Interoperable information modelling leveraging asset administration shell and large language model for quality control toward zero defect manufacturing

被引:0
作者
Shi, Dachuan [1 ]
Liedl, Philipp [2 ]
Bauernhansl, Thomas [3 ]
机构
[1] Fraunhofer Inst Mfg Engn & Automat IPA, Nobelstr 12, D-70569 Stuttgart, Germany
[2] Steinbeis Beratungszentrum Technol Transformat, Baumreute 31, D-73730 Esslingen, Germany
[3] Univ Stuttgart, Inst Industrielle Fertigung & Fabrikbetrieb IFF, Nobelstr 12, D-70569 Stuttgart, Germany
关键词
Interoperability; Large language model; Ontology; Asset administration shell; Zero defect manufacturing; Information modelling; Quality control; Industry; 4.0; SYSTEM;
D O I
10.1016/j.jmsy.2024.10.011
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
In the era of Industry 4.0, Zero Defect Manufacturing (ZDM) has emerged as a prominent strategy for quality improvement, emphasizing data-driven approaches for defect prediction, prevention, and mitigation. The success of ZDM heavily depends on the availability and quality of data typically collected from diverse and heterogeneous sources during production and quality control, presenting challenges in data interoperability. Addressing this, we introduce a novel approach leveraging Asset Administration Shell (AAS) and Large Language Models (LLMs) for creating interoperable information models that incorporate semantic contextual information to enhance the interoperability of data integration in the quality control process. AAS, initiated by German industry stakeholders, shows a significant advancement in information modeling, blending ontology and digital twin concepts for the virtual representation of assets. In this work, we develop a systematic, use-case-driven methodology for AAS-based information modeling. This methodology guides the design and implementation of AAS models, ensuring model properties are presented in a unified structure and reference external standardized vocabularies to maintain consistency across different systems. To automate this referencing process, we propose a novel LLM-based algorithm to semantically search model properties within a standardized vocabulary repository. This algorithm significantly reduces manual intervention in model development. A case study in the injection molding domain demonstrates the practical application of our approach, showcasing the integration and linking of product quality and machine process data with the help of the developed AAS models. Statistical evaluation of our LLM-based semantic search algorithm confirms its efficacy in enhancing data interoperability. This methodology offers a scalable and adaptable solution for various industrial use cases, promoting widespread data interoperability in the context of Industry 4.0.
引用
收藏
页码:678 / 696
页数:19
相关论文
共 60 条
  • [1] 15926browser, 2023, RDL Stands for Reference Data Library (search screen)
  • [2] Industry 4.0 In-Line AI Quality Control of Plastic Injection Molded Parts
    Aminabadi, Saeid Saeidi
    Tabatabai, Paul
    Steiner, Alexander
    Gruber, Dieter Paul
    Friesenbichler, Walter
    Habersohn, Christoph
    Berger-Weber, Gerald
    [J]. POLYMERS, 2022, 14 (17)
  • [3] [Anonymous], 2016, VDI 4499 Part 3:2016-04, Digital Factory-Data Management and System Architectures, Guideline
  • [4] Neural Networks for Entity Matching: A Survey
    Barlaug, Nils
    Gulla, Jon Atle
    [J]. ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2021, 15 (03)
  • [5] BaSyxEclipse Ba, 2024, Syx Java V2 SDK
  • [6] Online Prediction of Molded Part Quality in the Injection Molding Process Using High-Resolution Time Series
    Bogedale, Lucas
    Doerfel, Stephan
    Schrodt, Alexander
    Heim, Hans-Peter
    [J]. POLYMERS, 2023, 15 (04)
  • [7] Boss B., 2020, DIGITAL TWIN ASSET A
  • [8] A Model for Predictive Maintenance Based on Asset Administration Shell
    Cavalieri, Salvatore
    Salafia, Marco Giuseppe
    [J]. SENSORS, 2020, 20 (21) : 1 - 20
  • [9] Ontology-Driven Learning of Bayesian Network for Causal Inference and Quality Assurance in Additive Manufacturing
    Chen, Ruimin
    Lu, Yan
    Witherell, Paul
    Simpson, Timothy W.
    Kumara, Soundar
    Yang, Hui
    [J]. IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (03) : 6032 - 6038
  • [10] DIN, DIN ISO 2859-1:2014-08