Modeling and process parameter optimization of laser cutting based on artificial neural network and intelligent optimization algorithm

Laser cutting technology has proven advantageous in processing high-hardness metals, ceramics, and composites. However, the process parameters significantly influence the kerf and heat-affected zone widths. Therefore, it is necessary to establish an accurate prediction model of laser cutting quality...

Full description

Saved in:
Bibliographic Details
Published in:International journal of advanced manufacturing technology Vol. 127; no. 3-4; pp. 1177 - 1188
Main Authors: Ren, Xingfei, Fan, Jinwei, Pan, Ri, Sun, Kun
Format: Journal Article
Language:English
Published: London Springer London 01.07.2023
Springer Nature B.V
Subjects:
Artificial neural networks
CAE) and Design
Computer-Aided Engineering (CAD
Efficiency
Engineering
Genetic algorithms
Heat affected zone
Industrial and Production Engineering
Kerf
Laser beam cutting
Lasers
Machining
Mathematical models
Mechanical Engineering
Media Management
Neural networks
Optimization algorithms
Original Article
Particle swarm optimization
Prediction models
Process parameters
Sorting algorithms
Laser cutting
Artificial neural network
Particle swarm optimization
Heat-affected zone
Machining process modeling
ISSN:0268-3768, 1433-3015
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Laser cutting technology has proven advantageous in processing high-hardness metals, ceramics, and composites. However, the process parameters significantly influence the kerf and heat-affected zone widths. Therefore, it is necessary to establish an accurate prediction model of laser cutting quality to optimize the process parameters and improve processing quality and efficiency. This work proposes a laser-cutting quality prediction model based on an artificial neural network optimized by the particle swarm optimization algorithm. The particle swarm optimization algorithm is used to optimize the number of nodes in the hidden layer, activation function, initial weights, and biases for a more accurate model. This model considers the effects of average power, repetition frequency, and scan speed on the kerf width, heat-affected width, and processing efficiency. The non-dominated sorting genetic algorithm II is adopted for the process parameter optimization. Finally, the experiments are carried out to verify the model. The results show that the model has a high accuracy with a prediction error of less than 10% for kerf width and heat-affected zone. Moreover, the optimized process parameters meet the given machining targets and increase the machining efficiency by over 40%.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0268-3768
1433-3015
DOI:10.1007/s00170-023-11543-6