Mechanical performance prediction for friction riveting joints of dissimilar materials via machine learning

Research output: Journal contributionsConference article in journalResearchpeer-review

Standard

Mechanical performance prediction for friction riveting joints of dissimilar materials via machine learning. / Bock, Frederic Eberhard; Blaga, Lucian Attila; Klusemann, Benjamin.
In: Procedia Manufacturing, Vol. 47, 05.2020, p. 615-622.

Research output: Journal contributionsConference article in journalResearchpeer-review

Harvard

APA

Vancouver

Bibtex

@article{40d22613864442f9a722d28f57a57f23,
title = "Mechanical performance prediction for friction riveting joints of dissimilar materials via machine learning",
abstract = "Solid-state joining techniques have become increasingly attractive for joining similar and dissimilar materials because it enables further optimization of lightweight components. In contrast to fusion-based joining processes, solid-state joining prevents the occurrence of typical defects such as pores or hot cracking. Machine learning algorithms are powerful tools to identify and quantify relationships between essential features along the process-property chain. In particular, different supervised machine learning algorithms can be used to perform regression analyses and establish correlations between process parameters as well as resulting properties. This can help to circumvent the demand for conducting a vast number of additional experiments to determine optimized process parameters for desired material properties. Additionally, this knowledge can be utilized to obtain a deeper understanding of the underlying mechanisms. In this study, a number of regression algorithms, such as support vector machines, decision trees, random forest and 2nd-order polynomial regression have been applied to correlate process parameters and materials properties for the solid-state joining process of force-controlled friction riveting. Experimental data generated via a central-composite Design of Experiments, serves as source of two separate data sets: one for training and one for testing the machine learning algorithms. The performances of the different algorithms are evaluated based on the determination coefficient R2 and the standard deviation of the predictions on the test data set. The trained algorithms with the best performance measures can be used as predictive models to forecast specific influences of process parameters on mechanical properties. Through the application of these models, optimized process parameters can be determined that lead to desired properties.",
keywords = "Engineering, Decision trees, Process parameters, Random forests, Solid state joining, Support vector machines, Ultimate tesnile force",
author = "Bock, {Frederic Eberhard} and Blaga, {Lucian Attila} and Benjamin Klusemann",
note = "The authors acknowledge funding from the Helmholtz-Association via an ERC-Recognition-Award (ERC-RA-0022).; 23rd International Conference on Material Forming - 2020, ESAFORM 2020 ; Conference date: 04-05-2020 Through 08-05-2020",
year = "2020",
month = may,
doi = "10.1016/j.promfg.2020.04.189",
language = "English",
volume = "47",
pages = "615--622",
journal = "Procedia Manufacturing",
issn = "2351-9789",
publisher = "Elsevier B.V.",
url = "https://esaform2020.org/",

}

RIS

TY - JOUR

T1 - Mechanical performance prediction for friction riveting joints of dissimilar materials via machine learning

AU - Bock, Frederic Eberhard

AU - Blaga, Lucian Attila

AU - Klusemann, Benjamin

N1 - Conference code: 23

PY - 2020/5

Y1 - 2020/5

N2 - Solid-state joining techniques have become increasingly attractive for joining similar and dissimilar materials because it enables further optimization of lightweight components. In contrast to fusion-based joining processes, solid-state joining prevents the occurrence of typical defects such as pores or hot cracking. Machine learning algorithms are powerful tools to identify and quantify relationships between essential features along the process-property chain. In particular, different supervised machine learning algorithms can be used to perform regression analyses and establish correlations between process parameters as well as resulting properties. This can help to circumvent the demand for conducting a vast number of additional experiments to determine optimized process parameters for desired material properties. Additionally, this knowledge can be utilized to obtain a deeper understanding of the underlying mechanisms. In this study, a number of regression algorithms, such as support vector machines, decision trees, random forest and 2nd-order polynomial regression have been applied to correlate process parameters and materials properties for the solid-state joining process of force-controlled friction riveting. Experimental data generated via a central-composite Design of Experiments, serves as source of two separate data sets: one for training and one for testing the machine learning algorithms. The performances of the different algorithms are evaluated based on the determination coefficient R2 and the standard deviation of the predictions on the test data set. The trained algorithms with the best performance measures can be used as predictive models to forecast specific influences of process parameters on mechanical properties. Through the application of these models, optimized process parameters can be determined that lead to desired properties.

AB - Solid-state joining techniques have become increasingly attractive for joining similar and dissimilar materials because it enables further optimization of lightweight components. In contrast to fusion-based joining processes, solid-state joining prevents the occurrence of typical defects such as pores or hot cracking. Machine learning algorithms are powerful tools to identify and quantify relationships between essential features along the process-property chain. In particular, different supervised machine learning algorithms can be used to perform regression analyses and establish correlations between process parameters as well as resulting properties. This can help to circumvent the demand for conducting a vast number of additional experiments to determine optimized process parameters for desired material properties. Additionally, this knowledge can be utilized to obtain a deeper understanding of the underlying mechanisms. In this study, a number of regression algorithms, such as support vector machines, decision trees, random forest and 2nd-order polynomial regression have been applied to correlate process parameters and materials properties for the solid-state joining process of force-controlled friction riveting. Experimental data generated via a central-composite Design of Experiments, serves as source of two separate data sets: one for training and one for testing the machine learning algorithms. The performances of the different algorithms are evaluated based on the determination coefficient R2 and the standard deviation of the predictions on the test data set. The trained algorithms with the best performance measures can be used as predictive models to forecast specific influences of process parameters on mechanical properties. Through the application of these models, optimized process parameters can be determined that lead to desired properties.

KW - Engineering

KW - Decision trees

KW - Process parameters

KW - Random forests

KW - Solid state joining

KW - Support vector machines

KW - Ultimate tesnile force

UR - http://www.scopus.com/inward/record.url?scp=85085520581&partnerID=8YFLogxK

U2 - 10.1016/j.promfg.2020.04.189

DO - 10.1016/j.promfg.2020.04.189

M3 - Conference article in journal

AN - SCOPUS:85085520581

VL - 47

SP - 615

EP - 622

JO - Procedia Manufacturing

JF - Procedia Manufacturing

SN - 2351-9789

T2 - 23rd International Conference on Material Forming - 2020

Y2 - 4 May 2020 through 8 May 2020

ER -

Documents

DOI