Modeling, predictive and generalization capabilities of response surface methodology (RSM) and artificial neural network (ANN) have been performed to assess the thermal structure of the experimentally studied cat...Modeling, predictive and generalization capabilities of response surface methodology (RSM) and artificial neural network (ANN) have been performed to assess the thermal structure of the experimentally studied catalytic combustion of stabilized confined turbulent gaseous diffusion flames. The Pt/<i>γ</i>Al<sub>2</sub>O<sub>3</sub> and Pd/<i>γ</i>Al<sub>2</sub>O<sub>3</sub> disc burners were located in the combustion domain and the experiments were accomplished under both fuel-rich and fuel-lean conditions at a modified equivalence (fuel/air) ratio (<i><span style="white-space:nowrap;"><span style="font-family:Verdana, Helvetica, Arial;white-space:normal;background-color:#FFFFFF;">ø</span></span></i>) of 0.75 and 0.25, respectively. The thermal structure of these catalytic flames developed over the Pt and Pd disc burners w<span style="white-space:normal;font-family:;" "="">as</span><span style="white-space:normal;font-family:;" "=""> scrutinized via measuring the mean temperature profiles in the radial direction at different discrete axial locations along with the flames. The RSM and ANN methods investigated the effect of the two operating parameters namely (<i>r</i>), the radial distance from the center line of the flame, and (<i>x</i>), axial distance along with the flame over the disc, on the measured temperature of the flames and predicted the corresponding temperatures beside predicting the maximum temperature and the corresponding input process variables. A three</span><span style="white-space:normal;font-family:;" "="">-</span><span style="white-space:normal;font-family:;" "="">layered Feed Forward Neural Network was developed in conjugation with the hyperbolic tangent sigmoid (tansig) transfer function and an optimized topology of 2:10:1 (input neurons:hidden neurons:output neurons). Also the ANN method has been exploited to illustrate </span><span style="white-space:normal;font-family:;" "="">the </span><span style="white-space:normal;font-family:;" "="">effects of coded <i>R</i> and <i>X</i> input variables on the response in the three and two dimensions and to locate the predicted maximum temperature. The results indicated the superiority of ANN in the prediction capability as the ranges of & F_Ratio are 0.9181</span><span style="white-space:normal;font-family:;" "=""> </span><span style="white-space:normal;font-family:;" "="">- 0.9809 & 634.5</span><span style="white-space:normal;font-family:;" "=""> </span><span style="white-space:normal;font-family:;" "="">- 3528.8 for RSM method compared to 0.9857</span><span style="white-space:normal;font-family:;" "=""> </span><span style="white-space:normal;font-family:;" "="">- 0.9951 & 7636.4</span><span style="white-space:normal;font-family:;" "=""> </span><span style="white-space:normal;font-family:;" "="">- 24</span><span style="white-space:normal;font-family:;" "="">,</span><span style="white-space:normal;font-family:;" "="">028.4 for ANN method beside lower values </span><span style="white-space:normal;font-family:;" "="">for error analysis terms.</span>展开更多
Recent industrial explosions globally have intensified the focus in mechanical engineering on designing infras-tructure systems and networks capable of withstanding blast loading.Initially centered on high-profile fac...Recent industrial explosions globally have intensified the focus in mechanical engineering on designing infras-tructure systems and networks capable of withstanding blast loading.Initially centered on high-profile facilities such as embassies and petrochemical plants,this concern now extends to a wider array of infrastructures and facilities.Engineers and scholars increasingly prioritize structural safety against explosions,particularly to prevent disproportionate collapse and damage to nearby structures.Urbanization has further amplified the reliance on oil and gas pipelines,making them vital for urban life and prime targets for terrorist activities.Consequently,there is a growing imperative for computational engineering solutions to tackle blast loading on pipelines and mitigate associated risks to avert disasters.In this study,an empty pipe model was successfully validated under contact blast conditions using Abaqus software,a powerful tool in mechanical engineering for simulating blast effects on buried pipelines.Employing a Eulerian-Lagrangian computational fluid dynamics approach,the investigation extended to above-surface and below-surface blasts at standoff distances of 25 and 50 mm.Material descriptions in the numerical model relied on Abaqus’default mechanical models.Comparative analysis revealed varying pipe performance,with deformation decreasing as explosion-to-pipe distance increased.The explosion’s location relative to the pipe surface notably