Phong Cong Hong Nguyen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Phong Cong Hong Nguyen has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Young Choi
School of Mechanical Engineering, College of Engineering, Chung-Ang University, Seoul 06974, Korea
10 shared publications - Stephen Baek
School of Data Science, University of Virginia 1 , Charlottesville, Virginia 22903
4 shared publications - H. S. Udaykumar
Department of Mechanical Engineering, The University of Iowa, Iowa City, USA
3 shared publications - Joseph B. Choi
School of Data Science University of Virginia Charlottesville Virginia USA
3 shared publications Youngdoo Kim
Department of Mechanical Engineering, Chung-Ang University , Seoul 06974 , Republic of Korea
3 shared publicationsGia-Wei Chern
Department of Physics, University of Virginia, Charlottesville, Virginia 22904, USA
1 shared publication
Latest Publications
- 27 August 2025
- Published by Springer Nature
- p. 211-219
Investigation of the Modeling Capability of Kolomogrov-Arnold Network for Part Quality Prediction in Machining
- 27 August 2025
- Published by Springer Nature
- p. 211-219
Investigation of the Modeling Capability of Kolomogrov-Arnold Network for Part Quality Prediction in Machining
- Open Access
- 14 September 2023
- Published by American Physical Society (APS) in Physical Review Research
- Vol. 5 (3) , 033188
Convolutional neural networks for large-scale dynamical modeling of itinerant magnets
Complex spin textures in itinerant electron magnets hold promises for next-generation memory and information technology. The long-ranged and often frustrated electron-mediated spin interactions in these materials give rise to intriguing localized spin structures such as skyrmions. Yet, simulations of magnetization dynamics for such itinerant magnets are computationally difficult due to the need for repeated solutions to the electronic structure problems. We present a convolutional neural network (CNN) model to accurately and efficiently predict the electron-induced magnetic torques acting on local spins. Importantly, as the convolutional operations with a fixed kernel (receptive field) size naturally take advantage of the locality principle for many-electron systems, CNNs offer a scalable machine learning approach to spin dynamics. We apply our approach to enable large-scale dynamical simulations of skyrmion phases in itinerant spin systems. By incorporating the CNN model into Landau-Lifshitz-Gilbert dynamics, our simulations successfully reproduce the relaxation process of the skyrmion phase and stabilize a skyrmion lattice in larger systems. The CNN model also allows us to compute the effective receptive fields, thus providing a systematic and unbiased method for determining the locality of the original electron models.
- 14 September 2023
- Published by American Physical Society (APS) in Physical Review Research
- Vol. 5 (3) , 033188
Open AccessConvolutional neural networks for large-scale dynamical modeling of itinerant magnets
Complex spin textures in itinerant electron magnets hold promises for next-generation memory and information technology. The long-ranged and often frustrated electron-mediated spin interactions in these materials give rise to intriguing localized spin structures such as skyrmions. Yet, simulations of magnetization dynamics for such itinerant magnets are computationally difficult due to the need for repeated solutions to the electronic structure problems. We present a convolutional neural network (CNN) model to accurately and efficiently predict the electron-induced magnetic torques acting on local spins. Importantly, as the convolutional operations with a fixed kernel (receptive field) size naturally take advantage of the locality principle for many-electron systems, CNNs offer a scalable machine learning approach to spin dynamics. We apply our approach to enable large-scale dynamical simulations of skyrmion phases in itinerant spin systems. By incorporating the CNN model into Landau-Lifshitz-Gilbert dynamics, our simulations successfully reproduce the relaxation process of the skyrmion phase and stabilize a skyrmion lattice in larger systems. The CNN model also allows us to compute the effective receptive fields, thus providing a systematic and unbiased method for determining the locality of the original electron models.
- 28 April 2023
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 9 (17) , eadd6868
PARC: Physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials
The thermo-mechanical response of shock-initiated energetic materials (EMs) is highly influenced by their microstructures, presenting an opportunity to engineer EM microstructures in a “materials-by-design” framework. However, the current design practice is limited, as a large ensemble of simulations is required to construct the complex EM structure-property-performance linkages. We present the physics-aware recurrent convolutional (PARC) neural network, a deep learning algorithm capable of learning the mesoscale thermo-mechanics of EM from a modest number of high-resolution direct numerical simulations (DNS). Validation results demonstrated that PARC could predict the themo-mechanical response of shocked EMs with comparable accuracy to DNS but with notably less computation time. The physics-awareness of PARC enhances its modeling capabilities and generalizability, especially when challenged in unseen prediction scenarios. We also demonstrate that visualizing the artificial neurons at PARC can shed light on important aspects of EM thermos-mechanics and provide an additional lens for conceptualizing EM.
- 28 April 2023
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 9 (17) , eadd6868
PARC: Physics-aware recurrent convolutional neural networks to assimilate meso scale reactive mechanics of energetic materials
The thermo-mechanical response of shock-initiated energetic materials (EMs) is highly influenced by their microstructures, presenting an opportunity to engineer EM microstructures in a “materials-by-design” framework. However, the current design practice is limited, as a large ensemble of simulations is required to construct the complex EM structure-property-performance linkages. We present the physics-aware recurrent convolutional (PARC) neural network, a deep learning algorithm capable of learning the mesoscale thermo-mechanics of EM from a modest number of high-resolution direct numerical simulations (DNS). Validation results demonstrated that PARC could predict the themo-mechanical response of shocked EMs with comparable accuracy to DNS but with notably less computation time. The physics-awareness of PARC enhances its modeling capabilities and generalizability, especially when challenged in unseen prediction scenarios. We also demonstrate that visualizing the artificial neurons at PARC can shed light on important aspects of EM thermos-mechanics and provide an additional lens for conceptualizing EM.
- Open Access
- 22 March 2023
- Published by Wiley in Propellants, Explosives, Pyrotechnics
- Vol. 48 (4)
A Physics‐Aware Deep Learning Model for Energy Localization in Multiscale Shock‐To‐Detonation Simulations of Heterogeneous Energetic Materials
Predictive simulations of the shock‐to‐detonation transition (SDT) in heterogeneous energetic materials (EM) are vital to the design and control of their energy release and sensitivity. Due to the complexity of the thermo‐mechanics of EM during the SDT, both macro‐scale response and sub‐grid mesoscale energy localization must be captured accurately. This work proposes an efficient and accurate multiscale framework for SDT simulations of EM. We introduce a new approach for SDT simulation by using deep learning to model the mesoscale energy localization of shock‐initiated EM microstructures. The proposed multiscale modeling framework is divided into two stages. First, a physics‐aware recurrent convolutional neural network (PARC) is used to model the mesoscale energy localization of shock‐initiated heterogeneous EM microstructures. PARC is trained using direct numerical simulations (DNS) of hotspot ignition and growth within microstructures of pressed HMX material subjected to different input shock strengths. After training, PARC is employed to supply hotspot ignition and growth rates for macroscale SDT simulations. We show that PARC can play the role of a surrogate model in a multiscale simulation framework, while drastically reducing the computation cost and providing improved representations of the sub‐grid physics. The proposed multiscale modeling approach will provide a new tool for material scientists in designing high‐performance and safer energetic materials.
- 22 March 2023
- Published by Wiley in Propellants, Explosives, Pyrotechnics
- Vol. 48 (4)
Open AccessA Physics‐Aware Deep Learning Model for Energy Localization in Multiscale Shock‐To‐Detonation Simulations of Heterogeneous Energetic Materials
Predictive simulations of the shock‐to‐detonation transition (SDT) in heterogeneous energetic materials (EM) are vital to the design and control of their energy release and sensitivity. Due to the complexity of the thermo‐mechanics of EM during the SDT, both macro‐scale response and sub‐grid mesoscale energy localization must be captured accurately. This work proposes an efficient and accurate multiscale framework for SDT simulations of EM. We introduce a new approach for SDT simulation by using deep learning to model the mesoscale energy localization of shock‐initiated EM microstructures. The proposed multiscale modeling framework is divided into two stages. First, a physics‐aware recurrent convolutional neural network (PARC) is used to model the mesoscale energy localization of shock‐initiated heterogeneous EM microstructures. PARC is trained using direct numerical simulations (DNS) of hotspot ignition and growth within microstructures of pressed HMX material subjected to different input shock strengths. After training, PARC is employed to supply hotspot ignition and growth rates for macroscale SDT simulations. We show that PARC can play the role of a surrogate model in a multiscale simulation framework, while drastically reducing the computation cost and providing improved representations of the sub‐grid physics. The proposed multiscale modeling approach will provide a new tool for material scientists in designing high‐performance and safer energetic materials.
- 22 March 2023
- Published by Wiley in Propellants, Explosives, Pyrotechnics
- Vol. 48 (4)
Artificial Intelligence Approaches for Energetic Materials by Design: State of the Art, Challenges, and Future Directions
Artificial intelligence (AI) is rapidly emerging as a enabling tool for solving complex materials design problems. This paper aims to review recent advances in AI‐driven materials‐by‐design and their applications to energetic materials (EM). Trained with data from numerical simulations and/or physical experiments, AI models can assimilate trends and patterns within the design parameter space, identify optimal material designs (micro‐morphologies, combinations of materials in composites, etc.), and point to designs with superior/targeted property and performance metrics. We review approaches focusing on such capabilities with respect to the three main stages of materials‐by‐design, namely representation learning of microstructure morphology (i. e., shape descriptors), structure‐property‐performance (S−P−P) linkage estimation, and optimization/design exploration. We leave out “process” as much work remains to be done to establish the connectivity between process and structure. We provide a perspective view of these methods in terms of their potential, practicality, and efficacy towards the realization of materials‐by‐design. Specifically, methods in the literature are evaluated in terms of their capacity to learn from a small/limited number of data, computational complexity, generalizability/scalability to other material species and operating conditions, interpretability of the model predictions, and the burden of supervision/data annotation. Finally, we suggest a few promising future research directions for EM materials‐by‐design, such as meta‐learning, active learning, Bayesian learning, and semi‐/weakly‐supervised learning, to bridge the gap between machine learning research and EM research.
