Review
Engineering, Industrial
Chong Chen, Huibin Fu, Yu Zheng, Fei Tao, Ying Liu
Summary: The recent advance of digital twin (DT) has facilitated the development of predictive maintenance (PdM) by enabling accurate equipment status recognition and proactive fault prediction. However, the research and application of DT for PdM are still in their infancy, as the role of machine learning (ML) in this area has not been fully investigated.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Automation & Control Systems
Yunrui Wang, Wenzhe Ren, Yan Li, Chuanwei Zhang
Summary: This paper discusses the solutions and key technologies for realizing the deep integration of complex product manufacturing and operation and maintenance processes using digital twin technology, as well as demonstrates the feasibility and effectiveness of the integration method through a fault prediction case study on a certain type of electric multiple units (EMU) bogie.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2021)
Article
Chemistry, Multidisciplinary
Chuanwei Zhang, Lingling Dong, Yunrui Wang
Summary: This paper presents a complex product design-manufacturing-operations and maintenance integration method based on digital twin technology. It aims to solve the problem of information silos in the design, manufacturing, and operation and maintenance phases of complex products and integrate their processes. The paper proposes a framework for integration based on the digital twin, analyzes and discusses the implementation of various technologies, and provides a case study to verify the effectiveness of the proposed framework, process, and methodology.
APPLIED SCIENCES-BASEL
(2023)
Review
Construction & Building Technology
David Ojimaojo Ebiloma, Clinton Ohis Aigbavboa, Chimay Anumba
Summary: The recent COVID-19 pandemic has exposed the deteriorating state of many healthcare facilities, particularly in underdeveloped regions. It is crucial to identify determinants of efficient maintenance management in developing countries. This study emphasizes the importance of maintenance documentation as one of the main factors for efficient maintenance management, with the goal of achieving digital twin (DT) maintenance management in Nigerian hospital buildings.
Article
Health Care Sciences & Services
Skander Tahar Mulder, Amir-Houshang Omidvari, Anja J. Rueten-Budde, Pei-Hua Huang, Ki-Hun Kim, Babette Bais, Melek Rousian, Rihan Hai, Can Akgun, Jeanine Roeters van Lennep, Sten Willemsen, Peter R. Rijnbeek, David M. J. Tax, Marcel Reinders, Eric Boersma, Dimitris Rizopoulos, Valentijin Visch, Regine Steegers-Theunissen
Summary: Digital twin is a new concept in health care that aims to improve medical decision-making through a domain-adapted multimodal modeling approach. This paper describes a dynamic digital twin in health care specifically designed for women at risk for cardiovascular complications. Overcoming challenges and barriers is crucial for the implementation of digital twin in health care.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2022)
Article
Information Science & Library Science
Chao Fan, Cheng Zhang, Alex Yahja, Ali Mostafavi
Summary: This paper introduces a vision for a Disaster City Digital Twin paradigm, aiming to facilitate interdisciplinary convergence, integrate AI algorithms, and enhance visibility into disaster management and humanitarian actions. The proposed paradigm consists of four main components, with a focus on examining the current state of the art related to AI methods and approaches for each component.
INTERNATIONAL JOURNAL OF INFORMATION MANAGEMENT
(2021)
Article
Nuclear Science & Technology
Helin Gong, Tao Zhu, Zhang Chen, Yaping Wan, Qing Li
Summary: Reactor Operation Digital Twin (RODT) is gaining attention and investment in the field of nuclear engineering. The prototype of RODT was developed by Gong et al. at the Nuclear Power Institute of China. It includes a forward solver for real-time simulation and an inverse problem solver for parameter identification and state estimation. An advanced differential evolution algorithm is proposed to enhance the inverse solver, and a systematic uncertainty quantification considering noisy observations is introduced to improve the efficiency and accuracy of RODT. Numerical results demonstrate the potential of RODT for practical engineering applications.
