Language:

The prediction of part thickness using machine learning in aluminum hot stamping process with partition temperature control

International journal of advanced manufacturing technology, 2022-03, Vol.119 (5-6), p.3891-3902 [Peer Reviewed Journal]

The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 ;The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. ;ISSN: 0268-3768 ;EISSN: 1433-3015 ;DOI: 10.1007/s00170-021-08632-9

Full text available

Citations Cited by

Actions
1. Add to My Research
2. Remove from My Research
3. E-mail
4. Print
5. Permalink
6. Citation
7. EasyBib
8. EndNote
9. RefWorks
10. Delicious
11. Export RIS
12. Export BibTeX

Title:
The prediction of part thickness using machine learning in aluminum hot stamping process with partition temperature control
Author: Cai, Hanrong ; Xiao, Wenchao ; Zheng, Kailun
Subjects: Aluminum ; Blankholders ; CAE) and Design ; Complex systems ; Computer-Aided Engineering (CAD ; Engineering ; Finite element method ; Hot stamping ; Industrial and Production Engineering ; Machine learning ; Mechanical Engineering ; Media Management ; Original Article ; Process parameters ; Regression models ; Simulation ; Temperature ; Temperature control ; Thickening ; Thinning
Is Part Of: International journal of advanced manufacturing technology, 2022-03, Vol.119 (5-6), p.3891-3902
Description: Machine learning has successfully introduced a new method to predict forming quality in complex systems in the manufacturing industry. This paper studied machine learning methods in predicting the maximum thinning and thickening rates of hot-stamped parts. First, partition temperature control technique was introduced in the hot stamping process. The temperatures of the die, punch, and blank holder were controlled by twenty-two partitions, and each partition was set to an independent temperature. Then, a finite element model (FEM) was established to simulate the hot stamping of an aluminum box-shaped part. A total of 1600 sets of process parameters were generated, and they were automatically simulated in the FEM software with the help of python code. The results of the 1600 simulations were the maximum thinning rate and thickening rate of the part. Third, four machine learning models were established and trained. The models were tested with an independent testing data set, and their prediction accuracies were compared. The result showed that the gradient boosting regression model could accurately predict the maximum thinning and thickening rates.
Publisher: London: Springer London
Language: English
Identifier: ISSN: 0268-3768
EISSN: 1433-3015
DOI: 10.1007/s00170-021-08632-9
Source: ProQuest Central

Back to results list


INSPIRE LIBRARY - TON DUC THANG UNIVERSITY	(84-028) 37 755 057	Feedback
19 Nguyen Huu Tho St. Dist.7, HCM	thuvien@tdtu.edu.vn	Feedback

The prediction of part thickness using machine learning in aluminum hot stamping process with partition temperature control

The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022 ;The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2022. ;ISSN: 0268-3768 ;EISSN: 1433-3015 ;DOI: 10.1007/s00170-021-08632-9

Searching Remote Databases, Please Wait