- 22 March 2023
- Published by Wiley in Propellants, Explosives, Pyrotechnics
- Vol. 48 (4)
Artificial Intelligence Approaches for Energetic Materials by Design: State of the Art, Challenges, and Future Directions
Artificial intelligence (AI) is rapidly emerging as a enabling tool for solving complex materials design problems. This paper aims to review recent advances in AI‐driven materials‐by‐design and their applications to energetic materials (EM). Trained with data from numerical simulations and/or physical experiments, AI models can assimilate trends and patterns within the design parameter space, identify optimal material designs (micro‐morphologies, combinations of materials in composites, etc.), and point to designs with superior/targeted property and performance metrics. We review approaches focusing on such capabilities with respect to the three main stages of materials‐by‐design, namely representation learning of microstructure morphology (i. e., shape descriptors), structure‐property‐performance (S−P−P) linkage estimation, and optimization/design exploration. We leave out “process” as much work remains to be done to establish the connectivity between process and structure. We provide a perspective view of these methods in terms of their potential, practicality, and efficacy towards the realization of materials‐by‐design. Specifically, methods in the literature are evaluated in terms of their capacity to learn from a small/limited number of data, computational complexity, generalizability/scalability to other material species and operating conditions, interpretability of the model predictions, and the burden of supervision/data annotation. Finally, we suggest a few promising future research directions for EM materials‐by‐design, such as meta‐learning, active learning, Bayesian learning, and semi‐/weakly‐supervised learning, to bridge the gap between machine learning research and EM research.
- Open Access
- 27 January 2023
- Published by Oxford University Press (OUP) in Journal of Computational Design and Engineering
- Vol. 10 (2) , 589-601
Characterization and design of two-dimensional multi-morphology cellular structures for desired deformation
Multi-morphology cellular structures have recently gained increased attention in many areas owing to their capability to adjust their geometric and mechanical properties spatially. These cellular structures hence deform differently from conventional uniform cellular structures. However, the relationship between their geometric and the manner of their deformation has not been extensively investigated. In this study, the deformation of multi-morphology cellular structures was characterized, and a deformation prediction method was proposed. More closely, the effects of multi-morphology cellular structures’ design variables on their deformation were measured, and the effect of neighbouring unit cells at a given local area on deformation was evaluated. Based on the observations, a deformation prediction model considering the neighbouring effect was developed, and used in an optimization process for achieving the desired deformation. A numerical study was conducted to validate the proposed method, and the deformation of optimized multi-morphology cellular structures showed good agreement with the desired deformation.
- 27 January 2023
- Published by Oxford University Press (OUP) in Journal of Computational Design and Engineering
- Vol. 10 (2) , 589-601
Open AccessCharacterization and design of two-dimensional multi-morphology cellular structures for desired deformation
Multi-morphology cellular structures have recently gained increased attention in many areas owing to their capability to adjust their geometric and mechanical properties spatially. These cellular structures hence deform differently from conventional uniform cellular structures. However, the relationship between their geometric and the manner of their deformation has not been extensively investigated. In this study, the deformation of multi-morphology cellular structures was characterized, and a deformation prediction method was proposed. More closely, the effects of multi-morphology cellular structures’ design variables on their deformation were measured, and the effect of neighbouring unit cells at a given local area on deformation was evaluated. Based on the observations, a deformation prediction model considering the neighbouring effect was developed, and used in an optimization process for achieving the desired deformation. A numerical study was conducted to validate the proposed method, and the deformation of optimized multi-morphology cellular structures showed good agreement with the desired deformation.
