Article
Water Resources
Reza Shams, Mohsen Masihi, Ramin Bozorgmehry Boozarjomehry, Martin J. Blunt
Summary: A coupled statistical and conditional generative adversarial neural network is proposed for 3D reconstruction of porous media, providing faster reconstruction speed and the ability to effectively handle heterogeneous samples. The conditional nature of the generative model contributes to network stability and convergence, making it a reliable framework for reconstructing 3D microstructures from a single 2D image.
ADVANCES IN WATER RESOURCES
(2021)
Article
Computer Science, Artificial Intelligence
Fan Zhang, Xiaohai He, Qizhi Teng, Xiaohong Wu, Junfang Cui, Xiucheng Dong
Summary: This study proposes a recurrent neural network (RNN)-based generative model incorporating a generative adversarial network (GAN) to address the 2D-to-3D reconstruction problem. The model can recover the full 3D structures layer-by-layer based on the input 2D slices, and an adversarial training strategy is proposed to enhance the reconstruction ability. The experiments validate the accuracy, diversity, and stability of the proposed model in reproducing 3D realizations.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Energy & Fuels
Ting Zhang, Xin Ji, Fangfang Lu
Summary: The modeling and characterization of porous media is important for exploring and developing oil and natural gas resources. This paper proposes a three-dimensional multi-scale pattern generative adversarial network (3DMSPGAN) based on generative adversarial networks (GANs) for the 3D super-resolution reconstruction of porous media. Experimental results show that 3D-MSPGAN achieves faster speed and higher quality compared to typical methods.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Thermodynamics
Xiaogang Cheng, Fei Ren, Zhan Gao, Luoxi Wang, Lei Zhu, Zhen Huang
Summary: This paper proposes a new method to study the formation and distribution of soot in turbulent jet flames. The method uses multiplicative algebraic reconstruction technique (MART) for three-dimensional reconstruction of the flame and conditional-generative adversarial network (C-GAN) for two-dimensional soot signal prediction. By combining these two methods, the three-dimensional distribution of soot particles can be reconstructed. The accuracy of the method is verified through validation experiments and it has the potential to be applied to predict other optical signals.
COMBUSTION AND FLAME
(2023)
Article
Chemistry, Analytical
Ludia Eka Feri, Jaehun Ahn, Shahrullohon Lutfillohonov, Joonho Kwon
Summary: Due to the increasing use of permeable pavement, there is a growing need for studies to improve its design and durability. One of the important factors that can reduce the functionality of permeable pavement is the clogging issue. In this study, a three-dimensional microstructure reconstruction framework based on 3D-IDWGAN with an enhanced gradient penalty is proposed for clogging analysis in permeable pavement, showing improvements in three-dimensional image generation and physical property extraction.
Article
Engineering, Environmental
Pengfei Xia, Hualin Bai, Ting Zhang
Summary: The paper proposes a progressively growing multi-scale GAN model for the reconstruction of porous media, which benefits from multi-scale reconstruction to achieve results similar to real pore structures at faster speeds and with lower CPU/memory burden.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2022)
Article
Computer Science, Software Engineering
Evgeniy Kononov, Mikhail Tashkinov, Vadim V. Silberschmidt
Summary: This paper presents an algorithm based on the neural network operating on a principle of generative adversarial learning for stochastic reconstruction of three-dimensional material microstructure from its single two-dimensional cross-sectional image. The introduction of reconstruction error, which is invariant to translational and rotational transformations, helps improve the stability of neural network training and the quality of generated structures. The use of variational autoencoder also aids in extracting useful features and providing additional information for accurate structure reconstruction.
COMPUTER-AIDED DESIGN
(2023)
Article
Energy & Fuels
Xiangchao Shi, Dandan Li, Junhai Chen, Yan Chen
Summary: The 3D digital rock technology is widely used in analyzing rock physical properties and reservoir modeling. This article proposes an innovative algorithm for reconstructing 3D digital rock by improving the generator, discriminator, and noise vector in the network structure. The proposed method achieves good agreement with real samples in terms of various geological parameters.
JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY
(2023)
Article
Computer Science, Interdisciplinary Applications
Fei Hu, Chunlei Wu, Jiangwei Shang, Yiming Yan, Leiquan Wang, Huan Zhang
Summary: This paper explores a flexible approach to generate synthetic realizations with desired geological styles by introducing numerical codes and extending the existing mapping model. The resulting generative model can synthesize images that respect both hard data and exhibit specific geological styles.