influenced deformation levels,a key finding highlighted in the study.Moreover,quantitative findings indicated varying ratios of plastic dissipation energy(PDE)for different blast scenarios compared to the contact blast(P0).Specifically,P1(25 mm subsurface blast)and P2(50 mm subsurface blast)showed approximately 24.07%and 14.77%of P0’s PDE,respectively,while P3(25 mm above-surface blast)and P4(50 mm above-surface blast)exhibited lower PDE values,accounting for about 18.08%and 9.67%of P0’s PDE,respectively.Utilising energy-absorbing materials such as thin coatings of ultra-high-strength concrete,metallic foams,carbon fiber-reinforced polymer wraps,and others on the pipeline to effectively mitigate blast damage is recommended.This research contributes to the advancement of mechanical engineering by providing insights and solutions crucial for enhancing the resilience and safety of underground pipelines in the face of blast events.展开更多
The present study was conducted to present the comparative modeling, predictive and generalization abilities of response surface methodology (RSM) and artificial neural network (ANN) for the thermal structure of stabi...The present study was conducted to present the comparative modeling, predictive and generalization abilities of response surface methodology (RSM) and artificial neural network (ANN) for the thermal structure of stabilized confined jet diffusion flames in the presence of different geometries of bluff-body burners. Two stabilizer disc burners tapered at 30° and 60° and another frustum cone of 60°/30° inclination angle were employed all having the same diameter of 80 (mm) acting as flame holders. The measured radial mean temperature profiles of the developed stabilized flames at different normalized axial distances (x/dj) were considered as the model example of the physical process. The RSM and ANN methods analyze the effect of the two operating parameters namely (r), the radial distance from the center line of the flame, and (x/dj) on the measured temperature of the flames, to find the predicted maximum temperature and the corresponding process variables. A three-layered Feed Forward Neural Network in conjugation with the hyperbolic tangent sigmoid (tansig) as transfer function and the optimized topology of 2:10:1 (input neurons: hidden neurons: output neurons) was developed. Also the ANN method has been employed to illustrate such effects in the three and two dimensions and shows the location of the predicted maximum temperature. The results indicated the superiority of ANN in the prediction capability as the ranges of R2 and F Ratio are 0.868 - 0.947 and 231.7 - 864.1 for RSM method compared to 0.964 - 0.987 and 2878.8 7580.7 for ANN method beside lower values for error analysis terms.展开更多
Alzheimer’s disease is a primary age-related neurodegenerative disorder that can result in impaired cognitive and memory functions.Although connections between changes in brain networks of Alzheimer’s disease patien...Alzheimer’s disease is a primary age-related neurodegenerative disorder that can result in impaired cognitive and memory functions.Although connections between changes in brain networks of Alzheimer’s disease patients have been established,the mechanisms that drive these alterations remain incompletely understood.This study,which was conducted in 2018 at Northeastern University in China,included data from 97 participants of the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset covering genetics,imaging,and clinical data.All participants were divided into two groups:normal control(n=52;20 males and 32 females;mean age 73.90±4.72 years)and Alzheimer’s disease(n=45,23 males and 22 females;mean age 74.85±5.66).To uncover the wiring mechanisms that shaped changes in the topology of human brain networks of Alzheimer’s disease patients,we proposed a local naive Bayes brain network model based on graph theory.Our results showed that the proposed model provided an excellent fit to observe networks in all properties examined,including clustering coefficient,modularity,characteristic path length,network efficiency,betweenness,and degree distribution compared with empirical methods.This proposed model simulated the wiring changes in human brain networks between controls and Alzheimer’s disease patients.Our results demonstrate its utility in understanding relationships between brain tissue structure and cognitive or behavioral functions.The ADNI was performed in accordance with the Good Clinical Practice guidelines,US 21 CFR Part 50-Protection of Human Subjects,and Part 56-Institutional Review Boards(IRBs)/Research Good Clinical Practice guidelines Institutional Review Boards(IRBs)/Research Ethics Boards(REBs).展开更多
