Search

ANPR cameras allow the automatic detection of vehicle license plates and are increasingly used for law enforcement. However, also statistical data generated by ANPR cameras are a potential source of urban insights. In order for this data to reach its full potential for policy-making, we research how this data can be shared in digital twins, with researchers, for a diverse set of machine learning models, and even Open Data portals. This article's key objective is to find a way to anonymize and aggregate ANPR data in a way that it still can provide useful visualizations for local decision making. We introduce an approach to aggregate the data with geotemporal binning and publish it by combining nine existing data specifications. We implemented the approach for the city of Kortrijk (Belgium) with 43 ANPR cameras, developed the ANPR Metrics tool to generate the statistical data and dashboards on top of the data, and tested whether mobility experts from the city could deduct valuable insights. We present a couple of insights that were found as a result, as a proof that anonymized ANPR data complements their currently used traffic analysis tools, providing a valuable source for data-driven policy-making. [ABSTRACT FROM AUTHOR]

The chief objective of manufacturing process improvement efforts is to significantly minimize process resources such as time, cost, waste, and consumed energy while improving product quality and process productivity. This paper presents a novel physics-informed optimization approach based on artificial intelligence (AI) to generate digital process twins (DPTs). The utility of the DPT approach is demonstrated in the case of finish machining of aerospace components made from gamma titanium aluminide alloy (γ-TiAl). This particular component has been plagued with persistent quality defects, including surface and sub-surface cracks, which adversely affect resource efficiency. Previous process improvement efforts have been restricted to anecdotal post-mortem investigation and empirical modeling, which fail to address the fundamental issue of how and when cracks occur during cutting. In this work, the integration of in-situ process characterization with modular physics-based models is presented, and machine learning algorithms are used to create a DPT capable of reducing environmental and energy impacts while significantly increasing yield and profitability. Based on the preliminary results presented here, an improvement in the overall embodied energy efficiency of over 84%, 93% in process queuing time, 2% in scrap cost, and 93% in queuing cost has been realized for γ-TiAl machining using our novel approach. [ABSTRACT FROM AUTHOR]

An approach to the development of models for the digital description of the process of smelting a semi-finished product in an electric-arc furnace using machine-learning methods is presented. The capabilities and advantages of the models developed are shown considering, as an example, the oxidation (reduction) of metal impurities during smelting. [ABSTRACT FROM AUTHOR]

The European Commission (EC) has launched the European Green Deal communication, setting out the path for a fundamental transformation of Europe. Key element in this policy is a fully sustainable food system outlined in the farm-to-fork strategy. Such strategy requires a systems approach in which all aspects related to the production and consumption of sufficient and healthy food are considered, including economic, environmental (climate, ecosystems) and social aspects. Here, we present the systems approach concept for food production, following the farm-to-fork principle as embraced by the EC, and elaborate on how digitalisation and Artificial Intelligence (AI) can solve the challenges that a sustainable food system imposes. We present a number of research and innovation challenges and illustrate these by some specific examples. It is concluded that AI and digitalisation show great potential to support the transition towards a sustainable food system. This development will impact the roles and interactions of the actors in the entire value chain from farmers to consumers. Policy recommendations are made for a successful future implementation of AI in sustainable food production. • System approach is needed to achieve sustainable food systems. • AI and digitalisation are key to the transition towards sustainable food systems. • Data availability and use is important for actors in all stages from farm to fork. • Policy recommendations for a successful AI implementation in food systems. [ABSTRACT FROM AUTHOR]

A new idea of machine learning-based technological process segmentation with the use of multi-sensor measurement is proposed in this article. The proposed segmentation of the machining process through appropriate measurement data modelling provides valuable insight that is necessary for technological parameters optimization or predictive maintenance. By combining multi-sensor industrial measurement and data science, this new solution is a more advanced and effective way of determining qualitative characteristics of the machining process that must be taken into account when developing smart analytical approaches, such as digital twins. An experimental measuring system consisting of accelerometers and current transducers is described. The system is implemented on an industrial CNC machine in order to assess operating conditions of the spindle and axis drives during the milling process. A novel method of detecting and segmenting the milling phases is proposed, involving data preprocessing and time-series signals data analysis to detect specific patterns or features that are indicative of each phase of the milling process. When applied in smart structures or digital twins, the proposed segmentation method provides similar information to that obtained by tomography imaging; therefore, the new method is called as virtual tomography. The developed phase segmentation method is of vital practical importance in terms of industrial implementation of technological process measurement and diagnostic systems. Especially as it can provide valuable information concerning elementary cutting zones and their influence on the process efficiency or influence of the composite structure layers machining on the tool wear, not available using hitherto known methods. [Display omitted] • Novel unsupervised technique identifies milling phases, enhancing tool SOH prediction. • Phase-specific feature analysis boosts predictive model accuracy in tool monitoring. • Feature analysis reveals key features impacting milling process and tool health. • Approach advances manufacturing efficiency through virtual tomography in smart structures. [ABSTRACT FROM AUTHOR]

Dynamic grasping is a crucial technology in the field of underwater robotics, playing an essential role in executing complex tasks. However, traditional control methods encounter challenges in achieving an efficient and stable dynamic grasping process due to the complexities and uncertainties of underwater environments. This paper introduces a novel black-box intelligent optimization algorithm named Social Learning with Actor–Critic (SLAC) for the dynamic grasping of underwater robots. The core architecture of SLAC is based on the integration of two key algorithms: Intelligent Social Learning (ISL) for intelligent optimization and Soft Actor–Critic (SAC) for reinforcement learning. ISL enhances SAC by supplying a larger number of transitions, whereas SAC improves ISL with more effective strategies. These algorithms interact synergistically, augmenting their respective strengths throughout the learning process. To evaluate SLAC's performance, a comparison is made with six state-of-the-art methods across eight continuous control benchmark cases. The results highlight SLAC's exceptional learning capability and performance benefits. Furthermore, virtual reality software for the underwater robot and a corresponding digital twin system have been developed. The SLAC algorithm is trained in the digital twin environment before its application in the actual underwater setting. Through interactive training and iterative learning, both simulated and experimental results demonstrate the robot's proficiency in achieving efficient and stable dynamic grasping, effectively adapting to various underwater environments' variations and complexities. • A Social Learning with Actor-Critic algorithm for black box robot control systems. • SLAC combines the advantages of intelligent optimization and reinforcement learning. • SLAC outperforms DDPG, SAC, PPO, EA, ISL, ERL in Mujoco benchmarks. • Develop underwater robot VR software and digital twin system platform. • Design grasping tasks and verify the superiority of SLAC in engineering simulations. [ABSTRACT FROM AUTHOR]

