Twin Model Research Articles

Optimization of structural reinforcement assessment for architectural heritage digital twins based on LiDAR and multi-source remote sensing

This study investigates the geometric modelling of architectural heritage digital twins constructed based on multi-source point cloud data and its effectiveness in structural reinforcement assessment. Particular emphasis has been placed on the use of static stiffness rules to identify areas of structural weakness in the geometric models of digital twins and the need for their reinforcement, in order to prevent potential structural problems and to ensure the long-term preservation of the built heritage. Taking Yingxian wooden pagoda as a study case, based on the collection of multi-source point cloud data, the digital twin geometric model is constructed through fine modelling, decoupling of digital models, and geometric transformation. This enhances the true reflection of the column-architrave structure morphology, providing a more accurate model for structural stress analysis. Based on verifying the accuracy of the digital twin geometric model, the instability conditions are identified through static stiffness rules and the deformation values at multiple points are analyzed, enabling precise identification of weak areas in the column-architrave structure. Two types of reinforcement measures are designed and simulated for the structural weak areas identified through the geometric modelling, and the optimal reinforcement scheme is obtained after detailed analysis, according to which specific adjustments and optimization strategies are proposed to enhance the overall stability and durability of the structure. The results showed that the maximum deformation value of 4.65 mm existed in column M2W23, which required reinforcement. Aluminum reinforcement reduced the deformation to 3.5 mm (24.7% reduction), while CFRP fabric reinforcement was more effective, reducing the deformation to 2.8 mm (39.7% reduction), showing high stability. The research results demonstrate the potential application of digital twin technology in architectural heritage preservation and restoration, providing methodological and empirical guidance for heritage preservation research.

Application of the digital twin model in higher education

Application of the digital twin model in higher education

The genetic and environmental etiology of novel frequency-driven regional parcellations of abnormal white matter.

The prevalence of white matter disease increases with age and is associated with cerebrovascular disease, cognitive decline, and risk for dementia. MRI measures of abnormal signal in the white matter (AWM) provide estimates of damage, however, regional patterns of AWM may be differentially influenced by genetic or environmental factors. With our data-driven regional parcellation approach, we created a probability distribution atlas using Vietnam Era Twin Study of Aging (VETSA) data (n = 475, mean age 67.6 years) and applied a watershed algorithm to define separate regional parcellations. We report biometrical twin modeling for five anatomically distinct regions: (1) Posterior, (2) Superior frontal and parietal, (3) Anterior and inferior frontal with deep areas, (4) Occipital, and (5) Anterior periventricular. We tested competing multivariate hypotheses to identify unique influences and to explain sources of covariance among the parcellations. Family aggregation could be entirely explained by additive genetic influences, with additive genetic variance (heritability) ranging from 0.69 to 0.79. Most genetic correlations between parcellations ranged from moderate to high (rg = 0.57-0.85), although two were small (rg = 0.35-0.39), consistent with varying degrees of unique genetic influences. This proof-of-principle investigation demonstrated the value of our novel, data-driven parcellations, with identifiable genetic and environmental differences, for future exploration.

Research on key technologies of railway station codification digital twin

According to the requirements of railway transportation, to ensure that locomotives can receive frequency-shifted signal information through the track within the station, the track circuits must be codified. Due to the increased speed of train operations, braking has become more challenging, increasing the possibility of running a red signal compared to the present. Therefore, it is imperative to implement pre-overlay codification technology and equipment suitable for use in speed-enhanced sections. As the pre-overlay coding method must be adopted, it requires the isolation components in the interface equipment to have "fault-safe" performance. When the isolation component fails, the current or voltage introduced into the parallel track relay must not cause malfunction. Therefore, ensuring that the current and voltage of each component in the codified track meet the requirements is crucial. This research aims to establish a circuit simulation model based on MATLAB Simulink to achieve dynamic simulation of the pre-overlay ZPW-2000 codification circuit diagram of the 25Hz phase-sensitive track circuit in the electrified section. Through this model, the electrical characteristic indicators such as current, voltage, and waveform of each component on the circuit can be observed in real-time. This helps optimize the design and maintenance of the railway signal system, improving the safety and efficiency of train operations and contributing to the establishment of a digital twin model for the entire railway system's signal system.

