Process optimization and weld forming control based on GA-BP algorithm for riveting-welding hybrid bonding between magnesium and CFRP

In the process of riveting-welding hybrid bonding for magnesium and the carbon fiber reinforced polymer (CFRP), the weld morphology including weld penetration and weld width makes an important influence on the property of welded joint. In order to understand the optimal weld morphology, the relationship between the morphology coefficient phi (the ratio of penetration depth to width) and the joint strength was established under a series groups of welding parameters. In addition, in order to obtain ideal appearance and optimized welding parameters, a BP neural network model optimized by genetic algorithm is established, in which the weld penetration and weld width are taken as the input units of neural network, and the welding process parameters such as welding speed, laser power, and laser defocused amount are regarded as the output units of the neural network. The results show that the mean absolute percentage error (MAPE) of each group of data did not exceed 3% while minimum mean square error (MSE) reached 0.0097, which can ensure the production of welded joints with ideal uniform appearance and mechanical properties. This research provides a new method for control of welding quality in the process of riveting-welding hybrid bonding for magnesium and CFRP.

Automated summary

This study establishes the relationship between the morphology coefficient and joint strength, optimizes a neural network model using a genetic algorithm, ensuring ideal weld appearance and mechanical properties, thereby providing a new method to control welding quality in the process of riveting-welding hybrid bonding for magnesium and CFRP.