Irregular ocean waves contribute to random and non-linear hydrodynamic forces on marine and offshore platforms, in particular those made of slender bodies such as jack-ups. Keeping track of the structural fatigue, integrity, and reliability renders benefits to these platforms such as enabling predictive maintenance and risk-based decision support. While computational techniques are useful in providing insights to deepen our understanding of the physics involved, these are resource-intensive and not suited for predictive capabilities. Here we introduce an effective deep learning method based on Long Short Time Memory (LSTM) to predict unsteady hydrodynamic forces on jack-up legs, which are mainly governed by non-linear drag forces, as well as dynamic responses of the jack-up in terms of reaction forces and hull motion. The numerical OF-ABAQUS solver (one-way fluid-structure coupling) designed for jack-up by Li et al. (2022, 2023) is used to generate a database for the deep neural network, which takes in wave elevation time series as the input. A leaky non-linear rectification is used to trace the relationship between wave elevation (as the input) and hydrodynamic forces as well as structural responses (as the outputs). The LSTM model is trained using a stochastic gradient descent method, and the results are compared with the full-order numerical simulations. Once the hyper-parameters of the LSTM algorithm are identified, further tuning for each sea-state is not required. Instead, the same LSTM algorithm can be used for different sea-states. The predictions made with our LSTM model are real-time, 96,000 times faster than the full-order simulations, within a 6% error threshold, and use a negligible amount of central processing unit (CPU) power. This powerful tool can be used to obtain real-time predictions using computers on offshore platforms without high-performance computers inland. Further, the proposed LSTM-based method can be applied to create digital twins for jack-up platforms. [ABSTRACT FROM AUTHOR]

• Integrated digital twins Framework for revolutionizes defect diagnosis for pumps. • Domain adaptation boosts diagnostic model accuracy. • Promising potential for scalable industrial applications. Bearing defects in centrifugal pumps represent a prevalent source of equipment failure, often resulting in significant downtime and maintenance expenses. Deep learning algorithms can be used to detect defects. However, in the real world, there is always a scarcity of labeled data. To address this challenge, we propose a framework integrating digital twin technology with domain adaptation for accurate diagnosis of bearing defects. The proposed framework leverages the concept of digital twins to create a virtual representation of the pump bearing, enabling real-time monitoring and simulation of operating conditions. Domain adaptation techniques are then applied to transfer knowledge from synthetic data generated by the digital twin to the actual operating environment, overcoming the domain gap between synthetic and real-world data. The results highlight the potential of digital twin-assisted combined with domain adaptation techniques for enhancing predictive maintenance strategies in industrial applications. [ABSTRACT FROM AUTHOR]

Health monitoring of structures using ultrasonic guided waves is an evolving technology with potential applications in monitoring pipelines, civil bridges, and aircraft components. However, the sensitivity of guided waves to external parameters affects the reliability of monitoring systems based on them. These influencing factors and experimental related factors cannot be perfectly modeled, which give rise to the discrepancy between numerical simulations and experimental measurements. Therefore, it is important to address this inevitable discrepancy and generate close-to-experiment simulations. In this work, we present a deep learning-based Digital Twin framework containing multi-fidelity modeling to reduce the discrepancy between measurements and simulations and a deep generative model to generate close-to-experiment guided wave responses by harnessing the vital characteristics of the two sources. These realistic simulations (close to experiment) can then be used in assessing the reliability of health monitoring system by generating probability of detection curves. Furthermore, they can also be used for augmenting the training data for a machine learning algorithm. We use a measurement dataset corresponding to crack propagation and simulations to validate the proposed framework. The results show that the discrepancy is indeed reduced to a great extent, furthermore, we also show that this framework enables the computation of probability of detection from close-to-experiment data as a direct consequence of rapid generation of realistic simulations. • Structural health monitoring based on ultrasonic guided waves. • Discrepancy reduction between simulations and experiments. • A novel unifed deep neural network model blending simulations and experiments. • Enhanced ultrasonic guided waves signals generation. • Discrepancy quantification through phase and amplitude based misfit metrics. • Metamodel based computation of probability of detection. [ABSTRACT FROM AUTHOR]

The lubrication regimes of a laboratory scale journal bearing were analysed with wide band acoustic emission (AE) measurements. The analysis was supported by data-based clustering of AE data. Digital twin of the journal bearing was generated with Simpack multi-body simulation software to study opportunities for developing a hybrid methodology for more complex systems monitoring. The AE and data-based clustering approach can be effectively used to reveal fundamental lubrication modes, i.e., hydrodynamic (HL), mixed (ML) and boundary (BL) lubrication as a function of Hersey number, which can be evaluated in situ by utilizing digital twin. Besides AE the other parameters monitored were friction torque, bearing temperature, loading, sliding velocity and oil pressure. The materials used in the experiments were case-hardened 18CrNiMo7–6 steel and nitrided 42CrMo7 steel. The tests were lubricated with synthetic extreme-pressure gear oil (SGN 320) and the bearing temperature was kept constant during the tests. The bearing loading and sliding velocity during tests were varied in the wide range resulting in different lubrication situations. The acoustic emission signals power and frequency content was analysed, and essential features were extracted for data clustering. For lubrication regime change identification the parameters such as signal RMS and coefficient of variation (CV) proved to be important, while signal kurtosis showed to be the most sensitive in discovering anomalies. The high sensitivity requires data filtering to remove erroneous peaks and to reveal real trends more clearly. It is also interesting to notice the changes in AE frequency during changing to different lubrication regime. In literature different clustering and classification methods has been proposed and applied for journal bearing status identification. Here the selected unsupervised clustering method was the mean-shift clustering due to fact, that the lubrication regimes in the Stribeck curve form an inseparable continuum. The algorithm does not require specifying the number of clusters in advance, i.e., the clusters are determined by the algorithm with respect to the data. The results were compared to simulations with digital twin. i.e., by comparing simulated digital twin film thickness and measured AE kurtosis relative to measured Hersey number. It was concluded that digital twins can be utilized as virtual sensor for in situ detecting of lubrication regimes, if it is possible to calibrate the simulation with sensitive measurements, e.g., AE. It is obvious that simulations alone cannot predict suddenly appearing anomalies, such as impurities or surface fatigue failures. • Lubrication regimes in Stribeck curve can be detected with acoustic emission. • The kurtosis showed to be an important feature in detecting lubrication status. • Machine learning data clustering supports near real-time monitoring. • Digital twin can be used as virtual lubrication sensor if calibrated with AE. • Simulations alone cannot predict suddenly appearing anomalies. • With described hybrid approach the monitoring efficiency may be enhanced. [ABSTRACT FROM AUTHOR]

Teorema Milano, BLK Leica Premium Partner, is a company specialized in the distribution of tools for three-dimensional surveying. The use of the digital representation of 3D models is gaining more and more importance in documenting building construction processes, but also in many other areas. However, as popularity increases, false ideas can also arise. All over the world, reality capture technology developed by Leica Geosystems has given many projects a glimpse into the future. Long gone are the days of recording construction site conditions with a tape measure, spending hours crunching numbers and collecting data by hand, point by point. Reality capture was born out of existing and new innovative technologies fused together to capture digital datasets. This technology has allowed users to implement millions of pieces of information directly into the digitization process in order to create complete 3D models. Reality Capture has turned into a tool for capturing the surrounding world by transforming it into digitally manageable information (data, point clouds) as well as flat and two-dimensional static snapshots. We are now able to capture 3D digital twins, also known as digital realities: replicas of objects, people or places in the physical world created in digital form. Since the creation of the Digital Twins we have evolved towards a Smart Digital Reality that brings autonomy to the digital twin to transform its function and utility. Using technologies such as machine learning and artificial intelligence (AI), we can create systems to reduce, or even eliminate, human intervention and develop dynamic workflows that integrate the right data, in the right place and at the right time. Users can leverage data to empower their applications to self-resolve problems, increasing efficiency, productivity, quality and safety across industries. However, as reality capture technology evolves and becomes more widespread, some false myths have been created that we will see in this article. [ABSTRACT FROM AUTHOR]