ANNALS OF NUCLEAR ENERGY
(2023)
Article
Energy & Fuels
Huifang Wang, Ziquan Liu, Yongjin Xu, Xiaoxiong Wei, Lixin Wang
Summary: The study proposes a short text mining framework for operation and maintenance tasks of power equipment, showing that specific design for each module improves the application effectiveness.
CSEE JOURNAL OF POWER AND ENERGY SYSTEMS
(2021)
Article
Construction & Building Technology
Jianfeng Zhao, Haibo Feng, Qian Chen, Borja Garcia de Soto
Summary: The adoption of digital twin (DT) technologies in the Architecture Engineering Construction (AEC) industry can enhance the efficiency and responsiveness of facility management activities during the operation and maintenance (O&M) phase. However, challenges such as data integration and standards alignment hinder their future implementation. A conceptual framework is proposed to facilitate wider adoption of DT technologies in buildings' O&M phase.
JOURNAL OF BUILDING ENGINEERING
(2022)
Review
Mathematics
Alexandra I. Khalyasmaa, Alina I. Stepanova, Stanislav A. Eroshenko, Pavel V. Matrenin
Summary: Digital twin is an emerging technology for the digital transformation of the power industry. Its widespread application will lead to a new level of development in the industry. This article provides a comprehensive overview of the industrial application experience of digital twin technologies, with a focus on high-voltage power equipment lifecycle management. It highlights the importance of reliable data, and the use of artificial intelligence methods to automate data collection and processing in order to effectively manage the life cycle of power equipment.
Article
Automation & Control Systems
Yan Qin, Anushiya Arunan, Chau Yuen
Summary: In order to meet the high safety and reliability requirements in practice, the state of health (SOH) estimation of Lithium-ion batteries (LIBs) has been extensively studied. A digital twin framework is proposed to enable real-time SOH estimation without requiring a complete discharge cycle. The proposed method yields real-time SOH estimation with errors less than 1% for most sampling times in ongoing cycles.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Multidisciplinary
T. I. Zohdi
Summary: In many industrialized regions, large-scale photovoltaic systems have become an important part of the energy portfolio. The integration of solar-thermal systems can serve as a green bridge energy source to meet energy demands during peak periods. This study develops a digital-twin model to optimize the flow of solar power through a complex solar-thermal storage system, using machine learning and deep learning algorithms for rapid testing and simulation.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2023)
Article
Mathematics, Interdisciplinary Applications
T. Zohdi
Summary: The massive growth in data centers has led to increased interest and regulations for waste heat management. This study aims to optimize ventilation and cooling in data centers using a combined Digital-Twin and Machine-Learning framework, resulting in a model problem and iterative solution method.
COMPUTATIONAL MECHANICS
(2022)
Article
Multidisciplinary Sciences
Meng Han, Xianfei Zhou, Jianlin Jiao, Jiabo Chen, Kai Xu
Summary: In this paper, a secondary operation and maintenance supervision system based on AR modeling and indoor positioning is designed to facilitate the observation and tracking of operation and maintenance personnel in the process of secondary equipment operation and maintenance.
Article
Computer Science, Interdisciplinary Applications
Jianhao Lv, Xinyu Li, Yicheng Sun, Yu Zheng, Jinsong Bao
Summary: Affected by COVID-19, the maintenance process of machine tools is hindered, making unmanned maintenance an emerging trend. The challenges of depending on maintenance experts, dynamic maintenance environments, and unsynchronized interactions between physical and information sides hinder its widespread applications. To address this, a bio-inspired LIDA cognitive-based Digital Twin architecture is proposed for unmanned maintenance. The architecture includes three phases to support the cognitive cycle for unmanned maintenance. A case study on fault diagnosis of a drilling platform's rolling bearing validates the feasibility and advantages of the proposed architecture. This work provides valuable insights for unmanned maintenance of machine tools in dynamic production environments.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2023)
Article
Computer Science, Theory & Methods
Dan Xia, Chun Jiang, Jiafu Wan, Jiong Jin, Victor C. M. Leung, Miguel Martinez-Garcia
Summary: This article provides a survey on heterogeneous networks in smart factories, focusing on access control, fusion, and management in the context of expanding IIoT connectivity. It explores the challenges posed by the contradiction between high QoS requirements and limited network bandwidth in smart factory networks, and discusses existing and future network technologies that can address these challenges. Additionally, it analyzes current network fusion architecture and identifies areas for improvement.