COMPUTERS & GEOSCIENCES
(2023)
Article
Environmental Sciences
Zhe Guo, Haojie Guo, Xuewen Liu, Weijie Zhou, Yi Wang, Yangyu Fan
Summary: The paper introduces the characteristics of optical images and SAR images, proposes the Sar2color model for SAR-to-optical transformation, and evaluates the model and conducts ablation experiments.
Article
Materials Science, Multidisciplinary
Fan Zhang, Qizhi Teng, Honggang Chen, Xiaohai He, Xiucheng Dong
Summary: The study introduces a hybrid deep generative model for 3D porous media reconstruction, which combines VAE and GAN to improve training stability and generative capability. The use of a simple but useful loss function helps enhance accuracy.
COMPUTATIONAL MATERIALS SCIENCE
(2021)
Article
Engineering, Electrical & Electronic
Jinsong Yang, Jie Liu, Jingsong Xie, Changda Wang, Tianqi Ding
Summary: The proposed CGAN-2-D-CNN fusion diagnosis model is effective in diagnosing bearing faults with small sample data, showing close accuracy to the 2-D-CNN model directly used on a larger original sample size. The 2-D-CNN model after 2-D preprocessing also demonstrates higher fault classification accuracy compared to other models like 1-D-CNN, SVM, and LSTM.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Environmental Sciences
Shihong Wang, Jiayi Guo, Yueting Zhang, Yuxin Hu, Chibiao Ding, Yirong Wu
Summary: By utilizing CGAN and a small number of tracks to construct a 3D super-resolution dataset for building reconstruction, the quality of TomoSAR reconstruction has been effectively improved, especially in terms of height estimation and time efficiency.
Article
Environmental Sciences
Parnia Shokri, Mozhdeh Shahbazi, John Nielsen
Summary: This paper proposes a solution for crack detection and modeling in concrete structures using a stereo camera. By utilizing deep learning and optimizing model calibration, crack pixels can be accurately identified and 3D reconstruction can be performed. Experimental results show that structural cracks can be identified with high precision and an accurate 3D crack model can be generated.
Article
Computer Science, Artificial Intelligence
Mohamed Elhefnawy, Mohamed-Salah Ouali, Ahmed Ragab
Summary: This paper proposes an innovative multi-output regression method that converts numeric data variables into images to build accurate predictive models in industrial applications. The method utilizes deep generative modeling to learn the true distribution of complex data, leading to improved performance in predictions.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Honggang Chen, Xiaohai He, Cheolhong An, Truong Q. Nguyen
INFORMATION SCIENCES
(2020)
Article
Computer Science, Artificial Intelligence
Luping Liu, Meiling Wang, Xiaohai He, Linbo Qing, Honggang Chen
Summary: This study proposes an effective framework for fact-based visual question answering (FVQA) by coordinating a perception module and an explicit reasoning module. Experimental results show that the model outperforms other baselines on two public datasets, and it also provides interpretations of the reasoning process.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Honggang Chen, Xiaohai He, Hong Yang, Linbo Qing, Qizhi Teng
Summary: This article presents a feature-enriched deep convolutional neural network for compression artifacts reduction (FeCarNet), which outperforms state-of-the-art approaches in terms of restoration capacity and model complexity. By utilizing various techniques, FeCarNet effectively reduces compression artifacts in images, demonstrating significant advantages in this field.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Honggang Chen, Xiaohai He, Hong Yang, Junxi Feng, Qizhi Teng
Summary: This paper presents a two-stage deep generative adversarial quality enhancement network for improving the quality and accuracy of property analysis of rock CT images. The network enhances the quality of 3D CT images from the perspectives of 2D slices and 3D volumes, effectively eliminating artifacts and improving resolution. Experimental results demonstrate the effectiveness of the network for real-world 3D CT images of rock samples.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Review
Computer Science, Artificial Intelligence
Honggang Chen, Xiaohai He, Linbo Qing, Yuanyuan Wu, Chao Ren, Ray E. Sheriff, Ce Zhu
Summary: This article provides a comprehensive review of real-world single image super-resolution (RSISR), covering critical datasets, assessment metrics, and four major categories of RSISR methods. It compares representative RSISR methods on benchmark datasets in terms of reconstruction quality and computational efficiency, while also discussing challenges and promising research topics in RSISR.
INFORMATION FUSION
(2022)
Article
Computer Science, Artificial Intelligence
Yongfei Zhang, Ling Dong, Hong Yang, Linbo Qing, Xiaohai He, Honggang Chen
Summary: The deep learning-based image super-resolution method proposes a new blind image super-resolution approach to simulate different degradation methods, thus adapting better to various scenarios.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Chemistry, Analytical
Liqiang He, Shuhua Xiong, Ruolan Yang, Xiaohai He, Honggang Chen
Summary: This paper proposes a method to address the high computational complexity issue in VVC encoding by skipping the MTS process and utilizing coding information from neighboring CUs, leading to a 26.40% reduction in encoding time with a 0.13% increase in BDBR compared to VVC.
