Bee colony intelligence in fatigue life estimation of simulated magnesium alloy welds

Kalaycı, Can Berk; Karagöz, Sevcan; Karakaş, Özler

doi:10.1016/j.ijfatigue.2019.05.032

Cited by 20 publications

(10 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Swarm-based methodologies 103 have been designed by inspiring the social behaviours of ants, bees [104][105][106][107] or birds in their natural lives. They are algorithms based on swarm intelligence and collaboration.…”

Section: Swarm-based Algorithmsmentioning

confidence: 99%

Soft computing methods for fatigue life estimation: A review of the current state and future trends

Kalaycı

Karagöz

Karakaş

2020

Fatigue Fract Eng Mat Struct

Self Cite

View full text Add to dashboard Cite

Fatigue causes cracking or breakage in a material due to repeated loads; it causes the material to become unusable. Therefore, knowing the fatigue life of materials is crucial for the implementation of designs, economy and human life. Soft computing methodologies, a subset of artificial intelligence emerging to simulate human intelligence, deal with approximate models and seek solutions to complex real-life problems relying on both computational power of machines and the high accuracy of the algorithms. In this study, soft computing methods adapted for estimating/predicting the fatigue life of engineering structures and materials are investigated. For this purpose, 95 articles published between 1995 and 2020 have been examined in detail. With this review, it is aimed to reveal the efficiency of soft computing methods and contribute to their development. Recommendations have been made to draw attention to these methodologies which are expected to be used in many areas in the future.

show abstract

Section: Swarm-based Algorithmsmentioning

confidence: 99%

Soft computing methods for fatigue life estimation: A review of the current state and future trends

Kalaycı

Karagöz

Karakaş

2020

Fatigue Fract Eng Mat Struct

Self Cite

View full text Add to dashboard Cite

show abstract

“…Considering the time and cost issues, computational methods can be used to obtain results faster, cheaper, and more accurate than the traditional equations such as Mitchell, universal slope, modified universal slope, modified four-point correlation, uniform material law, and Roessle and Fatemi hardness. Kalayci et al 15,16 estimated the fatigue life of magnesium alloy welds with ABC intelligence and investigated soft computing methods for fatigue life estimation. Their study showed that the most commonly used algorithm for fatigue life estimation is predominantly ANN.…”

Section: Introductionmentioning

confidence: 99%

Low‐cycle fatigue parameters and fatigue life estimation of high‐strength steels with artificial neural networks

Soyer

Kalaycı

Karakaş

2022

Fatigue Fract Eng Mat Struct

Self Cite

View full text Add to dashboard Cite

Fatigue life estimation is essential for life safety and cost reasons. Fatigue parameters at low cycles must be estimated with high accuracy to correctly estimate fatigue life. Conventional equations for parameters at low cycles are inadequate and unable to calculate the values correctly. Artificial neural networks (ANNs) are used to estimate and optimize the parameters and are more accurate than traditional equations. This study aims to estimate the fatigue parameters at low cycles and fatigue life by ANN with basic tensile properties of high-strength steels (HSSs), which can be easily obtained from the literature. In particular, the fatigue strength exponent and fatigue ductility exponent primarily characterize the strain-life curve, and the estimation of these parameters is extremely important. To improve the accuracy of the estimation, activation functions, epoch numbers, training functions, elapsed times of training functions, and the number of hidden neurons is compared and determined.

show abstract

“…The mechanical properties of the shaft coupling material are listed in Table I. In order to obtain data on the stress state data of the shaft coupling as a fuse, analytical and numerical calculations of the shear stress in characteristic cross-sections were carried out [7]. The matching of analytical and numerical calculations confirmed the suitability of the numerical model of the initial (existing) shaft coupling.…”

Section: Boundary Conditionsmentioning

confidence: 90%

Design and Simulation of the Controlled Failure of Custom-Built Rigid Shaft Coupling

Rasovic¹,

Cekic²,

Kaljun³

2022

Int. j. simul. model.

View full text Add to dashboard Cite

In this paper, the use of conventional analytical calculating methods for designing the mechanical part with predicted endurance time is investigated. In a case study a design and dimensioning of custombuilt shaft coupling with torque limiting function was conducted. Necessary analytical calculations were carried out to determine the possible weak points of the current shaft coupling design. Numerical analyses of the newly designed shaft coupling were performed using predefined material properties and boundary conditions. Using Goodman criteria, the most suitable design was selected. Prototypes of shaft couplings with different designs based on the numerical analysis were tested to validate the numerical results. Analytical approach as well as numerical analysis were compared. The validation of the produced machine part is also performed. Results of the research work showed that conventional analytical methods can be applied to design and dimension a mechanical part with predicted failure following steps (methodology) described in the paper.

show abstract

Bee colony intelligence in fatigue life estimation of simulated magnesium alloy welds

Cited by 20 publications

References 38 publications

Soft computing methods for fatigue life estimation: A review of the current state and future trends

Soft computing methods for fatigue life estimation: A review of the current state and future trends

Low‐cycle fatigue parameters and fatigue life estimation of high‐strength steels with artificial neural networks

Design and Simulation of the Controlled Failure of Custom-Built Rigid Shaft Coupling

Contact Info

Product

Resources

About