ACM COMPUTING SURVEYS
(2023)
Article
Automation & Control Systems
Wei Jiang, Ziwei Song, Jinyu Zhan, Di Liu, Jiafu Wan
Summary: This article proposes a layerwise protection framework to protect the core IP of deep neural networks (DNNs) against security attacks. The framework utilizes CPU and FPGA coscheduling to improve the execution efficiency of confidentiality protection.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Automation & Control Systems
Haidong Shao, Wei Li, Baoping Cai, Jiafu Wan, Yiming Xiao, Shen Yan
Summary: This article proposes a dual-threshold attention-guided GAN (DTAGAN) to generate high-quality infrared thermal (IRT) images to assist fault diagnosis in rotating machinery under speed fluctuation and limited samples. The comparative experiments show that DTAGAN is superior to comparison methods in fault diagnosis of rotor-bearing system under speed fluctuation and limited samples.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Yiming Xiao, Haidong Shao, SongYu Han, Zhiqiang Huo, Jiafu Wan
Summary: This article proposes a novel joint transfer network for unsupervised bearing fault diagnosis from the simulation domain to the experimental domain. It uses bearing simulation data to construct the source domain, an improved loss function to achieve alignment across domains, and a weight allocation mechanism to suppress negative transfer.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Computer Science, Artificial Intelligence
Xiangdong Wang, Xiaofeng Hu, Jiafu Wan
Summary: This paper proposes a real-time resource allocation method for hull part smart picking and processing system (SPPS) based on digital twin (DT). Firstly, a multi-agent model of the multi-gantry crane system is established in virtual space to achieve real-time task allocation. Next, a real-time picking and processing scheduling policy is proposed to reduce the idle time of all workstations. Finally, the services available in the DT platform can be applied to optimize the system performance. Experimental results show that the proposed method can effectively improve workstation utilization rate and load balance.
JOURNAL OF INTELLIGENT MANUFACTURING
(2022)
Article
Computer Science, Interdisciplinary Applications
Shen Yan, Haidong Shao, Yiming Xiao, Bin Liu, Jiafu Wan
Summary: Anomaly detection of machine tools is crucial in the machinery industry. Deep learning has shown potential in this area, but challenges including the lack of labeled data and noise disturbances still exist. This paper proposes a hybrid robust convolutional autoencoder (HRCAE) to address these challenges and achieves better performance in unsupervised anomaly detection compared to other methods.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2023)
Article
Chemistry, Analytical
Zeliang Luo, Xiaoxuan Ding, Ning Hou, Jiafu Wan
Summary: Retinopathy of prematurity is a visually impairing disease with increasing incidence, making timely diagnosis and treatment significant. To address the lack of timely and effective screening in remote areas, a deep learning-based collaborative edge-cloud telemedicine system is proposed. By combining AI algorithms and a collaborative edge-cloud architecture, the system enables timely screening and diagnosis of retinopathy of prematurity in areas with limited medical resources.
Article
Computer Science, Artificial Intelligence
Tan Jinbiao, Wan Jiafu, Dan Xia
Summary: With the development of artificial intelligence, machine vision technology based on deep learning is an effective way to improve production efficiency. This paper proposes an intelligent component recognition method suitable for small datasets, aiming to explore an automatic system for component recognition suitable for industrial manufacturing environments. The method generates the dataset through an automated system architecture and a feature-based image cropping method, and designs a deep learning network based on coarse-fine-grained feature fusion to generate an intelligent recognition model of components. The designed network achieves an accuracy of 95.11% and outperforms traditional classical networks on multiple datasets.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jieyu Xie, Jiafu Wan
Summary: This paper introduces the key technology of digital twins in intelligent manufacturing and proposes a digital twin four-dimensional fusion modeling method to solve the application problems of digital twin technology in discrete manufacturing. The proposed method can describe the geometric and physical characteristics of a physical entity, map its behavior mechanism, and reveal the control logic and virtual-real mapping rules, providing important support for virtual-real intelligent mutual control.