Digital twin ushers in growth as one cutting-edge technology that enables high-precision, informative and real-time interaction of advanced composites, influencing the paradigm of composite analysis and design in aerospace, automotive, intelligent electronics and other fields. The online and fine evolution of digital twins at scale face challenges due to creating scalable predictions, updates, and controls with coupled information in workflows. In this work, an interactive digital twin methodology for complex composite structures (CCSDT) based on machine learning is introduced. To demonstrate the framework's feasibility and applicability, a hybrid architecture comprising hierarchical deep neural networks (H-DNNs), statistical inference and cross-scale physical constraints is proposed considering the fabric rubber composites (FRC) in aerospace field. The framework predicts 3D displacement and stress fields directly from sensing features and can incorporate dynamic updating and evaluation of computational models into data assimilation. Real-time prediction and uncertainty quantification are verified through synthetic and experimental data, and the capability of CCSDT in perception and decision is demonstrated by a case of cruise state monitoring. The comparison between the measured strain field and the post-processing predicted strain field shows the extensibility of the direct prediction results. These results provide guidance for the development of composite digital twins, stimulating the potential for cost-effective and efficient digital twin services. [Display omitted] [ABSTRACT FROM AUTHOR]

While machine learning (ML) has made significant contributions to the biopharmaceutical field, its applications are still in the early stages in terms of providing direct support for quality-by-design based development and manufacturing of biologics, hindering the enormous potential for bioprocesses automation from their development to manufacturing. However, the adoption of ML-based models instead of conventional multivariate data analysis methods is significantly increasing due to the accumulation of large-scale production data. This trend is primarily driven by the real-time monitoring of process variables and quality attributes of biopharmaceutical products through the implementation of advanced process analytical technologies. Given the complexity and multidimensionality of a bioproduct design, bioprocess development, and product manufacturing data, ML-based approaches are increasingly being employed to achieve accurate, flexible, and high-performing predictive models to address the problems of analytics, monitoring, and control within the biopharma field. This paper aims to provide a comprehensive review of the current applications of ML solutions in the design, monitoring, control, and optimisation of upstream, downstream, and product formulation processes of monoclonal antibodies. Finally, this paper thoroughly discusses the main challenges related to the bioprocesses themselves, process data, and the use of machine learning models in monoclonal antibody process development and manufacturing. Moreover, it offers further insights into the adoption of innovative machine learning methods and novel trends in the development of new digital biopharma solutions. • Provide a review of applications of ML in antibody design and manufacturing. • Identifying challenges related to bioprocesses and process data. • Offering a valuable reference with a thorough discussion and public datasets. • Proposing machine learning (ML) research directions in antibody manufacturing. • Identifying advanced ML solutions for digital twins within biopharma 4.0. [ABSTRACT FROM AUTHOR]

• Numerical simulation modeling is complex and computationally intensive. • Digital twin deployment requires lightweight and responsive systems. • Process sensor data drives deep learning algorithms to implement digital twins. • Generative adversarial networks enable monitoring of heat distribution changes. • Results contribute to weld quality assurance and blade structure optimization. In this paper, a novel method of using deep learning to construct a digital twin of the thermos-compression bonding blade's temperature field is presented. Usually, a heat transfer model based on numerical analysis can calculate the heat distribution in the welding process, but its complex modeling process and heavy computational effort are not appropriate for the deployment of the digital twin concept. The approach proposed in this paper is distinctive because it directly converts the collected process sensor data into the bonding blade's temperature field images and the bonding surface's temperature distribution curves for monitoring the welding process. This is achieved by training the generator and discriminator of the conditional depth convolutional generative adversarial network separately. The network is then capable of predicting the bonding blade's heat distribution within a certain range of welding parameters. Compared to methods based on numerical simulation, this approach is far more effective. Training and testing datasets were created to assess the suggested method's efficacy. Multi-scale structural similarity index, structural similarity index, peak signal-to-noise ratio, difference hash and mean absolute error were used to evaluate the simulations' quality. The results show that the simulation's results and the actual data agree quite well. The temperature changes that occur during the welding process may be quickly and accurately simulated using the proposed technology. [ABSTRACT FROM AUTHOR]

The soaring potential of edge computing leads to the emergence of cloud–edge collaboration. This hierarchy enables the deployment of artificial intelligence models in the cyber–physical venue. This paper presents Dual Digital Twin, the next level of digital twin, in the presence of two levels of communication availability, for battery system real-time monitoring and control in electric vehicles. To implement the dual digital twin concept, an online adaptive model reduction problem is formulated with time scale differences induced by the time sensitivity property of industrial applications and limitations of infrastructure. To minimize the model reduction error and battery system control penalty, the online adaptive battery reduced order model framework is proposed, consisting of the gated recurrent unit neural network to construct battery internal states given Internet of things sensor measurements, and incremental learning techniques to facilitate the update of the reduced-order model given data stream. Moreover, we design the physics-informed update of the neural network using the Lyapunov stability theorem to enhance the synchronization with the physical battery behavior. A Li-ion battery and single particle digital twin model with electrolyte and thermal dynamics are utilized in the simulation to justify the effectiveness of the proposed framework. Numerical results demonstrate 1.70% average reduced-order model prediction error and 43.3% accuracy improvement with the novel physics-informed online adaptive framework. The method is also robust concerning varying environmental factors and noise. • Introduce the dual digital twin concept and its realization in EV batteries. • Online adaptive model reduction problem with intrinsic time scale difference in AIoT system. • Cloud–edge collaborated AIoT online adaptive battery ROM framework. • Physics-informed ROM incremental learning algorithm to track the real system dynamics. [ABSTRACT FROM AUTHOR]

New-generation intelligent construction places higher demands on digitisation and intelligence of tunnel. Digital twin (DT) effectively supports high-fidelity modelling, virtual-real mapping, and analysis-based decision-making but with research in the initial stage. To begin with, this paper delves into the complexity and uncertainty inherent in tunnel construction, highlighting DT as a promising solution compared to exisiting technologies such as Building Information Modelling. Then, a systematic literature survey is conducted, revealing growing focus on DT research topics. To provide comprehensive insights into DT-related technologies and their application in tunnel construction, this paper clusters literature from perspectives of sensor networks, Internet of Things (IoT), computer vision-based twin data acquisition, communication, natural language processing (NLP), automatic control-based connection, and geometric, semantic, analytical integrated twin modelling. These aspects shed light on potentials and limitations of existing researh in developing a functional DT. In response to the challenges of information richness, timeliness, and analytical capabilities, an improved conceptual framework tailored for tunnel is proposed to close the information and control loop. Finally, the paper discusses the prospects and gaps of DT in theory and practice to leverage DT implementation. • Digital Twin greatly enhances the development of intelligent tunnel construction. • A comprehensive literature analysis is conducted to assess status of Digital Twin technologies in tunnel construction. • A close-loop conceptual framework of Digital Twin is proposed. • Gaps and future prospects of Digital Twin for tunnel construction are discussed. [ABSTRACT FROM AUTHOR]