Article
Computer Science, Artificial Intelligence
Honggang Chen, Xiaohai He, Hong Yang, Yuanyuan Wu, Linbo Qing, Ray E. Sheriff
Summary: This study proposes a self-supervised cycle-consistent learning-based scale-arbitrary super-resolution framework (SCL-SASR) for real-world images. The framework includes a Scale-Arbitrary Super-Resolution Network (SASRN) and an inverse Scale-Arbitrary Resolution-Degradation Network (SARDN), which ensure the adaptability to image-specific degradations and the ability to handle arbitrary scaling factors.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Physics, Fluids & Plasmas
Juan Li, Qizhi Teng, Ningning Zhang, Honggang Chen, Xiaohai He
Summary: Digital cores can accurately describe the internal structure of rocks at the pore scale, making it an effective method for analyzing the pore structure and other properties in rock physics and petroleum science. The proposed method, EWGAN-GP, reconstructs 3D structures from 2D images, achieving accurate and stable results compared to classical stochastic methods of image reconstruction.
Article
Physics, Fluids & Plasmas
Honggang Chen, Xiaohai He, Qizhi Teng, Raymond E. Sheriff, Junxi Feng, Shuhua Xiong
Article
Engineering, Electrical & Electronic
Zhengxin Chen, Xiaohai He, Chao Ren, Honggang Chen, Tingrong Zhang
Summary: This letter proposes a novel deep CNN called ESCNet for lightweight JPEG compression artifacts reduction, with enhanced separable convolution (ESConv) carefully designed to make full use of image multi-scale information for better dense pixel value predictions. The experimental results show that ESCNet achieves better performance in both objective indices and subjective quality compared with state-of-the-art methods, while greatly reducing network parameters and operations.
IEEE SIGNAL PROCESSING LETTERS
(2021)
Article
Engineering, Multidisciplinary
Akshay J. Thomas, Mateusz Jaszczuk, Eduardo Barocio, Gourab Ghosh, Ilias Bilionis, R. Byron Pipes
Summary: We propose a physics-guided transfer learning approach to predict the thermal conductivity of additively manufactured short-fiber reinforced polymers using micro-structural characteristics obtained from tensile tests. A Bayesian framework is developed to transfer the thermal conductivity properties across different extrusion deposition additive manufacturing systems. The experimental results demonstrate the effectiveness and reliability of our method in accounting for epistemic and aleatory uncertainties.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Zhen Zhang, Zongren Zou, Ellen Kuhl, George Em Karniadakis
Summary: In this study, deep learning and artificial intelligence were used to discover a mathematical model for the progression of Alzheimer's disease. By analyzing longitudinal tau positron emission tomography data, a reaction-diffusion type partial differential equation for tau protein misfolding and spreading was discovered. The results showed different misfolding models for Alzheimer's and healthy control groups, indicating faster misfolding in Alzheimer's group. The study provides a foundation for early diagnosis and treatment of Alzheimer's disease and other misfolding-protein based neurodegenerative disorders using image-based technologies.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Jonghyuk Baek, Jiun-Shyan Chen
Summary: This paper introduces an improved neural network-enhanced reproducing kernel particle method for modeling the localization of brittle fractures. By adding a neural network approximation to the background reproducing kernel approximation, the method allows for the automatic location and insertion of discontinuities in the function space, enhancing the modeling effectiveness. The proposed method uses an energy-based loss function for optimization and regularizes the approximation results through constraints on the spatial gradient of the parametric coordinates, ensuring convergence.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Bodhinanda Chandra, Ryota Hashimoto, Shinnosuke Matsumi, Ken Kamrin, Kenichi Soga
Summary: This paper proposes new and robust stabilization strategies for accurately modeling incompressible fluid flow problems in the material point method (MPM). The proposed approach adopts a monolithic displacement-pressure formulation and integrates two stabilization strategies to ensure stability. The effectiveness of the proposed method is validated through benchmark cases and real-world scenarios involving violent free-surface fluid motion.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Chao Peng, Alessandro Tasora, Dario Fusai, Dario Mangoni
Summary: This article discusses the importance of the tangent stiffness matrix of constraints in multibody systems and provides a general formulation based on quaternion parametrization. The article also presents the analytical expression of the tangent stiffness matrix derived through linearization. Examples demonstrate the positive effect of this additional stiffness term on static and eigenvalue analyses.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Thibaut Vadcard, Fabrice Thouverez, Alain Batailly
