Open AccessDiscrimination of molten pool penetration based on genetic algorithm optimization of BP neural network
Author(s) -
Boxue Chang,
Jingyue Huang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1437/1/012110
Subject(s) - artificial neural network , genetic algorithm , algorithm , welding , reliability (semiconductor) , computer science , materials science , artificial intelligence , mechanical engineering , engineering , machine learning , thermodynamics , physics , power (physics)
The metal spatter and light intensity of CO 2 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.