A Comparative Study of Attention-Augmented YOLO Architectures for Defect Detection in Fused Deposition Modelling

Hasan Cezayirli; Halil Tetik; Mehmet İsmet Can Dede; Wai Lwin Phone; Bugra Alkan

A Comparative Study of Attention-Augmented YOLO Architectures for Defect Detection in Fused Deposition Modelling

Hasan Cezayirli, Halil Tetik, Mehmet İsmet Can Dede, Wai Lwin Phone, Bugra Alkan

Research output: Contribution to conference › Paper › peer-review

5 Downloads (Pure)

Abstract

Additive manufacturing (AM), particularly fused deposition modelling (FDM), facilitates the fabrication of complex geometries with increasing flexibility and efficiency. Ensuring consistent print quality in FDM processes necessitates the development of accurate defect detection mechanisms. Attention-augmented YOLO (You Only Look Once) models have emerged as a promising solution for addressing this challenge. In this study, we systematically benchmark and evaluate the performance of YOLO architectures enhanced with attention mechanisms within the context of FDM 3D printing applications. The models were trained and evaluated using representative defect datasets. The attention-augmented models demonstrate improved detection performance.

Original language	English
Number of pages	8
Publication status	Published - 12 Sept 2025
Event	30th IEEE International Conference on Emerging Technologies and Factory Automation - Faculty of Engineering of University of Porto (FEUP), Porto, Portugal Duration: 9 Sept 2025 → 12 Sept 2025 https://etfa2025.ieee-ies.org

Conference

Conference	30th IEEE International Conference on Emerging Technologies and Factory Automation
Abbreviated title	EFTA2025
Country/Territory	Portugal
City	Porto
Period	9/09/25 → 12/09/25
Internet address	https://etfa2025.ieee-ies.org

Keywords

Fused Deposition Modeling
Additive Manufacturing
Defect Detection
Artificial Intelligence
Machine Vision
YOLO
Attention Mechanisms

Access to Document

A Comparative Study of Attention-Augmented YOLO Architectures for Defect Detection in Fused Deposition ModellingAccepted author manuscript, 18.5 MBLicence: CC BY 4.0

Cite this

@conference{bad74b51f0564fefb0c8bde20fa24a14,

title = "A Comparative Study of Attention-Augmented YOLO Architectures for Defect Detection in Fused Deposition Modelling",

abstract = "Additive manufacturing (AM), particularly fused deposition modelling (FDM), facilitates the fabrication of complex geometries with increasing flexibility and efficiency. Ensuring consistent print quality in FDM processes necessitates the development of accurate defect detection mechanisms. Attention-augmented YOLO (You Only Look Once) models have emerged as a promising solution for addressing this challenge. In this study, we systematically benchmark and evaluate the performance of YOLO architectures enhanced with attention mechanisms within the context of FDM 3D printing applications. The models were trained and evaluated using representative defect datasets. The attention-augmented models demonstrate improved detection performance.",

keywords = "Fused Deposition Modeling, Additive Manufacturing, Defect Detection, Artificial Intelligence, Machine Vision, YOLO, Attention Mechanisms",

author = "Hasan Cezayirli and Halil Tetik and Dede, \{Mehmet İsmet Can\} and Phone, \{Wai Lwin\} and Bugra Alkan",

year = "2025",

month = sep,

day = "12",

language = "English",

note = "30th IEEE International Conference on Emerging Technologies and Factory Automation, EFTA2025 ; Conference date: 09-09-2025 Through 12-09-2025",

url = "https://etfa2025.ieee-ies.org",

}

A Comparative Study of Attention-Augmented YOLO Architectures for Defect Detection in Fused Deposition Modelling. / Cezayirli, Hasan; Tetik, Halil; Dede, Mehmet İsmet Can et al.
2025. Paper presented at 30th IEEE International Conference on Emerging Technologies and Factory Automation, Porto, Portugal.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - A Comparative Study of Attention-Augmented YOLO Architectures for Defect Detection in Fused Deposition Modelling

AU - Cezayirli, Hasan

AU - Tetik, Halil

AU - Dede, Mehmet İsmet Can

AU - Phone, Wai Lwin

AU - Alkan, Bugra

PY - 2025/9/12

Y1 - 2025/9/12

N2 - Additive manufacturing (AM), particularly fused deposition modelling (FDM), facilitates the fabrication of complex geometries with increasing flexibility and efficiency. Ensuring consistent print quality in FDM processes necessitates the development of accurate defect detection mechanisms. Attention-augmented YOLO (You Only Look Once) models have emerged as a promising solution for addressing this challenge. In this study, we systematically benchmark and evaluate the performance of YOLO architectures enhanced with attention mechanisms within the context of FDM 3D printing applications. The models were trained and evaluated using representative defect datasets. The attention-augmented models demonstrate improved detection performance.

AB - Additive manufacturing (AM), particularly fused deposition modelling (FDM), facilitates the fabrication of complex geometries with increasing flexibility and efficiency. Ensuring consistent print quality in FDM processes necessitates the development of accurate defect detection mechanisms. Attention-augmented YOLO (You Only Look Once) models have emerged as a promising solution for addressing this challenge. In this study, we systematically benchmark and evaluate the performance of YOLO architectures enhanced with attention mechanisms within the context of FDM 3D printing applications. The models were trained and evaluated using representative defect datasets. The attention-augmented models demonstrate improved detection performance.

KW - Fused Deposition Modeling

KW - Additive Manufacturing

KW - Defect Detection

KW - Artificial Intelligence

KW - Machine Vision

KW - YOLO

KW - Attention Mechanisms

M3 - Paper

T2 - 30th IEEE International Conference on Emerging Technologies and Factory Automation

Y2 - 9 September 2025 through 12 September 2025

ER -