[1]陈 宏,陈新财,巩晓赟,等.基于知识图谱的风电机诊断系统构建与应用[J].郑州大学学报(工学版),2023,44(06):54-60.[doi:10.13705/j.issn.1671-6833.2023.06.007]
　CHEN Hong,CHEN Xincai,GONG Xiaobin,et al.Construction and Application of Wind Turbine Diagnosis System Based on Knowledge Graph[J].Journal of Zhengzhou University (Engineering Science),2023,44(06):54-60.[doi:10.13705/j.issn.1671-6833.2023.06.007]
点击复制

基于知识图谱的风电机诊断系统构建与应用()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
44
期数:
2023年06期
页码:
54-60
栏目:
出版日期:
2023-12-25

文章信息/Info

Title:
Construction and Application of Wind Turbine Diagnosis System Based on Knowledge Graph
作者:
陈 宏1; 2 ;  陈新财1 ;  巩晓赟3 ;  韩东洋1 ;  刘华杰1
1. 郑州大学 机械与动力工程学院,河南 郑州 450001;2. 哈密职业技术学院 机电系,新疆 哈密 839099;3. 郑州轻 工业大学 机电工程学院,河南 郑州 450000
Author(s):
CHEN Hong1; 2;  CHEN Xincai1;  GONG Xiaobin3;  HAN Dongyang1;  LIU Huajie1
1. School of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou 450001, China; 2. Department of Mechanical and Electrical, Hami Vocational and Technical College, Hami 839099, China; 3. School of Mechanical and Electrical Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China
关键词:
知识图谱;  知识抽取;  风力发电机;  故障诊断;  本体
Keywords:
knowledge graph;  knowledge extraction;  wind turbine;  fault diagnosis;  ontology
分类号:
TP391；TK8
DOI:
10.13705/j.issn.1671-6833.2023.06.007
文献标志码:
A
摘要:
针对风力发电机故障诊断与维修过程不明确以及历史故障数据记录大量遗留等问题,提出一种以知识图 谱的方式构建的风力发电机故障诊断系统。 首先,通过改进的命名实体识别模型 BERT-BiLSTM-CRF 对故障文本 进行知识抽取。 数据集采用了近 10 年来的风力发电机故障案例、事故分析等文本数据。 实验结果表明:在风力发 电机故障领域中,改进的实体识别方法相比于传统模型效果提升了 2. 54%。 其次,对抽取的知识实体进行结构化 分析,由于传统故障树在实际故障推理中缺乏目的性,且每个底事件相对于顶事件的重要性不同,提出以故障的特 征属性为分支条件引入到故障树推理中,完成故障树定性与定量分析,并结合故障模式影响和危害性分析( FMECA)完善故障领域知识模型;再对知识结构完成本体化建模,使用 Prot􀆧g􀆧 开发工具对故障树结构完成了基于六元 组概念的本体建模,使构建的本体知识库满足推理的前提条件。 最后,通过 Neo4j 实现知识模型的可视化,并提升 了知识数据的读写能力。
Abstract:
To address the precision problems in wind turbine fault diagnosis and maintenance processes, the lack of management of fault domain knowledge, and the large amount of historical fault data records left behind, a wind turbine fault diagnosis system was proposed to be constructed in the form of a knowledge graph. Firstly, knowledge extraction of fault texts was carried out by an improved named entity recognition model BERT-BiLSTM-CRF. The data set used text data of wind turbine fault cases and accident analysis in the past 10 years. And it was proved through experiments that the improved entity recognition method was 2. 54% more effective compared to the traditional model in the wind turbine fault domain. The extracted knowledge entities were then structurally analysed. As the traditional fault tree lacked purpose in actual fault reasoning, and each bottom event had different levels of importance to the top event, it was proposed that the characteristic attributes of the fault was introduced, as branching conditions, into the fault tree reasoning, to complete the fault tree qualitative and quantitative analysis, and the fault mode impact and hazard analysis ( FMECA) were combined to refine the fault domain knowledge model. Then Protg development tools were use to complete the ontology modelling of the fault tree structure based on the six-tuple concept, so that the constructed ontology knowledge base could meet the prerequisites for inference. Finally, the visualization of knowledge model was realized by Neo4j, and the ability of reading and writing knowledge data was improved.

参考文献/References:

[1] 王致杰, 徐余法, 刘三明. 大型风力发电机组状态监 测与智能故 障 诊 断 [ M] . 上 海: 上 海 交 通 大 学 出 版 社, 2013.

