Parameters prediction in additively manufactured Al-Cu alloy using back propagation neural network
Source abstract
Abstract
The relationship between tensile strength, wire feeding speed and travel speed is built based on Back Propagation (BP) neural network during the wire arc additive manufacturing (WAAM) process. The introduction of a genetic algorithm for optimising the BP neural network (GA-BP) and incorporation of additional parameter combinations through the forward model markedly enhance the prediction accuracy of the process parameter reverse model. The BP neural network with a genetic algorithm model exhibits excellent training results, and the sample population regression reaches 0.97. An error value of the optimised model is only 3.10% for wire feeding speed prediction, only 1.55% for travel speed prediction. The GA-BP reverse model optimises WAAM process parameters and achieves a tensile strength exceeding 230 MPa.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Additive Manufacturing Materials and Processes · Additive Manufacturing and 3D Printing Technologies · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Materials Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, People's Republic of China
AVIC Cheng'du Aircraft Industrial (Group) Co. Ltd., Chengdu, People's Republic of China
Funding
Defense Industrial Technology Development Program of China
References (42)
Show source-provided references
1. 10.1016/j.jmapro.2022.10.06010.1016/j.jmapro.2022.10.060 ↗
2. 10.1016/j.jallcom.2022.16734510.1016/j.jallcom.2022.167345 ↗
3. 10.1016/j.matchemphys.2022.12698810.1016/j.matchemphys.2022.126988 ↗
4. Li Q, , Wang F, , Wang G, . Wire and arc additive manufacturing of lightweight metal components in aeronautics and astronautics. Aeronaut Manuf Technol. 2018;61:74–89.
5. 10.1007/s00170-020-05966-810.1007/s00170-020-05966-8 ↗
6. 10.1016/j.matdes.2020.10937010.1016/j.matdes.2020.109370 ↗
7. 10.1016/j.istruc.2021.01.06810.1016/j.istruc.2021.01.068 ↗
8. 10.1016/j.addma.2021.10239710.1016/j.addma.2021.102397 ↗
9. 10.1016/j.jmatprotec.2007.02.03510.1016/j.jmatprotec.2007.02.035 ↗
10. 10.1016/j.jmatprotec.2007.10.03510.1016/j.jmatprotec.2007.10.035 ↗
11. 10.1088/1757-899X/1136/1/01202610.1088/1757-899X/1136/1/012026 ↗
12. McCulloch W, , Pitts W. A logical calculus of the ideas immanent in nervous activity. B Math Biol. 1943;5:115–133.
13. 10.1016/j.addma.2017.11.01210.1016/j.addma.2017.11.012 ↗
14. 10.1016/j.matdes.2018.07.00210.1016/j.matdes.2018.07.002 ↗
15. 10.1016/j.addma.2018.09.03410.1016/j.addma.2018.09.034 ↗
16. 10.1016/j.istruc.2022.10.13410.1016/j.istruc.2022.10.134 ↗
17. 10.1016/j.simpat.2022.10266410.1016/j.simpat.2022.102664 ↗
18. 10.1016/j.procir.2019.03.17410.1016/j.procir.2019.03.174 ↗
19. 10.1016/j.matpr.2022.10.00410.1016/j.matpr.2022.10.004 ↗
20. 10.1016/j.cirpj.2022.05.00410.1016/j.cirpj.2022.05.004 ↗
21. 10.1016/j.matpr.2021.10.37610.1016/j.matpr.2021.10.376 ↗
22. 10.1016/j.rcim.2022.10247010.1016/j.rcim.2022.102470 ↗
23. 10.1016/j.jmrt.2022.08.15410.1016/j.jmrt.2022.08.154 ↗
24. 10.1007/s11837-019-03761-910.1007/s11837-019-03761-9 ↗
25. 10.1016/j.addma.2015.07.00110.1016/j.addma.2015.07.001 ↗
26. 10.3390/ma1308196310.3390/ma13081963 ↗
27. 10.1016/j.matdes.2016.09.04310.1016/j.matdes.2016.09.043 ↗
28. Chan B. Modelling gas metal arc weld geometry using artificial neural network technology. Can Metall Quart. 1999;38:43–51.
29. 10.1016/S0924-0136(02)00803-810.1016/S0924-0136(02)00803-8 ↗
30. Geng C, , Lin Y, , Wang X, . Modeling research of artificial neural networks of YAG laser welding parameters. Trans China Weld Inst. 2001;22:37–40.
31. Xiong J, , Zhang W, , Hu Q, . Optimizing of welding parameters of YAG laser welding titanium alloy based on artificial neural net. Appl Laser. 2001;21:243–246.
32. 10.1016/j.matpr.2018.10.19310.1016/j.matpr.2018.10.193 ↗
33. 10.1016/j.addma.2021.10238710.1016/j.addma.2021.102387 ↗
34. 10.1080/0141861980822407210.1080/01418619808224072 ↗
35. 10.1016/j.jmst.2022.07.00110.1016/j.jmst.2022.07.001 ↗
36. 10.1007/s10845-020-01538-510.1007/s10845-020-01538-5 ↗
37. 10.1155/2015/36504910.1155/2015/365049 ↗
38. 10.1007/s10773-020-04470-910.1007/s10773-020-04470-9 ↗
39. 10.1155/2013/42574010.1155/2013/425740 ↗
40. 10.1186/s12911-020-01157-310.1186/s12911-020-01157-3 ↗
41. Yang B, , Su X, , Wang Y. BP neural network optimization based on an improved genetic algorithm. IEEE Xplore. 2002;1:64–68.
42. 10.1016/j.jallcom.2022.16829810.1016/j.jallcom.2022.168298 ↗