expected to effectively improve the management efficiency and intelligence level of gas stations. Some typical applications include data analysis, traffic prediction, and route planning in gas station, etc. Methods, Procedures, Process The key part of the digital twin system of gas station is how to achieve accurate and efficient vehicle detection and tracking under various environmental conditions. Aiming at this goal, this paper proposes a practical vehicle detection and tracking method for gas station scenarios. We assume the digital twin system consists of a number of digital cameras and precisious 3D models of scene and facilities in gas station. We then present the proposed vehicle detection and tracking pipeline which includes the following three steps: 1) camera internal and external parameters calibration with known scene; 2) vehicle detection and real-time multi-target tracking, and 3) cross-camera re-identification and occlusion handling. Results, Observations, Conclusions We have conducted extensive experiments on several datasets. Experimental results show that the proposed method has good robustness to lighting and occlusion, and can effectively solve the problem of vehicle detection and tracking for the digital twin system of gas station. Novel/Additive Information In a real gas station scenario, real-time tracking of multiple vehicles can be achieved with an accuracy over 90%.

At present, the automation production line has problems such as insufficient intelligence level. The intelligent monitoring, control and improvement of product quality and efficiency are the key common technologies faced by advanced manufacturing industry. Self-learning time varying digital twin (DT) system for intelligent monitoring is proposed in the paper. In the process of automatic production line processing and workpiece detection, an DT consisting of physical production line layer, edge monitoring layer and cloud evolution layer is built. The DT system realizes self-learning time-varying through active excitation of processing parameter optimization. The workpiece quality is a real-time representation of the tool condition, and the tool wear sensitive features extracted by the deep learning algorithm. Through the two-way drive of time-varying physical and virtual data, the tool wear characterization model can be evaluated, self-learning, updated and verified timely in the light of the actual condition to achieve tool condition monitoring and processing parameter optimization. The prediction model is self-iterative and simplified in the cloud, and the edge side is quickly matched and adaptive. Self-learning time-varying DT system based on self-driving of manufacturing process can adaptively improve the ability of intelligent monitoring.

With the rise of digital twin technology, the application of digital twin technology to industrial automation provides a new direction for the digital transformation of the global smart manufacturing industry. In order to further improve production efficiency, as well as realize enterprise digital empowerment, this paper takes a welding robot arm as the research object and constructs a welding robot arm digital twin system. Using three-dimensional modeling technology and model rendering, the welding robot arm digital twin simulation environment was built. Parent-child hierarchy and particle effects were used to truly restore the movement characteristics of the robot arm and the welding effect, with the help of TCP communication and Bluetooth communication to realize data transmission between the virtual segment and the physical end. A variety of UI components were used to design the human-machine interaction interface of the digital twin system, ultimately realizing the data-driven digital twin system. Finally, according to the digital twin maturity model constructed by Prof. Tao Fei's team, the system was scored using five dimensions and 19 evaluation factors. After testing the system, we found that the combination of digital twin technology and automation is feasible and achieves the expected results.

The ready-mix concrete supply chain is highly disruptive due to its product perishability and Just-in-Time (JIT) production style. A lack of technology makes the ready-mix concrete (RMC) industry suffer from frequent production failures, ultimately causing high customer dissatisfaction and loss of revenues. In this paper, we propose the first-ever digital twin (DT) system in the RMC industry that can serve as a decision support tool to manage production risk efficiently and effectively via predictive maintenance. This study focuses on the feasibility of digital twins for the RMC industry in three main areas holistically: (1) the technical feasibility of the digital twin system for ready-mix concrete plant production risk management; (2) the business value of the proposed product to the construction industry; (3) the challenges of implementation in the real-world RMC industry. The proposed digital twin system consists of three main phases: (1) an IoT system to get the real-time production cycle times; (2) a digital twin operational working model with descriptive analytics; (3) an advanced analytical dashboard with predictive analytics to make predictive maintenance decisions. Our proposed digital twin solution can provide efficient and interpretable predictive maintenance insights in real time based on anomaly detection, production bottleneck identification, process disruption forecast and cycle time analysis. Finally, this study emphasizes that state-of-the-art solutions such as digital twins can effectively manage the production risks of ready-mix concrete plants by automatically detecting and predicting the bottlenecks without waiting until a production failure happens to react.

