列控车载设备故障知识图谱的重叠三元组联合抽取方法

张凝; 张振海

doi:10.13238/j.issn.1004-2954.202407180006

English Version

您当前的位置：

首页 >

文章列表页 >

列控车载设备故障知识图谱的重叠三元组联合抽取方法

通信/信号 | 更新时间：2026-06-22

- 列控车载设备故障知识图谱的重叠三元组联合抽取方法
- Joint Extraction Method for Overlapping Triples in Fault Knowledge Graph of CTCS On-Board Equipment
- 铁道标准设计 2026年70卷第5期页码：219-229
- 作者机构：
  
  兰州交通大学自动化与电气工程学院，兰州 730070
- 作者简介：
  
  作者简介：张凝（2000—），女，硕士研究生，主要从事知识图谱和故障诊断研究工作，E-mail: 1026054855@qq.com。
  张振海（1983—），男，教授，2014年毕业于兰州交通大学交通信息工程及控制专业，工学博士，主要从事交通信息工程及控制和图像处理研究工作，E-mail: 764411629@qq.com。
- 基金信息：
  
  国家自然科学基金项目(61763025);甘肃省重点研发计划项目(2YF7GA141)
- DOI：10.13238/j.issn.1004-2954.202407180006
  中图分类号： U284.95;U284.92
- 收稿：2024-07-18，
  
  修回：2024-09-09，
  
  网络首发：2025-03-06，
  
  纸质出版：2026-05-20
- 稿件说明：
移动端阅览
张凝, 张振海. 列控车载设备故障知识图谱的重叠三元组联合抽取方法[J]. 铁道标准设计, 2026,70(5):219-229.

ZHANG Ning, ZHANG Zhenhai. Joint Extraction Method for Overlapping Triples in Fault Knowledge Graph of CTCS On-Board Equipment[J]. Railway Standard Design, 2026, 70(5): 219-229.
张凝, 张振海. 列控车载设备故障知识图谱的重叠三元组联合抽取方法[J]. 铁道标准设计, 2026,70(5):219-229. DOI： 10.13238/j.issn.1004-2954.202407180006.

ZHANG Ning, ZHANG Zhenhai. Joint Extraction Method for Overlapping Triples in Fault Knowledge Graph of CTCS On-Board Equipment[J]. Railway Standard Design, 2026, 70(5): 219-229. DOI： 10.13238/j.issn.1004-2954.202407180006.

摘要

【目的】

车载设备作为列控系统的核心，利用知识图谱研究故障案例，实现对其故障原因及处理方案的快速准确定位，对铁路行车安全和运输效率至关重要。

【方法】

针对其中关键步骤知识抽取采用传统流水线方法导致错误积累以及交互性差等问题，提出一种基于序列标注策略的重叠三元组联合抽取方法。首先，依据定义的实体与关系类型，采用“位置-实体-关系-角色”的序列标注策略，实现重叠三元组联合标注；其次，构建FMBCR（FaultRoBERTa-MHSA-BiLSTM-CRF incorporating Regularization Methods）模型准确抽取列控车载设备故障文本的全局语义信息，通过增加一种基于正则化模块READ（REgularization Method with Adversarial Training and Dropout）的KL（Kullback-Leibler

）发散损失算法优化模型的预测性能；最后，以列控车载设备故障数据为例进行实验分析与知识图谱可视化构建。

【结果】

通过充分的对比实验以及消融实验，结果表明，所提方法实现小样本重叠三元组的联合抽取，且抽取性能较传统方法有显著提升，FMBCR模型较现在广泛使用的CASREL联合抽取模型，准确率、召回率和F1值分别提升3.0%、4.3%和3.7%。

【结论】

研究结果可为列控车载设备故障维修智能信息检索和辅助决策等高级应用提供支持。

Abstract

[

Objective

]

As the core of the Chinese Train Control System（CTCS）

on-board equipment utilizes the knowledge graph to analyze fault cases and realize rapid and accurate identification of fault causes and treatment solutions

which is crucial for railway safety and transportation efficiency. [

Methods

]

To address issues such as error accumulation and poor interactivity caused by traditional pipeline methods in knowledge extraction

a joint extraction method for overlapping triples based on a sequence labeling strategy was proposed. Firstly

based on the defined entity and relationship types

a“position-entity-relationship-role” sequence labeling strategy was employed to achieve the joint labeling of overlapping triples. Secondly

the FMBCR（FaultRoBERTa-MHSA-BiLSTM-CRF incorporating regularization methods）model was constructed to accurately extract the global semantic information from fault texts of CTCS on-board equipment

and its predictive performance was optimized by incorporating a KL（Kullback-Leibler）divergence loss algorithm based on the regularization module READ（REgularization method with adversarial training and dropout）. Finally

experimental analysis and knowledge graph visualization construction were conducted

using fault data of CTCS on-board equipment as an example. [

Results

]

Through sufficient comparative experiments and ablation experiments

the results showed that the proposed method realized the joint extraction of overlapping triples under small-sample conditions

and the extraction performance was significantly improved compared with traditional methods. Compared with the widely used CASREL joint extraction model

the FMBCR model improved the precision

recall

and

1 score by 3.0%

4.3%

and 3.7%

respectively. [

Conclusion

]

The research findings provide support for advanced applications such as intelligent information retrieval and decision-making assistance for fault maintenance of CTCS on-board equipment.

