Back to Search
Start Over
Convolutional Neural Network for geometric deviation prediction in Additive Manufacturing
- Source :
- 30th CIRP DESIGN CONFERENCE, 30th CIRP DESIGN CONFERENCE, May 2020, Skukuza, South Africa
- Publication Year :
- 2020
- Publisher :
- Elsevier BV, 2020.
-
Abstract
- International audience; The geometrical quality of AM products is an indispensable concern when conducting Design for Additive Manufacturing (DfAM), since it dominates the geometrical consistency between the manufactured samples and the design intent and has an impact on the functionality of the products. Therefore, effective prediction of the geometric deviations prior to the mass production will provide useful information for designers in order for design optimization. Data-driven methods open up new possibilities to gain high-fidelity prediction based on existing observable data. In this paper, a Convolutional Neural Network based deep learning method is proposed which enables the prediction of deviations for different shapes and process settings. A data augmentation technique is also introduced to generate samples for network training based on a small number of available data. Through a case study, it's demonstrated that the trained network manages to accurately predict the geometric deviations of shapes manufactured with varied size and process parameter settings. The predicted deviations could substantially benefit DfAM in evaluation of geometrical consistency. Moreover, reverse compensation can be accordingly applied to the CAD model prior to the manufacturing process, thus increasing the geometrical accuracy of the manufactured parts. c 2020 The Authors. Published by Elsevier B.V. Peer-review under responsibility of the scientific committee of the CIRP Design Conference 2020.
- Subjects :
- 0209 industrial biotechnology
[SPI] Engineering Sciences [physics]
Computer science
media_common.quotation_subject
Convolutional Neural Network
CAD
[MATH] Mathematics [math]
02 engineering and technology
Process variable
[INFO] Computer Science [cs]
010501 environmental sciences
computer.software_genre
01 natural sciences
Convolutional neural network
Compensation (engineering)
[SPI]Engineering Sciences [physics]
Consistency (database systems)
020901 industrial engineering & automation
Geometric deviation modeling
[INFO]Computer Science [cs]
Quality (business)
[MATH]Mathematics [math]
0105 earth and related environmental sciences
General Environmental Science
media_common
business.industry
Deep learning
Process (computing)
Design for Additive Manufacturing
General Earth and Planetary Sciences
Artificial intelligence
Data mining
business
computer
Subjects
Details
- ISSN :
- 22128271
- Volume :
- 91
- Database :
- OpenAIRE
- Journal :
- Procedia CIRP
- Accession number :
- edsair.doi.dedup.....ba3cc0933bd68e8963a122108dc82561