Nothing Special   »   [go: up one dir, main page]

skip to main content
10.1145/3627915.3627917acmotherconferencesArticle/Chapter ViewAbstractPublication PagescsaeConference Proceedingsconference-collections
research-article

A BERT-based Framework for Production Line Fault Maintenance Knowledge Graph Construction

Published: 21 December 2023 Publication History

Abstract

The manufacturing industry is currently experiencing a wave of digitalization and intelligent transformation. With continuous upgrades of production equipment and systems, the complexity and diversity of production line faults are continuously increasing. Moreover, there is a weak correlation among fault-related information and a low utilization rate of fault knowledge. In light of the problems, an automatic knowledge graph construction framework is proposed for production line fault maintenance. The framework employs both BERT-based models and template-based methods to extract entities and relationships from text data. First, by obtaining relevant engineering documents from the production line and considering their characteristics, a pattern layer of the production line fault maintenance knowledge graph (PLFMKG) is constructed. Then, the BERT-BILSTM-CRF deep learning algorithm is applied to extract corresponding entities from the engineering documents related to production line faults. Subsequently, a template-based method is employed to extracting relationships. Meanwhile, a Chinese named entity recognition dataset is also established. consisting of three hundred sentences from engineering documents related to production line faults. Experimental results show that the BERT-based knowledge extraction method outperforms classic BiLSTM-CRF and BERT-LSTM-CRF models in processing production line fault maintenance data, validating its effectiveness. Finally, we visualize the constructed knowledge graph using the Neo4j graph database. The production line fault maintenance knowledge graph provides data support for subsequent production line fault reasoning and decision-making processes.

References

[1]
Wu C., Zhang L., Tang L.X., (2022). Construction and Application for Aircraft Engine Lubrication System Faults[J]. Journal of Beijing University of Aeronautics and Astronautics, 1-14.
[2]
Zhang D.H., Liu Z.Y., (2021). Review of the Research Status and Application Prospects of Knowledge Graphs in the Field of Intelligent Manufacturing[J]. Journal of Mechanical Engineering, 57(05): 90-113.
[3]
Sun J.D., Gu X.S., Li Y., (2017). Research on Chinese Entity Relation Extraction Algorithm Based on COAE2016 Dataset[J]. Journal of Shandong University (Natural Science), 52(09): 7-12.
[4]
Zhou Y. (2022). Research on Visual Analysis Methods for Domain Knowledge Graphs[D]. Southwest University of Science and Technology.
[5]
Zhai Z.H., Hu J.P., Huang Z.Q., (2021). Research on Construction and Application of Knowledge Graph for Industrial Equipment Failure Handling[J]. Computer Engineering and Applications, 1-16.
[6]
Guo L., Yan F., Li T., (2022). An automatic method for constructing machining process knowledge base from knowledge graph[J]. Robotics and Computer-Integrated Manufacturing, 73.
[7]
Buchgeher G., Gabauer D., Martinez-Gil J., (2021). Knowledge Graphs in Manufacturing and Production: A Systematic Literature Review[J]. IEEE Access, 9: 55537-55554.
[8]
Li G., Li Y.Q., Wang H.T., (2022). Knowledge Graph for Power Equipment Health Management: Basic Concepts, Key Technologies, and Research Progress[J]. Automation of Electric Power Systems, 46(03): 1-13.
[9]
Wang H.F., Qi G.L., Chen H.J., (2019). Knowledge Graph: Methods, Practices, and Applications[M].
[10]
Deliang Z., Weihua Z. and Jianming S. (2023). Construction of transformer substation fault knowledge graph based on a depth learning algorithm[J]. International Journal of Modeling, Simulation, and Scientific Computing, 14(01).
[11]
Hicham H., Imran K., Mohammad A., (2020). SemKoRe: Improving Machine Maintenance in Industrial IoT with Semantic Knowledge Graphs[J]. Applied Sciences-Basel, 10(18).
[12]
Wang Y., Wang Y.W and Ye Y. (2022). A Novel Method for Constructing Knowledge Graph of Railway Safety Risk[C]. CSAE'22, New York, NY, USA.
[13]
Bin Z., Bao H., Xinghai G., (2021). An end-to-end tabular information-oriented causality event evolutionary knowledge graph for manufacturing documents[J]. Advanced Engineering Informatics, 50.
[14]
Chen Y.F. (2021). Data-Driven Knowledge Graph Construction and Predictive Maintenance for Machine Tool Fault Diagnosis[D]. Chang'an University.
[15]
Chang Z.Y., Tao L.Z., Li J.J., (2018). Research on Knowledge Reuse Method for Machining Process Based on Machining Intention[J]. Journal of Mechanical Engineering, 54(03): 160-168.
[16]
Li X.L., Zhang S.S., Huang R., (2019). Methodology for Building Process Knowledge Graph for Process Reuse[J]. Journal of Northwestern Polytechnical University, 37(06): 1174-1183.
[17]
Hua B. (2022). Research on Knowledge Graph Construction and Semantic Similarity Measurement for Metallurgical Equipment Maintenance Records[D]. Donghua University.
[18]
U. Dombrowski, A. Reiswich and C. Imdahl (2019). Knowledge Graphs for an Automated Information Provision in the Factory Planning[C]. 2019 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM).
[19]
Ren T. (2021) Research and Application of OPC UA Information Model based on Knowledge Graph[D]. Zhejiang University.
[20]
Xu Q. (2020). Knowledge Graph-Based CNC Fault Diagnosis System[D]. Beijing University of Posts and Telecommunications.
[21]
Liu H., Li D., Yan L., (2021). Machinery Fault Diagnosis Based on Deep Learning for Time Series Analysis and Knowledge Graphs[J]. Journal of Signal Processing Systems, 93(12): 1433-1455.
[22]
Cai L., Wang S.T., Liu J.H., (2020). A Review of Data Annotation Research[J]. Journal of Software, 31(02): 302-320.
[23]
Huang Z., Xu W. and Yu K. (2015). Bidirectional LSTM-CRF Models for Sequence Tagging. https://doi.org/10.48550/arXiv.1508.01991

Index Terms

  1. A BERT-based Framework for Production Line Fault Maintenance Knowledge Graph Construction

    Recommendations

    Comments

    Please enable JavaScript to view thecomments powered by Disqus.

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    CSAE '23: Proceedings of the 7th International Conference on Computer Science and Application Engineering
    October 2023
    358 pages
    ISBN:9798400700590
    DOI:10.1145/3627915
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 21 December 2023

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Deep Learning
    2. Graph Database
    3. Knowledge Extraction
    4. Knowledge Graph

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    CSAE 2023

    Acceptance Rates

    Overall Acceptance Rate 368 of 770 submissions, 48%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 48
      Total Downloads
    • Downloads (Last 12 months)48
    • Downloads (Last 6 weeks)8
    Reflects downloads up to 21 Nov 2024

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media