煤矿综采设备故障知识图谱构建

蔡安江; 张妍; 任志刚

doi:10.13272/j.issn.1671-251x.2023020005

煤矿综采设备故障知识图谱构建

doi: 10.13272/j.issn.1671-251x.2023020005

西安建筑科技大学机电工程学院, 陕西西安　710000

基金项目: 工信部物联网集成创新与融合应用项目（2018-470）；榆林市科技计划项目（CXY-2022-172）。

详细信息

作者简介:
蔡安江（1965—），男，安徽舒城人，教授，博士研究生导师，研究方向为人工智能及智能制造，E-mail：cai_aj@163.com

中图分类号: TD632
计量
- 文章访问数: 214
- HTML全文浏览量: 37
- PDF下载量: 57
- 被引次数: 0
出版历程
- 收稿日期: 2023-02-01
- 修回日期: 2023-04-28
- 网络出版日期: 2023-05-16

Fault knowledge graph construction for coal mine fully mechanized mining equipment

School of Mechanical and Electrical Engineering, Xi'an University of Architecture and Technology, Xi'an 710000, China

摘要

摘要: 现有煤矿综采设备故障诊断方法缺乏对综采设备历史故障数据的系统化管理及应用，针对该问题，引入知识图谱技术对综采设备故障数据进行系统化管理。采用自顶而下的方法对综采设备故障知识进行本体构建，将综采设备故障知识归纳为故障位置、故障现象、故障原因、处理方法4类，并进行规范化命名；采用通用的命名实体标注方法BIOES对综采设备故障知识进行人工标注；将双向长短期记忆（BiLSTM）和条件随机场（CRF）相结合，构建BiLSTM−CRF模型，对已标注的综采设备故障知识进行命名实体识别，并通过人工抽取实体关系，从而实现故障知识抽取；结合BiLSTM−CRF模型的实体识别结果和人工抽取的实体关系，使用Neo4j图数据库存储综采设备故障知识，构建综采设备故障知识图谱。实验结果表明，相较于BiLSTM模型和BiLSTM−Attention模型，BiLSTM−CRF模型精确率显著提高，为87%，F₁值也有一定幅度上升，为69%。综采设备故障知识图谱的构建可为大规模、多域综采设备故障数据的有效分析、管理及应用提供支持。
- 煤矿综采设备 /
- 故障诊断 /
- 知识图谱 /
- 知识抽取 /
- BiLSTM /
- CRF
Abstract: The existing fault diagnosis methods for coal mine fully mechanized mining equipment lack systematic management and application of historical fault data of fully mechanized mining equipment. In response to this problem, knowledge graph technology is introduced to systematically manage the fault data of fully mechanized mining equipment. The top-down approach is used to construct the ontology of fully mechanized mining equipment fault knowledge. The knowledge of fully mechanized mining equipment fault is classified into four categories: fault location, fault phenomenon, fault cause, and treatment method. And the naming of the knowledge is standardized. The universal naming entity annotation method BIOES is used to manually annotate the fault knowledge of fully mechanized mining equipment. By combining bi-directional long short-term memory (BiLSTM) and conditional random field (CRF), the BiLSTM-CRF model is constructed. The marked fault knowledge of fully mechanized mining equipment is identified by the named entity, and the fault knowledge extraction is realized by manually extracting entity relationships. Combining the entity recognition results of the BiLSTM-CRF model with the manually extracted entity relationships, a Neo4j graph database is used to store the fault knowledge of fully mechanized mining equipment. A fault knowledge graph of fully mechanized mining equipment is constructed. The experimental results show that compared to the BiLSTM model and BiLSTM-Attention model, the acurracy of the BiLSTM-CRF model is significantly improved, reaching 87%. The F₁ value also has a certain increase, reaching 69%. The construction of fully mechanized mining equipment fault knowledge graph can provide support for the effective analysis, management, and application of large-scale and multi-domain fully mechanized mining equipment fault data.
- coal mine fully mechanized mining equipment /
- fault diagnosis /
- knowledge graph /
- knowledge extraction /
- BiLSTM /
- CRF

