Microstructural image based convolutional neural networks for efficient prediction of full-field stress maps in short fiber polymer composites

The increased demand for superior materials has highlighted the need of investigating the mechanical properties of composites to achieve enhanced constitutive relationships.Fiber-reinforced polymer composites have emerged as an integral part of materials development with tailored mechanical properties.However,the complexity and heterogeneity of such composites make it considerably more challenging to have precise quantification of properties and attain an optimal design of structures through experimental and computational approaches.In order to avoid the complex,cumbersome,and labor-intensive experimental and numerical modeling approaches,a machine learning(ML)model is proposed here such that it takes the microstructural image as input with a different range of Young’s modulus of carbon fibers and neat epoxy,and obtains output as visualization of the stress component S11(principal stress in the x-direction).For obtaining the training data of the ML model,a short carbon fiberfilled specimen under quasi-static tension is modeled based on 2D Representative Area Element(RAE)using finite element analysis.The composite is inclusive of short carbon fibers with an aspect ratio of 7.5that are infilled in the epoxy systems at various random orientations and positions generated using the Simple Sequential Inhibition(SSI)process.The study reveals that the pix2pix deep learning Convolutional Neural Network(CNN)model is robust enough to predict the stress fields in the composite for a given arrangement of short fibers filled in epoxy over the specified range of Young’s modulus with high accuracy.The CNN model achieves a correlation score of about 0.999 and L2 norm of less than 0.005 for a majority of the samples in the design spectrum,indicating excellent prediction capability.In this paper,we have focused on the stage-wise chronological development of the CNN model with optimized performance for predicting the full-field stress maps of the fiber-reinforced composite specimens.The development of such a robust and efficient algorithm would significantly reduce the amount of time and cost required to study and design new composite materials through the elimination of numerical inputs by direct microstructural images.

丰质子同位素^(65)As的初步观察

使用20.11A MeV ^(64)Zn束轰击17.2 mg/cm^2的Be靶,初步观察到了丰质子同位素^(65)As。采用由磁分析器、PPAC、电离室和PSSD组成的探测系统,成功地鉴別了反应产物的电荷态、原子系数和质量数。

Probabilistic Analysis and Design of HCP Nanowires:An Efficient Surrogate Based Molecular Dynamics Simulation Approach

We investigate the dependency of strain rate,temperature and size on yield strength of hexagonal close packed（HCP） nanowires based on large-scale molecular dynamics（MD） simulation.A variance-based analysis has been proposed to quantify relative sensitivity of the three controlling factors on the yield strength of the material.One of the major drawbacks of conventional MD simulation based studies is that the simulations are computationally very intensive and economically expensive.Large scale molecular dynamics simulation needs supercomputing access and the larger the number of atoms,the longer it takes time and computational resources.For this reason it becomes practically impossible to perform a robust and comprehensive analysis that requires multiple simulations such as sensitivity analysis,uncertainty quantification and optimization.We propose a novel surrogate based molecular dynamics（SBMD）simulation approach that enables us to carry out thousands of virtual simulations for different combinations of the controlling factors in a computationally efficient way by performing only few MD simulations.Following the SBMD simulation approach an efficient optimum design scheme has been developed to predict optimized size of the nanowire to maximize the yield strength.Subsequently the effect of inevitable uncertainty associated with the controlling factors has been quantified using Monte Carlo simulation.Though we have confined our analyses in this article for Magnesium nanowires only,the proposed approach can be extended to other materials for computationally intensive nano-scale investigation involving multiple factors of influence.

Vibration and Buckling Analyses of Sandwich Plates Containing Functionally Graded Metal Foam Core

In the present work,free vibration and buckling analyses of sandwich plates with various functionally graded foam cores are carried out.Foam cores are assumed to be made of metal,and three different configurations of the porous distribution in the core layer are taken into consideration.To carry out a comparative study between the distributions of pores in the core foam,the mass of foam in all three cases is kept the same.The vibration and buckling behaviors of skew plates are also analyzed as a part of the current investigation.The principle of minimization of potential energy and Hamilton’s principle are used for the derivation of the governing equations,while a C-0 finite element-based higher-order zigzag formulation is developed to solve the free vibration and buckling problems.The influences of gradation laws,boundary conditions,skew angle and geometry of plates are studied in detail for the dynamic and stability characteristics.It is found that both the non-dimensional natural frequency and buckling load decrease with the increase in the thickness of the metal foam cores,while they show an increasing trend as the skew angle of the plate increases.