|本期目录/Table of Contents|

[1]王明达,吴志生,朱光辉,等.燃气轮机故障知识图谱构建方法与应用研究*[J].中国安全生产科学技术,2023,19(11):121-128.[doi:10.11731/j.issn.1673-193x.2023.11.017]
　WANG Mingda,WU Zhisheng,ZHU Guanghui,et al.Research on construction method and application of knowledge graph for gas turbine fault[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2023,19(11):121-128.[doi:10.11731/j.issn.1673-193x.2023.11.017]
点击复制

燃气轮机故障知识图谱构建方法与应用研究*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
19
期数:
2023年11期
页码:
121-128
栏目:
职业安全卫生管理与技术
出版日期:
2023-11-30

文章信息/Info

Title:
Research on construction method and application of knowledge graph for gas turbine fault
文章编号:
1673-193X(2023)-11-0121-08
作者:
王明达; 吴志生; 朱光辉; 李云飞; 张榜
(1.中国石油大学（华东） 机电工程学院，山东 青岛 266580；
2.国家石油天然气管网集团有限公司 山东省分公司，山东 济南 250002)
Author(s):
WANG Mingda;  WU Zhisheng;  ZHU Guanghui;  LI Yunfei;  ZHANG Bang
(1.College of Mechanical and Electrical Engineering,China University of Petroleum,Qingdao Shandong 266580,China;
2.PipeChina Shandong Branch Co.,Jinan Shandong 250002,China)
关键词:
燃气轮机; 故障诊断; 知识图谱; 实体识别; 图数据库
Keywords:
gas turbine;  fault diagnosis;  knowledge graph;  entity recognition;  graph database
分类号:
X913.4；TK478
DOI:
10.11731/j.issn.1673-193x.2023.11.017
文献标志码:
A
摘要:
为更好地管理和利用燃气轮机故障知识，提高故障诊断的效率，提出燃气轮机故障知识构建方法。首先，根据故障文本知识特点，并结合专家知识设计燃气轮机故障文本知识本体概念模型。其次，采用BERT-BiLSTM-CRF、BERT-BiLSTM-Attention等深度学习模型实现燃气轮机故障命名实体识别及实体关系模型训练，在引入BERT模型获取动态字符后，相比BiLSTM-CRF模型，实体识别模型的综合评价指标F1提高7.98个百分点，相比Word2Vec特征表示方法提高0.89个百分点；在关系抽取中将BiLSTM-CRF抽取模型中的CRF模型替换为Attention模型并引入BERT模型后，综合评价指标F1提高8.49个百分点。最后，使用Neo4j图数据库完成知识的存储工作，并将知识图谱用于辅助故障分析。研究结果表明：知识图谱技术能够实现对燃气轮机组成部件故障先验知识的利用以及对故障原因的解释。研究结果可为燃气轮机故障诊断提供知识支持。
Abstract:
In order to better manage and utilize the gas turbine fault knowledge and improve the efficiency of fault diagnosis,a construction method of gas turbine fault knowledge was proposed.Firstly,the ontology conceptual model of gas turbine fault text knowledge was designed according to the characteristics of fault text knowledge and combined with expert knowledge.Secondly,the deep learning models such as BERT-BiLSTM-CRF and BERT-BiLSTM-Attention were used to realize the named entity recognition and entity relationship model training of gas turbine fault,and after introducing into BERT model to obtain the dynamic characters,the comprehensive evaluation index F1 of the entity recognition model was improved by 7.98 percentage points,and compared with the Word2Vec feature representation method,it was improved by 0.89 percentage points.After replacing the CRF model in the BiLSTM-CRF extraction model with the Attention model and introducing the BERT model in the relational extraction,the comprehensive evaluation index F1 improved by 8.49 percentage points.Finally,the Neo4j graph database was used to complete the knowledge storage work,and the knowledge graph was used to assist fault analysis.The results show that the knowledge graph technology can realize the utilization of priori knowledge for gas turbine constituent component faults and the explanation of fault causes.The results can provide knowledge support for gas turbine fault diagnosis.