图结构数据在社交网络、交通系统、生物信息等场景中广泛存在。图神经网络(graph neural networks,GNNs)利用消息传递机制迭代地聚合邻居信息,在节点分类、链路预测和图分类等任务中展现出良好性能。然而,随着数据规模的持续扩大与应用...图结构数据在社交网络、交通系统、生物信息等场景中广泛存在。图神经网络(graph neural networks,GNNs)利用消息传递机制迭代地聚合邻居信息,在节点分类、链路预测和图分类等任务中展现出良好性能。然而,随着数据规模的持续扩大与应用场景的日趋复杂,GNNs面临表达能力有限与泛化能力不足等关键挑战。近年来,以大语言模型(large language models,LLMs)为代表的基础模型迅速发展,展现出卓越的泛化与推理能力,为图机器学习领域带来了新的启发。基于此,本研究提出图基础模型(graph foundation model,GFM)的概念,希望通过在大规模图数据上预训练,获得能够灵活适配多种下游任务的通用模型;同时系统梳理了近年来图基础模型的相关研究,并依据其对GNNs与LLMs的依赖程度,将现有方法归纳为3类,综述其研究进展并介绍了作者团队在相关方向的实践探索经验。最后,展望了图基础模型未来发展可能面临的关键挑战与前景,以期为图机器学习领域的持续创新提供参考。展开更多
Recent advances in machine learning have demonstrated an enormous utility of deep learning approaches,particularly Graph Neural Networks(GNNs)for materials science.These methods have emerged as powerful tools for high...Recent advances in machine learning have demonstrated an enormous utility of deep learning approaches,particularly Graph Neural Networks(GNNs)for materials science.These methods have emerged as powerful tools for high-throughput prediction of material properties,offering a compelling enhancement and alternative to traditional first-principles calculations.While the community has predominantly focused on developing increasingly complex and universal models to enhance predictive accuracy,such approaches often lack physical interpretability and insights into materials behavior.Here,we introduce a novel computational paradigm—Self-Adaptable Graph Attention Networks integrated with Symbolic Regression(SA-GAT-SR)—that synergistically combines the predictive capability of GNNs with the interpretative power of symbolic regression.Our framework employs a self-adaptable encoding algorithm that automatically identifies and adjust attention weights so as to screen critical features from an expansive 180-dimensional feature space while maintainingO(n)computational scaling.The integratedSRmodule subsequently distills these features into compact analytical expressions that explicitly reveal quantum-mechanically meaningful relationships,achieving 23×acceleration compared to conventional SR implementations that heavily rely on first-principle calculations-derived features as input.This work suggests a new framework in computational materials science,bridging the gap between predictive accuracy and physical interpretability,offering valuable physical insights into material behavior.展开更多
抗体在免疫应答、疾病防御等方面都发挥着至关重要的作用。目前,抗体蛋白质结构预测方法对抗体的互补决定区预测仍然是一个挑战。本文设计了一种基于图神经网络的抗体蛋白质结构优化方法——图神经网络的抗体优化模型(optimization mode...抗体在免疫应答、疾病防御等方面都发挥着至关重要的作用。目前,抗体蛋白质结构预测方法对抗体的互补决定区预测仍然是一个挑战。本文设计了一种基于图神经网络的抗体蛋白质结构优化方法——图神经网络的抗体优化模型(optimization model of immune body structure based on graph neural network,GraphIR),给定抗体的初始结构,通过抗体预训练语言模型获得初始结构的互补决定区序列表征和其他序列特征以及结构特征。然后,设计了一个针对抗体结构优化的等变图神经网络优化抗体互补决定区结构。实验结果显示,在46个抗体基准测试集上,GraphIR预测的互补决定区(complementarity determining regions,CDR)H3区域的平均均方根偏差(root mean square deviation,RMSD)为1.37Å,预测精度比对标的方法ABodyBuilder、RepertoireBuilder、RosettaAntibody和Deep-Ab分别提升了7.45%、6.11%、7.65%和1.27%。展开更多
Multi-scale problems in Computational Fluid Dynamics(CFD)often require numerous simulations across various design parameters.Using a fixed mesh for all cases may fail to capture critical physical features.Moving mesh ...Multi-scale problems in Computational Fluid Dynamics(CFD)often require numerous simulations across various design parameters.Using a fixed mesh for all cases may fail to capture critical physical features.Moving mesh adaptation provides an optimal resource allocation to obtain high-resolution flow-fields on low-resolution meshes.However,most existing methods require manual experience and the flow posteriori information poses great challenges to practical applications.In addition,generating adaptive meshes directly from design parameters is difficult due to highly nonlinear relationships.The diffusion model is currently the most popular model in generative tasks that integrates the diffusion principle into deep learning to capture the complex nonlinear correlations.A dual diffusion framework,Para2Mesh,is proposed to predict the adaptive meshes from design parameters by exploiting the robust data distribution learning ability of the diffusion model.Through iterative denoising,the proposed dual networks accurately reconstruct the flow-field to provide flow features as supervised information,and then achieve rapid and reliable mesh movement.Experiments in CFD scenarios demonstrate that Para2Mesh predicts similar meshes directly from design parameters with much higher efficiency than traditional method.It could become a real-time adaptation tool to assist engineering design and optimization,providing a promising solution for high-resolution flow-field analysis.展开更多