Constant attempts have been made throughout human history to find solutions to complex issues. These attempts resulted in industrial revolutions and the transition from manual labour to the use of machines and new technologies. The latest advances in Artificial Intelligence (AI) are revolutionary. The use of these smart technologies in mining can lead to increased profitability, enhanced performance, improved safety, and better adherence to environmental regulations. In this paper, the applications of AI and digital twin systems in mining operations are reviewed, covering various components, including mineral exploration, drilling, blasting, loading, hauling, mineral processing, and environmental issues. Critical data inputs for each component are identified, and relevant tools and methods are discussed. These will be used to facilitate the development of digital twin models with the capabilities of learning, simulation, prediction, and optimisation. This study provides valuable insights into fully integrated digital twin mining systems, which will significantly improve mining efficiency and sustainability. Although innovative technologies, such as IoT and other intelligent tools, are increasingly being used in the mining sector, many mining processes still depend on human oversight to deal with challenges such as remote operations, geological variability, high investment costs, and a skills gap. There is, therefore, significant potential to enhance the use of sensors and IoT devices to support data collection for more integrated and powerful digital twin systems, to drive further innovation and operational improvements across the mining value chain.

The integration of Artificial Intelligence (AI) and Digital Twin (DT) technology is reshaping modern manufacturing by enabling real-time monitoring, predictive maintenance, and intelligent process optimisation. This paper presents the design and partial implementation of an AI-enabled Digital Twin System (AI-DT) for manufacturing, focusing on the deployment of Generative AI (GAI) and Predictive AI (PAI) modules. The GAI component is used to augment training data, perform geometric inspection, and generate 3D virtual testing environments from multiview video input. Meanwhile, PAI leverages sensor data to enable proactive defect detection and predictive quality analysis in welding processes. These integrated capabilities significantly enhance the system's ability to anticipate issues and support decision-making. While the framework also envisions incorporating Explainable AI (EAI), Context-Aware AI (CAI), and Agentic AI (AAI) for future extensions, the current work establishes a robust foundation for scalable, intelligent digital twin systems in smart manufacturing. Our findings contribute toward improving operational efficiency, quality assurance, and early-stage digital-physical convergence.

The era of big data produces massive data, and carrying out data mining can effectively obtain effective information in huge data, which provides support for efficient decision-making and intelligent optimization. The purpose of this paper is to establish a digital twin system, preprocess massive data using random matrix theory, and design the knowledge graph construction process based on digital twin technology. The BERT model, attention mechanism, BiLSTM model, and conditional random field of the joint deep learning technology are used to identify the knowledge entities in the digital twin system, extract the knowledge relations through the Transformer model, and utilize the TransE model for the knowledge representation in order to construct the knowledge graph. Then, the constructed knowledge graph is combined with the multi-feature attention mechanism to build an anomaly data prediction model in the digital twin system. Finally, the effectiveness of the methods in this paper is validated through corresponding experiments. The TransE model is used for knowledge representation. The accuracy of ternary classification is higher than 80% in all cases, and the MR value decreases by up to 64 compared to the TransR model. The F1 composite score of the anomaly data prediction model is 0.911, and the AUC value of the validation of knowledge graph effectiveness is 0.702. Combining deep learning with the knowledge graph, the knowledge information can be realized in the digital twin system’s accurate representation and enhance the data mining ability of the digital twin system.

The integration of Artificial Intelligence (AI) with Digital Twin (DT) technology has redefined the engineering landscape by enabling real-time, data-driven decision-making across the entire lifecycle of assets. This book chapter presents an in-depth exploration of AI-driven Digital Twin systems as transformative enablers of predictive modeling, intelligent control, and sustainable asset management. It addresses the evolution, architecture, and functional frameworks of Digital Twins while emphasizing the convergence of AI methodologies, including machine learning, deep learning, and reinforcement learning, in achieving adaptive and autonomous operations. The discussion extends to predictive maintenance, fault diagnosis, and Remaining Useful Life (RUL) estimation models that enhance operational reliability and performance resilience. Security, privacy, and trust mechanisms within interconnected Digital Twin ecosystems are analyzed to ensure data integrity and safe information exchange. The chapter also highlights standardization and interoperability protocols that support seamless integration across heterogeneous industrial platforms. A comprehensive focus is placed on the application of Digital Twins throughout the engineering asset lifecycle—from conceptual design and development to operational optimization and end-of-life management. AI-enhanced simulations enable real-time optimization, while data-driven prescriptive analytics facilitate intelligent decision-making for resource utilization and performance enhancement. The fusion of Digital Twin systems with circular economy principles advances environmental sustainability by promoting closed-loop material flows, energy efficiency, and reduced carbon footprints. Emerging challenges in large-scale implementation, such as computational scalability, data governance, and ethical AI adoption, are also discussed to provide a holistic understanding of this evolving domain. The chapter concludes that AI-enabled Digital Twins represent a paradigm shift toward intelligent, self-adaptive, and sustainable engineering systems. By bridging the gap between physical and digital domains, these systems are establishing the foundation for next-generation industrial transformation that aligns innovation with sustainability, resilience, and operational excellence.