BIG DATA AND COGNITIVE COMPUTING
(2023)
Article
Computer Science, Hardware & Architecture
Dan Xia, Jianhua Shi, Ke Wan, Jiafu Wan, Miguel Martinez-Garcia, Xin Guan
Summary: This article proposes a DT-based system architecture and a mobile-enhanced edge computing-cloud collaborative mechanism for intelligent planning and deployment of 6G networks, aiming to improve network performance and reduce operational costs.
IEEE WIRELESS COMMUNICATIONS
(2023)
Article
Automation & Control Systems
Xiangdong Wang, Xiaofeng Hu, Zijie Ren, Tianci Tian, Jiafu Wan
Summary: The digital twin workshop is a new workshop operation paradigm that combines virtual and physical space for precise decision-making. However, integrating models from different domains and updating parameters pose challenges. This paper proposes a knowledge graph (KG)-based multi-domain model integration method for digital twin workshops, which includes model elements, ontology, data, semantic integration, and network connection. The efficacy of the proposed method is demonstrated through scenarios in the subassembly workshop for hull construction.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Ligang Wu, Liang Zhang, Le Chen, Jianhua Shi, Jiafu Wan
Summary: This paper proposes a method based on a lightweight neural network and multisource information fusion for real-time monitoring of lump coal in the process of mining conveyor belt transportation. By performing image preprocessing, optimizing feature extraction, and fusing feature information, effective monitoring of lump coal is achieved.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Baotong Chen, Lei Wang, Shujun Yu, Jiafu Wan, Xuhui Xia
Summary: The regulation of production efficiency and equipment maintenance in intelligent production lines is a challenging problem. Existing approaches lack dynamic indicators to characterize the operational status and equipment workload. Inspired by human electrocardiogram, the electric drive signal of the equipment is proposed as a measure to monitor equipment performance and workload variations. Deep learning is used to monitor equipment performance, combining EECG features with multi-source heterogeneous data. An EECG-driven synchronous mapping approach is proposed to address workload imbalance and equipment degeneracy. The EECG-based solution is validated on a laboratory-level prototype platform, ensuring robust running of the assembly process in the presence of disturbances.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Article
Engineering, Industrial
Yiming Xiao, Haidong Shao, Minjie Feng, Te Han, Jiafu Wan, Bin Liu
Summary: To ensure researchers trust deep diagnostic models, interpretable rotating machinery fault diagnosis (RMFD) research has been developed. However, there is limited work on quantifying uncertainty in results and explaining its sources and composition. This paper proposes a Bayesian variational learning method to introduce uncertainty into the attention weights of Transformer and constructs a probabilistic Bayesian Transformer for trustworthy RMFD. By inferring prior and variational posterior distributions of attention weights, uncertainty is perceived, and an uncertainty quantification and decomposition scheme is developed to achieve confidence characterization of results and separation of epistemic and aleatoric uncertainty. The proposed method is validated in three out-of-distribution generalization scenarios.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Engineering, Biomedical
Ning Hou, Jianhua Shi, Xiaoxuan Ding, Chuan Nie, Cuicui Wang, Jiafu Wan
Summary: In this study, we propose an image synthesis method for retinopathy of prematurity (ROP) based on generative adversarial networks. The method utilizes image segmentation and adversarial autoencoder techniques to generate diverse ROP images. Experimental results demonstrate that the proposed method can generate realistic ROP fundus images.
PHYSICS IN MEDICINE AND BIOLOGY
(2023)
