Study of fatigue failure of construction steels by using modern methods of digital processing of microstructural images

Гончар, А. В.; Andreeva, Olga; Anosov, M. S.

doi:10.1016/j.matpr.2020.08.226

Cited by 4 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analysis of the obtained neural network classifier in the work's results suggests that the use of additional images can increase the classification accuracy by 8%. The results of the study [17,18] allow us to expect a similar effect (increasing the accuracy of the classifier), when the convolutional network with the similar structure is used and trained on a sample of images, supplemented with an autoencoder.…”

Section: Image Overlay Methodsmentioning

confidence: 87%

See 1 more Smart Citation

Using a Variational Autoencoder in the Task of Overlaying Multiple Images

Malyshev¹,

Андреев

Andreeva

et al. 2021

Proceedings of the 31th International Conference on Computer Graphics and Vision. Volume 2

View full text Add to dashboard Cite

The possibility and expediency of using variational autoencoders when expanding training datasets of neural networks for cases when the training set consists of several dozen samples is tested. Investigations are carried out on the example of images of «crack»-type defects. Brief information on the theory of variational autoencoders is given. Practical recommendations are given for constructing training sets of variational autoencoders. It is shown that deviation from the suggested recommendations will most likely not allow generating realistic images for the case of a small dataset. For the case of a dataset of eighty images, the distribution of «crack»- type defects in the hidden space after training the variational autoencoder is demonstrated. Examples of images with defects sampled from different parts of the distribution of latent factors are given. For the case of images of cracks, the continuity of the hidden space is demonstrated, when one image is sufficiently smoothly transformed into another on the way through the space of hidden features. A method for obtaining superimposed images based on the use of variational autoencoders is proposed. This method seems to be promising, since it allows automating the process of obtaining superimposed images. Examples of generated cracked superimposed images are shown.

show abstract

Section: Image Overlay Methodsmentioning

confidence: 87%

“…In [17], a similar problem was solved to quantify the accumulation of damage in metal structures during cyclic loading using a cellular automaton and a neural network that performs the classification task. Within the proposed procedure, images were generated by applying the developed rules of behavior of the cellular automaton.…”

Section: Image Overlay Methodsmentioning

confidence: 99%

Using a Variational Autoencoder in the Task of Overlaying Multiple Images

Malyshev¹,

Андреев

Andreeva

et al. 2021

Proceedings of the 31th International Conference on Computer Graphics and Vision. Volume 2

View full text Add to dashboard Cite

show abstract

“…For investigated steel, microstructure evolution due to low-cycle fatigue mainly consists in the appearance and subsequent growth of slip bands. The pretrained neural network 19,38 was used to obtain the data array containing information about the number, length, width, area, and orientation angle of the slip bands. The images sent to the input of the neural network were obtained using the algorithm of digital processing described below.…”

Section: Metallographic Studiesmentioning

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

Self Cite

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

WITHDRAWN: Unified LCF-HCF model for metals based on moving endurance surface, damage, and the Basquin-Manson-Coffin formulas

Holopainen,

Barriere

2023

International Journal of Fatigue

View full text Add to dashboard Cite

Study of fatigue failure of construction steels by using modern methods of digital processing of microstructural images

Cited by 4 publications

References 1 publication

Using a Variational Autoencoder in the Task of Overlaying Multiple Images

Using a Variational Autoencoder in the Task of Overlaying Multiple Images

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

WITHDRAWN: Unified LCF-HCF model for metals based on moving endurance surface, damage, and the Basquin-Manson-Coffin formulas

Contact Info

Product

Resources

About