Generation and Validation of CFD-Based ROMs for Real-Time Temperature Control in the Main Control Room of Nuclear Power Plants DOI Creative Commons
Seung-Hoon Kang, Dae Kyung Choi,

Sung-Man Son

et al.

Energies, Journal Year: 2024, Volume and Issue: 17(24), P. 6406 - 6406

Published: Dec. 19, 2024

This study develops and validates a Reduced Order Model (ROM) integrated with Digital Twin technology for real-time temperature control in the Main Control Room (MCR) of nuclear power plant. Utilizing Computational Fluid Dynamics (CFD) simulations, we obtained detailed three-dimensional thermal flow distributions under various operating conditions. A ROM was generated using machine learning techniques based on 94 CFD cases, achieving mean error 0.35%. The further validated against two excluded demonstrating high correlation coefficients (R > 0.84) low metrics, confirming its accuracy reliability. Integrating Heating, Ventilating, Air Conditioning (HVAC) system, conducted two-month simulation, showing effective maintenance MCR within predefined criteria through adaptive HVAC control. integration significantly enhances operational efficiency safety by enabling monitoring while reducing computational costs time associated full-scale analyses. Despite promising results, acknowledges limitations related to ROM’s dependency training data quality need more comprehensive validation diverse unforeseen Future research will focus expanding applicability, incorporating advanced methods, conducting pilot tests actual plant environments optimize Twin-based system.

Language: Английский

Recent Advances in Machine Learning‐Assisted Multiscale Design of Energy Materials DOI Creative Commons
Bohayra Mortazavi

Advanced Energy Materials, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 10, 2024

Abstract This review highlights recent advances in machine learning (ML)‐assisted design of energy materials. Initially, ML algorithms were successfully applied to screen materials databases by establishing complex relationships between atomic structures and their resulting properties, thus accelerating the identification candidates with desirable properties. Recently, development highly accurate interatomic potentials generative models has not only improved robust prediction physical but also significantly accelerated discovery In past couple years, methods have enabled high‐precision first‐principles predictions electronic optical properties for large systems, providing unprecedented opportunities science. Furthermore, ML‐assisted microstructure reconstruction physics‐informed solutions partial differential equations facilitated understanding microstructure–property relationships. Most recently, seamless integration various platforms led emergence autonomous laboratories that combine quantum mechanical calculations, language models, experimental validations, fundamentally transforming traditional approach novel synthesis. While highlighting aforementioned advances, existing challenges are discussed. Ultimately, is expected fully integrate atomic‐scale simulations, reverse engineering, process optimization, device fabrication, empowering system design. will drive transformative innovations conversion, storage, harvesting technologies.

Language: Английский

Citations

17
Towards sustainable industry 4.0: A survey on greening IoE in 6G networks DOI Creative Commons
Saeed Hamood Alsamhi, Ammar Hawbani, Radhya Sahal

et al.

Ad Hoc Networks, Journal Year: 2024, Volume and Issue: 165, P. 103610 - 103610

Published: Aug. 30, 2024

Language: Английский

Citations

6
A brief review of reduced order models using intrusive and non‐intrusive techniques DOI Creative Commons
Guglielmo Padula, Michele Girfoglio, Gianluigi Rozza

et al.

PAMM, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 12, 2024

Abstract Reduced Order Models (ROMs) have gained a great attention by the scientific community in last years thanks to their capabilities of significantly reducing computational cost numerical simulations, which is crucial objective applications like real time control and shape optimization. This contribution aims provide brief overview about such topic. We discuss both classic intrusive framework based on Galerkin projection technique hybrid/non‐intrusive approaches, including Physics Informed Neural Networks (PINN), purely Data‐Driven (NN), Radial Basis Functions (RBF), Dynamic Mode Decomposition (DMD) Gaussian Process Regression (GPR). also briefly mention geometrical parametrization dimensionality reduction methods Active Subspaces (ASs). Then we test performance approaches terms efficiency accuracy against three academic cases, lid driven cavity, flow past cylinder geometrically parametrized Stanford Bunny. Moreover, present some preliminary results related more complex case involving an industrial application.

Language: Английский

Citations

5
Synergistic Integration of Digital Twins and Neural Networks for Advancing Optimization in the Construction Industry: A Comprehensive Review DOI
Alexey Borovkov, Khristina Maksudovna Vafaeva, Nikolai Vatin

et al.

