Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Recurso digital |
| Langue: | |
| Publié: |
Zenodo
2025
|
| Accès en ligne: | https://doi.org/10.5281/zenodo.16940080 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866902006055043072 |
|---|---|
| author | Seipolt, Arne |
| author_facet | Seipolt, Arne |
| contents | <p><strong>Abstract</strong></p> <p>This paper presents a systematic literature review on the use of digital twins in manufacturing, with the goal of developing a comprehensive taxonomy that synthesizes existing categorizations. Given the increasing complexity and volume of literature in this domain, conventional review methods are becoming insufficient. To address this challenge, the study applies a novel approach named retrieval augmented generation. This is a technique that combines large language models with real-time information retrieval, enabling the automated identification and summarization of typologies across a broad corpus of publications. A total of 1,354 publications were initially screened, leading to 144 distinct categorizations relevant to digital twins in industrial contexts. The resulting taxonomy classifies digital twins along multiple dimensions, including life cycle stages, physical domain and hierarchy levels, model characteristics, digital thread connectivity and deployment strategies. This work provides both researchers and practitioners with a structured approach to understanding and implementing digital twins in manufacturing environments, as well as a guideline to completely describe a specific implementation. The taxonomy serves as a foundation for future research and as a practical tool for industrial applications, since it defines design decisions, which have to be made.</p> <p><strong>Supplementary Data</strong></p> <p>This Supplementary Data contains an .xlsx file, which gives Details about the Liteature Research. The Sheet "Summary" contains the AI Categorization and the AI Summary for every paper. Since four different hyperparameter combinations where used, this sheet summarizes the distinguished sheets, which where created by the RAG-Framework. Furthermore, it contains the results of the Summary Check, where the paper was checked by a human while only considering the AI-Summary. During the Detail Check, the complete paper was considered and a preliminary dimension and categories for the categorization created in the paper are stated. Both Checks contain inlude- and exclude criteria. The Column "Validation" contains a check, where 10 random papers in which the AI has not found a Categorization, whre checked in Detail if they really don´t contain a categorization. "Comparison to Fulltext" Contains the result of a fulltext-search for the keywords "Taxonomy", "Categorization", "Classification", and "Typology", while only papers not found by the AI are considered. It furthermore contains a detail check, if the paper contains a categorization of digital twins.</p> <p>The Sheet "Include - Exclude" contains a Summary of the include- and exclude-criteria.</p> <p>The Sheet "Inter Rater Agreement" contains the calculation of the inter rater agreement, which was used to evaluate the RAG-based literature research.</p> <p>The Sheets "1. Iteration" and "2. Iteration" contain the classification of DT implementations, which where used to evaluate the Taxonomy in the 1. and 2. iteration.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_16940080 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Supplementary Data for: Digital Twins in Manufacturing: A Systematic Literature Review with Retrieval-Augmented Generation Seipolt, Arne <p><strong>Abstract</strong></p> <p>This paper presents a systematic literature review on the use of digital twins in manufacturing, with the goal of developing a comprehensive taxonomy that synthesizes existing categorizations. Given the increasing complexity and volume of literature in this domain, conventional review methods are becoming insufficient. To address this challenge, the study applies a novel approach named retrieval augmented generation. This is a technique that combines large language models with real-time information retrieval, enabling the automated identification and summarization of typologies across a broad corpus of publications. A total of 1,354 publications were initially screened, leading to 144 distinct categorizations relevant to digital twins in industrial contexts. The resulting taxonomy classifies digital twins along multiple dimensions, including life cycle stages, physical domain and hierarchy levels, model characteristics, digital thread connectivity and deployment strategies. This work provides both researchers and practitioners with a structured approach to understanding and implementing digital twins in manufacturing environments, as well as a guideline to completely describe a specific implementation. The taxonomy serves as a foundation for future research and as a practical tool for industrial applications, since it defines design decisions, which have to be made.</p> <p><strong>Supplementary Data</strong></p> <p>This Supplementary Data contains an .xlsx file, which gives Details about the Liteature Research. The Sheet "Summary" contains the AI Categorization and the AI Summary for every paper. Since four different hyperparameter combinations where used, this sheet summarizes the distinguished sheets, which where created by the RAG-Framework. Furthermore, it contains the results of the Summary Check, where the paper was checked by a human while only considering the AI-Summary. During the Detail Check, the complete paper was considered and a preliminary dimension and categories for the categorization created in the paper are stated. Both Checks contain inlude- and exclude criteria. The Column "Validation" contains a check, where 10 random papers in which the AI has not found a Categorization, whre checked in Detail if they really don´t contain a categorization. "Comparison to Fulltext" Contains the result of a fulltext-search for the keywords "Taxonomy", "Categorization", "Classification", and "Typology", while only papers not found by the AI are considered. It furthermore contains a detail check, if the paper contains a categorization of digital twins.</p> <p>The Sheet "Include - Exclude" contains a Summary of the include- and exclude-criteria.</p> <p>The Sheet "Inter Rater Agreement" contains the calculation of the inter rater agreement, which was used to evaluate the RAG-based literature research.</p> <p>The Sheets "1. Iteration" and "2. Iteration" contain the classification of DT implementations, which where used to evaluate the Taxonomy in the 1. and 2. iteration.</p> |
| title | Supplementary Data for: Digital Twins in Manufacturing: A Systematic Literature Review with Retrieval-Augmented Generation |
| url | https://doi.org/10.5281/zenodo.16940080 |