Monitoring Aboveground Net Primary Production (ANPP) is critical to assess not only the current ecosystem status but also its long-term dynamics. In rangelands, the seasonal dynamics of ANPP determines forage availability, stock density, and livestock productivity. To develop a hybrid model to be used as a prediction engine for ANPP in the native grasslands of Uruguay. The model combines a parametric component based on the seasonal dynamics of ANPP, and an artificial neural network (ANN) component used to model the remaining non-linearities, which are mainly related to precipitation and temperature variability. The output of hybrid model is proposed as the "virtual entity" of a digital twin support decision system where the "physical entity" is characterized by a collection of bi-weekly (fortnight) ANPP estimates. Fortnight ANPP data were calculated from MODIS EVI for the 2001–2020 period. A sigmoidal functional response, having three parameters with an explicit biological interpretation, was fitted to the accumulated ANPP as a function of time. Forecasts were generated by extrapolating the sigmoidal functional response fit up to four fortnights ahead. From these fits, we obtained the fortnight ANPP values by differentiating the accumulated fortnight ANPP. Predictions (up to four fortnights) were generated for each fortnight and year. The residuals from these fits were modeled using a multilayer perceptron trained by backpropagation using climate variables as independent variables. The sigmoidal functional response model fit was highly significant for the accumulated ANPP profile. This model also had a high explanatory power for the accumulated ANPP curve. The median of the percentage absolute residuals for forecasts made 1 to 4 fortnights ahead ranged from 17% to 18%. The ANN significantly reduced this unexplained variability in ANPP, showing a median reduction in residuals of 35%, 31%, 30%, and 30% for 1 to 4 fortnights ahead forecasts, respectively, when compared to predictions from the sigmoidal functional response fit. By integrating both parametric and machine learning techniques, the hybrid model developed can make accurate predictions in a way that is both efficient and dependable. The hybrid model not only represents an advantage in terms of predictive power, but it also allows for a deeper understanding of the basic ecological processes involved in forage production. [Display omitted] • We developed a hybrid model (HM) and prediction engine for Aboveground Net Primary Production (ANPP). • Integrating parametric and machine learning techniques, this HM makes predictions that outperform traditional models. • The hybrid approach also helps in the understanding of basic ecological processes involved in forage production. • Applicability includes planning and optimizing grazing management of native grasslands in commercial farms. • We propose the use of the output of the HM as the "virtual entity" of a digital twin decision system to support grassland management. [ABSTRACT FROM AUTHOR]

• Digital twin solution is demonstrated for a CHS X-joint under fatigue loading. • Digital twin is capable of accurately identifying, locating and quantifying cracks. • Relationship between crack size and nearby strains is revealed via substructuring. • Crack diagnosis is performed with affordable strain sensors. • Physics-informed model is validated through strain-interfaced physical twins. This paper aims to introduce a strain-interfaced local digital twin solution for a welded circular hollow section (CHS) X-joint subjected to brace axial loading. The solution comprises a series of machine learning algorithms to (1) identify the presence of cracks, (2) locate the cracks and (3) quantify the extent of cracking. These algorithms make use of strain readings in the vicinity of the crack to perform the diagnosis, representing a remote sensing methodology, thereby eliminating physical inspections. The validation of the proposed methodology includes two experiments – one each in the high and low cycle fatigue regime – demonstrating its wide scale applicability. The success of these experiments highlights the strong potential of affordable strain sensors in crack diagnosis assessments for CHS joints. [ABSTRACT FROM AUTHOR]

Engineering has many necessary fields, and Structural Health Monitoring (SHM) is one of the most important of them. Sometimes in industrial environments, it is difficult and even impossible to collect data containing different real damages. Therefore, the problem of data acquisition represents a primary challenge in designing damage detection systems. The application of digital twin methods based on simulated models and/or Machine Learning (ML) models is a practical way to solve this problem. In this approach, a digital twin is generated for a compromised structure, utilizing a physics-based model to analyze diverse damage scenarios. Subsequently, an ML model is trained using data extracted from the physics-based model, functioning as the digital twin. This research proposes a method based on a digital twin for detecting damages in structures. The data produced from a Floating Wind Turbine (FWT) model was used to evaluate the performance of the proposed digital twin-based method. For this purpose, the FWT structure was simulated using a numerical model to address the data collection problem in the face of various uncertainties, such as changing loading conditions. In line with the concept of digital twin and to reduce the computational time, a Deep Convolution Long Short-Term Memory Neural Network (DCLSTMNN) model was designed and trained only with the frequency data of various scenarios of the simulated FWT model under constant loads (deterministic loads, including constant wind speed and airy wave model) to learn the damage-sensitive features. Then, to demonstrate the robustness of the proposed model under different uncertainties, the DCLSTMNN model was evaluated using the frequency data of the simulated FWT model under variable loading conditions (including Kaimal wind model and JONSWAP wave theory). Some vibration response components unrelated to the nature of the FWT model were removed using the Complete Ensemble Empirical Mode Decomposition (CEEMD) method. Then, the reconstructed vibration responses were used to create the frequency data using the Frequency Domain Decomposition (FDD) technique. The study results show that the proposed digital twin-based method can detect the location and severity of damage more accurately than other comparable methods despite various uncertainties. • A novel digital twin-based method is proposed for learning damage-sensitive features from data of various scenarios of the simulated simple FWT model to detect damage in the complex FWT model. • A Deep Convolution Long Short-Term Memory Neural Network (DCLSTMNN) model is designed to learn features and damage detection of the complex FWT model. • The proposed DCLSTMNN is trained with extracted data from the simulated simple FWT model and then tested with extracted data from the complex FWT model. [ABSTRACT FROM AUTHOR]

Vehicular Edge Computing (VEC) is a promising paradigm for providing low-latency and high-reliability services in the Internet of Vehicles (IoV). The increasing number of mobile devices and the diverse resource requirements of the growing IoV have resulted in a shift from centralized resource management to a decentralized approach. This shift offers improved fault tolerance, scalability, and privacy preservation. However, constructing collaborative awareness and coordination mechanisms between multiple vehicles and edge nodes in a decentralized manner is a challenge. To address this issue, we propose a decentralized many-to-many task offloading method that aims to minimize the average task completion latency of vehicles. In this study, we propose a data-sharing mechanism between vehicles and edge servers using the digital twin service, which provides global environmental perceptions to the vehicles by a low-cost approach. Additionally, we develop a mean-field multi-agent reinforcement learning algorithm to generate coordinated task offloading schemes. Instead of interacting with multiple agents, the vehicle only needs to respond to the mean action of the environment. Based on this transition, the agent generates coordinated task offloading decisions in complex scenarios. We evaluate the performance of our method using real urban traffic data. Experiment results verify the efficiency of our proposed method. [ABSTRACT FROM AUTHOR]

Decoupling the physical world and providing standardized service interfaces is still challenging when developing Location Based Services (LBS). This lack also hinders the possibility of developing Intelligent services on top of LBS architectures. In this paper, we propose a multi-layer Digital Twin-based architecture that aims to enable the development of machine learning-based Intelligent LBS (I-LBS) that are able to adapt, evolve, and perform Continual Learning (CL). The platform uses Digital Twins to ensure physical abstraction and provide cyber–physical knowledge to the I-LBSs, which is defined as an execution graph of operation modules. Finally, we simulated a use-case for this platform in the complex scenario of Healthcare organization and management where the I-LBS classifies allowed/not allowed trajectories of users inside a real-existing hospital scenario depending on their role in the organization. The use case is implemented as a Deep Learning-based reconstruction task of high-resolution trajectories processed by the DT architecture that also deploys the I-LBS. The platform is evaluated in terms of physical complexity and computational time on the DT side and on both a traditional machine learning setting and a replay-based CL one for the intelligence side to demonstrate the flexibility and adaptability features introduced by the components for dynamic or unseen scenarios. [ABSTRACT FROM AUTHOR]

