APL Machine Learning最新文献_第6页

Artificial neural network-based streamline tracing strategy applied to hypersonic waverider design 基于人工神经网络的流线跟踪策略在高超声速乘波机设计中的应用

APL Machine Learning Pub Date : 2023-02-14 DOI: 10.1063/5.0127034

Anagha G. Rao, Umesh Siddharth, Srisha M. V. Rao

{"title":"Artificial neural network-based streamline tracing strategy applied to hypersonic waverider design","authors":"Anagha G. Rao, Umesh Siddharth, Srisha M. V. Rao","doi":"10.1063/5.0127034","DOIUrl":"https://doi.org/10.1063/5.0127034","url":null,"abstract":"Streamline tracing in hypersonic flows is essential for designing a high-performance waverider and intake. Conventionally, the streamline equations are solved after obtaining the velocity field over a basic flow field from simplified flow differential equations or three-dimensional computational fluid dynamics. The hypersonic waverider shape is generated by repeatedly applying the streamline tracing approach along several planes. This approach is computationally expensive for iterative waverider optimization. We provide a novel strategy where an Artificial Neural Network (ANN) is trained to directly predict the streamlines without solving the differential equations. We consider the standard simple cone-derived waverider using Taylor–Maccoll equations for the conical flow field as a template for the study. First, the streamlines from the shock are solved for a wide range of cone angle and Mach number conditions resulting in an extensive database. The streamlines are parameterized by a third-order polynomial, and an ANN is trained to predict the coefficients of the polynomial for arbitrary inputs of Mach number, cone angle, and streamline originating locations. We apply this strategy to design a cone-derived waverider and compare the geometry obtained with the standard conical waverider design method and the simplified waverider design method. The ANN technique is highly accurate, with a difference of 0.68% from the standard method in the coordinates of the waverider. The performance of the three waveriders is compared using Reynolds averaged Navier–Stokes simulations. The ANN-derived waverider does not indicate severe flow spillage at the leading edge. The new ANN-based approach is 20 times faster than the standard method.","PeriodicalId":229559,"journal":{"name":"APL Machine Learning","volume":"266 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135797481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Physics-constrained 3D convolutional neural networks for electrodynamics 电动力学的物理约束三维卷积神经网络

APL Machine Learning Pub Date : 2023-01-31 DOI: 10.1063/5.0132433

A. Scheinker, R. Pokharel

引用次数: 0

Automatic identification of edge localized modes in the DIII-D tokamak DIII-D托卡马克边缘局域模式的自动识别

APL Machine Learning Pub Date : 2022-12-16 DOI: 10.1063/5.0134001

F. O’Shea, Semin Joung, David R Smith, R. Coffee

引用次数: 0

DyFraNet: Forecasting and backcasting dynamic fracture mechanics in space and time using a 2D-to-3D deep neural network DyFraNet:利用2D-to-3D深度神经网络预测和反演空间和时间上的动态断裂力学

APL Machine Learning Pub Date : 2022-11-15 DOI: 10.1063/5.0135015

Yu-Chuan Hsu, M. Buehler

{"title":"DyFraNet: Forecasting and backcasting dynamic fracture mechanics in space and time using a 2D-to-3D deep neural network","authors":"Yu-Chuan Hsu, M. Buehler","doi":"10.1063/5.0135015","DOIUrl":"https://doi.org/10.1063/5.0135015","url":null,"abstract":"The dynamics of material failure is a critical phenomenon relevant to a range of scientific and engineering fields, from healthcare to structural materials. We propose a specially designed deep neural network, DyFraNet, which can predict dynamic fracture behaviors by identifying a complete history of fracture propagation—from the onset of cracking, as a crack grows through the material, modeled as a series of frames evolving over time and dependent on each other. Furthermore, the model can not only forecast future fracture processes but also backcast to elucidate past fracture histories. In this scenario, once provided with the outcome of a fracture event, the model will reveal past events that led to this state and can also predict future evolutions of the failure process. By comparing the predicted results with atomistic-level simulations and theory, we show that DyFraNet can capture dynamic fracture mechanics by accurately predicting how cracks develop over time, including measures such as the crack speed, as well as when cracks become unstable. We use Gradient-weighted Class Activation Mapping, Grad-CAM, to interpret how DyFraNet perceives the relationship between geometric conditions and fracture dynamics, and we find that DyFraNet pays special attention to the areas around crack tips that have a critical influence in the early stage of fracture propagation. In later stages, the model pays increased attention to the existing or newly formed damaged regions in the material. The proposed approach offers the potential to accelerate the exploration of dynamical processes in material design against failure and can be adapted for all kinds of dynamical problems.","PeriodicalId":229559,"journal":{"name":"APL Machine Learning","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126958646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Classification of multi-frequency RF signals by extreme learning, using magnetic tunnel junctions as neurons and synapses 分类多频射频信号的极端学习，使用磁隧道连接作为神经元和突触