文摘Modeling, predictive and generalization capabilities of response surface methodology (RSM) and artificial neural network (ANN) have been performed to assess the thermal structure of the experimentally studied catalytic combustion of stabilized confined turbulent gaseous diffusion flames. The Pt/<i>γ</i>Al<sub>2</sub>O<sub>3</sub> and Pd/<i>γ</i>Al<sub>2</sub>O<sub>3</sub> disc burners were located in the combustion domain and the experiments were accomplished under both fuel-rich and fuel-lean conditions at a modified equivalence (fuel/air) ratio (<i><span style="white-space:nowrap;"><span style="font-family:Verdana, Helvetica, Arial;white-space:normal;background-color:#FFFFFF;">ø</span></span></i>) of 0.75 and 0.25, respectively. The thermal structure of these catalytic flames developed over the Pt and Pd disc burners w<span style="white-space:normal;font-family:;" "="">as</span><span style="white-space:normal;font-family:;" "=""> scrutinized via measuring the mean temperature profiles in the radial direction at different discrete axial locations along with the flames. The RSM and ANN methods investigated the effect of the two operating parameters namely (<i>r</i>), the radial distance from the center line of the flame, and (<i>x</i>), axial distance along with the flame over the disc, on the measured temperature of the flames and predicted the corresponding temperatures beside predicting the maximum temperature and the corresponding input process variables. A three</span><span style="white-space:normal;font-family:;" "="">-</span><span style="white-space:normal;font-family:;" "="">layered Feed Forward Neural Network was developed in conjugation with the hyperbolic tangent sigmoid (tansig) transfer function and an optimized topology of 2:10:1 (input neurons:hidden neurons:output neurons). Also the ANN method has been exploited to illustrate </span><span style="white-space:normal;font-family:;" "="">the </span><span style="white-space:normal;font-family:;" "="">effects of coded <i>R</i> and <i>X</i> input variables on the response in the three and two dimensions and to locate the predicted maximum temperature. The results indicated the superiority of ANN in the prediction capability as the ranges of & F_Ratio are 0.9181</span><span style="white-space:normal;font-family:;" "=""> </span><span style="white-space:normal;font-family:;" "="">- 0.9809 & 634.5</span><span style="white-space:normal;font-family:;" "=""> </span><span style="white-space:normal;font-family:;" "="">- 3528.8 for RSM method compared to 0.9857</span><span style="white-space:normal;font-family:;" "=""> </span><span style="white-space:normal;font-family:;" "="">- 0.9951 & 7636.4</span><span style="white-space:normal;font-family:;" "=""> </span><span style="white-space:normal;font-family:;" "="">- 24</span><span style="white-space:normal;font-family:;" "="">,</span><span style="white-space:normal;font-family:;" "="">028.4 for ANN method beside lower values </span><span style="white-space:normal;font-family:;" "="">for error analysis terms.</span>
文摘Recent industrial explosions globally have intensified the focus in mechanical engineering on designing infras-tructure systems and networks capable of withstanding blast loading.Initially centered on high-profile facilities such as embassies and petrochemical plants,this concern now extends to a wider array of infrastructures and facilities.Engineers and scholars increasingly prioritize structural safety against explosions,particularly to prevent disproportionate collapse and damage to nearby structures.Urbanization has further amplified the reliance on oil and gas pipelines,making them vital for urban life and prime targets for terrorist activities.Consequently,there is a growing imperative for computational engineering solutions to tackle blast loading on pipelines and mitigate associated risks to avert disasters.In this study,an empty pipe model was successfully validated under contact blast conditions using Abaqus software,a powerful tool in mechanical engineering for simulating blast effects on buried pipelines.Employing a Eulerian-Lagrangian computational fluid dynamics approach,the investigation extended to above-surface and below-surface blasts at standoff distances of 25 and 50 mm.Material descriptions in the numerical model relied on Abaqus’default mechanical models.Comparative analysis revealed varying pipe performance,with deformation decreasing as explosion-to-pipe distance increased.The explosion’s location relative to the pipe surface notably influenced deformation levels,a key finding highlighted in the study.Moreover,quantitative findings indicated varying ratios of plastic dissipation energy(PDE)for different blast scenarios compared to the contact blast(P0).Specifically,P1(25 mm subsurface blast)and P2(50 mm subsurface blast)showed approximately 24.07%and 14.77%of P0’s PDE,respectively,while P3(25 mm above-surface blast)and P4(50 mm above-surface blast)exhibited lower PDE values,accounting for about 18.08%and 9.67%of P0’s PDE,respectively.Utilising energy-absorbing materials such as thin coatings of ultra-high-strength concrete,metallic foams,carbon fiber-reinforced polymer wraps,and others on the pipeline to effectively mitigate blast damage is recommended.This research contributes to the advancement of mechanical engineering by providing insights and solutions crucial for enhancing the resilience and safety of underground pipelines in the face of blast events.
