Reduced-order modeling through machine learning and graph-theoretic approaches for brittle fracture applications

Hunter, Abigail; Moore, Bryan A.; Mudunuru, Maruti K.; Chau, Viet T.; Tchoua, Roselyne; Nyshadham, Chandramouli; Karra, Satish; O’Malley, Daniel; Rougier, Esteban; Viswanathan, Hari; Srinivasan, G.

doi:10.1016/j.commatsci.2018.10.036

Cited by 43 publications

(24 citation statements)

References 42 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extensions to higher-strain rates and other modes of failure will be considered in our future works. Lastly, our method can be coupled with other machine learning and graph-based methods [92][93][94][95] for increased accuracy of failure paths prediction, which is our future work.…”

Section: Discussionmentioning

confidence: 99%

Surrogate Models for Estimating Failure in Brittle and Quasi-Brittle Materials

et al. 2019

Self Cite

View full text Add to dashboard Cite

In brittle fracture applications, failure paths, regions where the failure occurs and damage statistics, are some of the key quantities of interest (QoI). High-fidelity models for brittle failure that accurately predict these QoI exist but are highly computationally intensive, making them infeasible to incorporate in upscaling and uncertainty quantification frameworks. The goal of this paper is to provide a fast heuristic to reasonably estimate quantities such as failure path and damage in the process of brittle failure. Towards this goal, we first present a method to predict failure paths under tensile loading conditions and low-strain rates. The method uses a k-nearest neighbors algorithm built on fracture process zone theory, and identifies the set of all possible pre-existing cracks that are likely to join early to form a large crack. The method then identifies zone of failure and failure paths using weighted graphs algorithms. We compare these failure paths to those computed with a high-fidelity fracture mechanics model called the Hybrid Optimization Software Simulation Suite (HOSS). A probabilistic evolution model for average damage in a system is also developed that is trained using 150 HOSS simulations and tested on 40 simulations. A non-parametric approach based on confidence intervals is used to determine the damage evolution over time along the dominant failure path. For upscaling, damage is the key QoI needed as an input by the continuum models. This needs to be informed accurately by the surrogate models for calculating effective moduli at continuum-scale. We show that for the proposed average damage evolution model, the prediction accuracy on the test data is more than 90%. In terms of the computational time, the proposed models are ≈ O ( 10 6 ) times faster compared to high-fidelity fracture simulations by HOSS. These aspects make the proposed surrogate model attractive for upscaling damage from micro-scale models to continuum models. We would like to emphasize that the surrogate models are not a replacement of physical understanding of fracture propagation. The proposed method in this paper is limited to tensile loading conditions at low-strain rates. This loading condition corresponds to a dominant fracture perpendicular to tensile direction. The proposed method is not applicable for in-plane shear, out-of-plane shear, and higher strain rate loading conditions.

show abstract

Section: Discussionmentioning

confidence: 99%

Surrogate Models for Estimating Failure in Brittle and Quasi-Brittle Materials

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Rovinelli et al 15 built a Bayesian Network (BN) to identify an analytical relationship between crack propagation and its driving force, which focuses on predicting the direction of crack propagation instead of the detailed crack path. Hunter et al 16 applied an Artificial Neural Network (ANN) to approximately learn the dominant trends and effects that can determine the overall material response. Moore et al 17 implemented a Random Forest (RF) and a Decision Tree (DT) to predict the dominant fracture path within the material.…”

Section: Introductionmentioning

confidence: 99%

“…Fernández-Godino et al 19 used an RNN to bridge meso and continuum scales for accelerating predictions in a high strain rate application problem. One common issue with previous works 10, [16][17][18][19] is that the models are built on manually selected features such as fracture length, orientation, distance between fractures, etc., instead of features learned from the raw data. Manually selected features could reduce the computation requirement, but it might cause information loss and degrade model performance.…”

Section: Introductionmentioning

confidence: 99%

StressNet - Deep learning to predict stress with fracture propagation in brittle materials

et al. 2021

Self Cite

View full text Add to dashboard Cite

Catastrophic failure in brittle materials is often due to the rapid growth and coalescence of cracks aided by high internal stresses. Hence, accurate prediction of maximum internal stress is critical to predicting time to failure and improving the fracture resistance and reliability of materials. Existing high-fidelity methods, such as the Finite-Discrete Element Model (FDEM), are limited by their high computational cost. Therefore, to reduce computational cost while preserving accuracy, a deep learning model, StressNet, is proposed to predict the entire sequence of maximum internal stress based on fracture propagation and the initial stress data. More specifically, the Temporal Independent Convolutional Neural Network (TI-CNN) is designed to capture the spatial features of fractures like fracture path and spall regions, and the Bidirectional Long Short-term Memory (Bi-LSTM) Network is adapted to capture the temporal features. By fusing these features, the evolution in time of the maximum internal stress can be accurately predicted. Moreover, an adaptive loss function is designed by dynamically integrating the Mean Squared Error (MSE) and the Mean Absolute Percentage Error (MAPE), to reflect the fluctuations in maximum internal stress. After training, the proposed model is able to compute accurate multi-step predictions of maximum internal stress in approximately 20 seconds, as compared to the FDEM run time of 4 h, with an average MAPE of 2% relative to test data.

show abstract

“…Another interesting application of ML is to obtain a data-driven representation of free-energy potentials in the atomic scale and upscale it to a phase-field model using integrable deep neural networks (Teichert et al, 2019). Specifically for brittle failure, ML has been recently used to build surrogate models based on explicit crack representation (Hunter et al, 2019) and in failure prediction using a discrete crack representation model for high-fidelity simulations that feed an artificial neural networks (ANN) algorithm (Moore et al, 2018;Schwarzer et al, 2019). Nonetheless, the noted studies have only shown the applicability of ML in failure analysis.…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Failure Prediction in Brittle Materials: A Phase Field-Based Machine Learning Framework

Moraes

Salehi

Zayernouri

2021

J Mach Learn Model Comput

View full text Add to dashboard Cite

Failure in brittle materials led by the evolution of micro-to macro-cracks under repetitive or increasing loads is often catastrophic with no significant plasticity to advert the onset of fracture. Early failure detection with respective location are utterly important features in any practical application, both of which can be effectively addressed using artificial intelligence. In this paper, we develop a supervised machine learning (ML) framework to predict failure in an isothermal, linear elastic and isotropic phase-field model for damage and fatigue of brittle materials. Time-series data of the phase-field model is extracted from virtual sensing nodes at different locations of the geometry. A pattern recognition scheme is introduced to represent time-series data/sensor node responses as a pattern with a corresponding label, integrated with ML algorithms, used for damage classification with identified patterns. We perform an uncertainty analysis by superposing random noise to the time-series data to assess the robustness of the framework with noise-polluted data. Results indicate that the proposed framework is capable of predicting failure with acceptable accuracy even in the presence of high noise levels. The findings demonstrate satisfactory performance of the supervised ML framework and the applicability of artificial intelligence and ML to a practical engineering problem, i.e., data-driven failure prediction in brittle materials.

show abstract

Reduced-order modeling through machine learning and graph-theoretic approaches for brittle fracture applications

Cited by 43 publications

References 42 publications

Surrogate Models for Estimating Failure in Brittle and Quasi-Brittle Materials

Surrogate Models for Estimating Failure in Brittle and Quasi-Brittle Materials

StressNet - Deep learning to predict stress with fracture propagation in brittle materials

Data-Driven Failure Prediction in Brittle Materials: A Phase Field-Based Machine Learning Framework

Contact Info

Product

Resources

About