Machine learning-based accelerated property prediction of two-phase materials using microstructural descriptors and finite element analysis

Ford, Emily; Maneparambil, Kailasnath; Rajan, Subramaniam; Neithalath, Narayanan

doi:10.1016/j.commatsci.2021.110328

Cited by 61 publications

(24 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lookman et al [38] employ an active learning approach to navigate the search space for identifying the candidates for guiding experiments or computations. Ford et al [39] explore the use of supervised ML to predict the mechanical properties of a family of two-phase materials using their microstructural images. However, ML techniques heavily depend on feature engineering and require expert knowledge, which is time-consuming and limited to their applications.…”

Section: Data-driven Homogenization Approachmentioning

confidence: 99%

DH-Net: Deformed Microstructure Homogenization via 3D Convolutional Neural Networks

Peng¹,

Liu²,

Huang³

et al. 2022

Preprint

View full text Add to dashboard Cite

With the rapid development of additive manufacturing, microstructures are attracting both academic and industrial interests. As an efficient way of analyzing the mechanical behaviors of microstructures, the homogenization method has been well studied in the literature. However, the classic homogenization method still faces challenges. Its computational cost is high for topological optimization that requires highly repeated calculation. The computation is more expensive when the microstructure is deformed from a regular cubic, causing changes for the virtual homogeneous material properties. To conquer this problem, we introduce a fine-designed 3D convolutional neural network (CNN), named DH-Net, to predict the homogenized properties of deformed microstructures. The novelty of DH-Net is that it predicts the local displacement rather than the homogenized properties. The macroscopic strains are considered as a constant in the loss function based on minimum potential energy. Thus DH-Net is label-free and more computation efficient than existing deep learning methods with the mean square loss function. We apply the shape-material transformation that a deformed microstructure with isotropic material can be bi-transformed into a regular structure with a transformed base material, such that the input with a CNN-friendly form feeds in DH-Net. DH-Net predicts homogenized properties with hundreds of acceleration compared to the standard homogenization method and even supports online computing. Moreover, it does not require a labeled dataset

show abstract

Section: Data-driven Homogenization Approachmentioning

confidence: 99%

DH-Net: Deformed Microstructure Homogenization via 3D Convolutional Neural Networks

Peng¹,

Liu²,

Huang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, this approach is rather limited by the number of metrics at our disposal and, also, by the fact that different metrics apply in each case, depending on the microstructure. Two-point correlation functions, reduced via principal component analysis (PCA), have been shown to provide a useful representation of microstructure and can also be applied to predict elastic properties [7,8]. Prediction of elastic properties in the form of full stress-strain curves has also been shown to be possible, with the use of synthetic pole figures constructed from electron backscatter diffraction (EBSD) data as input [9].…”

Section: Introductionmentioning

confidence: 99%

Digital Fingerprinting of Microstructures

White¹,

Tarakanov²,

Race³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Great opportunities for automated quantifying microstructural changes are opening up with using fractal analysis, 7,[9][10][11][12][13][14][15][16] neural networks, 15,[17][18][19][20][21] and artificial intelligence. 15,18,21 Fractal theory is used to investigate the collective evolution of surface short cracks under fatigue. 7,10,13 Textural fractography has been developed for study of fracture micromorphology.…”

Section: Introductionmentioning

confidence: 99%

Fatigue life prediction of structural steel using acoustic birefringence and characteristics of persistent slip bands

Гончар

Kurashkin

Andreeva

et al. 2021

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

Nondestructive evaluation methods provide additional information about the material fatigue behavior and enhance the comprehension of damage evolution thanks to relationship between microstructure and physical properties. This paper deals with optical and ultrasonic investigations of structural steel specimens tested for low-cycle fatigue. The development of persistent slip bands observed on the surface with an optical microscope was quantified using a previously trained neural network and fractal analysis. A surface damage parameter was defined as the ratio of total area of detected slip bands to the area of observed surface. Relationships between the rate of change and critical value of the damage parameter, the strain range, and the fatigue life were established. A single square relationship between relative number of cycles and ratio of the surface damage parameter to its critical value was obtained.Acoustic birefringence was measured by the echo method. The effect of the strain range on the rate of change in acoustic birefringence was investigated. A single linear relationship between relative number of cycles and change in acoustic birefringence was established. An algorithm for predicting the material remaining life, combining optical and ultrasonic data, was proposed.

show abstract

Machine learning-based accelerated property prediction of two-phase materials using microstructural descriptors and finite element analysis

Cited by 61 publications

References 51 publications

DH-Net: Deformed Microstructure Homogenization via 3D Convolutional Neural Networks

DH-Net: Deformed Microstructure Homogenization via 3D Convolutional Neural Networks

Digital Fingerprinting of Microstructures

Fatigue life prediction of structural steel using acoustic birefringence and characteristics of persistent slip bands

Contact Info

Product

Resources

About