Article
Engineering, Civil
Li-Feng Qin, Wei-Xin Ren, Chuan-Rui Guo
Summary: This article introduces the application of digital twins in structural health monitoring and proposes a physics-data hybrid framework for developing digital twin models. By integrating physical knowledge and data intelligence, this framework synchronizes the physical structure and monitoring data through a process of minimizing, providing a new perspective for smart bridge solutions.
INTERNATIONAL JOURNAL OF STRUCTURAL STABILITY AND DYNAMICS
(2023)
Review
Engineering, Industrial
Fei Tao, Bin Xiao, Qinglin Qi, Jiangfeng Cheng, Ping Ji
Summary: This paper provides a systematic research on the current studies of digital twin modeling and conducts a comprehensive and insightful analysis of digital twin models. It also investigates and summarizes the enabling technologies and tools for digital twin modeling and presents observations and future research recommendations.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Automation & Control Systems
Ren Li, Tianjin Mo, Jianxi Yang, Shixin Jiang, Tong Li, Yiming Liu
Summary: This article introduces a novel model called the bridge structure and health monitoring ontology, utilizing Semantic Web technologies to achieve fine-grained modeling of bridge structures, SHM systems, sensors, and sensory data. It addresses the serious data island problems in traditional SHM solutions and demonstrates the usefulness of a bridge SHM big data platform.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Geography, Physical
Hankan Li, Qing Zhu, Liguo Zhang, Yulin Ding, Yongxin Guo, Haoyu Wu, Qiang Wang, Runfang Zhou, Mingwei Liu, Yan Zhou
Summary: This study proposes a data-model-knowledge integrated representation data model for a digital twin railway, which explicitly describes the spatiotemporal and interaction relationships among railway features through a conceptual knowledge graph.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2022)
Article
Engineering, Mechanical
Bo Wang, Zengcong Li, Ziyu Xu, Zhiyong Sun, Kuo Tian
Summary: In this study, a novel digital twin modeling method is proposed to integrate experimental data and simulation data for real-time monitoring of structural strength. The method utilizes transfer learning-based multi-source data fusion to establish an accurate digital twin model. The proposed method shows excellent global and local accuracy in monitoring the variations of structural full-field strength.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Jiqun Song, Shimin Liu, Tenglong Ma, Yicheng Sun, Fei Tao, Jinsong Bao
Summary: This paper proposes a rapid transferable modeling approach for digital twin models, aiming to improve the modeling efficiency and resilience of digital twin models by reusing the multidimensional information of existing models. The approach provides a unified mapping and digital representation of physical entities based on information metamodels, and offers transferable approaches for the geometry dimension, behavior dimension, and algorithm dimension.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Jinfeng Liu, Xiaojian Wen, Honggen Zhou, Sushan Sheng, Peng Zhao, Xiaojun Liu, Chao Kang, Yu Chen
Summary: This paper presents a multidimensional modeling approach for machining processes using Digital Twin technology, which supports the design and execution phases of intelligent machining. The effectiveness of the applied framework and the proposed method is verified through testing key components of diesel engines.
ADVANCED ENGINEERING INFORMATICS
(2022)
Article
Engineering, Industrial
He Zhang, Qinglin Qi, Fei Tao
Summary: Digital twin has gained increasing attention in recent years. Modeling is crucial for the implementation of digital twin, especially in the context of shop-floor, which is considered the basic unit for smart manufacturing. This paper addresses the lack of attention to the multi-scale features of shop-floor in current research, hindering the effective application of digital twin. A multi-layer modeling framework is proposed to support model construction from unit layer to system layer to system of system layer, taking into account the mechanism of model changes over time. The specific procedures and methods for model assembly, fusion, and update are discussed for machines and shop-floor. The proposed framework, procedures, and methods are validated through a case study of a satellite AIT shop-floor.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Engineering, Civil
Danhui Dan, Yufeng Ying, Liangfu Ge
Summary: This paper proposes a digital twin system for bridges group in the regional transportation infrastructure network, which utilizes weigh-in-motion and multi-source machine vision fusion technology to monitor traffic loads, providing important support for intelligent transportation infrastructure systems.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Electrical & Electronic
Clement Ruah, Osvaldo Simeone, Bashir M. Al-Hashimi
Summary: Digital twin platforms are increasingly used in manufacturing and aerospace sectors for controlling, monitoring, and analyzing software-based communication systems. This paper proposes a Bayesian framework to address the challenge of model uncertainty in digital twin systems and enables core functionalities such as control and monitoring through multi-agent reinforcement learning.
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
(2023)
Article
Engineering, Industrial
Jinsong Yu, Yue Song, Diyin Tang, Jing Dai
Summary: This paper introduces a Digital Twin approach for health monitoring, using a nonparametric Bayesian network to construct a model that represents the dynamic degradation process and uncertainty propagation. Real-time model updating based on GPF and DPMM is proposed to enhance adaptability and reduce uncertainty, ensuring the effectiveness of health monitoring.
JOURNAL OF MANUFACTURING SYSTEMS
(2021)
Article
Construction & Building Technology
Sheng Yu, Dongsheng Li, Jinping Ou
Summary: This study proposes a structure health hybrid monitoring method using a digital twin bridge's finite element model to reconstruct un-monitored structural responses. Additionally, it evaluates the fatigue performance of a steel deck bridge by studying the distribution characteristics of welding residual stress and its coupling effect with other stresses.
STRUCTURAL CONTROL & HEALTH MONITORING
(2022)
Article
Computer Science, Interdisciplinary Applications
Weiwei Qian, Yu Guo, Kai Cui, Pengxing Wu, Weiguang Fang, Daoyuan Liu
Summary: This article proposes multidimensional data modeling and model validation methods for digital twin workshop (DTW), which effectively solves problems in intelligent manufacturing at the workshop level by establishing fifth-order tensor models and proposing mathematical verification methods.
