Predictions of the Total Crack Length in Solidification Cracking Through LSBoost

Zhang, Yun; Xu, Xiaojie

doi:10.1007/s11661-020-06130-3

Cited by 19 publications

(5 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In arc welding processes, studies have been made in the literature to prevent crack formation during solidification [50,51]. Factors affecting weld metal solidification cracking can be considered metallurgical and mechanical and often interact with each other, as mentioned before [52].…”

Section: Weld Metal Modification Approaches In Aluminum Arc Weldingmentioning

confidence: 99%

How to avoid solidification cracking in arc welding of aluminum alloys: a review on weld metal grain refinement approaches

Yolcu,

Kahraman

2023

Mater. Res. Express

View full text Add to dashboard Cite

Joining aluminum alloys with arc welding methods is frequently subject to literature and industrial applications. Although aluminum alloys have different difficulties in the arc welded process, the formation and elimination of solidification cracking defects is a more complex phenomenon. Since avoidance of this defect requires specific approaches and methods, special attempts and improvements have been studied frequently on this subject in recent years. Studies in the literature have clearly shown that this defect, which is often encountered in aluminum alloys, takes place along the grain boundaries. Therefore, the major approach to eliminate this defect is activating nucleation and decreasing the grain size. In this context, modification approaches in the literature, which are frequently used for arc welding of aluminum alloys, have been developed to use three different mechanisms including heterogeneous nucleation, dendrite fragmentation, and grain detachment. While it is aimed to increase heterogeneous nucleation by reinforcing filler metals with compounds in the inoculation approach; dendrite fragmentation and grain detachment are also aimed in the approaches where external effects and forces are used. Within the frame of references, it is also possible to review the external factors aiming to improve weld pool convection and thermal conditions under two headings, which are weld pool stirring and pulsed arc current approaches. The weld pool stirring approach also includes ultrasonic treatment and magnetic arc oscillation methods. In this study, solidification cracking defect that frequently occurs in the arc welding of aluminum alloys is explained fundamentally and the attempts to eliminate this defect are presented as a review paper in a comprehensive manner.

show abstract

Section: Weld Metal Modification Approaches In Aluminum Arc Weldingmentioning

confidence: 99%

How to avoid solidification cracking in arc welding of aluminum alloys: a review on weld metal grain refinement approaches

Yolcu,

Kahraman

2023

Mater. Res. Express

View full text Add to dashboard Cite

show abstract

“…where Y is the average value of Y, M is the number of samples in the dataset andŶ is the predicted value of Y. Further, to verify the stability of the MSR method, cross-validation of the linear regression [33,34] Compared with other verification methods, leave-one-out (LOO) is the most commonly used cross-validation method. A sample is taken from the data set and the remaining samples are used to build a model.…”

Section: Feature Selectionmentioning

confidence: 99%

Machine learning prediction of the optimal carrier concentration and band gap of quaternary thermoelectric materials via element feature descriptors

Wan

Wang

Liu

et al. 2021

Int J of Quantum Chemistry

View full text Add to dashboard Cite

While the thermoelectric (TE) materials have attracted significant attention in recent years, the design and discovery of new TE materials with optimal carrier concentration and band gap remains a great challenge. Herein, we report the development of machine learning (ML) methods to predict TE materials with introducing physically meaningful simple descriptors. Specifically, we use the number of electrons, Pauling electronegativity and relative atomic mass as the basic physical variables and compute 242 descriptors in 64 categories to characterize the molecular information of a TE material. Multiple stepwise regression is employed to reduce the dimensionality in the developed ML models, and 5 and 4 important features for the band gap and carrier concentration is selected, respectively. The important features are used as input of a total number of 19 ML methods to select the optimal ML models for the prediction of band gap and carrier concentration, respectively. It is shown that the least square support vector machines method is the best model for the prediction of the band gap, while the back propagating artificial neutral network model exhibits the best performance in predicting the carrier concentration values. This work provides novel theoretical guidance for the rapid prediction properties of TE materials. The simple descriptors we defined can accurately predict the band gap and carrier concentration of quaternary TE materials.

show abstract

“…The models generated show good agreement with the experimentally obtained crack lengths. [ 15 ] Such tools may be used in the future as a robust and inexpensive assistance in estimating the cracking susceptibility. Nevertheless, the testing of materials with regard to solidification cracking remains indispensable.…”

Section: Introductionmentioning

confidence: 99%

“…The models generated show good agreement with the experimentally obtained crack lengths. [15] Such tools may be used in the future DOI: 10.1002/adem.202101650 Various test methods are available for assessing the susceptibility of materials to solidification cracking during welding. In the widely used Varestraint test, the crack length is selected as a criterion as a function of the applied bending strain.…”

Section: Introductionmentioning

confidence: 99%

Assessment of the Solidification Cracking Susceptibility of Welding Consumables in the Varestraint Test by Means of an Extended Evaluation Methodology

et al. 2022

View full text Add to dashboard Cite

Various test methods are available for assessing the susceptibility of materials to solidification cracking during welding. In the widely used Varestraint test, the crack length is selected as a criterion as a function of the applied bending strain. Unfortunately, the crack length does not characterize the material behavior alone but depends to varying degrees on the individual test parameters used, which makes the interpretation of the results difficult. In addition, the crack length is not comparable under different test conditions. To overcome these disadvantages, we have developed a novel evaluation methodology that decouples the machine influence from the material behavior. The measured crack length is related to the maximum possible value specified by welding speed and deformation time. This relative crack length is calculated numerically, considering the orientation of the cracks. Experiments on two high‐alloy martensitic welding consumables show that, in contrast to the conventional evaluation, a comparison of different welding parameters becomes possible. Furthermore, the strain rate proved to be a suitable crack criterion in agreement with Prokhorov's hot cracking model.

show abstract

Predictions of the Total Crack Length in Solidification Cracking Through LSBoost

Cited by 19 publications

References 51 publications

How to avoid solidification cracking in arc welding of aluminum alloys: a review on weld metal grain refinement approaches

How to avoid solidification cracking in arc welding of aluminum alloys: a review on weld metal grain refinement approaches

Machine learning prediction of the optimal carrier concentration and band gap of quaternary thermoelectric materials via element feature descriptors

Assessment of the Solidification Cracking Susceptibility of Welding Consumables in the Varestraint Test by Means of an Extended Evaluation Methodology

Contact Info

Product

Resources

About