logo
ResearchBunny Logo
Generalisable 3D printing error detection and correction via multi-head neural networks

Engineering and Technology

Generalisable 3D printing error detection and correction via multi-head neural networks

D. A. J. Brion and S. W. Pattinson

Discover how Douglas A. J. Brion and Sebastian W. Pattinson have developed CAXTON, a cutting-edge system utilizing a multi-head neural network to automatically detect and correct errors in material extrusion. This innovative approach leverages a massive dataset of 1.2 million images to enhance the quality of additive manufacturing processes!

00:00
00:00
Playback language: English
Abstract
Material extrusion, a prevalent additive manufacturing (AM) method, suffers from errors limiting its use in end-use products. This paper presents a multi-head neural network trained on images automatically labelled by deviation from optimal printing parameters. The automated data acquisition and labelling creates a large dataset (1.2 million images from 192 parts), enabling real-time detection and correction of diverse errors across various geometries, materials, and printers. The system, CAXTON, is highly scalable and generalises to unseen scenarios, including different extrusion methods.
Publisher
Nature Communications
Published On
Aug 15, 2022
Authors
Douglas A. J. Brion, Sebastian W. Pattinson
Tags
material extrusion
additive manufacturing
neural network
error detection
automated data acquisition
real-time correction
CAXTON

Related Publications

Explore these studies to deepen your understanding of the subject.

Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization
Medicine and Health

Advancing diagnostic performance and clinical usability of neural networks via adversarial training and dual batch normalization

T. Han, S. Nebelung, et al.

Multi-color dual wavelength vat photopolymerization 3D printing via spatially controlled acidity
Engineering and Technology

Multi-color dual wavelength vat photopolymerization 3D printing via spatially controlled acidity

K. C. H. Chin, G. Ovsepyan, et al.

Detection and extraction of heavy metal ions using paper-based analytical devices fabricated via atom stamp printing
Engineering and Technology

Detection and extraction of heavy metal ions using paper-based analytical devices fabricated via atom stamp printing

Y. Guan and B. Sun

Phenotype prediction using biologically interpretable neural networks on multi-cohort multi-omics data
Medicine and Health

Phenotype prediction using biologically interpretable neural networks on multi-cohort multi-omics data

A. V. Hilten, J. V. Rooij, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny