Modelling fatigue delamination growth in fibre-reinforced composites: Power-law equations or artificial neural networks?

Allegri, Giuliano

doi:10.1016/j.matdes.2018.05.049

Cited by 31 publications

(16 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Allegri, 137 the extreme learning machine is used to incorporate features of physical behaviors in the training procedure. The physics knowledge is monotonic or semimonotonic constraints.…”

Section: Discussionmentioning

confidence: 99%

“…Other NNs are also applied in the literature to model the fatigue crack growth rate. For example, Allegri 137 used extreme learning to study the effect of mode mixity and stress ratios. In addition, RBFNNs are applied by Zhang et al, 15 considering stress ratio and overload effect, and by Mortazavi and Ince 138,139 for both the short and long cracks.…”

Section: Review Of Nn Applications In Fatiguementioning

confidence: 99%

See 1 more Smart Citation

Fatigue modeling using neural networks: A comprehensive review

Chen

Liu

2022

Fatigue Fract Eng Mat Struct

125

View full text Add to dashboard Cite

Neural network (NN) models have significantly impacted fatigue‐related engineering communities and are expected to increase rapidly due to the recent advancements in machine learning and artificial intelligence. A comprehensive review of fatigue modeling methods using NNs is lacking and will help to recognize past achievements and suggest future research directions. Thus, this paper presents a survey of 251 publications between 1990 and July 2021. The NN modeling in fatigue is classified into five applications: fatigue life prediction, fatigue crack, fatigue damage diagnosis, fatigue strength, and fatigue load. A wide range of NN architectures are employed in the literature and are summarized in this review. An overview of important considerations and current limitations for the application of NNs in fatigue is provided. Statistical analysis for the past and the current trend is provided with representative examples. Existing gaps and future research directions are also presented based on the reviewed articles.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Review Of Nn Applications In Fatiguementioning

confidence: 99%

Fatigue modeling using neural networks: A comprehensive review

Chen

Liu

2022

Fatigue Fract Eng Mat Struct

125

View full text Add to dashboard Cite

show abstract

“…Soft computing techniques including artificial neural networks (ANN) and machine learning offer new prospects to predict the mechanical behavior of thermoplastic commingled composites. Recent studies [15][16][17][18][19][20][21][22] have been used to predict the mechanical behavior of structural composite materials by computational modeling [23].…”

Section: Statistic Modeling and Soft Computing Techniquesmentioning

confidence: 99%

New Advances in Thermoplastic Commingled Composites: Processing and Molecular Dynamics

Benedetto¹,

Janotti²,

Gomes³

et al. 2022

Fundamental Concepts and Models for the Direct Problem

View full text Add to dashboard Cite

This chapter addresses a current and innovative topic related to thermoplastic commingled composites. Computational molecular dynamics simulations represent a very sophisticated technique for characterizing microstructures, but it is still not widely explored in the area of high-performance thermoplastic polymers. The molecular dynamics technique evaluates the movements of atoms as a function of time and temperature, according to external demands and boundary conditions of the molecular system. Based on thermodynamics, atomistic and classical mechanics theories, molecular dynamics simulations with empirical potentials aim at (i) the development of new polymeric materials, (ii) the optimization of polymer properties, and (iii) the characterization of these materials. The molecular dynamics technique provides a prediction of mechanical and thermal behavior of high-performance polymeric microstructures, reducing the number of tests and experimental practices, whichincreases the operational cost of engineering projects and the characterization of structural composite materials. Furthermore, this chapter also includes a scientific and technological literature background to demonstrate and highlight the conjuncture between thermal processing parameters, thermal degradation kinetics, processing optimization, thermal and mechanical characterization techniques. It also includes literature and experimental background based on previous studies.

show abstract

“…A FEM model was developed addressing intra-laminar damage and inter-laminar delamination, to estimate lowvelocity impact (LVI) and compression-after-impact responses of CFRCs which trained an ANN model. Two alternative modelling approaches for describing fatigue delamination growth in polymer-based fiberreinforced composites are discussed in [11]. In this study, single hidden layer ANN with the support of self-similarity principles are proposed as an alternative to semi-empirical power laws.…”

Section: Introductionmentioning

confidence: 99%