A deep learning-based model for defect detection in laser-powder bed fusion using in-situ thermographic monitoring

Hermann Baumgartl, Josef Tomas, Ricardo Buettner, Markus Merkel

Progress in Additive Manufacturing 2020 article cited by 268

Source Open-access PDF More in Engineering & Materials

importance 5/10 ai assisted Additive Manufacturing Materials and Processes additive manufacturing stage: research

Problem

Defects from suboptimal parameter settings in laser-powder bed fusion 3D printing are usually detected only after the process, not during printing.

Why it matters

Flawed metal parts are discovered only after printing, defeating in-process quality control.

What the AI did

Trained deep neural networks on off-axis thermographic images to recognize printing defects in-situ, using k-fold and hold-out cross validation plus class activation heatmaps for evaluation.

Results

Defects such as delamination and splatter recognized with 96.80% accuracy; small architecture with low computing requirements.

Impact

Enables in-situ defect detection during printing with a small, low-computation architecture.

Record

Venue	Progress in Additive Manufacturing
Published	2020
Work type	article
Authors	Hermann Baumgartl, Josef Tomas, Ricardo Buettner, Markus Merkel
Citations	268 (OpenAlex, at import time)
References	61
Model or method	not stated in source
Organization	not stated in source
Primary source	https://doi.org/10.1007/s40964-019-00108-3
Open access	hybrid
Keywords	laser-powder bed fusion, defect detection, deep learning, thermographic monitoring, additive manufacturing

Importance rating

5 / 10

real but narrower advance

In-situ defect detection enables real-time quality control in metal 3D printing, a real manufacturing advance; no scale or deployment stated.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Engineering & Materials

#	Paper	Year	Citations	Importance
1	Scaling deep learning for materials discovery Amil Merchant, Simon Batzner, Samuel S. Schoenholz, Muratahan Aykol, G...	2023	1,471	8
2	Application of Machine Learning in Material Synthesis and Property Prediction Guannan Huang, Yani Guo, Ye Chen, Zhengwei Nie	2023	165	7
3	Machine learning-guided discovery of ionic polymer electrolytes for lithium metal batteries Kai Li, Jifeng Wang, Yuanyuan Song, Ying Wang	2023	115	7
4	Machine Learning for Structural Health Monitoring of Aerospace Structures: A Review Gennaro Scarselli, Francesco Nicassio	2025	44	7
5	Power System Transient Stability Assessment Based on Machine Learning Algorithms and Grid Topology Mihail D. Senyuk, Murodbek Safaraliev, Firuz Kamalov, Hana Sulieman	2023	42	7