HTML全文

图 1 综采设备故障知识结构

Figure 1. Fault knowledge structure of fully mechanized mining equipment

下载: 全尺寸图片幻灯片

图 2 LSTM网络结构

Figure 2. Network structure of LSTM

下载: 全尺寸图片幻灯片

图 3 BiLSTM网络结构

Figure 3. Network structure of BiLSTM

下载: 全尺寸图片幻灯片

图 4 BiLSTM−CRF模型样例分析

Figure 4. Sample analysis of BiLSTM-CRF model

下载: 全尺寸图片幻灯片

图 5 综采设备故障知识图谱

Figure 5. Fault knowledge graph of fully mechanized mining equipment

下载: 全尺寸图片幻灯片

图 6 知识问答界面

Figure 6. Knowledge Q&A interface

下载: 全尺寸图片幻灯片

图 7 各模型训练、验证过程中精确率变化曲线

Figure 7. Accuracy curves of each model in training and verification process

下载: 全尺寸图片幻灯片

表 1 不同模型的实验结果对比

Table 1. Comparison of experimental results of different models %

模型精确率召回率 F₁

BiLSTM 69 67 68
BiLSTM−Attention 62 63 63
BiLSTM−CRF 87 69 69

下载: 导出CSV

参考文献(21)

[1]	李梅,杨帅伟,孙振明,等. 智慧矿山框架与发展前景研究[J]. 煤炭科学技术,2017,45(1):121-128,134. doi: 10.13199/j.cnki.cst.2017.01.021 LI Mei,YANG Shuaiwei,SUN Zhenming,et al. Study on framework and development prospects of intelligent mine[J]. Coal Science and Technology,2017,45(1):121-128,134. doi: 10.13199/j.cnki.cst.2017.01.021
[2]	王国法,王虹,任怀伟,等. 智慧煤矿2025情景目标和发展路径[J]. 煤炭学报,2018,43(2):295-305. doi: 10.13225/j.cnki.jccs.2018.0152 WANG Guofa,WANG Hong,REN Huaiwei,et al. 2025 scenarios and development path of intelligent coal mine[J]. Journal of China Coal Society,2018,43(2):295-305. doi: 10.13225/j.cnki.jccs.2018.0152
[3]	王国法,任世华,庞义辉,等. 煤炭工业“十三五”发展成效与“双碳”目标实施路径[J]. 煤炭科学技术,2021,49(9):1-8. doi: 10.13199/j.cnki.cst.2021.09.001 WANG Guofa,REN Shihua,PANG Yihui,et al. Development achievements of China's coal industry during the 13th Five-Year Plan period and future prospects[J]. Coal Science and Technology,2021,49(9):1-8. doi: 10.13199/j.cnki.cst.2021.09.001
[4]	李旭,吴雪菲,田野,等. 基于云平台的综采设备群远程故障诊断系统[J]. 工矿自动化,2021,47(7):57-62. doi: 10.13272/j.issn.1671-251x.17794 LI Xu,WU Xuefei,TIAN Ye,et al. Remote fault diagnosis system of fully mechanized mining equipment group based on cloud platform[J]. Industry and Mine Automation,2021,47(7):57-62. doi: 10.13272/j.issn.1671-251x.17794
[5]	张旭辉,潘格格,郭欢欢,等. 基于深度迁移学习的采煤机摇臂部滚动轴承故障诊断方法[J]. 煤炭科学技术,2022,50(4):256-263. ZHANG Xuhui,PAN Gege,GUO Huanhuan,et al. Fault diagnosis method for rolling bearing on shearer arm based on deep transfer learning[J]. Coal Science and Technology,2022,50(4):256-263.
[6]	聂同攀,曾继炎,程玉杰,等. 面向飞机电源系统故障诊断的知识图谱构建技术及应用[J]. 航空学报,2022,43(8):46-62. NIE Tongpan,ZENG Jiyan,CHENG Yujie,et al. Knowledge graph construction technology and its application in aircraft power system fault diagnosis[J]. Acta Aeronautica et Astronautica Sinica,2022,43(8):46-62.
[7]	林凌云,陈青,金磊,等. 基于知识图谱的变电站告警信息故障知识表示研究与应用[J]. 电力系统保护与控制,2022,50(12):90-99. LIN Lingyun,CHEN Qing,JIN Lei,et al. Research and application of substation alarm signal fault knowledge representation based on knowledge graph[J]. Power System Protection and Control,2022,50(12):90-99.
[8]	侯靖琳,仇润鹤,薛季爱,等. 基于知识图谱嵌入和补全的电梯故障预测[J]. 计算机工程与设计,2022,43(1):224-230. HOU Jinglin,QIU Runhe,XUE Ji'ai,et al. Elevator failure prediction based on embedding and completion of knowledge graph[J]. Computer Engineering and Design,2022,43(1):224-230.
[9]	马红兵. 综采工作面电气设备故障处理分析[J]. 内蒙古石油化工,2021,47(1):74-75. doi: 10.3969/j.issn.1006-7981.2021.01.028 MA Hongbing. Analysis of the processing in electrical equipment failure at fully mechanized working face[J]. Inner Mongolia Petrochemical Industry,2021,47(1):74-75. doi: 10.3969/j.issn.1006-7981.2021.01.028
