Optimization of processing parameters for waterjet-guided laser machining of SiC/SiC composites

Mengxuan Gao, Songmei Yuan (), Jiayong Wei, Jin Niu, Zikang Zhang, Xiaoqi Li, Jiaqi Zhang, Ning Zhou and Mingrui Luo
Additional contact information
Mengxuan Gao: Beihang University
Songmei Yuan: Beihang University
Jiayong Wei: Beihang University
Jin Niu: University of British Columbia (UBC)
Zikang Zhang: Beihang University
Xiaoqi Li: Beihang University
Jiaqi Zhang: Beihang University
Ning Zhou: Beihang University
Mingrui Luo: University of Chinese Academy of Sciences

Journal of Intelligent Manufacturing, 2024, vol. 35, issue 8, No 27, 4137-4157

Abstract: Abstract Interactions between light and matter during short-pulse water-jet guided laser materials processing are highly nonlinear, and acutely sensitive to laser machining parameters. Traditionally, the physical simulation calculation methods based on laser, water and composite materials are complicated. This work combines neural networks and physical simulation models in the understanding of laser drilling of composite materials. Neural networks are used to predict SiC/SiC composites laser drilling results by using processing parameters (average power, scanning speed, and filling spacing) as input parameters, optimal combinations of processing parameters based on the neural network are identified, and the effectiveness of the learned knowledge is validated using a physical simulation model. The results show that the neural network can identify the nonlinear effect of processing parameters on machining quality with the MAE of 0.054 and the RMSE of 0.067. The physical simulation model could explain why this nonlinear effect exists. This method can be applied to a wide range of fields. In the face of unknown material and physical processing processes, the approach of combining neural networks and physical simulation models has the potential to significantly reduce the optimization time and deepen the understanding of laser processing.

Keywords: SiCf; SiC composites; Laser machining; Physical simulation; Neural networks; Micro-structuring; Parameter optimization (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10845-023-02225-x Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joinma:v:35:y:2024:i:8:d:10.1007_s10845-023-02225-x

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10845

DOI: 10.1007/s10845-023-02225-x

Access Statistics for this article

Journal of Intelligent Manufacturing is currently edited by Andrew Kusiak

More articles in Journal of Intelligent Manufacturing from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().