Learning the Inverse Solution of Laser Drilling Model

Laser drilling cooling holes into turbine components is well established in industries. However, there are drawbacks related to setting and maintaining the appropriate manufacturing conditions, which can be formulated as an inverse problem. The inverse solution of a physical model describing long-pu...

Full description

Saved in:
Bibliographic Details
Published in:Journal of laser micro nanoengineering 2024-09, Vol.19 (2), p.93-101
Main Authors: Kheirandish, Zahra, Heinigk, Christian, Schulz, Wolfgang
Format: Article
Language:English
Subjects:
Ablation
Algorithms
Approximation
Drilling
Drilling and boring
Inverse problems
Laser cooling
Laser drilling
Lasers
Manufacturing
Metal sheets
Neural networks
Plant layout
Process parameters
Radiation
Sheet-metal
Turbines
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Laser drilling cooling holes into turbine components is well established in industries. However, there are drawbacks related to setting and maintaining the appropriate manufacturing conditions, which can be formulated as an inverse problem. The inverse solution of a physical model describing long-pulse laser drilling of sheet metal is learned through an artificial algorithm. The trained feedforward neural network predicts process parameters of desirable production outcomes. Here, the trained network predicts beam radius and pulse power to drill through getting a hole with specified conicity. The hyperparameters of the neural network are trained using algorithmic differentiation. Using a physical model improves the solvability of the inverse problem, since all trials during training belong to the applicable range of laser drilling and improves the training procedure going in a physically informed direction. Keywords: laser drilling, inverse solution, physically informed neural network, customized training loss, reduced model
ISSN:1880-0688
1880-0688
DOI:10.2961/jlmn.2024.02.2001