Construction Materials and Products, Journal Year: 2024, Volume and Issue: 7(4), P. 7 - 7

Published: Aug. 9, 2024

The object of research is the potential application digital twins and neural network modeling for optimizing construction processes. Method. Adopting a perspective approach, conducts an extensive review existing literature delineates theoretical framework integrating technologies. Insights from inform development methodologies, while case studies practical applications are explored to deepen understanding these integrated approaches system optimization. Results. yields following key findings: Digital Twins: Offer capability create high-fidelity virtual representations physical systems, enabling real-time data collection, analysis, visualization throughout project lifecycle. This allows proactive decision-making, improved constructability enhanced coordination between design field operations. Neural Network Modeling: Possesses power learn complex relationships vast datasets, predictive optimization behavior. networks can be employed forecast timelines, identify risks, optimize scheduling resource allocation. Integration Twins Networks: Presents transformative avenue processes by facilitating data-driven design, maintenance equipment infrastructure, performance monitoring. synergistic approach lead significant improvements in efficiency, reduced costs, overall quality.

Language: Английский

Citations

5
A Comparative Analysis of Machine Learning Algorithms for Predicting Fundamental Periods in Reinforced Concrete Frame Buildings DOI
Pramod Kumar,

Abhilash Gogineni,

Amit Kumar

et al.

Iranian Journal of Science and Technology Transactions of Civil Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 1, 2024

Language: Английский

Citations

4
Towards Digital Twin Modeling and Applications for Permanent Magnet Synchronous Motors DOI Creative Commons
Grace Firsta Lukman, Cheewoo Lee

Energies, Journal Year: 2025, Volume and Issue: 18(4), P. 956 - 956

Published: Feb. 17, 2025

This paper explores the potential of Digital Twin (DT) technology for Permanent Magnet Synchronous Motors (PMSMs) and establishes a foundation its modeling applications. While DTs have been widely applied in complex systems simulation software, their use electric motors, especially PMSMs, remains limited. study examines physics-based, data-driven, hybrid approaches evaluates feasibility real-time simulation, fault detection, predictive maintenance. It also identifies key challenges such as computational demands, data integration, lack standardized frameworks. By assessing current developments outlining future directions, this work provides insights into how can be implemented PMSMs drive advancements industrial

Language: Английский

Citations

0
Sustainable innovations in digital twin technology: a systematic review about energy efficiency and indoor environment quality in built environment DOI Creative Commons

N. Venkateswarlu,

Mahenthiran Sathiyamoorthy

Frontiers in Built Environment, Journal Year: 2025, Volume and Issue: 11

Published: March 13, 2025

In the contemporary digital age, built environment undergoes significant changes because of technological innovations that improve building management, optimize efficiency, and enhance overall productivity. Digital Twin technology has emerged as an indispensable tool for enhancing indoor environmental quality optimizing energy efficiency in existing buildings. This demonstrates its similarity to several SDGs, where twin is key achieving many them, especially those relevant our research: 7. Affordable clean energy; 3. Good health wellbeing are primary outcomes study; 9. Industry innovation infrastructure focus methodology; 11. Sustainable cities communication, which research contributes. However, some challenges require further consideration. First, assess methods tools used monitor represent parameters. Second, review previous studies on context quality. study systematically examined 261 academic articles address these challenges, identifying 17 publications investigating The emphasizes Building Information Modeling, Internet Things, Big Data, collectively monitoring management physical assets through real-time data replication. Our illustrates need a multidisciplinary framework rigorously analyze applications, comprehensive understanding consequences this requires integration different fields. confined application sensors environment, importance residents subjective impressions, comparative use estimation methods. For future investigation, enhanced international collaboration imperative scholarly exploration related field. Finally, can benefit significantly from implementing technology. must be addressed before achieve full potential creating sustainable energy-efficient

Language: Английский

Citations

0
Digital twin for smart wireless sensor networks DOI
Abidemi Emmanuel Adeniyi, Halleluyah Oluwatobi Aworinde,

Odunayo Dauda Olanloye

et al.

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 271 - 302

Published: Jan. 1, 2025

Language: Английский

Citations

0
Image-based deep learning for smart digital twins: a review DOI Creative Commons
Md Ruman Islam,

Mahadevan Subramaniam,

Pei-Chi Huang

et al.

Artificial Intelligence Review, Journal Year: 2025, Volume and Issue: 58(5)

Published: Feb. 24, 2025

Language: Английский

Citations

0
A Semi-automatic Pipeline for the Decay Mapping and the State of Conservation Assessment of Architectural Heritage Through Point Clouds DOI
Margherita Lasorella, Elena Cantatore,

M Rondinelli

et al.

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 52 - 67

Published: Jan. 1, 2025

Language: Английский

Citations

0