Evaluation of mechanical property predictions of refill Friction Stir Spot Welding joints via machine learning regression analyses on DoE data
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Standard
ESAFORM 2021: 24th International Conference on Material Forming. Liège: ULiège Library, 2021. 2589 (ESAFORM 2021 - 24th International Conference on Material Forming).
Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - CHAP
T1 - Evaluation of mechanical property predictions of refill Friction Stir Spot Welding joints via machine learning regression analyses on DoE data
AU - Bock, Frederic Eberhard
AU - Paulsen, Tino
AU - Brkovic, Nikola
AU - Rieckmann, Lennart
AU - Kroeger, Dennis
AU - Wolgast, Dominik
AU - Zander, Philip
AU - Suhuddin, Uceu F. H.
AU - dos Santos, Jorge Fernandez
AU - Klusemann, Benjamin
N1 - Conference code: 24
PY - 2021/4/2
Y1 - 2021/4/2
N2 - The high-potential of lightweight components consisting of similar or dissimilar materials can be exploited by Solid-State Joining techniques. Whereas defects such as pores and hot cracking are often an issue in fusion-based joining processes, via solid-state joining processes they can be avoided to enable high-quality welds. To define an optimal process window for obtaining anticipated joint properties, numerous time and cost consuming experiments are usually required. Building a predictive model based on regression analysis enables the identification and quantification of process-property relationships. On the one hand, mechanical property and performance predictions based on specific process parameters are needed, on the other hand, inverse determination of required process parameters for reaching desired properties or performances are demanded. If these relations are obtained, optimized process parameter sets can be identified while vast numbers of required experiments can be reduced, as underlying physical mechanisms are utilized. In this study, different regression analysis algorithms, such as linear regression, decision trees and random forests, are applied to the refill Friction Stir Spot Welding process for establishing correlations between process parameters and joint properties. Experimental data sets used for training and testing are based on a Box-Behnken Design of Experiments (DoE) and additional test experiments, respectively. The machine-learning based regression analyses are benchmarked against linear regression and DoE statistics. The results illustrate a decryption of relationships along the process-property chain and its deployment to predict mechanical properties governed by process parameters.
AB - The high-potential of lightweight components consisting of similar or dissimilar materials can be exploited by Solid-State Joining techniques. Whereas defects such as pores and hot cracking are often an issue in fusion-based joining processes, via solid-state joining processes they can be avoided to enable high-quality welds. To define an optimal process window for obtaining anticipated joint properties, numerous time and cost consuming experiments are usually required. Building a predictive model based on regression analysis enables the identification and quantification of process-property relationships. On the one hand, mechanical property and performance predictions based on specific process parameters are needed, on the other hand, inverse determination of required process parameters for reaching desired properties or performances are demanded. If these relations are obtained, optimized process parameter sets can be identified while vast numbers of required experiments can be reduced, as underlying physical mechanisms are utilized. In this study, different regression analysis algorithms, such as linear regression, decision trees and random forests, are applied to the refill Friction Stir Spot Welding process for establishing correlations between process parameters and joint properties. Experimental data sets used for training and testing are based on a Box-Behnken Design of Experiments (DoE) and additional test experiments, respectively. The machine-learning based regression analyses are benchmarked against linear regression and DoE statistics. The results illustrate a decryption of relationships along the process-property chain and its deployment to predict mechanical properties governed by process parameters.
KW - Engineering
KW - Solid-state joining
KW - Refill FSSW
KW - Linear regression
KW - Decision Tree Regression
KW - Random Forest Regression
KW - SHAP Value
KW - Explainable Machine Learning
UR - http://www.scopus.com/inward/record.url?scp=85119338928&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/d7b822c9-0728-3378-b54f-d7fd4e4f7e41/
U2 - 10.25518/esaform21.2589
DO - 10.25518/esaform21.2589
M3 - Article in conference proceedings
SN - 978-2-87019-302-0
T3 - ESAFORM 2021 - 24th International Conference on Material Forming
BT - ESAFORM 2021
PB - ULiège Library
CY - Liège
T2 - 24th International Conference on Material Forming - ESAFORM 2021
Y2 - 14 April 2021 through 16 April 2021
ER -