Machine learning and predicting the time-dependent dynamics of local yielding in dry foams

Viitanen, Leevi; Intyre, Jonatan R. Mac; Koivisto, Juha; Puisto, Antti; Alava, Mikko J.

doi:10.1103/physrevresearch.2.023338

Cited by 10 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A static value of −1 was used in the place of the fourth feature column values, representing the fourth film for each 3-fold feature. The model achieved a training score of 1.0 and a test score of 0.997, similar to the results where T1 events were predicted from images [24]. This high degree of predictability was achieved with only small training and test sets containing 500 and 350 samples, respectively.…”

Section: A Evaluating Single Featuressupporting

confidence: 79%

“…The same data set has been analyzed previously in Ref. [24] using a convolutional neural network, where we also report the detailed experimental setup. Briefly, the foam enters the cell from an inlet located at the center of the cell and expands toward the edges.…”

Section: A Experimental Proceduresmentioning

confidence: 99%

“…The present paper builds off our earlier work in Ref. [24], where we identified vertices and bubbles about to yield in T1 events in flowing 2D foam using convolutional neural networks (CNNs) [24]. Although this technique successfully focused on unstable states [Fig.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predicting and following T1 events in dry foams from geometric features

Tainio

Viitanen

Intyre

et al. 2021

Phys. Rev. Materials

Self Cite

View full text Add to dashboard Cite

Machine learning techniques have been recently applied in predicting deformation in amorphous materials. In this study, we extract structural features around liquid film vertices from images of flowing 2D foam and apply a multilayer perceptron to predict local yielding. We evaluate their importance in the description of the T1 events and show that a high level of predictability may be achieved using well-chosen combinations of features as the prediction data. The most relevant features are extracted by performing the predictions separately for isolated sets of features, and these findings are verified using principal component analysis. Using this approach, we determine which properties of the images are most important with regard to the physics of the processes. Our findings indicate that film lengths and angles between the liquid films joining at the vertex are the most important features that predict the local yield events. These two features describe 83% of the yield events. As an application, we extract the statistics of event waiting times from the experiment.

show abstract

Section: A Evaluating Single Featuressupporting

confidence: 79%

Section: A Experimental Proceduresmentioning

confidence: 99%

See 1 more Smart Citation

Predicting and following T1 events in dry foams from geometric features

Tainio

Viitanen

Intyre

et al. 2021

Phys. Rev. Materials

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent years have witnessed a surge in application of artificial intelligence (AI) in general and machine learning (ML) in particular to gain novel insights on properties of materials and related problems in physics [9][10][11][12][13][14][15][16][17][18][19]. Broadly speaking, such developments fall under the umbrella of the emerging research field of materials informatics [20], where informatics methods -including ML -are used to search for novel materials [21,22], establish novel structure-property relations [13,23], etc.…”

Section: Introductionmentioning

confidence: 99%

Machine learning reveals strain-rate-dependent predictability of discrete dislocation plasticity

Mińkowski,

Kurunczi-Papp,

Laurson

2021

Preprint

View full text Add to dashboard Cite

Predicting the behaviour of complex systems is one of the main goals of science. An important example is plastic deformation of micron-scale crystals, a process mediated by collective dynamics of dislocations, manifested as broadly distributed strain bursts and significant sample-to-sample variations in the response to applied loading. Here, by combining large-scale discrete dislocation dynamics simulations and machine learning, we study the problem of predicting the fluctuating stress-strain curves of individual small single crystals subject to strain-controlled loading using features of the initial dislocation configurations as input. Our results reveal an intriguing rate dependence of deformation predictability: For small strains predictability improves with increasing strain rate, while for larger strains the predictability vs strain rate relation becomes non-monotonic. We show that for small strains the rate-dependence of deformation predictability can be captured by considering the fraction of dislocations moving against the direction imposed by the external stress, serving as a measure of strain-rate-dependent complexity of the dislocation dynamics. The non-monotonic predictability vs strain rate relation for large strains is argued to be related to a transition from fluctuating to smooth plastic flow when strain rate is increased.

show abstract

“…The local yielding of amorphous materials, specifically foams, its observation and manipulation are hot topics involving basic science [1][2][3][4][5][6] and heavy industry. [7][8][9] Foams can be used to study the yielding of soft matter 10 and flow in complex geometries [11][12][13][14] as well as hidden correlations via hyperuniformity, a concept that reveals systems without long-range number density fluctuations from random (poissonian) ones.…”

Section: Introductionmentioning

confidence: 99%