关键词

Keywords

references

王晴雯，张振海．基于知识图谱的信号设备故障诊断方法[J]．铁道标准设计，2022,66（12）:149-156.

WANG Qingwen, ZHANG Zhenhai. Fault Diagnosis Method of Signal Equipment Based on Knowledge Graph[J]. Railway Standard Design, 2022,66（12）:149-156.

ZHAO S D, SU C, LU Z Y, et al. Recent Advances in Biomedical Literature Mining[J]. Briefings in Bioinformatics, 2021,22（3）:56-57.

薛莲，姚新文，郑启明，等．高铁列控车载设备故障知识图谱构建方法研究[J]．铁道科学与工程学报，2023,20（1）:34-43.

XUE Lian, YAO Xinwen, ZHENG Qiming, et al. Research on Construction Method of Fault Knowledge Graph of CTCS On-board Equipment [J]. Journal of Railway Science and Engineering, 2023，20（1）:34-43.

ZHENG Q H, SAPONARA S, TIAN X Y, et al. A Real-time Constellation Image Classification Method of Wireless Communication Signals Based on the Lightweight Network MobileViT [J]. Cognitive Neurodynamics, 2024,18（2）:659-671.

ZHENG Q H, TIAN X Y, YU Z G, et al. MobileRaT: a Lightweight Radio Transformer Method for Automatic Modulation Classification in Drone Communication Systems[J]. Drones, 2023,7（10）:596.

刘丹，张振海，翟秋宇，等．列控车载设备故障诊断的知识图谱构建与应用[J]．铁道标准设计，2025,69（5）:184-192.

LIU Dan, ZHANG Zhenhai, ZHAI Qiuyu, et al. Knowledge Graph Construction and Application for Fault Diagnosis of CTCS On-board E quipment[J]. Railway Standard Design,2025,69（5）:184-192.

万莎．基于知识图谱的联锁系统故障诊断研究[D]．成都：西南交通大学，2022.

WAN Sha. Research on Fault Diagnosis of Interlocking System Based on Knowledge Graph[D]. Chengdu: Southwest Jiaotong University，2022.

HIDALGO H L, BOEGLIN M, KAHN D, et al. Adapting PromptORE for Modern History: Information Extraction from Hispanic Monarchy Documents of the XVIth Century [EB/OL]. 2024: arXiv:2406.00027.https://arxiv. org/abs/2406.00027.

蒋萌，杨春成，尚海滨，等．地理实体与重叠空间关系联合抽取的改进CasRel模型法[J]．测绘学报，2023,52（8）:1387-1397.

JIANG Meng, YANG Chuncheng, SHANG Haibin, et al. Improved CasRel Model for Joint Extraction of Geographic Entity and Overlapping Space Relation[J]. Acta Geodaetica et Cartographica Sinica，2023,52（8）:1387-1397.

张仰森，刘帅康，刘洋，等．基于深度学习的实体关系联合抽取研究综述[J]．电子学报，2023,51（4）:1093-1116.

ZHANG Yangsen, LIU Shuaikang, LIU Yang, et al. Joint Extraction of Entities and Relations Based on Deep Learning: a Survey[J]. Acta Electronica Sinica, 2023,51（4）:1093-1116.

MIWA M, BANSAL M. End-to-end Relation Extraction Using LSTMS on Sequences and Tree Structures[C]∥Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics（Volume 1: Long Papers）. Berlin, Germany. Stroudsburg, PA, USA: Association for Computational Linguistics,2016:1105-1116.

ZENG D J, ZHANG H R, LIU Q Y. CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-task Learning [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020,34（5）:9507-9514.

李代祎，李忠良，严丽．一种面向中文的实体关系联合抽取方法研究[J]．小型微型计算机系统，2022,43（12）:2479-2486.

LI Daiyi, LI Zhongliang, YAN Li. Research on Chinese-oriented Entity Relation Joint Extraction Method[J]. Journal of Chinese Computer Systems, 2022,43（12）:2479-2486.

WEI Z P, SU J L, WANG Y, et al. A Novel Cascade Binary Tagging Framework for Relational Triple Extraction[EB/OL]. 2019: arXiv:1909.03227.https://arxiv. org/abs/1909.03227

王传栋，徐娇，张永．实体关系抽取综述[J]．计算机工程与应用，2020,56（12）:25-36.

