Arc welding seam forming accurate prediction method based on deep learning

Abstract

The invention discloses an arc welding seam forming accurate prediction method based on deep learning. The arc welding seam forming accurate prediction method comprises the steps that a correspondingwelding process is designed according to welding equipment, a welding material, a structural form and a welding method; designing a corresponding process experiment according to a welding process, andimplementing in batches; according to different combinations of welding equipment models, material marks, structural forms and welding methods, weld joint forming sub-databases are established respectively; constructing a deep neural network taking the process parameters as input and taking the weld joint forming size and the weld joint section profile as output, and training and evaluating the deep neural network by utilizing data of the sub-database to obtain a weld joint forming prediction model; and real-time technological parameters in the welding seam forming process are collected and input into the welding seam forming prediction model, the corresponding welding seam forming size and welding seam section contour are output, and accurate prediction of arc welding seam forming is achieved. According to the invention, accurate prediction of weld joint forming can be realized.

Description

technical field [0001] The invention relates to the field of intelligent welding, in particular to a deep learning-based accurate prediction method for arc welding seam formation. Background technique [0002] With the increasing demands on the performance, precision, cost, manufacturing cycle and light weight of metal parts and large structural parts in important technical fields such as aerospace, bridges and ships, energy and transportation, welding technology has gradually changed from extensive design and production. Turn to the mode of full parametric design, precise process control and efficient and intelligent manufacturing. For arc welding technology, which occupies a major position in the welding field, its digitalization degree has become the core and key of welding structure performance and reliability control. [0003] The size of the weld formation is determined by the process parameters, which seriously affects the microstructure and stress distribution of th...

AI Technical Summary

Problems solved by technology

However, the arc welding process is a complex metallurgical process involving complex physical effects such as arc heat, force, sound, light, electricity, and magnetism, welding wire melting, molten pool flow, weld solidification, and solid-state phase transition of components. Field, flow field, phase field and other physical fields have strong coupling effects, and the heat and mass transfer process of the rapid transition of metal materials into solid, liquid, and gas is extremely complicated, resulting in arc plasma morphology, droplet transfer, weld forming quality, and structure. Significant changes and differences in strength and toughness are also the internal causes of defects such as pores, cracks, humps, and lack of fusion, and are the key to achieving efficient welding process stability control and component strength and toughness regulation.

Therefore, for the highly nonlinear MIMO system of arc welding from welding process parameters to weld shape dimensions, conventional mathematical modeling methods are difficult to do.

[0004] The existing weld formation prediction systems based on conventional methods such as mathematical modeling and logical reasoning all have single functions, low precision, weak generalization ability, and no autonomy due to limitations such as high welding data dependence, inefficient analysis, and difficult applications. Problems such as learning ability cannot be practically applied, thus greatly limiting the digitization of welding or additive process design, the high efficiency of welding numerical calculation and the intelligence of the process

Images