Gaussian process regression to predict the morphology of friction-stir-welded aluminum/copper lap joints

Krutzlinger, M.; Meltzer, E.; Muehlegg, M.; Zaeh, Michael F.

doi:10.1007/s00170-018-03229-1

Cited by 13 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GPR is a nonparametric ML model that entails the potential for directionality between the input and output variables and correlates random variables to their neighboring sets [17]. GPR is programmed with 42 experimental datasets by placing a function on each data point; this function is utilized thereafter to estimate the output vector via computing the mean and covariance of the data, as illustrated in figure 3(b).…”

Section: Machine Learning Modelling For Fswmentioning

confidence: 99%

Failure evaluation on tailor made aerospace aluminum alloys via underwater friction stir welding employing predictive machine learning technologies

2024

Eng. Res. Express

View full text Add to dashboard Cite

Employing tailor-made alloys with uneven thickness achieves light weighting, a critical issue for reducing emissions, leading to lower aircraft pollutants and fuel costs. The research utilizes advanced machine learning techniques such as Gaussian process regression (GPR), artificial neural networks (ANN) linear regression (LR), and support vector machines (SVM) to predict the ultimate tensile strength of underwater friction stir welding of AA6082-T6 and A2219-T83 tailor-made joints. The models have been evaluated with an assortment of kernel functions, including the polynomial kernel (PK), the radial basis function (RBF), and the Pearson VII universal kernel (PUK). To acquire experimental data, we used a Central Composite Design (CCD) technique, incorporating various factors in the process encompassing tool tilt angle (TA), rotating speed (RS), and welding speed (WS). The SVM radial basis function model (SRBP) had a maximum correlation coefficient of 0.9995 and a minimum root mean square error value (RMSE) of 0.5433 in the training set and 0.6271 in the test set. The ANN model predicted the UTS with an error margin of 0.21%, while the SRBP model showed a 0.52% error, and the LR model exhibited a significantly higher error of 7.73%. A peak tensile strength of 252.98 MPa was recorded in the S20 specimen, accounting for 85.61% of the base metal's (AA6082 T6) strength. A reduced acute tearing ridge indicates petite, shallow dimples due to the inherent cooling. Through the analysis of metrics and residuals, high accuracy rates were observed when employing the ANN and SRBP models to predict mechanical traits.

show abstract

Section: Machine Learning Modelling For Fswmentioning

confidence: 99%

Failure evaluation on tailor made aerospace aluminum alloys via underwater friction stir welding employing predictive machine learning technologies

2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…One of the most typical characteristics of GPR reflects on its precisely theoretical basis, which adds Gaussian prior the distribution to the non‐parametric regression function and deduces the posterior distribution of the unpredicted target. [ 55–57 ] Moreover, the excellent adaptability and strong generalization ability allow GPR to deal with complex issues of high dimension, small, and nonlinear data. Compared with ANN and SVM, GPR could achieve the aims of adaptive acquisition of super parameters, flexible inference of non‐parameters, and probabilistic output.…”

Section: Machine Learning Algorithms For Polymer Materialsmentioning

confidence: 99%

“…One of the most typical characteristics of GPR reflects on its precisely theoretical basis, which adds Gaussian prior the distribution to the non-parametric regression function and deduces the posterior distribution of the unpredicted target. [55][56][57] 3…”

Section: Machine Learning Algorithms For Polymer Materialsmentioning

confidence: 99%

New Opportunity: Machine Learning for Polymer Materials Design and Discovery

Chen

et al. 2022

Advcd Theory and Sims

View full text Add to dashboard Cite

Under the guidance of the material genome initiative (MGI), the use of data‐driven methods to discover new materials has become an innovation of materials science. The polymer materials have been one of the most important parts in materials science for the excellent physical and chemical properties as well as corresponding complex structures. Machine learning, as the core of data‐driven methods, has taken an important place in polymer materials design and discovery. In this review, the authors have introduced the applications of machine learning in the design and discovery of polymer materials. The development tendency of published papers about machine learning in polymer materials, the commonly used algorithms, the polymer descriptors, the workflow of machine learning in polymer materials, and recent progresses of machine learning in materials are summarized. Then, the detail of how to use machine learning to assist design and discovery of polymer materials is fully discussed combined with two cases. Finally, the opportunities and challenges on the future development prospects of machine learning in the field of polymer materials are proposed.

show abstract

“…The confirmatory test revealed perfect agreements amidst empirical and mathematics outcomes. As the morphology of the FSW for the Al sample is very ganglion, a regression was adopted to forecast the morphology of the interfacial area of the aluminum joint by Krutzlinger et al [21].…”

Section: Introductionmentioning

confidence: 99%

A comparative study of multiple-criteria decision-making methods for selecting the best process parameters for friction stir welded Al 6061 alloy

Sabry,

Mourad,

Alkhedher

et al. 2023

Welding International

View full text Add to dashboard Cite

The selection of welding process parameters is a difficult operation that proves the need for process evaluation. Several decision-making strategies have been presented for assessing friction stirring welding (FSW) process parameter selection difficulties considering the process up and down. It should be noted that few comparative studies have been conducted on the FSW problem without consideration of decision-making strategies. This article compares three multi-attribute decision-making strategies to select the parameters of the FSW process. The aim of this work applied different decision-making strategies TOPSIS, GRA, hybrid GRA-TOPSIS, COCOSO, and MACROS, using entropy for the calculated weight for all different decisionmaking. The proposed methods in this study are validated by representing the accurate decision maker's preferences and consideration of uncertainty. The decision-makers choose GRA-TOPSIS and TOPSIS as the best approach with higher efficiency. GRA was determined to be more time-consuming and to have the most variety of outcomes, whereas COCOSO and MACROS were unable to produce a definite best result.

show abstract

Gaussian process regression to predict the morphology of friction-stir-welded aluminum/copper lap joints

Cited by 13 publications

References 44 publications

Failure evaluation on tailor made aerospace aluminum alloys via underwater friction stir welding employing predictive machine learning technologies

Failure evaluation on tailor made aerospace aluminum alloys via underwater friction stir welding employing predictive machine learning technologies

New Opportunity: Machine Learning for Polymer Materials Design and Discovery

A comparative study of multiple-criteria decision-making methods for selecting the best process parameters for friction stir welded Al 6061 alloy

Contact Info

Product

Resources

About