WANG Chuandong, XU Jiao, ZHANG Yong. Survey of Entity Relation Extraction[J]. Computer Engineering and Applications,2020，56（12）:25-36.

ZHENG S C, WANG F, BAO H Y, et al. Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme[C]∥Proceedings of the 55th Annual Meeting of the Association forComputational Linguistics（Volume1: Long Papers）. Vancouver, Canada. Stroudsburg，PA, USA: Association for Computational Linguistics, 2017:1227-1236.

吴赛赛，周爱莲，谢能付，等．基于深度学习的作物病虫害可视化知识图谱构建[J]．农业工程学报，2020,36（24）:177-185.

WU Saisai, ZHOU Ailian, XIE Nengfu, et al. Construction of Visualization Domain-specific Knowledge Graph of Crop Diseases and Pests Based on Deep Learning[J]. Transactions of the Chinese Society of Agricultural Engineering,2020,36（24）:177-185.

NAYAK T, NG H T. Effective Modeling of Encoder-decoder Architecture for Joint Entity and Relation Extraction[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020,34（5）:8528-8535.

朱秀宝，周刚，陈静，等．基于增强序列标注策略的单阶段联合实体关系抽取方法[J]．计算机科学，2023,50（8）:184-192.

ZHU Xiubao, ZHOU Gang, CHEN Jing, et al. Single-stage Joint Entity and Relation Extraction Method Based on Enhanced Sequence Annotation Strategy[J]. Computer Science, 2023,50（8）:184-192.

LIU F Y, VULI C' I, KORHONEN A, et al. Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders [EB/OL]. 2021: arXiv:2104.08027.https://arxiv. org/abs/2104.08027

ILYAS A, SANTURKAR S, TSIPRAS D, et al. Adversarial Examples Are Not Bugs, they Are Features[C]∥Neural Information Processing Systems. , 2019.

束嘉伟，杨挺，耿毅男，等．面向电力知识图谱构建的重叠实体关系联合抽取方法[J]．高电压技术，2024,50（11）:4912-4922.

SHU Jiawei, YANG Ting, GENG Yinan, et al. Joint Extraction Method for Overlapping Entity Relationships in the Construction of Electric Power Knowledge Graph [J]. High Voltage Engineering，2024,50（11）:4912-4922.

魏伟，赵小强，丁艳华，等．基于BiLSTM和改进注意力机制的高铁车载设备故障诊断[J]．铁道学报，2022,44（11）:53-62.

WEI Wei, ZHAO Xiaoqiang, DING Yanhua, et al. Fault Diagnosis of Vehicle On-board Equipment Based on BiLSTM and Attention Mechanism[J]. Journal of the China Railway Society, 2022, 44（11）:53-62.

周长玉，李想，焦润海，等．基于领域知识图谱的变压器故障联合推理[J]．中国电机工程学报，2025,45（6）:2160-2170.

ZHOU Changyu, LI Xiang, JIAO Runhai, et al. Joint Reasoning for Transformer Faults Based on Domain Knowledge Graphs[J]. Proceedings of the Chinese Society for Electrical Engineering, 2025，45（6）:2160-2170.

林海香，白万胜，赵正祥，等．面向高速铁路道岔运维文本的知识抽取方法[J]．铁道科学与工程学报，2024,21（7）:2569-2580.

LIN Haixiang, BAI Wansheng, ZHAO Zhengxiang, et al. Knowledge Extraction Method for Operation and Maintenance Texts of High-speed Railway Turnout[J]. Journal of Railway Science and Engineering，2024,21（7）:2569-2580.

SHARMA R, MORWAL S, AGARWAL B. Named Entity Recognition Using Neural Language Model and CRF for Hindi Language[J]. Computer Speech and Language, 2022,74:101356.

WU Lijun, et al. R-drop: Regularized dropout for neural networks [J]. Advances in Neural Information Processing Systems, 2021,34:10890-10905.

许鑫，马文政，张浩，等．基于融合对抗训练的农作物品种信息抽取方法[J]．农业机械学报，2023,54（12）:272-279,337.

XU Xin, MA Wenzheng, ZHANG Hao, et al. Crop Variety Information Extraction Method Based on Integrated Adversarial Training[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023，54（12）:272-279,337.

ZHOU R G, CHANG S D, LI Y C. A Neural Network Architecture for Information Extraction in Chinese Drug Package Insert[J]. IEEE Access, 2020,8:51256-51264.

FU T J, LI P H, MA W Y. GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction[C]∥Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy. Stroudsburg, PA, USA: Association for Computational Linguistics, 2019:1409-1418.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

列控车载设备故障诊断的知识图谱构建与应用

知识图谱驱动的关键结构物工程方案智能决策关键技术研究与应用

基于知识图谱的轨道交通运营风险事件智能分析研究

基于知识图谱的信号设备故障诊断方法

大跨度公铁合建钢结构桥梁参数化建模及编码研究