参考文献/References:

［1］王明达,张榜,吴志生，等.基于强化学习的城镇燃气事故信息抽取方法［J］.中国安全生产科学技术,2023,19(3):39-45. WANG Mingda,ZHANG Bang,WU Zhisheng,et al.Information extraction method of urban gas accidents based on reinforcement learning［J］.Journal of Safety Science and Technology,2023,19(3):39-45.
［2］朱涛.航改燃气轮机燃烧室故障模式、影响及危害性分析［J］.航空发动机,2022,48(1):33-39. ZHU Tao.Failure mode,effects and criticality analysis of aero-derivative gas turbine combustor［J］.Aeroengine,2022,48(1):33-39.
［3］VIEGAS R A,FRANCISCO DE ASSIS DA SILVA MOTA,COSTA A P C S,et al.A multi-criteria-based hazard and operability analysis for process safety［J］.Process Safety and Environmental Protection,2020,144:310-321.
［4］SAWANT U,GARG S,CHAKRABARTI S,et al.Neural architecture for question answering using a knowledge graph and web corpus［J］.Information Retrieval Journal,2019,22(3-4):324-349.
［5］郭恒,黎荣,张海柱,等.多域融合的高速列车维修性设计知识图谱构建［J］.中国机械工程,2022,33(24):3015-3023. GUO Heng,LI Rong,ZHANG Haizhu,et al.Construction of knowledge graph of maintainability design based on multi-domain fusion of high-speed trains［J］.China Mechanical Engineering,2022,33(24):3015-3023.
［6］LIU J T,SCHMID F,LI K P,et al.A knowledge graph-based approach for exploring railway operational accidents［J］.Reliability Engineering & System Safety,2021,207:107352.
［7］TANG Y C,LIU T T,LIU G Y,et al.Enhancement of power equipment management using knowledge graph［C］//Proceedings of the 2019 IEEE Innovative Smart Grid Technologies-Asia (ISGT Asia).Chengdu:IEEE,2019：905-910.
［8］QU Q H,ZHENG W J,Qi W W,et al.Research on the construction method of knowledge graph for electric power wireless private network［C］//2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC).IEEE,2020.
［9］盛林,马波,张杨.基于知识图谱的旋转机械故障诊断方法［J］.机电工程,2022,39(9):1194-1202. SHENG Lin,MA Bo,ZHANG Yang.Fault diagnosis method for rotating machinery based on knowledge graph［J］.Journal of Mechanical & Electrical Engineering,2022,39(9):1194-1202.
［10］WANG X,HE X G,CAO Y X,et al.Kgat:Knowledge graph attention network for recommendation ［C］//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.Alaska,USA:ACM,2019,1179:950-958.
［11］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.
［12］许驹雄,李敏波,刘孟珂,等.发动机故障领域知识图谱构建与应用［J］.计算机系统应用,2022,31(7):66-76. XU Juxiong,LI Minbo,LIU Mengke,et al.Construction and application of knowledge graph in diesel engine fault field［J］.Computer Systems & Applications,2022,31(7):66-76.
［13］王芳.图书发行标准领域本体构建方法的研究［J］.数字技术与应用,2019,37(11):192-195. WANG Fang.Research on the construction method of ontology in book issuance standards［J］.Digital Technology & Application,2019,37(11):192-195.
［14］周义棋,刘畅,龙增,等.电网应急预案知识图谱构建方法与应用［J］.中国安全生产科学技术,2023,19(1):5-13. ZHOU Yiqi,LIU Chang,LONG Zeng,et al.Construction method and application of knowledge graph in emergency plans for power grid［J］.Journal of Safety Science and Technology,2023,19(1):5-13.
［15］邱云飞,邢浩然,李刚.矿井建设知识图谱构建研究综述［J］.计算机工程与应用,2023,59(7):64-79. QIU Yunfei,XING Haoran,LI Gang.Summary of research on construction of knowledge graph for mine construction［J］.Computer Engineering and Applications,2023,59(7):64-79.
［16］黄微,卢国强,赵旭.基于知识图谱的微博主题演变路径研究［J］.情报理论与实践,2022,45(3):173-181. HUANG Wei,LU Guoqiang,ZHAO Xu.Ｒesearch on the evolution path of microblog topic based on knowledge graph［J］.Information Studies:Theory & Application,2022,45(3):173-181.
［17］谢庆,蔡扬,谢军,等.基于ALBERT的电力变压器运维知识图谱构建方法与应用研究［J］.电工技术学报,2023,38(1):95-106. XIE Qing,CAI Yang,XIE Jun,et al.Research on construction method and application of knowledge graph for power transformer operation and maintenance based on ALBERT［J］.Transactions of China Electrotechnical Society,2023,38(1):95-106.

