Dynamic data-driven railway bridge construction knowledge graph update method

被引:6
作者
Lai, Jianbo [1 ]
Zhu, Jun [1 ,2 ]
Guo, Yukun [1 ]
You, Jigang [1 ]
Xie, Yakun [1 ]
Wu, Jianlin [1 ]
Hu, Ya [1 ]
机构
[1] Southwest Jiaotong Univ, Fac Geosci & Environm Engn, Chengdu, Peoples R China
[2] Southwest Jiaotong Univ, Fac Geosci & Environm Engn, Chengdu 611756, Peoples R China
基金
中国国家自然科学基金;
关键词
MANAGEMENT; ONTOLOGY;
D O I
10.1111/tgis.13111
中图分类号
P9 [自然地理学]; K9 [地理];
学科分类号
0705 ; 070501 ;
摘要
Effectively integrating and correlating multisource data involved in the bridge construction process is crucial for the improvement of the bridge informatization level. In the current issues of dynamic numerous data and low information sharing between different engineering departments, the traditional information management methods are inefficient in providing comprehensive and accurate data support for construction safety. Focusing on the bridge construction stage, this article proposes a dynamic data-driven construction method of railway bridge construction knowledge graph (KG) in combination with dynamic data (materials, personnel, equipment and sensors) in the construction process and KG technology. By taking a railway bridge as a case, the study develops a prototype system and analyzes the effectiveness of bridge construction KG in material traceability, personnel and equipment management and construction safety guidance, which can provide comprehensive and accurate data support for bridge construction management and construction optimization. The results show that: (1) bridge construction KG that takes into account the dynamic features of bridge projects can effectively integrate multiple elements; (2) the bridge construction KG is dynamically updated through real-time comparison and advance prediction based on the dynamic data collected by multi-sensing equipment at the construction site, and can provide effective data support for guiding bridge construction safety; and (3) the construction management prototype system based on railway bridge construction KG can provide accurate data support for material traceability, personnel and equipment management and assisted risk event decision-making. The results of the comparative experiment between the KG group and the spreadsheet group showed that utilizing the KG saved approximately 50% of time and achieved a 20% higher accuracy rate in the material traceability task compared to the spreadsheet group. In general, this study proposes a dynamic data-driven construction method of railway bridge construction KG, which can effectively realize the effective integration and management of multisource data in the bridge construction process, provide the necessary scientific basis for fine bridge management, and help to improve bridge informatization management level.
引用
收藏
页码:2099 / 2117
页数:19
相关论文
共 50 条
  • [41] ProCAVIAR: Hybrid Data-Driven and Probabilistic Knowledge-Based Activity Recognition
    Bettini, Claudio
    Civitarese, Gabriele
    Giancane, Davide
    Presotto, Riccardo
    IEEE ACCESS, 2020, 8 : 146876 - 146886
  • [42] A novel data-driven approach for proactive risk assessment in shield tunnel construction
    Zhou, Xin-Hui
    Shen, Shui-Long
    Zhou, Annan
    TRANSPORTATION GEOTECHNICS, 2025, 50
  • [43] Automatic Knowledge Graph Construction Based on Relational Data of Power Terminal Equipment
    Su, Zheng
    Hao, Mukai
    Zhang, Qiang
    Chai, Bo
    Zhao, Ting
    2020 5TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION SYSTEMS (ICCCS 2020), 2020, : 761 - 765
  • [44] DDE KG Editor: A data service system for knowledge graph construction in geoscience
    Hou, Chengbin
    Liu, Kaichuang
    Wang, Tianheng
    Shi, Shunzhong
    Li, Yan
    Zhu, Yunqiang
    Hu, Xiumian
    Wang, Chengshan
    Zhou, Chenghu
    Lv, Hairong
    GEOSCIENCE DATA JOURNAL, 2024, 11 (04): : 1073 - 1085
  • [45] A Heterogeneous Geospatial Data Retrieval Method Using Knowledge Graph
    Liu, Junnan
    Liu, Haiyan
    Chen, Xiaohui
    Guo, Xuan
    Zhao, Qingbo
    Li, Jia
    Kang, Lei
    Liu, Jianxiang
    SUSTAINABILITY, 2021, 13 (04) : 1 - 21
  • [46] A bilevel data-driven method for sewer deposit prediction under uncertainty
    Liu, Wenli
    He, Yexin
    Liu, Zihan
    Luo, Hanbin
    Liu, Tianxiang
    WATER RESEARCH, 2023, 231
  • [47] A causality based feature selection approach for data-driven dynamic security assessment
    Bellizio, Federica
    Cremer, Jochen L.
    Sun, Mingyang
    Strbac, Goran
    ELECTRIC POWER SYSTEMS RESEARCH, 2021, 201 (201)
  • [48] Automating Common Data Integration for Improved Data-Driven Decision-Support System in Industrial Construction
    Wu, Lingzi
    Li, Zuofu
    AbouRizk, Simaan
    JOURNAL OF COMPUTING IN CIVIL ENGINEERING, 2022, 36 (02)
  • [49] Data-Driven Construction of User Utility Functions from Radio Connection Traces in LTE
    Garcia, Antonio J.
    Gijon, Carolina
    Toril, Matias
    Luna-Ramirez, Salvador
    ELECTRONICS, 2021, 10 (07)
  • [50] Data-Driven Approach to Scenario Determination for VR-Based Construction Safety Training
    Mo, Yunjeong
    Zhao, Dong
    Du, Jing
    Liu, Weihua
    Dhara, Ajay
    CONSTRUCTION RESEARCH CONGRESS 2018: SAFETY AND DISASTER MANAGEMENT, 2018, : 116 - 125