Repository logo

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

Published version

Change log


Brion, Douglas AJ 
Pattinson, Sebastian W.  ORCID logo


Abstract: Material extrusion is the most widespread additive manufacturing method but its application in end-use products is limited by vulnerability to errors. Humans can detect errors but cannot provide continuous monitoring or real-time correction. Existing automated approaches are not generalisable across different parts, materials, and printing systems. We train a multi-head neural network using images automatically labelled by deviation from optimal printing parameters. The automation of data acquisition and labelling allows the generation of a large and varied extrusion 3D printing dataset, containing 1.2 million images from 192 different parts labelled with printing parameters. The thus trained neural network, alongside a control loop, enables real-time detection and rapid correction of diverse errors that is effective across many different 2D and 3D geometries, materials, printers, toolpaths, and even extrusion methods. We additionally create visualisations of the network’s predictions to shed light on how it makes decisions.



Article, /639/166/988, /639/166/987, /639/301/930, /639/705/1042, /139, /123, /141, /119, article

Journal Title

Conference Name

Journal ISSN


Volume Title


Nature Publishing Group UK
RCUK | Engineering and Physical Sciences Research Council (EPSRC) (EP/N509620/1, EP/V062123/1)
Royal Society (RGS/R2/192433)
Academy of Medical Sciences (SBF005/1014)
Is supplemented by: