Skip to main navigation Skip to search Skip to main content

Lifecycle-aware knowledge graphs with human-in-the-loop agentic retrieval for automotive manufacturing

  • Chao Yang
  • , Ying Liu*
  • , Hao Dong
  • , Peixing Zhang
  • , Jinzhi Lu
  • , Bing Zhu
  • , Risto Ojala
  • , Kari Tammi
  • *Corresponding author for this work

Research output: Contribution to journal › Article › Scientific › peer-review

1 Citation (Scopus)
12 Downloads (Pure)

Abstract

Modern automotive manufacturing demands agile coordination; however, operational decision-making remains severely hindered by data fragmentation across siloed enterprise systems and the lack of intuitive information retrieval mechanisms. While graph-based models offer a promising foundation for structural data integration, querying them requires formal languages (e.g., Cypher) that remain largely inaccessible to domain experts. To address these challenges, this paper proposes a lifecycle-aware knowledge graph schema and an agentic retrieval framework for cross-domain integration and retrieval in automotive manufacturing. First, we introduce a multi-dimensional graph schema that unifies automotive manufacturing knowledge across product design, process planning, production organization, and shop-floor execution. To faithfully capture the complexity of such heterogeneous data, the schema explicitly separates manufacturing entities into four complementary dimensions: persistent identity, engineering specification, released version, and runtime state. Second, we develop a schema-grounded, complexity-adaptive agentic retrieval framework designed for condition-based structural retrieval to enable reliable and flexible access to domain knowledge. By integrating Large Language Models (LLMs) reasoning with targeted human-in-the-loop confirmation gates, the framework translates natural language queries into verifiable and executable subgraph matching and path traversals. The proposed approach is validated using real-world data sources. Structural evaluations demonstrate its capability to support cross-domain integration and multi-hop query traversal, while quantitative experiments show that the agentic retrieval pipeline significantly outperforms conventional generative baselines, achieving an execution accuracy of 95.0% on a rigorous industrial benchmark. Overall, this work provides a structured foundation for lifecycle-aware knowledge representation and reliable graph-based retrieval in automotive manufacturing.

Original languageEnglish
Article number105122
JournalAdvanced Engineering Informatics
Volume76
DOIs
Publication statusPublished - Nov 2026
Publication typeA1 Journal article-refereed

Funding

We acknowledge the funding provided by the Finnish Henry Ford Foundation , and the AiWo project , a co-innovation project funded by Business Finland .

Keywords

  • Agentic retrieval
  • Automotive manufacturing
  • Human-in-the-loop
  • Knowledge graph
  • Large language models

Publication forum classification

  • Publication forum level 1

Fingerprint

Dive into the research topics of 'Lifecycle-aware knowledge graphs with human-in-the-loop agentic retrieval for automotive manufacturing'. Together they form a unique fingerprint.

Cite this