文摘The present study was conducted to present the comparative modeling, predictive and generalization abilities of response surface methodology (RSM) and artificial neural network (ANN) for the thermal structure of stabilized confined jet diffusion flames in the presence of different geometries of bluff-body burners. Two stabilizer disc burners tapered at 30° and 60° and another frustum cone of 60°/30° inclination angle were employed all having the same diameter of 80 (mm) acting as flame holders. The measured radial mean temperature profiles of the developed stabilized flames at different normalized axial distances (x/dj) were considered as the model example of the physical process. The RSM and ANN methods analyze the effect of the two operating parameters namely (r), the radial distance from the center line of the flame, and (x/dj) on the measured temperature of the flames, to find the predicted maximum temperature and the corresponding process variables. A three-layered Feed Forward Neural Network in conjugation with the hyperbolic tangent sigmoid (tansig) as transfer function and the optimized topology of 2:10:1 (input neurons: hidden neurons: output neurons) was developed. Also the ANN method has been employed to illustrate such effects in the three and two dimensions and shows the location of the predicted maximum temperature. The results indicated the superiority of ANN in the prediction capability as the ranges of R2 and F Ratio are 0.868 - 0.947 and 231.7 - 864.1 for RSM method compared to 0.964 - 0.987 and 2878.8 7580.7 for ANN method beside lower values for error analysis terms.
基金Fundamental Research Funds for the Central Universities in China,No.N161608001 and No.N171903002
文摘Alzheimer’s disease is a primary age-related neurodegenerative disorder that can result in impaired cognitive and memory functions.Although connections between changes in brain networks of Alzheimer’s disease patients have been established,the mechanisms that drive these alterations remain incompletely understood.This study,which was conducted in 2018 at Northeastern University in China,included data from 97 participants of the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset covering genetics,imaging,and clinical data.All participants were divided into two groups:normal control(n=52;20 males and 32 females;mean age 73.90±4.72 years)and Alzheimer’s disease(n=45,23 males and 22 females;mean age 74.85±5.66).To uncover the wiring mechanisms that shaped changes in the topology of human brain networks of Alzheimer’s disease patients,we proposed a local naive Bayes brain network model based on graph theory.Our results showed that the proposed model provided an excellent fit to observe networks in all properties examined,including clustering coefficient,modularity,characteristic path length,network efficiency,betweenness,and degree distribution compared with empirical methods.This proposed model simulated the wiring changes in human brain networks between controls and Alzheimer’s disease patients.Our results demonstrate its utility in understanding relationships between brain tissue structure and cognitive or behavioral functions.The ADNI was performed in accordance with the Good Clinical Practice guidelines,US 21 CFR Part 50-Protection of Human Subjects,and Part 56-Institutional Review Boards(IRBs)/Research Good Clinical Practice guidelines Institutional Review Boards(IRBs)/Research Ethics Boards(REBs).
