Self-piercing riveting (SPR) has been widely used in automobile industry, and the strength prediction of SPR joints always attracts the attention of researchers. In this work, a prediction method of the cross-tension strength of SPR joints was proposed on the basis of finite element (FE) simulation and extreme gradient boosting decision tree (XGBoost) algorithm. An FE model of SPR process was established to simulate the plastic deformations of rivet and substrate materials and verified in terms of cross-sectional dimensions of SPR joints. The residual mechanical field from SPR process simulation was imported into a 2D FE model for the cross-tension testing simulation of SPR joints, and cross-tension strengths from FE simulation show a good consistence with the experiment result. Based on the verified FE model, the mechanical properties and thickness of substrate materials were varied and then used for FE simulation to obtain cross-tension strengths of a number of SPR joints, which were used to train the regression model based on the XGBoost algorithm in order to achieve prediction for cross-tension strength of SPR joints. Results show that the cross-tension strengths of SPR steel/aluminum joints could be successfully predicted by the XGBoost regression model with a respective error less than 7.6% compared to experimental values.
Jianping Lin
,
Chengwei Qi
,
Hailang Wan
,
Junying Min
,
Jiajie Chen
,
Kai Zhang
,
Li Zhang
. Prediction of Cross-Tension Strength of Self-Piercing Riveted Joints Using Finite Element Simulation and XGBoost Algorithm[J]. Chinese Journal of Mechanical Engineering, 2021
, 34(2)
: 36
-36
.
DOI: 10.1186/s10033-021-00551-w
Self-piercing riveting (SPR) has been widely used in automobile industry, and the strength prediction of SPR joints always attracts the attention of researchers. In this work, a prediction method of the cross-tension strength of SPR joints was proposed on the basis of finite element (FE) simulation and extreme gradient boosting decision tree (XGBoost) algorithm. An FE model of SPR process was established to simulate the plastic deformations of rivet and substrate materials and verified in terms of cross-sectional dimensions of SPR joints. The residual mechanical field from SPR process simulation was imported into a 2D FE model for the cross-tension testing simulation of SPR joints, and cross-tension strengths from FE simulation show a good consistence with the experiment result. Based on the verified FE model, the mechanical properties and thickness of substrate materials were varied and then used for FE simulation to obtain cross-tension strengths of a number of SPR joints, which were used to train the regression model based on the XGBoost algorithm in order to achieve prediction for cross-tension strength of SPR joints. Results show that the cross-tension strengths of SPR steel/aluminum joints could be successfully predicted by the XGBoost regression model with a respective error less than 7.6% compared to experimental values.
[1] J Min, K Zhang, S Wang, et al. Effects of rivet structure on penetration force in friction stir blind riveting of aluminum alloy sheets. Journal of Mechanical Engineering, 2020, 56(6): 159-168. (in Chinese)
[2] L Liu, Qin Yu, Z Wang, et al. Making ultrastrong steel tough by grain-boundary delamination. Science, 2020: eaba9413.
[3] Y Hou, J Min, N Gu, et al. Investigation of evolving yield surfaces of dual-phase steels. Journal of Material Processing Technology, 2019.
[4] J Lin, Y Hou, J Min, et al. Effect of constitutive model on springback prediction of MP980 and AA6022-T4. International Journal of Material Forming, 2019, 13: 1-13.
[5] K Mori, T Kato, Y Abe, et al. Plastic joining of ultra high strength steel and aluminium alloy sheets by self piercing rivet. CIRP Annals, 2006, 55(1): 283-286.
[6] K Martinsen, S J Hu, B E Carlson. Joining of dissimilar materials. CIRP Annals, 2015, 64(2): 679-699.
[7] G Michalos, S Makris, N Papakostas, et al. Automotive assembly technologies review: challenges and outlook for a flexible and adaptive approach. CIRP Journal of Manufacturing Science and Technology, 2010, 2(2): 81-91.
[8] H Jiang, C Zeng, G Li, et al. Effect of locking mode on mechanical properties and failure behavior of CFRP/Al electromagnetic riveted joint. Composite Structures, 2020: 113162.
[9] H Jiang, Y Cong, J Zhang, et al. Fatigue response of electromagnetic riveted joints with different rivet dies subjected to pull-out loading. International Journal of Fatigue, 2019, 129: 105238.1-105238.13.
