Data and physical dual-driven variable time-delay welding thermal field predictive control method and system
By employing a data- and physics-driven variable time-delay welding thermal field prediction and control method, welding parameters are collected in real time and combined with Gaussian process regression and dynamic thermal hysteresis calculation. This solves the problem of heat accumulation hysteresis during the welding process, achieves precise control of dissimilar aluminum alloy joints, avoids grain boundary liquefaction cracking, and ensures welding quality.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- ANHUI UNIV OF SCI & TECH
- Filing Date
- 2026-05-20
- Publication Date
- 2026-07-17
AI Technical Summary
In existing automated welding technologies, fixed parameter control makes it difficult to achieve precise phase matching and data verification, resulting in delayed heat accumulation during the welding process. This can easily lead to grain boundary liquefaction cracking and softening in dissimilar aluminum alloy joints. In particular, in the manufacturing of lightweight bodies for new energy vehicles, the welding of dissimilar aluminum alloys such as 6082 and C611 is difficult to effectively solve the problems of gradual temperature gradient and nonlinear expansion of molten pool volume caused by heat accumulation during long-term continuous welding.
A variable time-delay welding thermal field prediction and control method based on data and physics is adopted. By collecting welding parameters in real time, the confidence interval of weld width is predicted by Gaussian process regression model. Combined with the measured data of the weld pool and the dynamic thermal hysteresis solution engine, the heat transfer hysteresis time is identified online. The optimal control command sequence is solved by constrained optimizer to achieve precise control of welding parameters.
It effectively eliminates pure hysteresis in heat conduction, adaptively adjusts thermal expansion, significantly reduces the risk of grain boundary softening and cracking in the semi-molten zone of dissimilar aluminum alloy joints, and ensures the mechanical properties of structural components for new energy vehicles.
Smart Images
Figure CN122411037A_ABST