arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.07877cs.LGphysics.app-ph
收藏

用于复合材料微观结构均匀化的神经网络 Transformer 模型

A Neural Network Transformer Model for Composite Microstructure Homogenization

Stevens Institute of Technology(史蒂文斯理工学院)

Emil Pitz, Kishore Pochiraju

AI总结:

本文提出一种 Transformer 神经网络架构,通过预测线弹性纤维与弹塑性基体复合微观结构的非线性均匀化应力-应变响应,实现了高效且可泛化的微观结构到属性转换。

摘要:

复合材料微观结构中的非均匀性和不确定性,如果进行严格建模会导致计算瓶颈,如果进行近似处理则会导致应力场和失效预测的求解不准确。尽管存在适用于分析任意和非线性微观结构的方法,但其计算成本使得它们在大规模结构分析中不切实际。代理模型或降阶模型(ROM)通常能提高效率,但通常针对单一微观结构进行校准。均匀化方法(如 Mori-Tanaka 方法)为广泛的组分属性提供快速均匀化。然而,应力相和应变平均等简化假设,使得在微观结构中考虑确定性和随机性变化变得不可行。本文提出了一种 Transformer 神经网络架构,能够捕获各种微观结构和组分知识,使其能够作为计算高效的均匀化代理模型。给定弹性基体中线性弹性纤维的任意复合材料微观结构图像或抽象表示,该 Transformer 网络可预测依赖于历史、非线性和均匀化的应力-应变响应。测试了两种微观结构特征编码方法:使用主成分分析(PCA)计算两点统计量进行降维,以及采用带有卷积神经网络(CNN)的自编码器。两种方法均能准确预测均匀化材料响应。所开发的 Transformer 神经网络为微观结构到属性的转换提供了高效手段,可泛化并扩展至多种微观结构。本文描述了网络架构、训练和测试数据生成,以及在循环加载和随机加载下的性能。

英文摘要:

Heterogeneity and uncertainty in a composite microstructure lead to either computational bottlenecks if modeled rigorously or to solution inaccuracies in the stress field and failure predictions if approximated. Although methods suitable for analyzing arbitrary and non-linear microstructures exist, their computational cost makes them impractical to use in large-scale structural analysis. Surrogate models or Reduced Order Models (ROMs) commonly enhance efficiencies but are typically calibrated with a single microstructure. Homogenization methods, such as the Mori-Tanaka method, offer rapid homogenization for a wide range of constituent properties. However, simplifying assumptions, like stress and strain averaging in phases, render the consideration of both deterministic and stochastic variations in microstructure infeasible. This paper illustrates a transformer neural network architecture that captures the knowledge of various microstructures and constituents, enabling it to function as a computationally efficient homogenization surrogate model. Given an image or an abstraction of an arbitrary composite microstructure of linearly elastic fibers in an elastoplastic matrix, the transformer network predicts the history-dependent, non-linear, and homogenized stress-strain response. Two methods for encoding microstructure features were tested: calculating two-point statistics using Principal Component Analysis (PCA) for dimensionality reduction and employing an autoencoder with a Convolutional Neural Network (CNN). Both methods accurately predict the homogenized material response. The developed transformer neural network offers an efficient means for microstructure-to-property translation, generalizable and extendable to a variety of microstructures. The paper describes the network architecture, training and testing data generation, and performance under cycling and random loadings.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