The personal digital twin extends to individual persons, a concept that originated in engineering to twin complex machines with a digital simulation containing a model of its functions to monitor its past and present behaviour, and repair, correct, improve or otherwise ensure its optimal operation. Several independent trends in technological developments are seen to converge towards the elaboration of the digital replication of individual human data and life history, notably in health industries. Among the main ones, we consider the ubiquitous distribution of digital assistants, the rapid progress of machine learning concurrent with the exponential growth of 'personal' Big Data and the incipient interest in developing lifelogs. The core hypothesis here is that among the psychological effects of the digital transformation, the externalization of cognitive faculties such as memory, planning and judgement, the decision-making processes located within the human person are also emigrating to digital functions, perhaps as a prelude to a later re-integration within the person via brain–computer interfaces. The paper concludes with ethical considerations about these ongoing developments. This article is part of the theme issue 'Towards symbiotic autonomous systems'. [ABSTRACT FROM AUTHOR]

Digital twins (DT) are emerging as an extremely promising paradigm for run-time modelling and performability prediction of cyber-physical systems (CPS) in various domains. Although several different definitions and industrial applications of DT exist, ranging from purely visual three-dimensional models to predictive maintenance tools, in this paper, we focus on data-driven evaluation and prediction of critical dependability attributes such as safety. To that end, we introduce a conceptual framework based on autonomic systems to host DT run-time models based on a structured and systematic approach. We argue that the convergence between DT and self-adaptation is the key to building smarter, resilient and trustworthy CPS that can self-monitor, self-diagnose and—ultimately—self-heal. The conceptual framework eases dependability assessment, which is essential for the certification of autonomous CPS operating with artificial intelligence and machine learning in critical applications. This article is part of the theme issue 'Towards symbiotic autonomous systems'. [ABSTRACT FROM AUTHOR]

Over the next 10 years, we are likely to see the convergence of two independent evolutionary paths: one leading to an augmentation of machine capabilities; the other with the augmentation of human capabilities. This convergence will not happen at a specific point in time; instead, it will be the result of progressive overlapping, to the point that it might be difficult to identify a defining moment. The following decade will likely be quite different from the present one. 5G will probably be remembered as a transitional system, artificial intelligence (AI) as a misplaced objective. We are looking forward to a communications fabric created by autonomous systems that will exist both in the physical world as well as in cyberspace, determining a continuum that gives rise to digital reality and where intelligence is an emerging property of the ambient. Hence, the dichotomy between AI and natural intelligence will no longer exist and AI will be considered as a tool for human augmentation and as the glue connecting minds and machines. This article is part of the theme issue 'Towards symbiotic autonomous systems'. [ABSTRACT FROM AUTHOR]

Purpose: Axial alignment of the talar implant in total ankle arthroplasty remains a major issue, since the real axis of motion of each patient is impossible to determine with usual techniques. Further knowledge regarding individual axis of motion of the ankle is therefore needed. Material and methods: Therefore, digital twins, artificial intelligence, and machine learning technology were used to identify a real personalized motion axis of the tibiotalar joint. Three-dimensional (3D) models of distal extremities were generated using computed tomography data of normal patients. Digital twins were used to reproduce the mobility of the ankles, and the real ankle of the patients was matched to the digital twin with machine learning technology. Results: The results showed that a personalized axis can be obtained for each patient. When the origin of the axis is the centre of mass of the talus, this axis can be represented in a geodesic system. The mean value of the axis is a line passing in first approximation through the centre of the sphere (with a variation of 3 mm from the centre of the mass of the talus) and through a point with the coordinates 91.6° west and 7.4° north (range 84° to 98° west; − 2° to 12° north). This study improves the understanding of the axis of the ankle, as well as its relationship to the possibility to use the geodesic system for robotic in ankle arthroplasty. Conclusion: The consideration of a personalized axis of the ankle might be helpful for better understanding of ankle surgery and particularly total ankle arthroplasty. [ABSTRACT FROM AUTHOR]

A wide variety of computational models covering statistical, mechanistic, and machine learning (locked and adaptive) methods are explored for use in biopharmaceutical manufacturing. Limited discussion exists on how to establish the credibility of a computational model for application in biopharmaceutical manufacturing. In this work, we tried to use the American Society of Mechanical Engineers (ASME) Verification and Validation 40 (V&V 40) standard and FDA proposed AI/ML model life cycle management framework for Software as a Medical Device (SaMD) in biopharmaceutical manufacturing use cases, by applying to a set of curated hypothetical examples. We discussed the need for standardized frameworks to facilitate consistent decision making to enable efficient adoption of computational models in biopharmaceutical manufacturing and alignment of existing good practices with existing frameworks. In the study of our examples, we anticipate existing frameworks like V&V 40 can be adopted. [ABSTRACT FROM AUTHOR]

The qualitative analysis results of teachers' abilities are difficult to quantify, and ability problems in the teaching process are difficult to be effectively measured. In order to study methods to improve teachers' teaching abilities, this paper builds a corresponding teacher competence evaluation model based on machine learning and digital twin technology, establishes a data collection model for teachers' professional competence, and establishes a data fusion model. It includes data cleaning model based on XML information template, data integration model, multi-index screening mechanism and clustering strategy based on perturbation attributes. On this basis, this paper uses decision tree algorithm, random forest algorithm and neural network algorithm to construct three scheduling rule mining models aiming at teachers' professional ability. In addition, this paper establishes a digital twin-driven multi-knowledge model scheduling optimization architecture that uses the three scheduling rules mined. The research results show that the model constructed in this paper has good performance. [ABSTRACT FROM AUTHOR]

• Incore detectors results better than ex-core detectors, blending them leads to highest accuracy. • ROM is applicable when direct measurement information is unavailable. • Bayesian principles play a crucial role for core digital twins under uncertain conditions. In constructing a digital twin for a nuclear reactor core, it is important to consider the influence of randomness from various sources. Data assimilation (DA) can combine time distribution observations with dynamic models to approximate the real state of a physical system. Machine learning (ML) and DA share similarities under the Bayesian framework, and using probabilistic ML may provide a way to improve or replace current DA techniques. This paper proposes using a probabilistic ML as Bayesian neural network (BNN) to solve an inverse problem of core monitoring and demonstrates its feasibility through a pressurized water reactor core simulation analysis. Model order reduction technology is also analyzed, and the feasibility and benefit of using it to achieve core monitoring under steady-state conditions is preliminarily verified and discussed. Future work will focus on improving estimation and prediction models under transient operating conditions by unifying DA and ML under the Bayesian framework. [ABSTRACT FROM AUTHOR]