This paper combines the digital twin system modeling method to conduct an in‐depth study and analysis of graph‐theoretic combinatorial optimization. This paper provides new ideas and approaches for optimal numerical analysis work by studying the digital twin modeling method that integrates digital modeling and graph theory combination, provides theoretical support for safe, stable, and economic operation of the system, proposes a solution for digital twin model based on big data platform, focuses on the nearest neighbor propagation (AP) and graph theory combination, solves the digital twin real‐time monitoring data asynchronous, incomplete problem, and applies the algorithm to the digital twin model based on the big data platform for data preprocessing to achieve better results. This paper also presents a web‐based digital twin system based on intelligent practical needs, analysis, and comparison of existing models, combined with digital twin technology, detailing the differences and connections between the various levels of numerical analysis and the implementation of this data in various fields, such as user management, equipment health management, product quality management, and workshop 3D navigation and detailed modeling of the digital twin system based on this numerical analysis to realize remote online monitoring, analysis, and management. In this paper, for the numerical analysis process, firstly, the key technologies of modeling and simulation operation control of production line based on digital twin are studied, and the rapid response manufacturing system based on a digital twin is designed and validated. Secondly, a scheduling technology framework for capacity simulation evaluation and optimization is established, and batching optimization, outsourcing decision, and rolling scheduling techniques are thus proposed to form a batching optimization algorithm based on priority rules, which realizes batching processing, outsourcing decision, and rolling scheduling of production orders to optimize equipment utilization and capacity. Finally, digital twin‐based modeling is designed, and the validation results demonstrate the system’s superior performance in achieving information interaction between physical and virtual production lines, optimization of numerical analysis, and display of results.

Many core technologies of Industry 4.0 have gained substantial advancement in recent years. Digital Twin (DT) has become the key technology and tool for manufacturing industries to realize intelligent cyber-physical integration and digital transformation by leveraging these technologies. Although there have been many DT-related works, there is no standard definition, unified framework, and implementation approach of DT until now. Widely developing DTs for the manufacturing industry is still challenging. Thus, this paper proposes a novel implementation framework of digital twins for intelligent manufacturing, denoted as IF-DTiM, which possesses several distinct merits to distinguish itself from previous works. First, IF-DTiM fully utilizes new-generation container technology so that DT-related applications and services can be packaged in a self-contained way, rapidly deployed, and robustly operated with the capabilities of failover, autoscaling, and load balancing. Second, it leverages existing intelligent cloud manufacturing services to realize the intelligence for DT externally in a scalable and plug-and-play manner instead of using traditional approaches to embed intelligence in DT. Third, IF-DTiM contains Product DT for products, Equipment DT (i.e., EQ DT) for equipment, and Process DT for production lines, which can generically fulfill the demands and scenarios to achieve intelligent manufacturing for various manufacturing industries. Testing results show that IF-DTiM can achieve remarkable performance in rapid deployment and real-time data exchanges of DT-related applications. Finally, we develop an example DTiM system for CNC machining based on IF-DTiM to demonstrate its efficacy and applicability in facilitating the manufacturing industry to build their DT systems. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Developing Digital Twin (DT) systems to realize intelligent manufacturing is challenging. The proposed IF-DTiM (Implementation Framework of Digital Twins for Intelligent Manufacturing) provides a novel container-technology and cloud-manufacturing-service-based systematic methodology for building DTiM. In this paper, we present the system architecture and several operational scenarios (e.g., how to create and use DTs) of IF-DTiM, together with the design of its core functional mechanisms (e.g., rapid deployment scheme for DT, real-time data exchange for DT, DT interface pattern, and general workflow architecture for DT). Also, an example DTiM system for CNC machining based on IF-DTiM is presented to facilitate the practitioners to adopt the designs and niches in IF-DTiM to build their desired DTiM systems.

Blockchain empowered access control for digital twin system with attribute-based encryption

Marine engines play a decisive role in ensuring the stable operation of vessels. With the rapid advancement of artificial intelligence technologies, digital twin (DT) systems, leveraging sensor-based data acquisition and AI-driven methodologies, enable the integration between physical and virtual spaces. Notably, the engine fault diagnosis functionality within DT systems is critical to ensuring their practicality and reliability. This study focuses on the Zi-chai 8180 methanol–diesel dual-fuel engine and proposes a fault diagnosis method for application in marine dual-fuel engine DT systems. The methodology tightly integrates engine bench test data, historical data, simulation models, performance and fault databases, and a diagnostic decision-making system. A multi-label learning algorithm is employed as the core of the coupled fault diagnosis framework to achieve DT system-based coupled fault identification. The experimental results show that the proposed diagnostic method achieves an overall accuracy of 96.18% on 13 fault datasets, with a low Hamming Loss of 0.0069 and a high Average Precision of 0.9776, outperforming the comparative multi-label learning algorithms. These results demonstrate the effectiveness of the proposed approach for coupled fault diagnosis and provide a feasible basis for continuous online optimisation and information interaction in marine engine digital twin systems.

Construction method and case study of digital twin system for combine harvester