[10] R Haque, Y Durandet. Strength prediction of self-pierce riveted joint in cross-tension and lap-shear. Materials & Design, 2016, 108: 666-678.
[11] Z Xie, W Yan, C Yu, et al. Tensile capacity of self-piercing rivet connections in thin-walled steel structures. Journal of Constructional Steel Research, 2018, 144: 211-220.
[12] W Yan, Z Xie, C Yu, et al. Experimental investigation and design method for the shear strength of self-piercing rivet connections in thin-walled steel structures. Journal of Constructional Steel Research, 2017, 133: 231-240.
[13] Y Ma, M Lou, Y Li, et al. Effect of rivet and die on self-piercing rivetability of AA6061-T6 and mild steel CR4 of different gauges. Journal of Materials Processing Technology, 2018, 251: 282-294.
[14] C Westerberg. Finite element simulation OF crash testing of self-piercing rivet joints, peel specimen. Lund University, 2006.
[15] R Porcaro, A G Hanssen, M Langseth, et al. The behavior of a self-piercing riveted connection under quasi-static loading conditions. International Journal of Solids and Structures, 2006, 43(17): 5110-5131.
[16] P O Bouchard, T Laurent, L Tollier. Numerical modeling of self-pierce riveting—From riveting process modeling down to structural analysis. Journal of Materials Processing Technology, 2008, 202(1-3): 290-300.
[17] J F C Moraes, J B Jordon, X Su, et al. Effect of process deformation history on mechanical performance of AM60B to AA6082 self-pierce riveted joints. Engineering Fracture Mechanics, 2019, 209: 92-104.
[18] H Chen, J Shen, W Chen, et al. Grinding chatter detection and identification based on BEMD and LSSVM. Chin. J. Mech. Eng. , 2019, 32: 1.
[19] S Shao, W Sun, R Yan, et al. A deep learning approach for fault diagnosis of induction motors in manufacturing. Chinese Journal of Mechanical Engineering, 2017, 30: 1347-1356.
[20] M Fujishima, K Narimatsu, N Irino, et al. Adaptive thermal displacement compensation method based on deep learning. CIRP Journal of Manufacturing Science and Technology, 2019, 25: 22-25.
[21] M Postel, B Bugdayci, F Kuster, et al. Neural network supported inverse parameter identification for stability predictions in milling. CIRP Journal of Manufacturing Science and Technology, 2020.
[22] G Yavuz, M H Arslan, O K Baykan, et al. Shear strength predicting of FRP-strengthened RC beams by using artificial neural networks. Science and Engineering of Composite Materials, 2014, 21(2): 239-255.
[23] X Qin, S Cui, L Liu, et al. Prediction of mechanical strength based on deep learning using the scanning electron image of microscopic cemented paste backfill. Advances in Civil Engineering, 2018: 1-7.
[24] J T Liu, Z Zhao, Y Bi, et al. Prediction and compensation of force-induced deformation for a dual-machine-based riveting system using FEM and neural network. The International Journal of Advanced Manufacturing Technology, 2019, 103(9-12): 3853-3870.
[25] F Hönsch, J Domitner, C Sommitsch, et al. Numerical simulation and experimental validation of self-piercing riveting (SPR) of 6xxx aluminium alloys for automotive applications. Journal of Physics: Conference Series, 2018: 1063.
[26] Y Abe, T Kato, K Mori. Self-piercing riveting of high tensile strength steel and aluminium alloy sheets using conventional rivet and die. Journal of Materials Processing Technology, 2009, 209(8): 3914-3922.
[27] X B Zhu, X Yang, Y B Li, et al. Reinforcing cross-tension strength of adhesively bonded joints using metallic solder ball. International Journal of Adhesion & Adhesives, 2016, 68: 263-272.
[28] M Carandente, R J Dashwood, I G Masters, et al. Improvements in numerical simulation of the SPR process using a thermo-mechanical finite element analysis. Journal of Materials Processing Technology, 2016, 236: 148-161.
[29] R Haque. Quality of self-piercing riveting (SPR) joints from cross-sectional perspective: A review. Archives of Civil and Mechanical Engineering, 2018, 18(1): 83-93.
[30] T Q Chen. XGBoost: A scalable tree boosting system. The 22nd ACM SIGKDD International ConferenceACM, 2016.