Digital twins (DTs) have attracted widespread attention in academia and industry in recent years. It can accurately reflect the physical world in real-time, enabling online monitoring, control, and prediction operations. Their foundation is super-real-time computing and high data representation capabilities. However, current DTs do not achieve 3D super-real-time computing. This study proposes a novel 3D computational method for solving fluid–solid coupling problems in a super-real-time. The method is based on a mixed solution framework that combines traditional numerical methods with deep learning operators. Specifically, the method employs multi-core CPU parallel acceleration to solve the solid equations while leveraging the computing power of GPU to solve the fluid equations. The fluid–solid coupling is achieved through information exchange between the GPU and the multi-core CPU. In addition, the proposed method introduces a new deep learning operator framework based on the DeepONET. The framework is accompanied by a database structure that facilitates model training and validation and a loss function that guides the training. The space nuclear reactor, an improved TOPAZ-II system, was selected to demonstrate its feasibility. Four non-training transient conditions were simulated to test the generalization performance. The results show that the proposed method achieves an average error between the calculated results and reference values below 2.5%, with the average error of thermodynamic parameters below 1.5%. The average deviation between system parameter peak values during the transient process and the reference value was less than 5 s. The result meets the acceptable error level and satisfies the super-real-time requirements with a time acceleration ratio of approximately 1.17, which is 60 times faster than traditional numerical methods. The results demonstrate the accuracy and efficiency of the proposed method for DT. [ABSTRACT FROM AUTHOR]

• A data-driven method is proposed to evaluate the ultimate response of masonry arches. • Machine learning metamodels, in the form of artificial neural networks, are adopted. • Numerical datasets using Matlab, Python and FEM software are generated. • A fast and accurate prediction of the collapse mode and ultimate load is achieved. • Source Matlab, Python files and generated datasets accompany the article. A data-driven methodology is proposed, for the investigation of the ultimate response of masonry arches. Aiming to evaluate their structural response in a computationally efficient framework, machine learning metamodels, in the form of artificial neural networks, are adopted. Datasets are numerically built, integrating Matlab, Python and commercial finite element software. Heyman's assumptions are adopted within non-linear finite element analysis, incorporating contact-friction laws between adjacent stones, to capture failure in the arch. The artificial neural networks are trained, validated, and tested using the least square minimization technique. It is shown that the proposed scheme can be used to provide a fast and accurate prediction of the deformed geometry, the collapse mechanism and the ultimate load. Cases studies demonstrate the efficiency of the method in random, new arch geometries. Relevant Matlab/Python scripts and datasets are provided. The method can be extended towards structural health monitoring and the concept of digital twin. [ABSTRACT FROM AUTHOR]

• A digital twin model framework for crack growth prediction is proposed. • An improved method for crack growth prediction based on machine learning under variable amplitude load is proposed. • A fusion method of multi-source crack growth prediction results is proposed. This paper proposes a digital twin method based on multi-source crack growth prediction data fusion. In this method, two different prediction methods based on theoretical model correction and machine learning model correction are constructed, which avoids the inapplicability of a single method in practical applications. Meantime, based on the consistency retention method corresponding to each model, the influence of uncertainty factors on crack growth prediction is gradually reduced by inputting crack detection data. Subsequently, by fusing the historical data and prediction data, the crack growth prediction result with the smallest deviation and higher reliability is output. The verification results show that the digital twin model proposed in this paper can effectively reduce the influence of uncertainty factors on crack growth prediction and realize the dynamic prediction of crack growth. [ABSTRACT FROM AUTHOR]

Advanced cyber-attacks against critical infrastructure and the energy sector are becoming more common. With the invention of autonomous control systems (ACS) within advanced nuclear reactor designs, system designers, reactor operators, and regulators must consider cybersecurity during the design and operational phases. This article provides a cyber threat assessment of machine learning (ML)-based digital twinning (DT) technologies in the context of advanced reactor ACS. A cyber–physical testbed was created to emulate nuclear reactor digital instrumentation and controls (I&C) and act as a basis for the ACS. The ACS was designed as two plant-level DTs predicting reactor malfunctions and determining control actions and two component-level DTs responsible for classifying component states and forecasting component inputs and outputs (I/O). Two duplicate ACS designs– one using a traditional ML framework and one using an automated ML (AutoML) framework– were created and tested against cyber-attacks on training data, real-time process data, and ML model architectures to determine their respective qualitative cyber-risk in terms of likelihood and impact. Both frameworks showed similar cyber-resilience against training, real-time, and ML architecture attacks, proving that neither is inherently more secure. Recommended safeguard and security measures are posed to system designers, reactor operators, and regulators to maintain the cybersecurity of ML-based DT technologies such as ACS, prompting a holistic view of shared responsibility for maintaining cyber-secure ML-based systems. • Autonomous control system design and implementation. • Cyber threat assessment of machine learning-based digital twins. • Cyber-risk comparison of traditional machine learning and automated machine learning frameworks. [ABSTRACT FROM AUTHOR]

Electronic Centralized Aircraft Monitoring (ECAM) parameters play a vital role in the operation of an aircraft to reduce the workload of the cockpit crew. A wide-body commercial aircraft with a triple-spool turbofan engine is examined within the scope of the study. This study is focused on the estimation of the ECAM primary engine parameters: Engine Pressure Ratio, Exhaust Gas Temperature, Fuel Flow, and Shaft Speeds without any additional measurement for data continuity. The recorded flight data obtained from a commercial aircraft is processed with machine learning methods, and the most suitable estimation method is tried to be determined. Correlation analysis is carried out for each data in the study to show strong predictor candidates. The modeling process is conducted by using MATLAB. Results indicate that the Fine Decision Tree is better at memorizing data, while the Wide Neural Network is better at generalizing data. Computational results show that the developed models are outstandingly precise and accurate to estimate aircraft's ECAM data to ensure flight safety for health and performance monitoring of an engine. Thus, when an unreliable situation occurs while performing the flight in practical conditions, the cockpit crew will be able to overcome this situation by Digital Twin. • Predicting the primary engine parameters using machine learning methods. • Creating the Digital Twin for Electronic Centralized Aircraft Monitoring (ECAM). • Proposing a software-based system for flight reliability and safety. • Providing health and performance monitoring for a turbofan engine. [ABSTRACT FROM AUTHOR]

Precision livestock farming (PLF) is an emerging field that uses technology to optimize livestock production and management. It involves using sensors, cameras, and other data collection devices to gather information on animal behavior, health, and welfare. A digital twin is a virtual replica of a physical system that can be used for simulation, testing, and optimization. This tutorial will provide an overview of the procedure for creating a PLF digital twin with cameras and sensors. We will discuss the benefits of PLF, the hardware and software components needed, and the steps involved in creating a digital twin. PLF digital twins have a range of potential applications and benefits, including improved livestock health and welfare, increased productivity, and efficiency, and reduced environmental impact. At the end of the tutorial, we will host a roundtable discussion of the potential applications and benefits of PLF digital twins. [ABSTRACT FROM AUTHOR]

The current Industry 4.0 revolution promotes the use of cyber–physical systems to enhance manufacturing and other industrial processes via automation, real-time analysis, etc. Data communication between individual systems plays an important role in this revolution's success. As defined by researchers, Digital Twin is the digital representation of a physical system that enables predictive maintenance. Due to the increase in environmental pollution, battery-powered electric vehicles (EVs) are regarded as the urgent solution to internal combustion engines in the transportation business, despite obstacles such as safety concerns and range estimation. State of Health (SoH) and State of Charge (SoC) are two battery metrics that, when precisely anticipated, permit safer and longer battery use. Predicting these parameters online is computationally and financially expensive. Alternately, some of these factors could be predicted in the cloud rather than on the vehicle, hence cutting costs. Consequently, the EV business is one example where cloud-to-vehicle data connection saves total costs. A digital twin for an EV battery would aid in the estimate of battery parameters for predictive maintenance. This paper presents a Digital Twin paradigm for EV battery management in which SoH is predicted in the cloud and SoC is estimated on-vehicle. A continuous learning method is also proposed for forecasting SoH, whereas the Kalman filter is used to estimate SoC. The proposed framework predicts the SoH with a mean square error of 0.022. [ABSTRACT FROM AUTHOR]