Summary: This contribution presents a methodology for detecting isolated branches of periodic solutions to nonlinear mechanical equations. The method combines harmonic balance method-based solving procedure with the Melnikov energy principle. It is able to predict the location of isolated branches of solutions near families of autonomous periodic solutions. The relevance and accuracy of this methodology are demonstrated through academic and industrial applications.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Weisheng Zhang, Yue Wang, Sung-Kie Youn, Xu Guo
Summary: This study proposes a sketch-guided topology optimization approach based on machine learning, which incorporates computer sketches as constraint functions to improve the efficiency of computer-aided structural design models and meet the design intention and requirements of designers.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Leilei Chen, Zhongwang Wang, Haojie Lian, Yujing Ma, Zhuxuan Meng, Pei Li, Chensen Ding, Stephane P. A. Bordas
Summary: This paper presents a model order reduction method for electromagnetic boundary element analysis and extends it to computer-aided design integrated shape optimization of multi-frequency electromagnetic scattering problems. The proposed method utilizes a series expansion technique and the second-order Arnoldi procedure to reduce the order of original systems. It also employs the isogeometric boundary element method to ensure geometric exactness and avoid re-meshing during shape optimization. The Grey Wolf Optimization-Artificial Neural Network is used as a surrogate model for shape optimization, with radar cross section as the objective function.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
C. Pilloton, P. N. Sun, X. Zhang, A. Colagrossi
Summary: This paper investigates the smoothed particle hydrodynamics (SPH) simulations of violent sloshing flows and discusses the impact of volume conservation errors on the simulation results. Different techniques are used to directly measure the particles' volumes and stabilization terms are introduced to control the errors. Experimental comparisons demonstrate the effectiveness of the numerical techniques.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Ye Lu, Weidong Zhu
Summary: This work presents a novel global digital image correlation (DIC) method based on a convolution finite element (C-FE) approximation. The C-FE based DIC provides highly smooth and accurate displacement and strain results with the same element size as the usual finite element (FE) based DIC. The proposed method's formulation and implementation, as well as the controlling parameters, have been discussed in detail. The C-FE method outperformed the FE method in all tested examples, demonstrating its potential for highly smooth, accurate, and robust DIC analysis.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Mojtaba Ghasemi, Mohsen Zare, Amir Zahedi, Pavel Trojovsky, Laith Abualigah, Eva Trojovska
Summary: This paper introduces Lung performance-based optimization (LPO), a novel algorithm that draws inspiration from the efficient oxygen exchange in the lungs. Through experiments and comparisons with contemporary algorithms, LPO demonstrates its effectiveness in solving complex optimization problems and shows potential for a wide range of applications.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Jingyu Hu, Yang Liu, Huixin Huang, Shutian Liu
Summary: In this study, a new topology optimization method is proposed for structures with embedded components, considering the tension/compression asymmetric interface stress constraint. The method optimizes the topology of the host structure and the layout of embedded components simultaneously, and a new interpolation model is developed to determine interface layers between the host structure and embedded components.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Qiang Liu, Wei Zhu, Xiyu Jia, Feng Ma, Jun Wen, Yixiong Wu, Kuangqi Chen, Zhenhai Zhang, Shuang Wang
Summary: In this study, a multiscale and nonlinear turbulence characteristic extraction model using a graph neural network was designed. This model can directly compute turbulence data without resorting to simplified formulas. Experimental results demonstrate that the model has high computational performance in turbulence calculation.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Jacinto Ulloa, Geert Degrande, Jose E. Andrade, Stijn Francois
Summary: This paper presents a multi-temporal formulation for simulating elastoplastic solids under cyclic loading. The proper generalized decomposition (PGD) is leveraged to decompose the displacements into multiple time scales, separating the spatial and intra-cyclic dependence from the inter-cyclic variation, thereby reducing computational burden.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)
Article
Engineering, Multidisciplinary
Utkarsh Utkarsh, Valentin Churavy, Yingbo Ma, Tim Besard, Prakitr Srisuma, Tim Gymnich, Adam R. Gerlach, Alan Edelman, George Barbastathis, Richard D. Braatz, Christopher Rackauckas
Summary: This article presents a high-performance vendor-agnostic method for massively parallel solving of ordinary and stochastic differential equations on GPUs. The method integrates with a popular differential equation solver library and achieves state-of-the-art performance compared to hand-optimized kernels.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2024)