Open Access

ARTICLE

Physics-Informed Gaussian Process Regression with Bayesian Optimization for Laser Welding Quality Control in Coaxial Laser Diodes

Ziyang Wang¹, Lian Duan^1,2,*, Lei Kuang¹, Haibo Zhou¹, Ji’an Duan¹

1 State Key Laboratory of Precision Manufacturing for Extreme Service Performance, Central South University, Changsha, 410000, China
2 College of Mechanical Engineering, Hunan University of Science and Technology, Xiangtan, 411201, China

* Corresponding Author: Lian Duan. Email:

(This article belongs to the Special Issue: Computing Technology in the Design and Manufacturing of Advanced Materials)

Computers, Materials & Continua 2025, 84(2), 2587-2604. https://doi.org/10.32604/cmc.2025.065648

Received 18 March 2025; Accepted 23 May 2025; Issue published 03 July 2025

Abstract

The packaging quality of coaxial laser diodes (CLDs) plays a pivotal role in determining their optical performance and long-term reliability. As the core packaging process, high-precision laser welding requires precise control of process parameters to suppress optical power loss. However, the complex nonlinear relationship between welding parameters and optical power loss renders traditional trial-and-error methods inefficient and imprecise. To address this challenge, a physics-informed (PI) and data-driven collaboration approach for welding parameter optimization is proposed. First, thermal-fluid-solid coupling finite element method (FEM) was employed to quantify the sensitivity of welding parameters to physical characteristics, including residual stress. This analysis facilitated the identification of critical factors contributing to optical power loss. Subsequently, a Gaussian process regression (GPR) model incorporating finite element simulation prior knowledge was constructed based on the selected features. By introducing physics-informed kernel (PIK) functions, stress distribution patterns were embedded into the prediction model, achieving high-precision optical power loss prediction. Finally, a Bayesian optimization (BO) algorithm with an adaptive sampling strategy was implemented for efficient parameter space exploration. Experimental results demonstrate that the proposed method effectively establishes explicit physical correlations between welding parameters and optical power loss. The optimized welding parameters reduced optical power loss by 34.1%, providing theoretical guidance and technical support for reliable CLD packaging.

---

Keywords

---