Multiple nonlinear regression prediction model for process parameters of Al alloy self-piercing riveting

Box-Behnken design (BBD) response surface test was carried out to investigate the parameters of AL1420, AA5052 and AA5182 Al alloy self-piercing riveting. The sheet thickness, sheet hardness and rivet hardness were used as input values. Meanwhile, the multiple nonlinear regression models were established by using the punch stroke, the maximum riveting force and the failure load as the output response values. The result showed that the errors between the prediction values of the model and the actual values were within 8%. The interaction of sheet thickness and rivet hardness has the greatest impact on the failure load and maximum riveting force, and the punch stroke was mainly affected by the interaction of sheet hardness and rivet hardness.(c) 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

The Box-Behnken design was utilized to investigate the parameters of aluminum alloy self-piercing riveting, and multiple nonlinear regression models were established, showing the significant impact of the interaction between sheet thickness and rivet hardness on the riveting performance.