Fatigue life prediction of glass fiber reinforced epoxy composites using artificial neural networks

C, Hemanth Kumar; Swamy, R. P.

doi:10.1016/j.coco.2021.100812

Cited by 29 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, machine learning (ML) based big data driven methods have played an important role in developing a predictive capability for material properties and lightweight design based on extensive experimental evidence [20][21][22][23] . Indeed, support vector machine (SVM), Random-Forest (RF), Gaussian process regression (GPR), shallow neural network (SNN), deep neural network (DNN), Linear regression (LR), and artificial neural networks (ANN) have all been found to make accurate life and crack propagation predictions, based on fatigue-related data for conventionally processed metals and alloys [24][25][26][27][28][29][30][31][32] . Regarding AM metals, a variety of ML methods have been employed to predict the mechanical properties, to optimise the AM processing as well as for the online defect detection, as briefly summarized in Table 1.…”

Section: Introductionmentioning

confidence: 99%

The potency of defects on fatigue of additively manufactured metals

Peng

Qian

et al. 2022

International Journal of Mechanical Sciences

115

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

The potency of defects on fatigue of additively manufactured metals

Peng

Qian

et al. 2022

International Journal of Mechanical Sciences

115

View full text Add to dashboard Cite

“…A significant group of published papers currently concerns the fatigue of additive manufactured parts 25–27 . ML methods are also often used to predict the fatigue life of non‐metallic materials 28–30 . Sometimes ML methods are used to predict the fatigue life of machines 31–33 .…”

Section: Introductionmentioning

confidence: 99%

Application of machine learning methods in multiaxial fatigue life prediction

Pałczyński

Skibicki

Pejkowski

et al. 2022

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

This paper compares the results of multiaxial fatigue life estimation using machine learning methods and classical fatigue models. The fatigue life of PA38-T6 aluminum alloy under uniaxial, proportional, and non-proportional loading, including asynchronous loading, is studied. Machine learning methods are trained only on basic loadings, namely, axial, torsional, and 90 out-of-phase. The results obtained with the machine learning algorithms, dense neural networks, support vector regression (with linear and radial basis functions), decision tree, random forest, and XGBoost algorithms, are comparable to the results of classical models like Ellyin-Goło s, Fatemi-Socie, and Ince-Glinka. The best results are achieved for dense neural networks. In that case, they are often slightly more accurate than those obtained using classical methods.

show abstract

“…In the traditional fatigue test, the test specimen is subjected to cyclic loading until the material fails. Based on the experimental test results, a S – N curve can be made, in which N and S represent the number of fatigue load tests and the material failure stress, respectively. − However, the S – N curve does not contain information on the microstructural changes during fatigue, for example, the relationship between the microstructural changes of the material and the number of cycles from the beginning to failure . Another test method put forward was the mechanical loss method, which can obtain more information about the evolution of the material structure .…”

Section: Introductionmentioning

confidence: 99%

Fatigue Characteristics of Poly(ether-b-amide) Elastomers during Cyclic Dynamic Tests and the Underlying Microstructural Evolution

Zhu

Brückner

Neumeyer

et al. 2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The dynamic fatigue behavior of the poly(ether-b-amide) (PEBA) elastomers was characterized by a combination of step increase load test (SILT), step increase strain test (SIST), and single load dynamic creep (SLDC). PEBA had crystalline hard segments of polyamide 12 (PA12) and soft segments of poly(tetramethylene oxide) (PTMO). The crystalline morphologies before and after the tests were studied by ex situ wide-angle X-ray diffraction (WAXD) and small-angle X-ray scattering (SAXS). Fast stress relaxation can be seen under the applied strain well below than the elongation at break. Remarkable dynamic creep can be observed under the applied load triggering yielding of the specimen, which is substantially less than the ultimate tensile strength. Although the presence of high content of amorphous PTMO renders high entropic elasticity, the disintegration of the crystalline hard domains of PA12 is expected to determine the relaxation rate, creep rate, and modulus, as strain-induced crystallization in soft domains did not occur and no trace was found by WAXD. SAXS patterns showed that the orientation of the PA12 lamellae at lower stresses or strains can largely be restored. However, the fractured and highly aligned PA12 lamellae resulted in classic four-point or two-lobe SAXS patterns, which implied the underlying microstructural changes after the cyclic dynamic tests.

show abstract

Fatigue life prediction of glass fiber reinforced epoxy composites using artificial neural networks

Cited by 29 publications

References 13 publications

The potency of defects on fatigue of additively manufactured metals

The potency of defects on fatigue of additively manufactured metals

Application of machine learning methods in multiaxial fatigue life prediction

Fatigue Characteristics of Poly(ether-b-amide) Elastomers during Cyclic Dynamic Tests and the Underlying Microstructural Evolution

Contact Info

Product

Resources

About