BR-FEEL: A backdoor resilient approach for federated edge learning with fragment-sharing

In the resource-constrained federated edge learning (FEEL) systems, fragment-sharing is an efficient approach for multiple clients to cooperatively train a giant model with billions of parameters. Compared with the classical federated learning schemes where the local model is fully trained and exchanged by each client, the fragment-sharing only requires each client to optionally choose a parameter-fragment to train and share, according to its storage, computing, and networking abilities. However, when the full model is no longer delivered in fragment-sharing, the backdoor attacks hidden behind the fragments become harder to be detected, which introduces formidable challenge for the security of FEEL systems. In this paper, we firstly show that the existing fragment-sharing works suffer a lot from the backdoor attacks. Then, a Backdoor-Resilient approach, named BR-FEEL, is introduced to defend against the potential backdoor attacks. Specifically, a twin model is built by each benign client to integrate the parameter-fragments from others. A knowledge distillation process is designed on each client to transfer the clean knowledge from its twin model to local model. With the twin model and knowledge distillation process, our BR-FEEL approach makes sure that the local models of the benign clients will not be backdoored. Experiments on CIFAR-10 and GTSRB datasets with MobileNetV2 and ResNet-34 are conducted. The numerical results demonstrate the efficacy of BR-FEEL on reducing attack success rates by over 90% compared to other baselines under various attack methods.

Cross-domain diagnosis for polymer electrolyte membrane fuel cell based on digital twins and transfer learning network✰

Existing research on fault diagnosis for polymer electrolyte membrane fuel cells (PEMFC) has advanced significantly, yet performance is hindered by variations in data distributions and the requirement for extensive fault data. In this study, a cross-domain adaptive health diagnosis method for PEMFC is proposed, integrating the digital twin model and transfer convolutional diagnosis model. A physical-based high-fidelity digital twin model is developed to obtain diverse and high-quality datasets for training diagnosis method. To extract long-term time series features from the data, a temporal convolutional network (TCN) is proposed as a pre-trained diagnosis model for the source domain, with feature extraction layers that can be reused to the transfer learning network. It is demonstrated that the proposed pre-trained model can hold the ability to accurately diagnose the various fuel cell faults, including pressure, drying, flow, and flooding faults, with 99.92 % accuracy, through the effective capture of the long-term dependencies in time series data. Finally, a domain adaptive transfer convolutional network (DATCN) is established to improve the diagnosis accuracy across diverse fuel cells by learning domain-invariant features. The results show that the DATCN model, tested on three different target domain devices with adversarial training using only 10 % normal data, can achieve an average accuracy of 98.5 % (30 % improved over traditional diagnosis models). This proposed method provides an effective solution for accurate cross-domain diagnosis of PEMFC devices, significantly reducing the reliance on extensive fault data.

Dynamic Capabilities for the Twin Transformation Climb: A Capability Maturity Model

AbstractDigital transformation and sustainability transformation are at the top of organizations’ agendas to remain competitive. While guidance on both transformations exists separately, even more research on integrating digital and sustainability transformation, namely twin transformation, is required. Specifically, deeper knowledge about relevant twin transformation capabilities and progress is needed for effective implementation. To enhance the understanding and provide corresponding guidance, we developed a twin transformation capability maturity model focusing on dynamic capabilities required to realize twin transformation based on a structured literature review and interviews with 13 experts. Further, we demonstrated its use with a technology service provider. Our contribution is twofold: First, accounting for organizations’ twin transformation starting points in terms of their digitalization and sustainability experience and expertise, we reveal three pathways to becoming a twin transformer. Second, our work provides an overview of 45 relevant twin transformation capabilities structured along six capability dimensions and four maturity stages. Our work also provides relevant practical implications supporting organizations in assessing their twin transformation maturity building the foundation for targeted capability development.

A Study on Service-Oriented Digital Twin Modeling Methods for Weaving Workshops

A Study on Service-Oriented Digital Twin Modeling Methods for Weaving Workshops

Chronic pain is specifically associated with updating working memory: a longitudinal twin study.

Worse executive function (EF) is associated with chronic pain and could mechanistically contribute to pain chronification. It is unclear whether there is overall impairment in EFs or whether there are impairments in specific cognitive domains. Furthermore, the possible genetic risk underlying these associations has not been tested. Participants were from the Colorado Longitudinal Twin study; 786 same-sex twins completed a battery of EF tasks at ages 23 and/or 28 and 634 of these twins self-reported chronic pain at mean age = 28.1; prevalence = 27.76% using the Brief Pain History Questionnaire. The EF tasks were used to define a Common EF factor and 2 factors specific to updating working memory and shifting mental set. We estimated the phenotypic and genetic associations of stable EF variance across ages 23 and 28, as well as EF variance unique to age 28, with pain. With respect to stable EF variance, pain phenotypically correlated with the Updating-specific factor (r = -0.21, P = 0.008) but did not significantly correlate with the Common EF factor (r = -0.06, P = 0.350) nor with the Shifting-specific factor (r = -0.03, P = 0.709). There were no significant phenotypic correlations between pain and EF variance unique to age 28. A twin model indicated that pain and Updating-specific variance share genetic risk (rA = -0.46, P = 0.005) but not environmental risk (rE = 0.05, P = 0.844). Updating working memory shares a phenotypic and genetic relationship with pain in young adults. Impairments in gating or monitoring pain signals may play a mechanistic role in pain development.

