Efficient parameter selection in laser welding via Bayesian optimization
Open Access
- 27 February 2026
- journal article
- research article
- Published by Springer Nature in Journal of Intelligent Manufacturing
- p. 1-17
Abstract
Identifying suitable process parameters is essential for developing effective laser welding processes. Traditionally, this involves extensive experimentation and relies heavily on expert knowledge. Bayesian optimization can be used to minimize both the experimental effort and the need for expert information. This study demonstrates the merit of Bayesian optimization for laser welding and explains the methodology for implementing the optimization technique. A strategy for selecting evaluation methods and the design of a suitable cost function to meet specific quality criteria is proposed. For the experimental demonstration, butt joint laser welding of AA1050 aluminum alloy was performed with options to adapt the laser power, welding speed, focus position, and the intensity distribution of the laser beam by changing the power distribution in a multi-core fiber. The success of the optimization was validated by finding several parameter sets producing welds that met the defined quality levels. Furthermore, the properties of the underlying surrogate model of the Bayesian optimizer generated further information that helped to improve the welding process.Keywords
Funding Information
- Ministerium für Wissenschaft, Forschung und Kunst Baden-Württemberg (sustainability support of the projects of the Exzellenzinitiative II)
- Ministerium für Wissenschaft, Forschung und Kunst Baden-Württemberg (InnovationCampus Future Mobility)
- Deutsche Forschungsgemeinschaft (DFG object number: 625617 INST 41/990-1 FUGG)
- Universität Stuttgart
This publication has 35 references indexed in Scilit:
- AMBayes: a Bayesian data-driven framework for large-scale full-field prediction and process optimization with limited samples in additive manufacturingJournal of Intelligent Manufacturing, 2025
- Machine learning for density prediction and process optimization of 316L stainless steel fabricated by selective laser meltingJournal of Intelligent Manufacturing, 2025
- Recent advances in joining technologies of aluminum alloys: a reviewDiscover Materials, 2024
- Optimization framework of laser oscillation welding based on a deep predictive reward reinforcement learning netJournal of Intelligent Manufacturing, 2024
- Optimization of laser annealing parameters based on bayesian reinforcement learningJournal of Intelligent Manufacturing, 2024
- Multi-objective optimization of laser welding process parameters of steel/Al based on BO-RF and MOJSJournal of Mechanical Science and Technology, 2024
- Deep Learning2024
- A new hot-tearing criterionMetallurgical and Materials Transactions A, 1999
- Bayesian methods in global optimizationJournal of Global Optimization, 1991
- On the distribution of points in a cube and the approximate evaluation of integralsUSSR Computational Mathematics and Mathematical Physics, 1967