Weld Bead Size Prediction of Wire and Arc Additive Manufacturing Based on ACS-DBN

Authors

Dong Hai, 1. School of Applied Technology, Shenyang University, Shenyang 110041, China; ;
Xiuxiu Gao, 2. School of Mechanical, Shenyang University, Shenyang 110041, China;
Mingqi Wei, 2. School of Mechanical, Shenyang University, Shenyang 110041, China;

Abstract

Abstract: Welding pass overlap is the essence of wire and arc additive manufacturing (WAAM) technology. Appropriate process parameter selection is of great significance to control the welding pass geometry and improve the dimensional accuracy of the molded parts. A prediction model of deep beilef network (DBN) optimized by adaptive cuckoo search (ACS) algorithm is constructed. The welding width and residual height of the weld pass are predicted based on the four technological parameters of the given nozzle height, welding current, welding speed and wire feeding speed. The optimal number of hidden layers and hidden elements are determined based on the experimental method, and the prediction model of WAAM weld pass size based on ASC-DBN is established. Simulation experiments are used to verify the performance of ASC-DBN prediction model. By comparing with the traditional models, the results show that the ACS-DBN model can effectively map the complex non-linear relationship between the weld pass size and welding process parameters of WAAM, and the prediction error of the weld pass size under the ACS-DBN prediction model is less than 6%, which has higher accuracy and stability compared with other prediction models.

Recommended Citation

Hai, Dong; Gao, Xiuxiu; and Wei, Mingqi (2022) "Weld Bead Size Prediction of Wire and Arc Additive Manufacturing Based on ACS-DBN," Journal of System Simulation: Vol. 33: Iss. 12, Article 7.
DOI: 10.16182/j.issn1004731x.joss.21-FZ0723
Available at: https://dc-china-simulation.researchcommons.org/journal/vol33/iss12/7

First Page

2828

Revised Date

2021-07-20

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.21-FZ0723

Last Page

2837

CLC

TP391.9

Recommended Citation

Dong Hai, Gao Xiuxiu, Wei Mingqi. Weld Bead Size Prediction of Wire and Arc Additive Manufacturing Based on ACS-DBN[J]. Journal of System Simulation, 2021, 33(12): 2828-2837.

Corresponding Author

Xiuxiu Gao,

DOI

10.16182/j.issn1004731x.joss.21-FZ0723