Affordable generic digital twins for existing building environment management and an onsite deployment

The energy consumption during the operation and maintenance phase of buildings is huge. As the built-up area in China increases, the demand for energy conservation in existing buildings has become a key focus of its dual carbon policy. Intelligent operation and maintenance based on digital twins is an emerging means to reduce carbon emissions from buildings, but it faces some problems in the process of promotion. Complete digital and intelligent transformation requires significant investment and has certain requirements for project parties and operation and maintenance teams. Small businesses or individual households have relatively simple requirements for intelligent operation and maintenance scenarios and do not require complete digital twins. To address the above issues, this article uses an affordable universal digital twin framework to provide a digital solution for intelligent operation and maintenance of existing buildings. This solution allows networking communication between devices and uses IoT modules to monitor and control the environment. This digital twinning model can reduce the measurement and control of energy-consuming end devices without on-site transformation and has rich scalability. This article uses the solution to deploy an office at a university in Henan Province and specifically measures the power consumption of displays, indoor environment, and air conditioning. According to the needs, it expands the space occupation, fans, air handlers, lights, and other end devices of the digital twin. The digital twin accurately presents the energy consumption of the office during extreme weather conditions, which has an auxiliary role in promoting digital twins in the region and optimizing energy consumption in existing buildings.

Does Catch-Up Growth Come with a Cognitive Cost? Cognitive Outcome and Growth Patterns in Growth Discordant Identical Twins

To determine whether it is the magnitude of early postnatal catch-up growth (CUG) in response to fetal growth restriction (FGR) or the FGR itself that negatively impacts cognitive outcome in a model of monochorionic twins discordant for fetal growth. This analysis is part of the LEMON study, a cohort study including all monochorionic twins with selective FGR aged 3 through 17years. Growth measurements as documented by our primary care system were collected retrospectively. An age-appropriate neurodevelopmental test was performed generating a full-scale IQ (FSIQ). CUG at 2years was calculated as (weight [kg] at 2years-birth weight [kg]). We used a multivariable regression model investigating the association between FSIQ (outcome) and birth weight zscore, gestational age at birth and CUG at 2years (predictors). Generalized estimating equations accounted for the fact that observations between cotwins are not independent. Median age at follow-up of the 46 included twin pairs was 11 (IQR 8-13) years. Birth weight z score and gestational age at birth were significantly associated with FSIQ, with β-coefficients of 5.897 (95% CI 3.382-8.411), and 2.589 (95% CI 1.227-3.951), respectively (P<.0001). Adjusted for birth weight z score and gestational age, CUG in the first 2years after birth was not significantly associated with FSIQ (β-coefficient 0.108 [95% CI -1.373 to 1.590], P=.886). Our results, combining detailed growth measurements and neurodevelopmental follow-up in a discordant identical twin model, demonstrate that FGR itself rather than early postnatal CUG has negative consequences for cognitive development.

Real-time digital twin of autonomous ships based on virtual-physical mapping model

The advancement of intelligent technology has propelled the development of smart unmanned vessels into a new phase. To address the urgent demands of current smart ship development, this paper develops a comprehensive ship digital twin system based on a virtual-real mapping algorithm, focusing on the fundamental elements of digital twin model construction. Using the smart unmanned experimental ship Dolphin 1 as a prototype, a digital twin virtual model is proposed. This system leverages real-time internal and external data from the entire vessel to track its navigational status, performance indicators, sailing trends, and surrounding flow field information, offering coordinated “human-machine” navigation assistance. Based on historical data collected from the vessel's long-term navigation, a real-time precise prediction of the vessel's navigational state and hydrodynamic performance is conducted using physics-informed neural network algorithm. This establishes a self-learning iterative virtual-physical mapping model that enables autonomous updates and evolution. As the real navigation data of the vessel continuously update, the virtual model can more accurately simulate the vessel's state in real time. The proposed digital twin model has been tested through sea trials under real sea conditions, demonstrating its high accuracy, robustness, and potential for enhancing navigational safety and efficiency. This system marks a significant step forward in the integration of digital twin technology with maritime navigation, providing a valuable tool for the future development of smart shipping.