JOURNAL OF COMPUTING AND INFORMATION SCIENCE IN ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Konstantinos Mykoniatis, Gregory A. Harris
Summary: Virtual commissioning is a key technology in Industry 4.0 that utilizes a digital twin model to test and verify control systems in a simulated environment before physical commissioning. It can also integrate and test modular production control systems during or prior to the construction of the physical system. The development and deployment of a digital twin emulator involves a hybrid simulation- and data-driven modeling approach to support design decisions and validate system behavior.
JOURNAL OF INTELLIGENT MANUFACTURING
(2021)
Article
Engineering, Mechanical
Xin Fang, Guijie Liu, Honghui Wang, Xiaojie Tian
Summary: This paper proposes a digital twin method based on multi-source data fusion for crack growth prediction. By constructing two different prediction methods and incorporating consistency retention method and crack detection data, dynamic prediction of crack growth is achieved.
ENGINEERING FAILURE ANALYSIS
(2023)
Article
Computer Science, Information Systems
Hyun Yoo, Kyungyong Chung, Soyoung Han
Summary: This study suggests predicting cardiac disease induction risks based on health big data using multimedia extraction, analyzing relationships and risk factors using multivariate and similarity analysis. By extracting 27 significant items out of 210 with an accuracy error of 0.21, the model shows potential for providing personalized data in building an effective healthcare system.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Hoill Jung, Kyungyong Chung
Summary: With the development of information technology, ambient intelligence has been integrated into various fields to create new convergence service industries. Human-oriented technologies for improving quality of life are continuously developed through IT convergence, particularly in healthcare. The use of smart IT devices in healthcare services enables more efficient healthcare delivery to meet people's needs.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2021)
Article
Chemistry, Multidisciplinary
Chang-Min Kim, Ellen J. Hong, Kyungyong Chung, Roy C. Park
Summary: Mammography is effective for early detection of breast cancer but difficult for experts. Research on finding lesions in mammography images using AI is active. The proposed model using multi-model-based image channel expansion and visual pattern shaping showed the best performance in breast cancer diagnosis.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Ji-Won Baek, Kyungyong Chung
Summary: Providing information about Alzheimer's disease is difficult due to the unknown cause. This study proposes a prediction support model for dementia using regression analysis and image style transfer to manage and prevent the disease. By transforming the brain's style and comparing the similarities of influencing factors, the factors affecting Alzheimer's disease can be identified.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Joo-Chang Kim, Kyungyong Chung
Summary: This article introduces a method that estimates missing values by selecting a representative value and using a multimodal RNN. In the heterogeneous environment of a mobile health platform, missing values must be considered due to various factors. By connecting single-modal RNNs into one neural network and using a fully connected network to handle multimodal data, missing values can be effectively estimated. The evaluation results show that this method has higher accuracy than traditional methods.
APPLIED SCIENCES-BASEL
(2022)
Article
Chemistry, Multidisciplinary
Ji-Won Baek, Kyungyong Chung
Summary: In order to minimize damage in the event of a fire, a Swin Transformer-based object detection model using explainable meta-learning mining is proposed. The method merges the Swin Transformer and YOLOv3 model and applies meta-learning to build an explainable object detection model. It detects small objects of smoke in fire image data and classifies them according to the color of the smoke generated when a fire breaks out to predict and classify the risk of fire occurrence.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Ji-Won Baek, Kyungyong Chung
Summary: This study proposes a Graph Neural Network-based Multi-Context mining method for predicting emerging health risks. It collects and pre-processes disease information, behavioral pattern information, and mental health information of chronic disease patients. By expanding the graph and analyzing users' connection relations, it can predict similar chronic disorders and symptoms. The regression analysis and clustering technique are evaluated for performance.
Article
Computer Science, Information Systems
Ji-Soo Kang, Kyungyong Chung
Summary: This study proposes the use of salient target augmentation (STAug) as a data augmentation technique to protect the colors and shapes of plant images. By pasting one image's salient target into a different image to mix the two images, it is possible to create a rigid classification model.
Article
Computer Science, Information Systems
Sung-Soo Park, Hye-Jeong Kwon, Ji-Won Baek, Kyungyong Chung
Summary: This study proposes a dimensional expansion and time-series data augmentation policy for pose estimation based on skeletons, improving the model's performance by using 3D skeleton data.
Article
Computer Science, Information Systems
Hye-Jeong Kwon, Dong-Hoon Shin, Kyungyong Chung
Summary: This study proposes an anomaly classification method using generative adversarial networks to address data imbalance in chest X-ray data, calculating anomaly scores through weighted multi-scale similarity, and achieving high classification accuracy.
Article
Computer Science, Information Systems
Hyun-Jin Kim, Ji-Won Baek, Kyungyong Chung
Summary: This study proposes a method using fuzzy clustering and normalization to generate associations between video content data, which improves accuracy and confidence, and identifies significant objects in video content.
Article
Computer Science, Information Systems
Ji-Won Baek, Kyungyong Chung
Summary: The study proposes a method for health knowledge mining in a P2P edge network, with visualized results for easy access to relevant information by users. The evaluation using F-measure based on recall and precision shows the effectiveness of the method at different support levels.
Article
Computer Science, Information Systems
Hyun Yoo, Soyoung Han, Kyungyong Chung
Summary: Medical expert support systems utilizing medical data and intelligent image analysis contribute significantly to the field of medicine, requiring validation and transparent internal structure. This study introduces a cardiomegaly diagnosis support model based on CNN using ResNet, providing internal neural network information with an accuracy close to 80% and a visual feature map.