文摘图结构数据在社交网络、交通系统、生物信息等场景中广泛存在。图神经网络(graph neural networks,GNNs)利用消息传递机制迭代地聚合邻居信息,在节点分类、链路预测和图分类等任务中展现出良好性能。然而,随着数据规模的持续扩大与应用场景的日趋复杂,GNNs面临表达能力有限与泛化能力不足等关键挑战。近年来,以大语言模型(large language models,LLMs)为代表的基础模型迅速发展,展现出卓越的泛化与推理能力,为图机器学习领域带来了新的启发。基于此,本研究提出图基础模型(graph foundation model,GFM)的概念,希望通过在大规模图数据上预训练,获得能够灵活适配多种下游任务的通用模型;同时系统梳理了近年来图基础模型的相关研究,并依据其对GNNs与LLMs的依赖程度,将现有方法归纳为3类,综述其研究进展并介绍了作者团队在相关方向的实践探索经验。最后,展望了图基础模型未来发展可能面临的关键挑战与前景,以期为图机器学习领域的持续创新提供参考。
基金supported by National Natural Science Foundation of China (No.12374057)Fundamental Research Funds for the Central Universities. The work (S.T.) at Los Alamos National Laboratory (LANL) was performed at the Center for Integrated Nanotechnologies (CINT), a U.S. Department of Energy, Office of Science user facility at LANL.
文摘Recent advances in machine learning have demonstrated an enormous utility of deep learning approaches,particularly Graph Neural Networks(GNNs)for materials science.These methods have emerged as powerful tools for high-throughput prediction of material properties,offering a compelling enhancement and alternative to traditional first-principles calculations.While the community has predominantly focused on developing increasingly complex and universal models to enhance predictive accuracy,such approaches often lack physical interpretability and insights into materials behavior.Here,we introduce a novel computational paradigm—Self-Adaptable Graph Attention Networks integrated with Symbolic Regression(SA-GAT-SR)—that synergistically combines the predictive capability of GNNs with the interpretative power of symbolic regression.Our framework employs a self-adaptable encoding algorithm that automatically identifies and adjust attention weights so as to screen critical features from an expansive 180-dimensional feature space while maintainingO(n)computational scaling.The integratedSRmodule subsequently distills these features into compact analytical expressions that explicitly reveal quantum-mechanically meaningful relationships,achieving 23×acceleration compared to conventional SR implementations that heavily rely on first-principle calculations-derived features as input.This work suggests a new framework in computational materials science,bridging the gap between predictive accuracy and physical interpretability,offering valuable physical insights into material behavior.
文摘抗体在免疫应答、疾病防御等方面都发挥着至关重要的作用。目前,抗体蛋白质结构预测方法对抗体的互补决定区预测仍然是一个挑战。本文设计了一种基于图神经网络的抗体蛋白质结构优化方法——图神经网络的抗体优化模型(optimization model of immune body structure based on graph neural network,GraphIR),给定抗体的初始结构,通过抗体预训练语言模型获得初始结构的互补决定区序列表征和其他序列特征以及结构特征。然后,设计了一个针对抗体结构优化的等变图神经网络优化抗体互补决定区结构。实验结果显示,在46个抗体基准测试集上,GraphIR预测的互补决定区(complementarity determining regions,CDR)H3区域的平均均方根偏差(root mean square deviation,RMSD)为1.37Å,预测精度比对标的方法ABodyBuilder、RepertoireBuilder、RosettaAntibody和Deep-Ab分别提升了7.45%、6.11%、7.65%和1.27%。
基金co-supported by the Aeronautical Science Foundation of China(Nos.2018ZA52002 and 2019ZA052011)。
文摘Multi-scale problems in Computational Fluid Dynamics(CFD)often require numerous simulations across various design parameters.Using a fixed mesh for all cases may fail to capture critical physical features.Moving mesh adaptation provides an optimal resource allocation to obtain high-resolution flow-fields on low-resolution meshes.However,most existing methods require manual experience and the flow posteriori information poses great challenges to practical applications.In addition,generating adaptive meshes directly from design parameters is difficult due to highly nonlinear relationships.The diffusion model is currently the most popular model in generative tasks that integrates the diffusion principle into deep learning to capture the complex nonlinear correlations.A dual diffusion framework,Para2Mesh,is proposed to predict the adaptive meshes from design parameters by exploiting the robust data distribution learning ability of the diffusion model.Through iterative denoising,the proposed dual networks accurately reconstruct the flow-field to provide flow features as supervised information,and then achieve rapid and reliable mesh movement.Experiments in CFD scenarios demonstrate that Para2Mesh predicts similar meshes directly from design parameters with much higher efficiency than traditional method.It could become a real-time adaptation tool to assist engineering design and optimization,providing a promising solution for high-resolution flow-field analysis.