GIS-Based Digital Twin Model for Solar Radiation Mapping to Support Sustainable Urban Agriculture Design

GIS-Based Digital Twin Model for Solar Radiation Mapping to Support Sustainable Urban Agriculture Design

Digital twin for subcritical extraction driven by data-mechanism fusion

Abstract Addressing the key issue of low automation in the production process due to the complex associations involved in sub-critical extraction, this study focuses on sub-critical extraction as the subject matter. It integrates data models with mechanism models to construct a multidimensional digital twin model and conduct systematic research. By combining simulation methods with real-time experimental data, the study establishes multilevel machine characteristics of data, behavior, and mechanisms, and identifies data patterns. From the perspectives of the physical production line, virtual production line, and data transmission, it builds an interactive mapping platform for multi-source data and carries out corresponding application research.

Digital twin-driven attention-guided convolutional networks for intelligent fault diagnosis across different domains

Fault diagnosis of rolling bearings is crucial in industries to ensure the reliability, safety, and economic feasibility of mechanical systems. Conventional data-driven methods for fault diagnosis depend on pre-existing datasets containing various failure modes for training. However, obtaining such datasets can be challenging, especially in critical industrial environments, hindering the applicability of these methods across different scenarios. To address this challenge, this research introduces a novel approach called a digital twin-driven attention-guided convolutional network (DTACN) for bearing fault diagnostics with limited data. This study offers two significant enhancements: (1) Development of an intricate digital twin model for bearings, which includes multi-scale Kinetic simulations of the bearing’s operational parameters. This model utilizes the architectural characteristics of the bearing and the severity of the failure to predict the vibratory system’s response accurately; and (2) Establishment of a domain adaptation-based framework employing deep convolutional models and attention mechanism to transfer knowledge from simulated signals to real signals. This framework facilitates efficient fault recognition even in scenarios with limited prior knowledge. The effectiveness of the proposed approach has been rigorously validated through comprehensive experiments.

A digital twin model of urban utility tunnels and its application

Background Multiple pipelines in utility tunnels may lead to various accidents and serious social impact. In the era of digitalization, how to better model the operation of a utility tunnel, dynamically predict the accident evolutions, and support corresponding decision-makings are essential issues. Methods In this study, a CFD-based digital twin framework for accidents in utility tunnels is proposed. First, Kalman filtering is applied to correct the parameter drift of sensors used for long-term monitoring. A data interaction system is then developed based on Internet of Things (IOT) and OPC Unified Architecture (OPC UA) to comprehensively manage data transmission within the utility tunnel. Subsequently, a natural gas leakage prediction model is developed to enable the efficient prediction of the spatial and temporal distribution in the case of leakage. Finally, these components are integrated for visualization in a digital twin platform for natural gas leakage in utility tunnels. Additionally, numerical simulations are employed to validate of the proposed method. Results The utility tunnel data transmission system based on IoT and OPC UA proposed in this paper is case-validated. By comparing the simulation results at 10 s, 20 s, 30 s, and 40 s, the model accurately predicts the methane concentration at the leak position after 10 seconds and maintains acceptable accuracy thereafter. The simulation results of different cases are introduced to verify the reliability of the risk indicator proposed in this paper, which increases with the leakage rate. Finally, A process for visualizing numerical simulation is proposed into a digital twin. Conclusions The proposed predictive digital twin technology facilitates the rapid risk assessment of and emergency management of natural gas accidents in utility tunnels. Based on the results of predictive model, a risk indicator is introduced to evaluate the natural gas accidents.

Testing the causal impact of amyloidosis on total Tau using a genetically informative sample of adult male twins.

The amyloid cascade hypothesis predicts that amyloid-beta (Aβ) aggregation drives tau tangle accumulation. We tested competing causal and non-causal hypotheses regarding the direction of causation between Aβ40 and Aβ42 and total Tau (t-Tau) plasma biomarkers. Plasma Aβ40, Aβ42, t-Tau, and neurofilament light chain (NFL) were measured in 1,035 men (mean = 67.0 years) using Simoa immunoassays. Genetically informative twin modeling tested the direction of causation between Aβs and t-Tau. No clear evidence that Aβ40 or Aβ42 directly causes changes in t-Tau was observed; the alternative causal hypotheses also fit the data well. In contrast, exploratory analyses suggested a causal impact of the Aβ biomarkers on NFL. Separately, reciprocal causation was observed between t-Tau and NFL. Plasma Aβ40 or Aβ42 do not appear to have a direct causal impact on t-Tau. In contrast, Aβ aggregation may causally impact NFL in cognitively unimpaired men in their late 60s.