 WANG Z J, XU Y F, LIU S M. Condition monitoring and intelligent fault diagnosis of large wind turbine[ M] . Shanghai: Shanghai Jiao Tong University Press, 2013. 
[2] 胡澜也, 蒋文博, 李艳婷. 基于 LightGBM 的风力发电机 故障诊断[J]. 太阳能学报, 2021, 42(11): 255-259. 
HU L Y, JIANG W B, LI Y T. Fault diagnosis of wind turbine based on LightGBM [ J] . Acta Energiae Solaris Sinica, 2021, 42(11) : 255-259. 
[3] 温竹鹏,陈捷,刘连华,等. 基于小波变换和优化 CNN 的风电齿轮箱故障诊断[ J] . 浙江大学学报( 工学版) , 2022,56(6) :1212-1219. 
WEN Z P, CHEN J, LIU L H, et al. Fault diagnosis of wind power gearbox based on wavelet transform and optimized CNN [ J] . Journal of Zhejiang University ( Engineering Edition) , 2022,56(6) : 1212-1219. 
[4] 高洁. 基于贝叶斯网络的复杂工业过程故障诊断问题 研究[D] . 杭州: 浙江大学, 2019. 
GAO J. Research on fault diagnosis of complex industrial process based on Bayesian network[D] . Hangzhou: Zhejiang University,2019. 
[5] 杭婷婷, 冯钧, 陆佳民. 知识图谱构建技术: 分类、调查 和未来方向[J]. 计算机科学, 2021, 48(2): 175-189. 
HANG T T, FENG J, LU J M. Knowledge graph construction techniques: taxonomy, survey and future directions[J]. Computer Science, 2021, 48(2): 175-189. 
[6] 侯梦薇, 卫荣, 陆亮, 等. 知识图谱研究综述及其在 医疗领域的应用[ J] . 计算机研究与发展, 2018, 55 (12) : 2587-2599. 
HOU M W, WEI R, LU L, et al. Research review of knowledge graph and its application in medical domain [ J ] . Journal of Computer Research and Development, 2018, 55(12) : 2587-2599.
 [7] WU J S, XU X M, LIAO X, et al. Intelligent diagnosis method of data center precision air conditioning fault based on knowledge graph[J]. Electronics, 2023, 12(3): 498. 
[8] 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 H, LI R, ZHANG H Z, et al. Construction of knowledge graph of maintainability design based on multidomain fusion of high-speed trains[ J] . China Mechanical Engineering, 2022, 33(24) : 3015-3023.
 [9] 吴闯,张亮,唐希浪,等. 航空发动机润滑系统故障知 识图谱构建及应用[ J/ OL] . (2022-03-06) [2022-09- 27] . https:∥kns. cnki. net / kns8 / defaultresult / index. 
WU C, ZHANG L, TANG X L, et al. Construction and application of aeroengine lubricating system fault knowledge graph [ J/ OL] . ( 2022 - 03 - 06) [ 2022 - 09 - 27] . https:∥kns. cnki. net / kns8 / defaultresult / index. 
[10] ANJUM N, HARDING J, YOUNG R, et al. Verification of knowledge shared across design and manufacture using a foundation ontology [ J] . International Journal of Production Research, 2013, 51(22) : 6534-6552. 
[11] RANDALL D, PROCTER R, LIN Y W, et al. Distributed ontology building as practical work[J]. International Journal of Human-Computer Studies, 2011, 69(4): 220-233.
 [12] 周亮, 黄志球, 黄传林. 故障树领域本体及 SWRL 规 则的构建方法研究[ J] . 计算机科学, 2015, 42( 8) : 198-202. 
ZHOU L, HUANG Z Q, HUANG C L. Construction method for fault tree domain ontology supporting SWRL rules[ J] . Computer Science, 2015, 42(8) : 198-202.
 [13] HODKIEWICZ M, KLÜWER J W, WOODS C, et al. An ontology for reasoning over engineering textual data stored in FMEA spreadsheet tables[ J] . Computers in Industry, 2021, 131: 103496.
 [14] 李涛, 王次臣, 李华康. 知识图谱的发展与构建[ J] . 南京理工大学学报, 2017, 41(1) : 22-34. 
LI T, WANG C C, LI H K. Development and construction of knowledge graph[ J] . Journal of Nanjing University of Science and Technology, 2017, 41(1) : 22-34. 
[15] 常晓莹,宋绍京,王华. 垃圾分类知识图谱构建研究与 实现[ J] . 计算机应用与软件,2022,39(5) :247-252. 
CHANG X Y, SONG S J, WANG H. Research and implementation on the construction of knowledge map of waste classification [ J] . Computer Application and Software, 2022,39(5) : 247-252. 
[16] 谢腾, 杨俊安, 刘辉. 基于 BERT-BiLSTM-CRF 模型的 中文实体识别[ J] . 计算机系统应用, 2020, 29( 7) : 48-55. 
XIE T, YANG J A, LIU H. Chinese entity recognition based on BERT-BiLSTM-CRF model[ J] . Computer Systems & Applications, 2020, 29(7) : 48-55. 
[17] 李新民, 罗学科, 李文, 等. 基于 FTA 的水质微型站 智能故障诊断专家系统研究[ J] . 给水排水, 2020, 56 (5) :143-148. 
LI X M, LUO X K, LI W, et al. Study on intelligent fault diagnosis expert system for water quality mini-station based on FTA [ J ] . Water & Wastewater Engineering, 2020, 56(5) :143-148.

更新日期/Last Update: 2023-10-22