相似文献/References:

[1]马成正.基于概率神经网络的液氨汽车罐车复合故障诊断[J].中国安全生产科学技术,2011,7(3):114.
　MA Cheng-zheng.Compound Fault Diagnosis of Liquid Ammonia Tank Car Based on Probabilistic Neural Network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(11):114.
[2]李佃祥,于洪国,周江涛.油管静水试压装置安全控制系统设计与开发[J].中国安全生产科学技术,2012,8(12):103.
　LI Dian xiang,YU Hong guo,ZHOU Jiang tao.Design and development of safe control system of tubing hydraulic pressure experiment equipment[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(11):103.
[3]雷雨,吴超,王秉.人对声信号的安全认知模型构建及其应用[J].中国安全生产科学技术,2018,14(6):27.[doi:10.11731/j.issn.1673-193x.2018.06.004]
　LEI Yu,WU Chao,WANG Bing.Construction and application of safety cognition model for human to acoustic signals[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2018,14(11):27.[doi:10.11731/j.issn.1673-193x.2018.06.004]
[4]刘剑,刘丽,黄德,等.基于风量-风压复合特征的通风系统阻变型故障诊断[J].中国安全生产科学技术,2020,16(1):85.[doi:10.11731/j.issn.1673-193x.2020.01.014]
　LIU Jian,LIU Li,HUANG De,et al.Resistance variant fault diagnosis of ventilation system based on composite features of air volume and air pressure[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(11):85.[doi:10.11731/j.issn.1673-193x.2020.01.014]
[5]潘伟,徐刚,熊方杰.基于非线性技术锅炉故障分析*[J].中国安全生产科学技术,2020,16(12):176.[doi:10.11731/j.issn.1673-193x.2020.12.028]
　PAN Wei,XU Gang,XIONG Fangjie.Analysis of boiler fault based on nonlinear technology[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2020,16(11):176.[doi:10.11731/j.issn.1673-193x.2020.12.028]
[6]倪景峰,乐晓瑞,常立峰,等.基于决策树的矿井通风阻变型故障诊断及传感器优化布置*[J].中国安全生产科学技术,2021,17(2):34.[doi:10.11731/j.issn.1673-193x.2021.02.005]
　NI Jingfeng,LE Xiaorui,CHANG Lifeng,et al.Resistance variant fault diagnosis and optimized layout of sensors for mine ventilation based on decision tree[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(11):34.[doi:10.11731/j.issn.1673-193x.2021.02.005]
[7]张瑞程,王新颖,胡磊磊,等.基于一维卷积神经网络的燃气管道泄漏声发射信号识别*[J].中国安全生产科学技术,2021,17(2):104.[doi:10.11731/j.issn.1673-193x.2021.02.016]
　ZHANG Ruicheng,WANG Xinying,HU Leilei,et al.Acoustic emission signal identification of gas pipeline leakage based on one-dimensional convolution neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(11):104.[doi:10.11731/j.issn.1673-193x.2021.02.016]
[8]倪景峰,李振,乐晓瑞,等.基于随机森林的阻变型通风网络故障诊断方法*[J].中国安全生产科学技术,2022,18(4):34.[doi:10.11731/j.issn.1673-193x.2022.04.005]
　NI Jingfeng,LI Zhen,LE Xiaorui,et al.Resistance variant fault diagnosis method of ventilation network based on random forest[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(11):34.[doi:10.11731/j.issn.1673-193x.2022.04.005]
[9]付敏,郝镒林,李萌,等.安全工程技术领域数字孪生应用研究综述*[J].中国安全生产科学技术,2022,18(4):243.[doi:10.11731/j.issn.1673-193x.2022.04.035]
　FU Min,HAO Yilin,LI Meng,et al.Summary of digital twin application research in field of safety engineering technology[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(11):243.[doi:10.11731/j.issn.1673-193x.2022.04.035]
[10]徐海军,李彦斌,王进,等.基于模糊Petri网的有载分接开关故障诊断方法研究*[J].中国安全生产科学技术,2022,18(5):222.[doi:10.11731/j.issn.1673-193x.2022.05.034]
　XU Haijun,LI Yanbin,WANG Jin,et al.Research on fault diagnosis method of on-load tap changer based on Fuzzy Petri net[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2022,18(11):222.[doi:10.11731/j.issn.1673-193x.2022.05.034]

备注/Memo

备注/Memo:
收稿日期： 2023-07-23
* 基金项目： 国家自然科学基金项目（52075549）
作者简介： 王明达，博士，讲师，主要研究方向为油气设备安全检测与监测、安全工程信息化。
更新日期/Last Update: 2023-12-06