Efficient parameter selection in laser welding via Bayesian optimization
Michael Haas et al.
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.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.