APL Machine Learning Pub Date : 2022-11-02 DOI: 10.1063/5.0155447

N. Leroux, Danijela Markovi'c, D. Sanz-Hern'andez, J. Trastoy, P. Bortolotti, A. Schulman, L. Benetti, A. Jenkins, Ricardo Ferreira, J. Grollier, F. A. Mizrahi

引用次数: 0

Pair distribution function analysis for oxide defect identification through feature extraction and supervised learning 基于特征提取和监督学习的氧化缺陷配对分布函数分析

APL Machine Learning Pub Date : 2022-10-13 DOI: 10.1063/5.0130681

Shuyan Zhang, Jie Gong, Sharon Chu, Daniel Z. Xiao, B. Reeja‐Jayan, A. McGaughey

{"title":"Pair distribution function analysis for oxide defect identification through feature extraction and supervised learning","authors":"Shuyan Zhang, Jie Gong, Sharon Chu, Daniel Z. Xiao, B. Reeja‐Jayan, A. McGaughey","doi":"10.1063/5.0130681","DOIUrl":"https://doi.org/10.1063/5.0130681","url":null,"abstract":"Feature extraction and a neural network model are applied to predict defect types and concentrations in experimental anatase TiO2 samples. A dataset of TiO2 structures with vacancies and interstitials of oxygen and titanium is built, and the structures are relaxed using energy minimization. The features of the calculated pair distribution functions (PDFs) of these defected structures are extracted using linear methods (principal component analysis and non-negative matrix factorization) and non-linear methods (autoencoder and convolutional neural network). The extracted features are used as inputs to a neural network that maps feature weights to the concentration of each defect type. The performance of this machine learning pipeline is validated by predicting defect concentrations based on experimentally measured TiO2 PDFs and comparing the results to brute-force predictions. A physics-based initialization of the autoencoder has the highest accuracy in predicting defect concentrations. This model incorporates physical interpretability and predictability of material structures, enabling a more efficient characterization process with scattering data.","PeriodicalId":229559,"journal":{"name":"APL Machine Learning","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125345246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rotationally equivariant super-resolution of velocity fields in two-dimensional flows using convolutional neural networks 二维流场旋转等变超分辨卷积神经网络

APL Machine Learning Pub Date : 2022-02-22 DOI: 10.1063/5.0132326

Y. Yasuda, R. Onishi

{"title":"Rotationally equivariant super-resolution of velocity fields in two-dimensional flows using convolutional neural networks","authors":"Y. Yasuda, R. Onishi","doi":"10.1063/5.0132326","DOIUrl":"https://doi.org/10.1063/5.0132326","url":null,"abstract":"This paper investigates the super-resolution of velocity fields in two-dimensional flows from the viewpoint of rotational equivariance. Super-resolution refers to techniques that enhance the resolution of an image from low to high resolution, and it has recently been applied in fluid mechanics. Rotational equivariance of super-resolution models is defined as the property by which the super-resolved velocity field is rotated according to a rotation of the input, leading to inferences that are covariant with the orientation of fluid systems. In physics, covariance is often related to symmetries. To better understand the connection with symmetries, the notion of rotational consistency of datasets is introduced within the framework of supervised learning, which is defined as the invariance of pairs of low- and high-resolution velocity fields with respect to rotation. This consistency is sufficient and necessary for super-resolution models to learn rotational equivariance from large datasets. Such a large dataset is not required when rotational equivariance is imposed on super-resolution models through the use of prior knowledge in the form of equivariant kernel patterns. Nonetheless, even if a fluid system has rotational symmetry, this symmetry may not carry over to a velocity dataset, which is not rotationally consistent. This inconsistency can arise when the rotation does not commute with the generation of low-resolution velocity fields. These theoretical assertions are supported by the results of numerical experiments, where two existing convolutional neural networks (CNNs) are converted into rotationally equivariant CNNs and the inferences of these CNNs are compared after the supervised training.","PeriodicalId":229559,"journal":{"name":"APL Machine Learning","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121537759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2