Conceptual Framework for Synthetic Data Generation in Remanufacturing

Dominik Koch; Florian Stamer; Gisela Lanza

doi:10.1007/978-3-031-86893-1_35

Conceptual Framework for Synthetic Data Generation in Remanufacturing

Dominik Koch^*
, Florian Stamer
, Gisela Lanza

^*Corresponding author for this work

Karlsruhe Institute of Technology

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

Abstract

Remanufacturing requires effective defect detection, but data scarcity and defect variability challenge ML model training. This paper presents a synthetic data generation pipeline focusing on bevel gears, simulating geometric defects like broken teeth, and applying scene randomization to diversify the dataset. The pipeline successfully generates synthetic data for geometric defects, supporting automated segmentation and annotation. However, the current results are limited to geometric defects. Future work will expand to surface and material defects using MDL graphs to improve the pipeline’s applicability. In conclusion, while the pipeline shows potential, real-world validation is necessary to confirm its robustness in remanufacturing.

Original language	English
Title of host publication	Production at the Leading Edge of Technology : Proceedings of the 14th Congress of the German Academic Association for Production Technology (WGP), Chemnitz University of Technology, December 2024
Editors	Welf-Guntram Drossel, Steffen Ihlenfeldt, Martin Dix
Number of pages	9
Publisher	Springer Nature
Publication date	2025
Pages	317-325
ISBN (Print)	978-3-031-86892-4, 978-3-031-86895-5
ISBN (Electronic)	978-3-031-86893-1
DOIs	https://doi.org/10.1007/978-3-031-86893-1_35
Publication status	Published - 2025
Externally published	Yes

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Research areas and keywords

optical inspection
remanufacturing
synthetical data
Engineering

ASJC Scopus Subject Areas

Industrial and Manufacturing Engineering
Economics, Econometrics and Finance (miscellaneous)
Safety, Risk, Reliability and Quality

Access to Document

10.1007/978-3-031-86893-1_35

Cite this

Koch, D., Stamer, F., & Lanza, G. (2025). Conceptual Framework for Synthetic Data Generation in Remanufacturing. In W.-G. Drossel, S. Ihlenfeldt, & M. Dix (Eds.), Production at the Leading Edge of Technology: Proceedings of the 14th Congress of the German Academic Association for Production Technology (WGP), Chemnitz University of Technology, December 2024 (pp. 317-325). (Lecture Notes in Production Engineering; Vol. Part F679). Springer Nature. https://doi.org/10.1007/978-3-031-86893-1_35

Koch, Dominik ; Stamer, Florian ; Lanza, Gisela. / Conceptual Framework for Synthetic Data Generation in Remanufacturing. Production at the Leading Edge of Technology: Proceedings of the 14th Congress of the German Academic Association for Production Technology (WGP), Chemnitz University of Technology, December 2024. editor / Welf-Guntram Drossel ; Steffen Ihlenfeldt ; Martin Dix. Springer Nature, 2025. pp. 317-325 (Lecture Notes in Production Engineering).

@inbook{58f790f8886f4104a5e96e53b1de4edc,

title = "Conceptual Framework for Synthetic Data Generation in Remanufacturing",

abstract = "Remanufacturing requires effective defect detection, but data scarcity and defect variability challenge ML model training. This paper presents a synthetic data generation pipeline focusing on bevel gears, simulating geometric defects like broken teeth, and applying scene randomization to diversify the dataset. The pipeline successfully generates synthetic data for geometric defects, supporting automated segmentation and annotation. However, the current results are limited to geometric defects. Future work will expand to surface and material defects using MDL graphs to improve the pipeline{\textquoteright}s applicability. In conclusion, while the pipeline shows potential, real-world validation is necessary to confirm its robustness in remanufacturing.",

keywords = "optical inspection, remanufacturing, synthetical data, Engineering",

author = "Dominik Koch and Florian Stamer and Gisela Lanza",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.",