Digital twins can act as a transformative role in improving the operational performance of multiple energy networks (MEN) by examining the impact of implementing newer technologies, extra equipment, control strategies, etc. The objective of this series of papers is to present digital twins of MEN that can be simulated in real-time using the holomorphic embedding method. While Part I concentrated on mechanism-driven modeling of the holomorphic embedding-based model (HEM), this paper (Part II) focuses on data-driven simulation to ensure the twin is synchronized with actual physical objects. A parametric synchronization method (PSM) is proposed, which assists HEM in closely matching the actual dynamic behavior with time-varying characteristics. A machine learning surrogate model (MLSM) is proposed to accelerate the search of HEM's convergence radius, which is critical to maintaining the twin's real-time computational performance. Finally, the finalized digital twins are tested on the OPAL-RT simulation platform equipped with a real-time simulator. In a medium-sized MEN test case with a minor time step of 0.01 s, the digital twins can be validated with a faster than real-time performance even without the assistance of parallel computing. • An architecture of digital twins for multiple energy networks is proposed. • Parametric synchronization method is proposed to maintain parameters up-to-date. • Machine learning surrogate model is proposed to accelerate the execution speed. • Digital twin is validated on simulation platform equipped with real-time simulator. [ABSTRACT FROM AUTHOR]

The use of Machine Learning (ML) has rapidly spread across several fields of applied sciences, having encountered many applications in Structural Dynamics and Vibroacoustic (SD&V). An advantage of ML algorithms compared to traditional techniques is that physical phenomena can be modeled using only sampled data from either measurements or simulations. This is particularly important in SD&V when the model of the studied phenomenon is either unknown or computationally expensive to simulate. This paper presents a survey on the application of ML algorithms in three classical problems of SD&V: structural health monitoring, active control of noise and vibration, and vibroacoustic product design. In structural health monitoring, ML is employed to extract damage-sensitive features from sampled data and to detect, localize, assess, and forecast failures in the structure. In active control of noise and vibration, ML techniques are used in the identification of state-space models of the controlled system, dimensionality reduction of existing models, and design of controllers. In vibroacoustic product design, ML algorithms can create surrogates that are faster to evaluate than physics-based models. The methodologies considered in this work are analyzed in terms of their strength and limitations for each of the three considered SD&V problems. Moreover, the paper considers the role of digital twins and physics-guided ML to overcome current challenges and lay the foundations for future research in the field. • Review of machine learning applied in vibroacoustic and structural dynamics. • Basic principles of the machine learning methods commonly used are presented. • Control, structural health monitoring and design are the most relevant applications. • The current implementation scenario and challenges are reviewed for each application. • This article sheds light on trends and research opportunities merging both fields. [ABSTRACT FROM AUTHOR]

A structure generation model based on a generative adversarial network (GAN) is developed to synthesize artificial porous microstructures of solid oxide fuel cell (SOFC) anodes. Different from the conventional framework of GANs, additional training is performed for the generator to control statistical parameters, namely, volume fractions, of the generated structures. The developed model is validated by comparing the synthesized structures with the real electrode microstructures obtained by three-dimensional microscopy analysis. Microstructural parameters, such as volume fraction, specific surface area, and triple-phase boundary density, are used for the comparison in addition to the visual observation. The effect of the input vector size for the generator and the definition of the loss on the ability to generate realistic structures and control the volume fractions of the structures is investigated. The developed model successfully generates realistic anode microstructures with accurately controlled volume fractions, even for compositions not included in the training datasets. It is also found that the balance between the losses influences the accuracy of the volume fraction control and diversity of the generated structures. The GAN model developed is expected to be helpful in constructing a digital twin of electrode fabrication and evaluation processes. [Display omitted] • Conditional GAN is developed to generate synthetic porous structures of SOFC anode. • Realistic porous microstructure of Ni-YSZ anode is successfully generated. • Additional training for generator is performed based on volume fraction loss. • Volume fractions of generated structures are successfully controlled. • Developed model is useful for constructing a digital twin of electrode fabrication. [ABSTRACT FROM AUTHOR]

The development of fuel cells highly depends on the reliable operation of fuel cells on test benches for testing purposes. Even though the test bench's control software contains an alarm module, it is only able to detect the most extreme failures due to the widespread operating parameter range of a fuel cell. This paper presents a novel machine learning based approach to monitor the operation of fuel cell stacks on a test bench and thereby ensuring the proper conduction of the tests. Methods for monitoring the operating conditions set by the test bench using clustering as well as methods to monitor the fuel cell's performance using digital twins are proposed. The developed methods are applied on real testing data to demonstrate their ability to detect even slight deviations that remained undiscovered to the state of the art monitoring system of the test bench. After automating, the proposed methods allow a more sensitive monitoring of the fuel cell operation on test benches leading to more usable data and clearer test results and thereby speeding up the development of fuel cells. • Lifelong performance monitoring of fuel cells. • Detecting anomalies using machine learning. • Using recurrent neural networks to predict fuel cell performance. • Neural network as digital twin. [ABSTRACT FROM AUTHOR]

• This paper presents a feed-forward neural network for predicting hydroelastic response of VLFS. • The Levenberg-Marquardt optimisation techniques is shown to provide higher prediction accuracy. • The ANN is trained using dataset generated by finite element-boundary element method.The trained machine is used to predict the hydroelastic response under regular and irregular sea. • ANN is useful for applications such as structural health monitoring and digital twin. The response of a very large floating structure (VLFS) must take into consideration the elastic deformation of the structure (commonly termed hydroelastic response) under wave action. Conventionally, the hydroelastic response could be computed by using the coupled finite element-boundary element (FE-BE) method, where the mat-like structure is modelled using plate theory and the water modelled using the potential theory. The FE-BE method requires the structure to be discretised into finer elements and the wetted surface boundary to be represented by smaller panels to accurately capture the hydroelastic response of the structure. Thus, the coupled FE-BE method could be computationally expensive when the structure gets larger or when subjected to waves of smaller wavelengths. To accelerate the computational time in predicting the hydroelastic response of the VLFS, a surrogate model trained using the feed-forward neural network is proposed. The hydroelastic responses under different wavelengths, structural stiffnesses and wave directions are first generated where these data are split into three groups for training, validation, and testing (prediction) purposes. The accuracy of the prediction in terms of correlation coefficient R is compared for the different train datasets, the number of neurons and hidden layers as well as the optimisation techniques. The finding shows that an accuracy of close to 99% to the ground truth could be achieved with only 80% of the train dataset. The hydroelastic response under irregular wave conditions predicted using the feed-forward neural network framework is also presented. [ABSTRACT FROM AUTHOR]