[10]	胡芳槐. 基于多种数据源的中文知识图谱构建方法研究[D]. 上海: 华东理工大学, 2015. HU Fanghuai. Chinese knowledge graph construction method based on multiple data sources[D]. Shanghai: East China University of Science and Technology, 2015.
[11]	吴玉龙. 综采工作面煤矿机械设备常见故障研究[J]. 科技创新与应用,2022,12(29):162-164,168. WU Yulong. Research on common faults of coal mining machinery and equipment in fully mechanized working face[J]. Technology Innovation and Application,2022,12(29):162-164,168.
[12]	王萌,王昊奋,李博涵,等. 新一代知识图谱关键技术综述[J]. 计算机研究与发展,2022,59(9):1947-1965. doi: 10.7544/issn1000-1239.20210829 WANG Meng,WANG Haofen,LI Bohan,et al. Survey on key technologies of new generation knowledge graph[J]. Journal of Computer Research and Development,2022,59(9):1947-1965. doi: 10.7544/issn1000-1239.20210829
[13]	卢绍帅,陈龙,卢光跃,等. 面向小样本情感分类任务的弱监督对比学习框架[J]. 计算机研究与发展,2022,59(9):2003-2014. doi: 10.7544/issn1000-1239.20210699 LU Shaoshuai,CHEN Long,LU Guangyue,et al. Weakly-supervised contrastive learning framework for few-shot sentiment classification tasks[J]. Journal of Computer Research and Development,2022,59(9):2003-2014. doi: 10.7544/issn1000-1239.20210699
[14]	TONG Fan, LUO Zheheng, ZHAO Dongsheng. A deep network based integrated model for disease named entity recognition[C]. IEEE International Conference on Bioinformatics and Biomedicine, Kansas, 2017: 618-621.
[15]	金相臣,吴子锐,石敏,等. 基于BiLSTM的地质片段层位预测方法[J]. 高技术通讯,2021,31(6):607-614. doi: 10.3772/j.issn.1002-0470.2021.06.005 JIN Xiangchen,WU Zirui,SHI Min,et al. Geological segment horizon prediction method based on BiLSTM[J]. Chinese High Technology Letters,2021,31(6):607-614. doi: 10.3772/j.issn.1002-0470.2021.06.005
[16]	LEI Jianbo,TANG Buzhou,LU Xueqin,et al. A comprehensive study of named entity recognition in Chinese clinical text[J]. Journal of the American Medical Informatics Association,2014,21(5):808-814. doi: 10.1136/amiajnl-2013-002381
[17]	施海昕,诸建超,严骏驰,等. 基于卷积神经网络和LSTM循环神经网络的客户复购预测方法[J]. 高技术通讯,2021,31(7):713-722. doi: 10.3772/j.issn.1002-0470.2021.07.004 SHI Haixin,ZHU Jianchao,YAN Junchi,et al. A prediction method of clients' repurchase based on CNN and LSTM RNN[J]. Chinese High Technology Letters,2021,31(7):713-722. doi: 10.3772/j.issn.1002-0470.2021.07.004
[18]	周旭峰,王醒策,武仲科,等. 基于组合RNN网络的EMG信号手势识别[J]. 光学精密工程,2020,28(2):424-442. ZHOU Xufeng,WANG Xingce,WU Zhongke,et al. Gesture recognition with EMG signals based on ensemble RNN[J]. Optics and Precision Engineering,2020,28(2):424-442.
[19]	宋雅文,杨志豪,罗凌,等. 基于字符卷积神经网络的生物医学变异实体识别方法[J]. 中文信息学报,2021,35(5):63-69. doi: 10.3969/j.issn.1003-0077.2021.05.008 SONG Yawen,YANG Zhihao,LUO Ling,et al. Biomedical mutation entity recognition method based on character convolution neural network[J]. Journal of Chinese Information Processing,2021,35(5):63-69. doi: 10.3969/j.issn.1003-0077.2021.05.008
[20]	ANGLES R,GUTIERREZ C. Survey of graph database models[J]. ACM Computing Surveys,2008,40(1):1-39.
[21]	赵志宏,李晴,杨绍普,等. 基于BiLSTM与注意力机制的剩余使用寿命预测研究[J]. 振动与冲击,2022,41(6):44-50,196. ZHAO Zhihong,LI Qing,YANG Shaopu,et al. Remaining useful life prediction based on BiLSTM and attention mechanism[J]. Journal of Vibration and Shock,2022,41(6):44-50,196.