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
Chemistry, Analytical
Jung-Sing Jwo, Cheng-Hsiung Lee, Ching-Sheng Lin
Summary: Introducing Industry 4.0 into the manufacturing processes of aircraft composite materials is inevitable due to the complexity of the aerospace and defense industry. This study proposes the concept of Data Twin to simplify high-fidelity virtual models and uses machine learning approaches to achieve it. A microservice software architecture, Cyber-Physical Factory (CPF), is also proposed to simulate the shop floor environment, along with two war rooms for establishing a collaborative platform.
Article
Computer Science, Interdisciplinary Applications
Concetta Semeraro, Mario Lezoche, Herve Panetto, Michele Dassisti
Summary: The Digital Twin (DT) is a virtual copy of a physical system that predicts failures and opportunities for change, prescribes actions in real-time, and optimizes unexpected events. However, modeling the virtual copy is complex and requires accurate models. This paper proposes a new approach that uses modeling patterns and their invariance property to design a DT. The potential of invariance modeling patterns is demonstrated through a real industrial application.
JOURNAL OF INDUSTRIAL INFORMATION INTEGRATION
(2023)
Article
Computer Science, Interdisciplinary Applications
Giovanni Lugaresi, Andrea Matta
Summary: Industry 4.0 has brought forth technologies that enable data-driven production planning and control. Digital twins, utilized for decision making based on the current state of manufacturing systems, depend on accurately representing the physical counterpart. Automating model generation through process mining can speed up the development of digital twins, but traditional techniques struggle with complex production environments. This paper proposes object-centric process mining and an algorithm for generating accurate digital models of manufacturing systems with complex material flows, and it has been successfully tested on real systems.
COMPUTERS IN INDUSTRY
(2023)
Article
Automation & Control Systems
Yi Qin, Xingguo Wu, Jun Luo
Summary: This article proposes a digital twin model of life-cycle rolling bearing driven by the combination of data and model. By using measured signals and the bearing fault dynamic model, the size and evolution law of bearing defects can be estimated. These information is then introduced into the bearing dynamic model in virtual space, and finally the data in virtual space is mapped to the corresponding data in physical space using an improved neural network.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Review
Engineering, Industrial
Carlos Henrique dos Santos, Jose Arnaldo Barra Montevechi, Jose Antonio de Queiroz, Rafael de Carvalho Miranda, Fabiano Leal
Summary: The use of simulation as Digital Twin to support decision-making is a well-established research field, with integration of simulation with physical systems allowing virtual models to be aligned with the current state of processes. Even though the Digital Twin concept is relatively new, its principles have been used for decades in decision-making through simulation, with ongoing discussions and uncertainties regarding simulation models in this research field.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Computer Science, Interdisciplinary Applications
Jinjiang Wang, Xiaotong Niu, Robert X. Gao, Zuguang Huang, Ruijuan Xue
Summary: This paper proposes a digital twin-driven virtual commissioning method to simulate machining processes in a virtual environment and obtain better commissioning results.
ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING
(2023)
Article
Engineering, Manufacturing
Timea Czyetko, Alex Kummer, Tunas Ruppert, Janos Abonyi
Summary: This paper provides a structured guideline for improving data-based process development within the BPM life cycle, demonstrating how Industry 4.0-induced tools and models can be integrated within the BPM life cycle for more efficient process excellence and evidence-based decision-making. The proposed methodology is implemented on an assembly company, confirming the effectiveness of the improvement steps.
CIRP JOURNAL OF MANUFACTURING SCIENCE AND TECHNOLOGY
(2022)
Article
Engineering, Industrial
Litong Zhang, Yu Guo, Weiwei Qian, Weili Wang, Daoyuan Liu, Sai Liu
Summary: This paper proposes a modelling and online training method for digital twin workshop to address the difficulties in modelling, simulation, and verification. It describes a multi-level digital twin aggregate modelling method and a digital twin organization system. A spatio-temporal data model is constructed based on the data demand for digital twin aggregates. The paper also presents a training method using truncated normal distribution and a verification method based on real-virtual error for digital twin models. The effectiveness of real-time status monitoring, online model training, and production simulation is verified through a case study.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2023)
Article
Engineering, Industrial
Siamak Khayyati, Baris Tan
Summary: This study focuses on the implementation of production control policies in manufacturing systems using machine learning, addressing the selection of information sources, forming clusters of information signals, and determining optimal policy parameters. Two experiments demonstrate the effectiveness of this approach in improving system performance through proper selection and utilization of real-time signals for production control.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Automation & Control Systems
Andrew Eyring, Nathan Hoyt, Joe Tenny, Reuben Domike, Yuri Hovanski
Summary: With advancements in technology and smart manufacturing, the use of digital twins in factories and processes is becoming more common and useful. By combining discrete event simulation and live data, digital twins can provide more accurate predictions of future performance and issues, leading to smarter decision-making and implementation of solutions.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Automation & Control Systems
Ling Xu, Huihui Yu, Hanxiang Qin, Yingqian Chai, Ni Yan, Daoliang Li, Yingyi Chen
Summary: This article reviews publications related to digital twin, summarizes the connotation of digital twin, and explores its potential and challenges in aquaponics. The article introduces the implementation technologies of digital twin and discusses its applications in aquaponics, highlighting the added value it may bring and future research directions.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Hardware & Architecture
Jose Antonio Marmolejo-Saucedo
Summary: This paper discusses the application of digital twin technology in engineering and supply chain domains, proposing the integration of large-scale optimization problems into a digital platform for real-time decision-making. By addressing challenges through the interface of commercial supply chain management platform and heuristic optimization algorithms, the periodic decisions of the Digital Supply Chain Twin engine are achieved.
