CAREER: A Multichannel Convolutional Neural Network Framework for Prediction of Damage Nucleation Sites in Microstructure

职业生涯：用于预测微观结构中损伤成核位点的多通道卷积神经网络框架

• 批准号: 2142164
• 负责人: Brandon Runnels
• 金额: $ 50.51万
• 依托单位: University of Colorado at Colorado Springs
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-06-01 至 2023-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2142164&HistoricalAwards=false
• 关键词: CAREER; Multichannel; Convolutional; Neural; Network

This Faculty Early Career Development (CAREER) award supports research that will aim to answer the longstanding question: What causes materials to fail? Structural materials are the building blocks of modern lifestyle, supporting applications ranging from infrastructure to national security, yet the mechanisms underlying their failure are not well understood. The first stage of catastrophic failure is often the nucleation of small voids, through a complex and multifaceted process that has so far evaded simplified models. This project will leverage advanced machine learning methods, which can identify subtle trends in large datasets, with damage mechanics models to unravel the nuances of pore nucleation. The result will be a computer model that is able to rapidly screen materials to determine damage susceptibility. The educational part of this project is twofold. First, the project will make advances in machine learning-based mechanics of materials accessible to budding and amateur engineers and scientists through an internet-based application, called “Solid Genius.” Solid Genius will be freely available, allowing direct manipulation and exploration of the material model and its predictive capability through a user-friendly educational interface. Second, the project will develop a new graduate course to provide training for rising researchers in machine learning-based damage mechanics.Experimental evidence indicates that grain boundaries are preferential sites for pore nucleation, but no meaningful correlations between grain boundary properties and failure likelihood have yet been conclusively established. A multi-channel convolutional neural network (MCCNN) machine learning framework is planned that will be able to identify potential pore nucleation sites in pristine microstructure. The framework will simultaneously account for both nonlocal properties (microstructure, grain texture, etc.) and local properties (pointwise curvature, inclination, etc.), synthesizing them against a training dataset to produce a reliable estimator of failure likelihood. Training data will consist of reconstructed experimental micrographs and EBSD data, divided into “failure” and “no-failure” partitions. The raw experimental data will then be enriched with secondary calculations and supplemental mechanics simulations to supply non-visible channels such as grain boundary energy and mechanical stress. The trained MCCNN framework will then be used in concert with a damage mechanics model to further probe the early-time behavior of pore initiation and growth. Development will include an emphasis on determining physical interpretability of each aspect of the MCCNN model, such as formalizing the connection between individual convolutional layers and feature segmentation in microstructure, to facilitate a more rigorous application of the framework to the problem of damage assessment.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.

这个教师早期职业发展（CAREER）奖支持旨在回答长期存在的问题的研究：是什么原因导致材料失败？结构材料是现代生活方式的基石，支持从基础设施到国家安全的各种应用，但其失效的机制尚不清楚。灾难性破坏的第一阶段通常是小空洞的成核，这是一个复杂而多方面的过程，迄今为止还没有简化的模型。该项目将利用先进的机器学习方法，可以识别大型数据集中的微妙趋势，并利用损伤力学模型来揭示孔隙成核的细微差别。其结果将是一个计算机模型，能够快速筛选材料，以确定损坏的敏感性。该项目的教育部分是双重的。首先，该项目将通过一个名为“Solid Genius”的基于互联网的应用程序，为初出茅庐的业余工程师和科学家提供基于机器学习的材料力学方面的进展。Solid Genius将免费提供，允许通过用户友好的教育界面直接操作和探索材料模型及其预测能力。第二，该项目将开发一个新的研究生课程，为基于机器学习的损伤力学的新兴研究人员提供培训。实验证据表明，晶界是孔隙成核的优先位置，但晶界性质和失效可能性之间尚未确定有意义的相关性。计划建立一个多通道卷积神经网络（MCCNN）机器学习框架，该框架将能够识别原始微观结构中潜在的孔隙成核位点。该框架将同时考虑两个非局部性质（微观结构，晶粒织构等）。和局部特性（逐点曲率、倾斜度等），将它们与训练数据集进行合成，以产生故障可能性的可靠估计值。训练数据将由重建的实验显微照片和EBSD数据组成，分为“故障”和“无故障”分区。然后，原始实验数据将通过二次计算和补充力学模拟来丰富，以提供不可见的通道，例如晶界能和机械应力。然后将训练好的MCCNN框架与损伤力学模型一起使用，以进一步探测孔隙萌生和生长的早期行为。开发将包括重点确定MCCNN模型每个方面的物理可解释性，例如将各个卷积层之间的连接和微观结构中的特征分割形式化，该奖项反映了NSF的法定使命，并被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准。

项目成果

Automated determination of grain boundary energy and potential-dependence using the OpenKIM framework

• DOI: 10.1016/j.commatsci.2023.112057
• 发表时间: 2022-12
• 期刊: Computational Materials Science
• 影响因子: 3.3
• 作者: Brendon Waters;Daniel S. Karls;I. Nikiforov;R. Elliott;E. Tadmor;B. Runnels