Light‐emitting diodes (LEDs) are among the key innovations that have revolutionized the lighting industry, due to their versatility in applications, higher reliability, longer lifetime, and higher efficiency compared with other light sources. The demand for increased lifetime and higher reliability has attracted a significant number of research studies on the prognostics and lifetime estimation of LEDs, ranging from the traditional failure data analysis to the latest degradation modeling and machine learning based approaches over the past couple of years. However, there is a lack of reviews that systematically address the currently evolving machine learning algorithms and methods for fault detection, diagnostics, and lifetime prediction of LEDs. To address those deficiencies, a review on the diagnostic and prognostic methods and algorithms based on machine learning that helps to improve system performance, reliability, and lifetime assessment of LEDs is provided. The fundamental principles, pros and cons of methods including artificial neural networks, principal component analysis, hidden Markov models, support vector machines, and Bayesian networks are presented. Finally, discussion on the prospects of the machine learning implementation from LED packages, components to system level reliability analysis, potential challenges and opportunities, and the future digital twin technology for LEDs lifetime analysis is provided. [ABSTRACT FROM AUTHOR]

The goal of this work is to achieve the defect-free production of parts made using Additive Manufacturing (AM) processes. As a step towards this goal, the objective is to detect flaws in AM parts during the process by combining predictions from a physical model (simulation) with in-situ sensor signatures in a machine learning framework. We hypothesize that flaws in AM parts are detected with significantly higher statistical fidelity (F-score) when both in-situ sensor data and theoretical predictions are pooled together in a machine learning model, compared to an approach that is based exclusively on machine learning of sensor data (black-box model) or physics-based predictions (white-box model). We test the hypothesized efficacy of such a gray-box model or digital twin approach in the context of the laser powder bed fusion (LPBF) and directed energy deposition (DED) AM processes. For example, in the DED process, we first predicted the instantaneous spatiotemporal distribution of temperature in a thin-wall titanium alloy part using a computational heat transfer model based on graph theory. Subsequently, we combined the preceding physics-derived thermal trends with in-situ temperature measurements obtained from a pyrometer in a readily implemented supervised machine learning framework (support vector machine). We demonstrate that the integration of temperature predictions from an ab initio heat transfer model and in-situ sensor data is capable of detecting flaws in the DED-produced thin-wall part with F-score approaching 90%. By contrast, the F-score decreases to nearly 80% when either temperature measurements from the in-situ sensor or temperature distribution predictions from the theoretical model are used alone by themselves. This work thus demonstrates an early foray into the digital twin paradigm for real-time process monitoring in AM via seamless integration of physics-based modeling (simulation), in-situ sensing, and data analytics (machine learning). [ABSTRACT FROM AUTHOR]

Assessing the harmfulness of defects based on images is becoming more and more common in industry. At present, these defects can be inserted in digital twins that aimto replicate in a mechanical model what is observed on a component so that an image-based diagnosis can be further conducted. However, the variety of defects, the complexity of their shape, and the computational complexity of finite element models related to their digital twin make this kind of diagnosis too slow for any practical application. We show that a classification of observed defects enables the definition of a dictionary of digital twins. These digital twins prove to be representative of model-reduction purposes while preserving an acceptable accuracy for stress prediction. Nonsupervised machine learning is used for both the classification issue and the construction of reduced digital twins. The dictionary items are medoids found by a k-medoids clustering algorithm. Medoids are assumed to be well distributed in the training dataset according to a metric or a dissimilarity measurement. In this paper, we propose a new dissimilaritymeasurement between defects. It is theoretically founded according to approximation errors in hyper-reduced predictions. In doing so, defect classes are defined according to their mechanical effect and not directly according to their morphology. In practice, each defect in the training dataset is encoded as a point on a Grassmann manifold. This methodology is evaluated through a test set of observed defects totally different from the training dataset of defects used to compute the dictionary of digital twins. The most appropriate item in the dictionary for model reduction is selected according to an error indicator related to the hyper-reduced prediction of stresses. No plasticity effect is considered here (merely isotropic elastic materials), which is a strong assumption but which is not critical for the purpose of this work. In spite of the large variety of defects, we provide accurate predictions of stresses formost of defects in the test set. [ABSTRACT FROM AUTHOR]

A new friction processing technique is developed for lap welding of Al–Cu sheets using inter diffusion of copper and aluminium at their interface. The metals selectively melt at the interface at a temperature near their eutectic point. This paper proposes a digital twin approach for real-time temperature monitoring at the joint interface using the machine's real-time current data. The real time temperature data is used to predict exact instance of interface melting and to control the resulting weld microstructure. The digital twin model is calibrated using a finite element model which is in turn calibrated using experiments. Moving average of machine current and temperature history are used to predict real time interface temperature using a linear regression based recursive machine learning model with high precision. The model predictions have an R2 value of 99.5%. The digital twin approach resulted in significant increase in joint strength and fracture energy. [Display omitted] • Machine current is used to predict weld zone temperatures using finite element method. • A recursive machine learning model is trained to predict weld interface temperatures. • 5s moving average of machine current is used as input to the machine learning model. • Excellent predictions are achieved using the machine learning model. • Welds created using digital twin approach have enhanced weld strength and ductility. [ABSTRACT FROM AUTHOR]

High dimensional quantum entanglement based on orbital angular momentum (OAM) can provide infinite freedom theoretically, providing a significant improvement on the capacity of the quantum communication. However, the vortex beam that carries OAM signal can be easily distorted by atmospheric turbulence and can degrade the performance of the system. Consequently, for the operation, administration and maintenance of quantum system, an accurate digital twin model of the turbulent channel is necessary. Digital twin model is a mathematical model which can reflect the influence of atmospheric channel on quantum system by theoretical analysis. Nevertheless, it is challenging to achieve for the complex mechanism of atmospheric turbulence. To address this problem, deep learning (DL) techniques have been studied recently. Whereas, for the training of DL, a massive number of labeled samples are needed, i.e., the actual free-space channel, which are hard to be obtained in practical systems. The pool generalization also hinders the use of these DL-based algorithms in practice. To overcome the above challenges, we propose a self-supervised DL algorithm, which does not need any labeled samples in advance, meaning the training of the algorithm can be restarted any time once the environment changes. Compared with previous studies, the proposed algorithm can better suite as the digital twin of the turbulent channel. To verify the performance of the proposed algorithm, we perform extensive verification, whose results demonstrate the superior performance of the proposed method. [ABSTRACT FROM AUTHOR]

Digital twins have emerged as a key technology for optimizing the performance of engineering products and systems. High-fidelity numerical simulations constitute the backbone of engineering design, providing insight into the performance of complex systems. However, large-scale, dynamic, non-linear models require significant computational resources and are prohibitive for real-time digital twin applications. To this end, reduced order models (ROMs) are employed, to approximate the high-fidelity solutions while accurately capturing the dominant aspects of the physical behavior. The present work proposes a new machine learning (ML) platform for the development of ROMs to handle large-scale numerical problems dealing with transient nonlinear partial differential equations. Our framework, named as FastSVD-ML-ROM , utilizes (i) a singular value decomposition (SVD) update methodology, to compute a linear subspace of the multi-fidelity solutions during the simulation process, (ii) convolutional autoencoders for nonlinear dimensionality reduction, (iii) feed-forward neural networks to map the input parameters to the latent spaces, and (iv) long–short term memory networks to predict and forecast the dynamics of parametric solutions. The efficiency of the FastSVD-ML-ROM framework is demonstrated for a 2D linear convection–diffusion benchmark, the problem of fluid flow around a cylinder, the 2D lid-driven cavity problem at high Reynolds numbers, and the 3D blood flow inside an arterial segment. The accuracy of the reconstructed results indicates the robustness of the proposed approach. [ABSTRACT FROM AUTHOR]