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

这个教师早期职业发展（Career）奖支持的研究旨在回答一个长期存在的问题：是什么导致材料失效？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，但其失效的机制尚未得到很好的理解。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，迄今为止还无法通过简化模型来实现。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细微趋势，并使用损伤力学模型来揭示孔隙成核的细微差别。结果将是一个能够快速筛选材料以确定损伤敏感性的计算机模型。这个项目的教育意义是双重的。首先，该项目将在基于机器学习的材料力学方面取得进展，新手和业余工程师和科学家可以通过一个名为“Solid Genius”的基于互联网的应用程序访问这些材料。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。其次，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，但晶界性质与破坏可能性之间没有明确的相关性。一个多通道卷积神经网络（MCCNN）机器学习框架将能够识别原始微观结构中潜在的孔隙成核位点。该框架将同时考虑非局部属性（微观结构，纹理等）和局部属性（点曲率，倾角等），将它们与训练数据集合成，以产生可靠的故障可能性估计器。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”两部分。原始实验数据将通过二次计算和补充力学模拟来丰富，以提供晶界能和机械应力等不可见通道。训练后的MCCNN框架将与损伤力学模型一起使用，以进一步探索孔隙形成和生长的早期行为。开发将包括强调确定mcnn模型的每个方面的物理可解释性，例如形式化各个卷积层之间的连接和微观结构中的特征分割，以促进框架更严格地应用于损伤评估问题。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。

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.