Novel optimal sensor placement method towards the high-precision digital twin for complex curved structures

The complex shape of the structure and the new needs for high-precision in digital twin modeling pose challenges for sensor placement optimization. A novel optimal sensor placement towards the high-precision digital twin (OSP-HDT) method is proposed for complex curved structures. It comprises three key aspects. Firstly, leveraging the spatial dimensionality reduction method, the complex curved surface is simplified into a planar representation. Subsequently, candidate sensor placement points can be easily identified by dividing the background mesh in the plane and screening them within the curved surface. These candidate points are then binary encoded to facilitate the subsequent optimization. Secondly, the method collects result data from the finite element model, treating it as virtual sensor data. Using this data, a surrogate model is constructed and then the objective function is formulated based on both the global and local critical areas precision of the surrogate model. Thirdly, the sensor placement optimization model is constructed, followed by optimization design using the efficient multi-objective covariance matrix adaptive evolutionary strategy. Through the steps above, the optimal sensor placement can be identified. To validate the proposed OSP-HDT method, an experiment is conducted on an S-shaped variable cross-section stiffened shell, with the construction of the corresponding digital twin. Compared to the uniform placement with an equivalent number of sensors, the OSP-HDT method demonstrated a significant 9.0% improvement in global precision and a remarkable 62.1% enhancement in local precision of critical areas. Furthermore, when compared to the random sensor placement strategies, the OSP-HDT method exhibited a 20.5% increase in global precision, together with a 44.2% increase in the local precision. Notably, even when compared to the full sensor placement, the OSP-HDT method can maintain comparable local precision, while significantly reducing the number of sensors by 77.6%. The above comparison indicates that the proposed OSP-HDT method can build a digital twin model with higher global and local precision for complex structures.

Digital Twin and federated learning enabled cyberthreat detection system for IoT networks

The widespread deployment of Internet of Things (IoT) devices across various smart city applications presents significant security challenges, increased by the rapidly evolving landscape of cyber threats. Traditional security solutions, including those using Federated Learning with federated averaging, suffer from inefficiencies due to random node selection and partial data sampling, which can hinder the detection of comprehensive network-wide attacks. This paper introduces a novel Cyberthreat Detection System for IoT networks that leverages Digital Twin technology and an optimized Federated Learning approach. Our hypothesis implies integrating Digital Twin models within an IoT security framework to improve real-time cyberthreat detection capabilities. We implement a 'Adaptive Thresholding with Early Stopping method' based methodology in Federated Learning to systematically train and aggregate local models based on predefined training rounds, thereby ensuring that all local models contribute to the global model until a target accuracy is achieved. This method significantly improves the detection of zero-day attacks by reducing dependency on random selections and partial data. The system architecture features Digital Twins of IoT medical infrastructure components—such as radiology, intensive care, and outpatient care—positioned at the network edge to minimize latency and bandwidth usage. Comparative evaluations of our model against traditional federated averaging methods demonstrate superior performance, with enhancements in model aggregation efficiency evidenced by higher F1 scores and reduced CPU usage. Specifically, our distributed digital twin environment at the edge layer shows 14% and 33% latency reductions compared to fog and cloud-based implementations, respectively. This study highlights the potential of Digital Twin and advanced Federated Learning methodologies to secure IoT networks against evolving and growing cyber threats.

Digital twin-assisted intelligent fault diagnosis for bearings

Abstract Data-driven intelligent fault diagnosis methods generally require a large amount of labeled data and considerable time to train network models. However, obtaining sufficient labeled data in practical industrial scenarios has always been a challenge, which hinders the practical application of data-driven methods. A digital twin (DT) model of rolling bearings can generate labeled training dataset for various bearing faults, supplementing the limited measured data. This paper proposes a novel DT-assisted approach to address the issue of limited measured data for bearing fault diagnosis. First, a dynamic model of bearing with damages is introduced to generate simulated bearing acceleration vibration signals. A DT model is constructed in Simulink, where the model parameters are updated based on the actual system behavior. Second, the structural parameters of the DT model are adaptively updated using least squares method with the measured data. Third, a Vision Transformer (ViT) -based network, integrated with short-time Fourier transform, is developed to achieve accurate fault diagnosis. By applying short-time Fourier transform at the input end of the ViT network, the model effectively extracts additional information from the vibration signals. Pre-training the network with an extensive dataset from miscellaneous tasks enables the acquisition of pre-trained weights, which are subsequently transferred to the bearing fault diagnosis task. Experiments results verify that the proposed approach can achieve higher diagnostic accuracy and better stability.