Study of the fatigue behavior of composites using modular ANN with the incorporation of a posteriori failure probability

Diniz, Bruno da Cunha; Júnior, Raimundo Carlos Silvério Freire

doi:10.1016/j.ijfatigue.2019.105357

Cited by 17 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To that end, Equation 8 was applied (generalized power law), relating the mean stress values with their stress amplitude counterparts. This same methodology was used by Pestana et al, 11 Diniz et al, 19 and Barbosa et al 20

\log ((), σ_{a}) = A - B {[\log (N)]}^{C}

…”

Section: Ann Models Proposedmentioning

confidence: 99%

“…The multilayer perceptron (trained with the backpropagation algorithm 16 ) was used to develop the ANN 6 . This model, which has been applied successfully to resolve many engineering problems, 17–26 can simulate material/component behavior by means of ANN training. Its generalization provides results similar to those of the experimental data 27…”

Section: Ann Models Proposedmentioning

confidence: 99%

“…To obtain additional details on these fatigue tests and on the conductors specifications interested readers should refer to Fadel, 13 Pestana, 14 The multilayer perceptron (trained with the backpropagation algorithm 16 ) was used to develop the ANN. 6 This model, which has been applied successfully to resolve many engineering problems, [17][18][19][20][21][22][23][24][25][26] can simulate material/component behavior by means of ANN training.…”

Section: Available Datamentioning

confidence: 99%

See 2 more Smart Citations

Estimating fatigue behavior of a family of aluminum overhead conductors using ANNs

Cãmara

Badibanga

Ferreira

et al. 2021

Fatigue Fract Eng Mat Struct

Self Cite

View full text Add to dashboard Cite

This study aimed to create an artificial neural network (ANN) architecture capable of estimating the fatigue behavior of aluminum overhead conductors, considering specific weight (W) and bending stiffness (EI) as parameters of influence. ANN training and testing is conducted by using a dataset obtained from fatigue tests carried out in a 50 m resonant bench at the University of Brasilia (UnB). ANNs are used to construct constant life diagrams for this family of conductors, and to compare the results obtained experimentally. Our findings show that for the architectures analyzed, it is possible to accurately estimate the fatigue behavior of this family of aluminum conductors.

show abstract

\log ((), σ_{a}) = A - B {[\log (N)]}^{C}

…”

Section: Ann Models Proposedmentioning

confidence: 99%

Section: Ann Models Proposedmentioning

confidence: 99%

Section: Available Datamentioning

confidence: 99%

See 1 more Smart Citation

Estimating fatigue behavior of a family of aluminum overhead conductors using ANNs

Cãmara

Badibanga

Ferreira

et al. 2021

Fatigue Fract Eng Mat Struct

Self Cite

View full text Add to dashboard Cite

show abstract

“…Several models for fatigue life prediction of composite materials are proposed in literature [46][47][48][49][50]. The fatigue life model used in this study is the Epaarachchi model (Eq.…”

Section: Wöhler Curvesmentioning

confidence: 99%

Influence of moisture and drying on fatigue damage mechanisms in a woven hemp/epoxy composite: Acoustic emission and micro-CT analysis

Barbiere

Touchard

Chocinski–Arnault

et al. 2020

International Journal of Fatigue

View full text Add to dashboard Cite

For the last 20 years, plant fibres have emerged as an alternative to glass fibres in composites.However, a crucial issue with plant fibre composites is their durability, i.e. their long-term hygrothermal and fatigue performances. This study deals with the influence of different conditionings (Ambient, Wet and Wet/dry) on the fatigue behaviour of [(±45)] 7 hemp/epoxy composites. The induced damage mechanisms are investigated by acoustic emission and micro-CT. Results show that the Wet samples exhibit the lowest fatigue sensitivity despite their greatest damage quantity, whereas the Wet/dry specimens behave like pre-damaged Ambient ones.Micro-CT scans show that the same type of damage appears in all cases: cracks are made of a coalescence of partial debondings at hemp yarn/matrix interfaces, which can lead to macro-cracks crossing the sample thickness.Moreover it is demonstrated that, during fatigue tests, the evolution of cumulative AE energy and hysteresis loop energy, and the evolution of damage quantity measured by micro-CT and final hysteresis energy, are very similar whatever the conditioning.

show abstract

“…Training of an ANN is achieved by adjusting the interconnection weights until the prediction error is reduced to an acceptable level. ANNs have been successfully applied for evaluating the fatigue performance of composites, but mostly for stress-life curves (Diniz and Freire Júnior, 2020;El Kadi, 2006). Ref.…”

Section: Introductionmentioning

confidence: 99%

Embedding artificial neural networks into twin cohesive zone models for composites fatigue delamination prediction under various stress ratios and mode mixities

Zhang

2022

International Journal of Solids and Structures

View full text Add to dashboard Cite

Study of the fatigue behavior of composites using modular ANN with the incorporation of a posteriori failure probability

Cited by 17 publications

References 10 publications

Estimating fatigue behavior of a family of aluminum overhead conductors using ANNs

Estimating fatigue behavior of a family of aluminum overhead conductors using ANNs

Influence of moisture and drying on fatigue damage mechanisms in a woven hemp/epoxy composite: Acoustic emission and micro-CT analysis

Embedding artificial neural networks into twin cohesive zone models for composites fatigue delamination prediction under various stress ratios and mode mixities

Contact Info

Product

Resources

About