MOBILE NETWORKS & APPLICATIONS
(2022)
Article
Materials Science, Multidisciplinary
Javier Ordenes, Norman Toro, Aldo Quelopana, Alessandro Navarra
Summary: The Alhue mining district in Chile is a high-grade polymetallic deposit with variable amounts of copper sulfides, which affect the cyanidation process. Similar deposits can be found in the central zone of Chile and other areas around the world.
Article
Thermodynamics
Hongcheng Li, Dan Yang, Huajun Cao, Weiwei Ge, Erheng Chen, Xuanhao Wen, Chongbo Li
Summary: Advances in energy-saving technology are crucial for achieving carbon neutrality. The development of digital twin technology has attracted significant attention in creating physical-virtual data space and improving energy management capacity. The utilization of a data-driven hybrid Petri net model has shown higher accuracy in predicting energy behavior and enhancing energy efficiency in manufacturing processes.
Article
Engineering, Manufacturing
M. Resman, M. Pipan, M. Simic, N. Herakovic
ADVANCES IN PRODUCTION ENGINEERING & MANAGEMENT
(2019)
Article
Chemistry, Multidisciplinary
Maja Turk, Miha Pipan, Marko Simic, Niko Herakovic
APPLIED SCIENCES-BASEL
(2020)
Article
Environmental Sciences
Maja Turk, Marko Simic, Miha Pipan, Niko Herakovic
Summary: This paper proposes a digital transformation of the manual assembly process by implementing a multi-criterial algorithm to adjust and configure a smart manual assembly workstation, aiming to achieve efficient and ergonomic performance.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Article
Engineering, Electrical & Electronic
Marko Simic, Davorin Ambrus, Vedran Bilas
Summary: In this article, a machine-learning-based approach using line-scan EMI data is presented for rapid estimation of metallic object depth. The proposed method utilizes the spatial response of a metal detector to extract features and infer depth. Experimental evaluation shows that the method outperforms the benchmark non-linear least squares (NLS) inversion method at depths >10 cm.
IEEE SENSORS JOURNAL
(2023)
Article
Engineering, Electrical & Electronic
Marko Simic, Davorin Ambrus, Vedran Bilas
Summary: The magnetic polarizability tensor (MPT) is a quantitative measure of the perturbation of a time-varying magnetic field caused by a metallic object, and it is highly correlated with the object's geometry and material properties. This article demonstrates the measurement of MPT using inversion-based techniques with a mono-coil pulse induction metal detector (MD) and an electromagnetic (EM) tracking system. The experiments conducted on a dataset of nonferrous metallic objects of various sizes, shapes, and materials show good agreement with simulations, with a normalized root-mean-square error (NRMSE) of under 13.5%. The repeatable measurements with an NRMSE of <5.5% indicate the great potential of the proposed system for hidden metallic object detection.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Davorin Ambrus, Marko Simic, Darko Vasic, Vedran Bilas
Summary: This article investigates a specific search coil tracking problem related to the use of EMI sensors for classifying buried low metal objects. The proposed approach utilizes a moving search coil as a magnetic field beacon, two triaxial TMR sensors as anchors, and the EKF to estimate five degrees of freedom information on the coil's relative pose.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Industrial
Mihael Debevec, Marko Simic, Vukica Jovanovic, Niko Herakovic
JOURNAL OF MANUFACTURING SYSTEMS
(2020)
Article
Engineering, Manufacturing
M. Turk, M. Pipan, M. Simic, N. Herakovic
ADVANCES IN PRODUCTION ENGINEERING & MANAGEMENT
(2020)