基于知识和数据融合驱动的设备故障诊断方法Fault Diagnosis Method for Equipment Driven by Knowledge and Data Fusion
刘晶;高立超;孙跃华;冯显宗;季海鹏;
摘要(Abstract)：
传统设备故障诊断方法通常基于单一的机理知识或运行数据,难以解决多复杂工况、多故障类型的设备故障问题。针对以上问题,提出了一种基于知识和数据融合驱动的设备故障诊断方法,从单纯依赖机理知识或运行数据到两者融合驱动,进一步形成故障图谱诊断系统,不仅通过优化的双向长短时记忆网络模型对设备运行数据进行故障分类,而且可以展示详细故障信息以及相似故障。经实验分析验证,故障诊断准确率平均达到95.03%,同时系统通过基于融合故障链的知识图谱进行辅助决策,返回故障相关信息。对比传统分类模型准确率表现突出,并实现了机理知识与数据驱动相融合的设备故障领域图谱构建。
关键词(KeyWords)： 知识图谱;特征提取;故障诊断;LSTM;融合分类
基金项目(Foundation): 天津市科技计划项目(2019年天津市人工智能重大专项)(19ZXZNGX00040);; 河北省自然科学基金项目(F2019202062)
作者(Authors): 刘晶;高立超;孙跃华;冯显宗;季海鹏;
DOI: 10.13705/j.issn.1671-6841.2021283
参考文献(References)：
- [1] 郑近德，潘海洋，程军圣，等.基于自适应经验傅里叶分解的机械故障诊断方法[J].机械工程学报，2020,56(9):125-136.ZHENG J D,PAN H Y,CHENG J S,et al.Adaptive empirical Fourier decomposition based mechanical fault diagnosis method[J].Journal of mechanical engineering,2020,56(9):125-136.
- [2] 刘晶，秦国帅，孟德凯，等.数据融合驱动的余热锅炉阀门调节方法[J].燕山大学学报，2021,45(1):76-86,94.LIU J,QIN G S,MENG D K,et al.Data fusion driven waste heat boiler valve adjustment method[J].Journal of Yanshan university,2021,45(1):76-86,94.
- [3] 陈彦光，刘海顺，李春楠，等.基于刑事案例的知识图谱构建技术[J].郑州大学学报(理学版),2019,51(3):85-90.CHEN Y G,LIU H S,LI C N,et al.Knowledge graph construction techniques based on criminal cases[J].Journal of Zhengzhou university (natural science edition),2019,51(3):85-90.
- [4] 昝红英，窦华溢，贾玉祥，等.基于多来源文本的中文医学知识图谱的构建[J].郑州大学学报(理学版),2020,52(2):45-51.ZAN H Y,DOU H Y,JIA Y X,et al.Construction of Chinese medical knowledge graph based on multi-source corpus[J].Journal of Zhengzhou university (natural science edition),2020,52(2):45-51.
- [5] WANG X,HE X N,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.New York,ACM Press,2019:950-958.
- [6] HE Q B.Time-frequency manifold for nonlinear feature extraction in machinery fault diagnosis[J].Mechanical systems and signal processing,2013,35(1/2):200-218.
- [7] WANG Y,XU G H,LIANG L,et al.Detection of weak transient signals based on wavelet packet transform and manifold learning for rolling element bearing fault diagnosis[J].Mechanical systems and signal processing,2015,54/55:259-276.
- [8] PAN H,HE X,TANG S,et al.An improved bearing fault diagnosis method using one-dimensional CNN and LSTM[J].Strojni?ki vestnik-journal of mechanical engineering,2018,64 (7/8):443-452.