.png){kind=icon}
.png){kind=icon}
Return
Welding heat source parameter optimization using a dynamic hybrid surrogate model
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engappai.2025.113637.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate calibration of welding heat source parameters is essential for reliable simulation-based prediction of weld quality and residual stresses in critical engineering structures such as pipelines and pressure vessels. However, traditional calibration methods are time-consuming and computationally expensive, limiting their industrial practicality. To address this issue, this paper proposes an intelligent optimization framework for welding heat source calibration, integrating a hybrid surrogate model based on a dynamic feature fusion mechanism with the Newton-Raphson-based optimizer (NRBO). The framework first achieves automated high-precision extraction of molten pool geometric features through isoparametric transformation and computer graphics techniques. Subsequently, a stacking ensemble strategy integrates heterogeneous surrogate models, while incorporating a self-attention-enhanced multilayer perceptron (Self-Attention-MLP) to dynamically fuse outputs from sub-models, which enhances capability of the hybrid surrogate model to capture the complex nonlinear mapping relationships between heat source parameters and molten pool features. Finally, an efficient parameter optimization workflow is established by combining the NRBO algorithm with the objective of minimizing geometric errors in the molten pool. Experimental results demonstrate that the hybrid surrogate model achieves coefficients of determination (R2) of 0.955 and 0.983 for predicting molten pool width and depth, respectively, significantly outperforming individual baseline models. The optimized double-ellipsoidal heat source parameters(front axial length af = 5.2, rear axial length ar = 6.1, transverse expansion coefficient b = 0.7, and depth coefficient c = 9.35) were validated via simulation, yielding predicted molten pool width and depth of 12.90 mm and 9.03 mm, respectively. These results exhibit relative errors of 3.3% and 3.4% compared to experimental measurements (13.34 mm and 9.35 mm), confirming the effectiveness and reliability of the proposed method. This study provides industry practitioners with a practical tool for improving simulation fidelity and accelerating process design in demanding industrial applications such as pressure vessel manufacturing and pipeline construction.
Keywords:
Welding heat source parameters
Hybrid surrogate model
Self-attention mechanism
Molten pool feature extraction
Journal
IF:
8
Papers:
5.3K
Citations:
3.5W