Abstract

The metal spatter and light intensity of CO2 welding in the vicinity of the melt pool during the short transition of the melt droplet seriously affect the realtime and reliability of weld feature extraction. The mapping relationship between welding pool characteristic parameters and melting depth is established by using BP neural network optimized by genetic algorithm. The results show that the training results and test results of the optimized BP neural network model of genetic algorithm have little error and meet the requirements of precision. The model can well reflect the relationship between the melting depth and the characteristic parameters of the melting pool.

Details

Title
Discrimination of molten pool penetration based on genetic algorithm optimization of BP neural network
Author
Chang, Boxue 1 ; Huang, Jingyue 2 

 Guilin University Of Aerospace Technology, Guilin, 541004, China 
 Guilin University Of Electronic Technology, Guilin, 541004, China 
Publication year
2020
Publication date
Jan 2020
Publisher
IOP Publishing
ISSN
17426588
e-ISSN
17426596
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2569074893
Copyright
© 2020. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.