year = "2025",

doi = "10.1007/978-3-031-86893-1\_35",

language = "English",

isbn = "978-3-031-86892-4",

series = "Lecture Notes in Production Engineering",

publisher = "Springer Nature",

pages = "317--325",

editor = "Welf-Guntram Drossel and Steffen Ihlenfeldt and Martin Dix",

booktitle = "Production at the Leading Edge of Technology",

address = "Singapore",

}

Koch, D, Stamer, F & Lanza, G 2025, Conceptual Framework for Synthetic Data Generation in Remanufacturing. in W-G Drossel, S Ihlenfeldt & M Dix (eds), Production at the Leading Edge of Technology: Proceedings of the 14th Congress of the German Academic Association for Production Technology (WGP), Chemnitz University of Technology, December 2024. Lecture Notes in Production Engineering, vol. Part F679, Springer Nature, pp. 317-325. https://doi.org/10.1007/978-3-031-86893-1_35

Conceptual Framework for Synthetic Data Generation in Remanufacturing. / Koch, Dominik; Stamer, Florian; Lanza, Gisela.
Production at the Leading Edge of Technology: Proceedings of the 14th Congress of the German Academic Association for Production Technology (WGP), Chemnitz University of Technology, December 2024. ed. / Welf-Guntram Drossel; Steffen Ihlenfeldt; Martin Dix. Springer Nature, 2025. p. 317-325 (Lecture Notes in Production Engineering; Vol. Part F679).

Research output: Contributions to collected editions/works › Article in conference proceedings › Research › peer-review

TY - CHAP

T1 - Conceptual Framework for Synthetic Data Generation in Remanufacturing

AU - Koch, Dominik

AU - Stamer, Florian

AU - Lanza, Gisela

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025

Y1 - 2025

N2 - Remanufacturing requires effective defect detection, but data scarcity and defect variability challenge ML model training. This paper presents a synthetic data generation pipeline focusing on bevel gears, simulating geometric defects like broken teeth, and applying scene randomization to diversify the dataset. The pipeline successfully generates synthetic data for geometric defects, supporting automated segmentation and annotation. However, the current results are limited to geometric defects. Future work will expand to surface and material defects using MDL graphs to improve the pipeline’s applicability. In conclusion, while the pipeline shows potential, real-world validation is necessary to confirm its robustness in remanufacturing.

AB - Remanufacturing requires effective defect detection, but data scarcity and defect variability challenge ML model training. This paper presents a synthetic data generation pipeline focusing on bevel gears, simulating geometric defects like broken teeth, and applying scene randomization to diversify the dataset. The pipeline successfully generates synthetic data for geometric defects, supporting automated segmentation and annotation. However, the current results are limited to geometric defects. Future work will expand to surface and material defects using MDL graphs to improve the pipeline’s applicability. In conclusion, while the pipeline shows potential, real-world validation is necessary to confirm its robustness in remanufacturing.

KW - optical inspection

KW - remanufacturing

KW - synthetical data

KW - Engineering

UR - https://www.scopus.com/pages/publications/105011695302

U2 - 10.1007/978-3-031-86893-1_35

DO - 10.1007/978-3-031-86893-1_35

M3 - Article in conference proceedings

AN - SCOPUS:105011695302

SN - 978-3-031-86892-4

SN - 978-3-031-86895-5

T3 - Lecture Notes in Production Engineering

SP - 317

EP - 325

BT - Production at the Leading Edge of Technology

A2 - Drossel, Welf-Guntram

A2 - Ihlenfeldt, Steffen

A2 - Dix, Martin

PB - Springer Nature

ER -

Koch D, Stamer F, Lanza G. Conceptual Framework for Synthetic Data Generation in Remanufacturing. In Drossel WG, Ihlenfeldt S, Dix M, editors, Production at the Leading Edge of Technology: Proceedings of the 14th Congress of the German Academic Association for Production Technology (WGP), Chemnitz University of Technology, December 2024. Springer Nature. 2025. p. 317-325. (Lecture Notes in Production Engineering). doi: 10.1007/978-3-031-86893-1_35