- Open Access
- 2 February 2022
- Published by Oxford University Press (OUP) in Journal of Computational Design and Engineering
- Vol. 9 (1) , 155-167
Lightweight design with metallic additively manufactured cellular structures
Lightweight design is essential in modern product development and is prevalent in automotive, aerospace, and biomedical applications. The utilization of cellular structure, aided by advancements in additive manufacturing, is among the most effective methods for achieving lightweight design without sacrificing structural integrity and functionality. In this paper, a stress-based structural optimization method is proposed for the design of lightweight components filled with octet functionally graded cellular structures fabricated using selective laser melting (SLM) with the AlSi10Mg alloy. The proposed method includes two main parts: the homogenization-based characterization of SLM-octet-cellular structures and the utilization of the characterized cellular structures for lightweight structure optimum design. Tensile and compression experiments were utilized to validate the proposed homogenization-based characterization method, showing that the simulation and experimental results were in agreement. In addition, the effectiveness of the proposed design optimization method was validated using the three-point bending beam design problem. The experimental results revealed that components filled with functionally graded cellular structures can withstand 15.25$\%$ more load than those with uniform cellular structures. This investigation presents a complete, validated, and industry-oriented lightweight design method, which is useful for the development of future green products.
- 2 February 2022
- Published by Oxford University Press (OUP) in Journal of Computational Design and Engineering
- Vol. 9 (1) , 155-167
Open AccessLightweight design with metallic additively manufactured cellular structures
Lightweight design is essential in modern product development and is prevalent in automotive, aerospace, and biomedical applications. The utilization of cellular structure, aided by advancements in additive manufacturing, is among the most effective methods for achieving lightweight design without sacrificing structural integrity and functionality. In this paper, a stress-based structural optimization method is proposed for the design of lightweight components filled with octet functionally graded cellular structures fabricated using selective laser melting (SLM) with the AlSi10Mg alloy. The proposed method includes two main parts: the homogenization-based characterization of SLM-octet-cellular structures and the utilization of the characterized cellular structures for lightweight structure optimum design. Tensile and compression experiments were utilized to validate the proposed homogenization-based characterization method, showing that the simulation and experimental results were in agreement. In addition, the effectiveness of the proposed design optimization method was validated using the three-point bending beam design problem. The experimental results revealed that components filled with functionally graded cellular structures can withstand 15.25$\%$ more load than those with uniform cellular structures. This investigation presents a complete, validated, and industry-oriented lightweight design method, which is useful for the development of future green products.
- 3 June 2021
- Published by Springer Nature in Structural and Multidisciplinary Optimization
- Vol. 64 (4) , 1983-1995
Multiscale design of functionally graded cellular structures for additive manufacturing using level-set descriptions
- 3 June 2021
- Published by Springer Nature in Structural and Multidisciplinary Optimization
- Vol. 64 (4) , 1983-1995
Multiscale design of functionally graded cellular structures for additive manufacturing using level-set descriptions
- Open Access
- 13 May 2021
- Published by Oxford University Press (OUP) in Journal of Computational Design and Engineering
- Vol. 8 (3) , 813-823
Implicit-based computer-aided design for additively manufactured functionally graded cellular structures
Additive manufacturing has enabled the fabrication of complex structures such as cellular structures. Although numerous design frameworks have been proposed for cellular structures, their effectiveness was limited owing to the use of B-rep-based representation. To address the limitations in previous research, this study proposes an implicit-based computer-aided design framework customized for additively manufactured functionally graded cellular structures (AM-FGCSs). The proposed design framework effectively aids in both single- and multiscale structural optimization for designing FGCSs. Moreover, implicit-based modeling afforded a reliable geometric representation that could efficiently assist computation tasks such as visualization, validation, and process planning for fabrication. In addition, two case studies were conducted to demonstrate the effectiveness of the proposed framework for designing FGCSs. The first case study on a three-point bending beam design problem proved the practicality of implicit-based representation in multiscale structural design. Meanwhile, the second case study validated the proficiency of the proposed framework in process planning for fabrication and engineering analysis, the two most vital computation tasks in designing cellular structures.
- 13 May 2021
- Published by Oxford University Press (OUP) in Journal of Computational Design and Engineering
- Vol. 8 (3) , 813-823
Open AccessImplicit-based computer-aided design for additively manufactured functionally graded cellular structures
Additive manufacturing has enabled the fabrication of complex structures such as cellular structures. Although numerous design frameworks have been proposed for cellular structures, their effectiveness was limited owing to the use of B-rep-based representation. To address the limitations in previous research, this study proposes an implicit-based computer-aided design framework customized for additively manufactured functionally graded cellular structures (AM-FGCSs). The proposed design framework effectively aids in both single- and multiscale structural optimization for designing FGCSs. Moreover, implicit-based modeling afforded a reliable geometric representation that could efficiently assist computation tasks such as visualization, validation, and process planning for fabrication. In addition, two case studies were conducted to demonstrate the effectiveness of the proposed framework for designing FGCSs. The first case study on a three-point bending beam design problem proved the practicality of implicit-based representation in multiscale structural design. Meanwhile, the second case study validated the proficiency of the proposed framework in process planning for fabrication and engineering analysis, the two most vital computation tasks in designing cellular structures.