A Machine Learning Framework for Bridging the Mechanical Responses of a Material at Multiple Structure Length Scales

用于桥接材料在多个结构长度尺度上的机械响应的机器学习框架

• 批准号: 2027105
• 负责人: Surya Kalidindi
• 金额: $ 50万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-15 至 2024-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2027105&HistoricalAwards=false
• 关键词: Machine; Learning; Framework; Bridging; Mechanical

The safety of structures bearing load depends upon the ability of the engineers to predict the behavior under operating conditions during the design phase. This means that the engineers must know the behavior of materials that are used in these structures accurately. Damage and failure in materials start at the atomic scale and propagate through the structural length scales to manifest itself. Therefore, it is important to be able to predict material response through multiple scales based on experimental observations and computational modeling. Much effort has been put towards achieving this capability but the immense amount of information that is obtained from advanced experimental techniques and physics-based numerical simulations has proven intractable. This award aims to transform the current practices in the field of mechanics of materials by introducing machine learning to optimize the extraction and fusion of information and knowledge from the disparate and expansive experimental and numerical datasets. The goal is to dramatically improve the efficiency and output compared to the current protocols of material behavior prediction, which will also accelerate the materials discovery process. It is expected that theses outcomes will provide significant competitive advantages to the US industry in a broad range of advanced materials technology areas, including those related to healthcare, energy, and national security. The award will also be a vehicle to train graduate and undergraduate students at the intersection of materials science, mechanics of materials, and data and information sciences. The research outcomes and developed tools will be transferred into commercial practice through multiple industrial collaborations.It is proposed to accomplish the research objective described above by developing and deploying a novel Bayesian machine learning framework that is centered on systematically uncovering the physics controlling the multiscale materials phenomena of interest. The overall strategy involves establishing suitable high-fidelity reduced-order (i.e., surrogate) models to capture the localization tensors for elastic and plastic deformations in multiphase polycrystalline microstructures. In turn, these models will be used to formulate a computationally efficient strategy for Bayesian sequential design of experiments that identifies the most optimal experiments offering the highest potential for information (or knowledge) gain. As a result, several high-throughput experimental assays will be designed and evaluated to critically examine their value for reliably calibrating the unknown material parameters in sophisticated plasticity theories. Based on the results of these investigations, novel high-throughput protocols will be designed and implemented to demonstrate the significant cost and time savings achieved in the multiscale characterization of the mechanical behavior of heterogeneous structural materials. Specifically, the new protocols will be validated using samples of polycrystalline dual-phase steels.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

结构承受荷载的安全性取决于工程师在设计阶段预测其在运行条件下的性能的能力。这意味着工程师必须准确地了解这些结构中使用的材料的性能。材料的损伤和失效始于原子尺度，并通过结构长度尺度传播，从而表现出来。因此，能够基于实验观察和计算建模通过多尺度预测材料响应是很重要的。为了实现这一能力，人们付出了很多努力，但从先进的实验技术和基于物理的数值模拟中获得的大量信息已被证明是棘手的。该奖项旨在通过引入机器学习来优化从不同的和扩展的实验和数值数据集中提取和融合信息和知识，从而改变材料力学领域的当前实践。与目前的材料行为预测协议相比，目标是显着提高效率和输出，这也将加速材料发现过程。预计这些成果将为美国工业在广泛的先进材料技术领域提供显著的竞争优势，包括与医疗保健、能源和国家安全相关的领域。该奖项还将成为培养材料科学、材料力学、数据和信息科学交叉领域的研究生和本科生的工具。研究成果和开发的工具将通过多个工业合作转化为商业实践。我们建议通过开发和部署一个新的贝叶斯机器学习框架来实现上述研究目标，该框架以系统地揭示控制感兴趣的多尺度材料现象的物理为中心。总体策略包括建立合适的高保真度降阶（即替代）模型，以捕获多相多晶微结构中弹性和塑性变形的局部化张量。反过来，这些模型将用于制定计算效率策略的贝叶斯顺序设计的实验，以确定最优的实验，提供信息（或知识）增益的最大潜力。因此，将设计和评估几个高通量实验分析，以严格检查其在复杂塑性理论中可靠校准未知材料参数的价值。基于这些研究结果，新的高通量协议将被设计和实施，以证明在非均质结构材料力学行为的多尺度表征中实现的显著成本和时间节省。具体来说，新方案将使用多晶双相钢样品进行验证。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Development of a Robust CNN Model for Capturing Microstructure-Property Linkages and Building Property Closures Supporting Material Design

• DOI: 10.3389/fmats.2022.851085
• 发表时间: 2022-03-11
• 期刊: FRONTIERS IN MATERIALS
• 影响因子: 3.2
• 作者: Mann, Andrew;Kalidindi, Surya R.
• 通讯作者: Kalidindi, Surya R.

Recurrent localization networks applied to the Lippmann-Schwinger equation

应用于 Lippmann-Schwinger 方程的循环定位网络

• DOI: 10.1016/j.commatsci.2021.110356
• 发表时间: 2021
• 期刊: Computational Materials Science
• 影响因子: 3.3
• 作者: Kelly, Conlain;Kalidindi, Surya R.
• 通讯作者: Kalidindi, Surya R.

Bayesian calibration of continuum damage model parameters for an oxide-oxide ceramic matrix composite using inhomogeneous experimental data

• DOI: 10.1016/j.mechmat.2022.104487
• 发表时间: 2022-10
• 期刊: Mechanics of Materials
• 影响因子: 3.9
• 作者: Adam P. Generale;R. Hall;R. Brockman;V. R. Joseph;G. Jefferson;L. Zawada;J. Pierce;S. Kalidindi

Gaussian process autoregression models for the evolution of polycrystalline microstructures subjected to arbitrary stretching tensors

• DOI: 10.1016/j.ijplas.2023.103532
• 发表时间: 2023-01
• 期刊: International Journal of Plasticity
• 影响因子: 9.8
• 作者: S. Hashemi;S. Kalidindi

Multiresolution investigations of thermally aged steels using spherical indentation stress-strain protocols and image analysis

• DOI: 10.1016/j.mechmat.2022.104265
• 发表时间: 2022-02
• 期刊: Mechanics of Materials
• 影响因子: 3.9
• 作者: Almambet Iskakov;S. Kalidindi