Predicting Microstructure-Sensitive Fatigue-Crack Path in 3D Using a Machine Learning Framework
Reads0
Chats0
TLDR
A convolutional neural network (CNN)-based methodology is developed to establish spatial relationships between micromechanical/microstructural features in a cyclically loaded, uncracked microstructure and the 3D crack path, the latter quantified by the vertical deviation of the crack along a specified axis.Abstract:
The overarching aim of this paper is to explore the use of machine learning (ML) to predict the microstructure-sensitive evolution of a three-dimensional (3D) crack surface in a polycrystalline alloy. A convolutional neural network (CNN)-based methodology is developed to establish spatial relationships between micromechanical/microstructural features in a cyclically loaded, uncracked microstructure and the 3D crack path, the latter quantified by the vertical deviation (i.e., z-offset) of the crack along a specified axis. The proposed methodology consists of (i) a feature selection and reduction scheme to identify a lower-dimensional representation of the experimentally measured microstructure and computed micromechanical fields, which allows for computational feasibility in predicting the z-offsets; (ii) a CNN model to compute the z-offset as a function of the local, lower-dimensional feature data; and (iii) a radial basis function smoothing spline to ensure spatial continuity between the independently predicted z-offsets. The proposed CNN-based methodology is shown to improve on the accuracies obtained using existing ML models such as XGBoost and to provide a definitive way of quantifying model uncertainty associated with CNN predictions. To further investigate the applicability of ML models, multiple prediction strategies with which to deploy ML algorithms are proposed and the relative performance of ML algorithms corresponding to each prediction strategy are analyzed. The presented work thus provides a framework to find an encoded representation of 3D microstructure and micromechanical data and develop methods to predict microstructure-sensitive crack evolution based on this encoded representation, while quantifying associated prediction uncertainties.read more
Citations
More filters
Journal ArticleDOI
Artificial intelligence and machine learning in design of mechanical materials
TL;DR: The applications in mechanical property prediction, materials design and computational methods using ML-based approaches are summarized, followed by perspectives on opportunities and open challenges in this emerging and exciting field.
Journal ArticleDOI
Using Deep Learning to Predict Fracture Patterns in Crystalline Solids
TL;DR: In this article, a machine learning approach was proposed to predict fracture processes connecting molecular simulation into a physics-based data-driven multiscale model, based on atomistic modeling and a novel image-processing approach.
Journal ArticleDOI
Fatigue modeling using neural networks: A comprehensive review
TL;DR: A comprehensive review of fatigue modeling methods using neural networks is presented in this article . But, the review is limited to five applications: fatigue life prediction, fatigue crack, fatigue damage diagnosis, fatigue strength, and fatigue load.
Journal ArticleDOI
Data-Driven Enhancement of Fracture Paths in Random Composites
TL;DR: The proposed methodology enables the generation of new crack patterns, the underlying structure and dynamical properties of which are consistent, by construction, with those obtained from high-fidelity computations, and can be used to enrich datasets and perform uncertainty quantification at multiple scales, at a fraction of the computational cost associated with full-scale simulations.
Posted ContentDOI
A deep learning approach for complex microstructure inference.
Ali Riza Durmaz,Ali Riza Durmaz,Ali Riza Durmaz,Martin Müller,Bo Lei,Akhil Thomas,Akhil Thomas,Dominik Britz,Elizabeth A. Holm,Chris Eberl,Chris Eberl,Frank Mücklich,Peter Gumbsch,Peter Gumbsch +13 more
TL;DR: Concepts about required data amounts and interpretability are resolved to pave the way for DL's day-to-day application for microstructure quantification.
References
More filters
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Journal ArticleDOI
Greedy function approximation: A gradient boosting machine.
TL;DR: A general gradient descent boosting paradigm is developed for additive expansions based on any fitting criterion, and specific algorithms are presented for least-squares, least absolute deviation, and Huber-M loss functions for regression, and multiclass logistic likelihood for classification.
Journal ArticleDOI
Cumulative fatigue damage and life prediction theories: a survey of the state of the art for homogeneous materials
Ali Fatemi,Linsheng Yang +1 more
TL;DR: A comprehensive review of cumulative fatigue damage theories for metals and their alloys, emphasizing the approaches developed between the early 1970s to the early 1990s, can be found in this paper, where the authors grouped these theories into six categories: linear damage rules, nonlinear damage curve and two-stage linearization approaches; life curve modification methods; approaches based on crack growth concepts; continuum damage mechanics models; and energy-based theories.
Journal ArticleDOI
Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science
Ankit Agrawal,Alok Choudhary +1 more
TL;DR: In this article, the authors look at how data-driven techniques are playing a big role in deciphering processing-structure-property-performance relationships in materials, with illustrative examples of both forward models (property prediction) and inverse models (materials discovery).