计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (7): 310-318.doi: 10.11896/jsjkx.231000223

• 人工智能 • 上一篇    下一篇

基于动态图表示的设备故障推理预测方法

张慧, 张骁雄, 丁鲲, 刘姗姗   

  1. 1 国防科技大学第六十三研究所 南京 210007
    2 国防科技大学大数据与决策实验室 长沙 410073
  • 收稿日期:2023-10-31 修回日期:2024-03-02 出版日期:2024-07-15 发布日期:2024-07-10
  • 通讯作者: 丁鲲(dingkun18@nudt.edu.cn)
  • 作者简介:(zhanghui82@nudt.edu.cn)
  • 基金资助:
    ****能力**服务提升(24220407)

Device Fault Inference and Prediction Method Based on Dynamic Graph Representation

ZHANG Hui, ZHANG Xiaoxiong, DING Kun, LIU Shanshan   

  1. 1 The Sixty-Third Research Institute,National University of Defense Technology,Nanjing 210007,China
    2 Laboratory for Big Data and Decision,National University of Defense Technology,Changsha 410073,China
  • Received:2023-10-31 Revised:2024-03-02 Online:2024-07-15 Published:2024-07-10
  • About author:ZHANG Hui,born in 1982,postgra-duate,assistant researcher.His main research interests include intelligent data processing and data engineering.
    DING Kun,born in 1978,postgraduate,researcher.His main research interests include data engineering and network management.
  • Supported by:
    **** Capacity ** Service Improvement(24220407).

PDF (PC)

519

摘要： 高效的设备运维可以保障设备的正常运行。然而,随着设备复杂程度越来越高,设备的维护和故障排查的复杂度和难度也不断增加。因此,人工方式越来越不能满足智能化设备的运维需要。智能运维将人工智能等新兴技术运用于运维过程,可以作为设备运维的有力支撑。但现有的很多方法依旧存在着未考虑动态性等不足。针对上述问题,提出了一种基于动态知识图谱表示学习的设备故障推理预测方法,用于预测目标设备是否与故障设备存在潜在的关联。该方法结合动态知识图谱表示学习和图表示推理模型,可以利用实时数据更新图网络,并运用图表示推理模型对新的故障数据进行推理。首先,使用动态知识图谱来表示设备运维数据,记录设备随时间的演化过程,从而有效地表达设备之间关系的动态变化性;然后,通过表示学习获得动态知识图谱中源故障设备和目标设备的时间感知表示;最后,将时间感知表示作为输入进行故障推理预测,判断设备之间是否存在潜在的关联。预测结果可以辅助运维人员解决相应的设备故障问题。在多个数据集上进行了实验,验证了所提方法的有效性。

关键词: 动态知识图谱, 表示学习, 链接推理预测, 时间感知, 设备运维

Abstract: Effective equipment operation and maintenance is able to ensure the proper operation of equipment.Nevertheless,as the equipment becomes more and more sophisticated,the complexity and difficulty of maintaining and troubleshooting these devices are constantly increasing.As a result,equipment operation and maintenance mode that only rely on manual efforts is gradually unable to meet the requirements of intelligent equipment.Intelligent operation and maintenance that applies many new emerging technologies such as artificial intelligence to process of operation and maintenance can be used as a strong support for equipment operation and maintenance task.However,many existing methods still have deficiencies such as lack of considering dynamic cha-racteristics.In order to solve these problems,a device fault inference and prediction method that is based on dynamic knowledge graph representation learning is proposed.The method can predict whether a target device is potentially associated with a faulty device time during the operation and maintenance process.The proposed method combines dynamic knowledge graph representation learning with graph representation inference models,updates the graph network based on real-time data,and employs graph representation inference models to infer new fault data.Firstly,it takes advantage of a dynamic knowledge graph to represent the equipment operation and maintenance data,so as to records the evolution of the equipment over time.The representation effectively denote dynamic changes of the relationship between the devices.Next,the time-aware representations of the source faulty equipment and the target equipment in the dynamic knowledge graph are obtained through representation learning.Finally,the time-aware representations are used as inputs for fault inference prediction,which predicts whether there exists any potential correlation between the equipment so as to assist the operation and maintenance engineer in solving the corresponding equipment fault problems.Experiments on multiple datasets verify the effect of the proposed method.

Key words: Dynamic knowledge graph, Representation learning, Link inference prediction, Time awareness, Device operations and maintenance

中图分类号: 

  • TP391
[1]WANG S,LU H,WANG S,et al.Research progress of KPIanomaly detection in intelligent operation and maintenance[J].Telecommunications Science,2021,37(5):42-51.
[2]XIA L,LIANG Y,LENG J,et al.Maintenance planning recommendation of complex industrial equipment based on knowledge graph and graph neural network[J].Reliability Engineering and System Safety,2023,232:109068.
[3]SI X S,HU C H,ZHOU Z J.Fault prediction model based on evidential reasoning approach[J].Science China Information Sciences,2010,53(10):2032-2046.
[4]WANG R G,WU J,LIU C,et al.Aircraft equipment failure cause discrimination method basedon maintenance log[J].Journal of Software,2019,30(5):1375-1385.
[5]FAN Y,NOWACZYK S,RÖGNVALDSSON T.Transfer lear-ning for remaining useful life prediction based on consensus self-organizing models[J].Reliability Engineering and System Safety,2020,203:107098.
[6]CHUI K T,GUPTA B B,VASANT P.A genetic algorithm optimized RNN-LSTM model for remaining useful life prediction of turbofan engine[J].Electronics,2021,10(3):285.
[7]GUO R,WANG Y,ZHANG H,et al.Remaining useful life prediction for rolling bearings using EMD-RISI-LSTM[J].IEEE Transactions on Instrumentation and Measurement,2021,70:1-12.
[8]REN S,SHI L,LIU Y,et al.Apersonalised operation and maintenance approach for complex products based on equipment portrait of product-service system[J].Robotics and Computer-Integrated Manufacturing,2023,80:102485.
[9]CHOI E,XU Z,LI Y,et al.Learning the graphical structure of electronic health records with graph convolutional transformer[C]//Proceedings of the AAAI Conference on Artificial Intelligence.AAAI,2020:606-613.
[10]WU L,CUI P,PEI J,et al.Graph neural networks:foundation,frontiers and applications[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.ACM,2022:4840-4841.
[11]DORNAIKA F,DAHBI R,BOSAGHZADEH A,et al.Efficient dynamic graph construction for inductive semi-supervised lear-ning[J].Neural Networks,2017,94:192-203.
[12]ZHOU X H,WANG Y J,XU H Z,et al.Fusion learning based unsupervised anomaly detection for multi-dimensional time series[J].Journal of Computer Research and Development,2023,60(3):496-508.
[13]QI Q,SHEN R Y,WANG J Y.GAD:topology-aware time series anomaly detection[J].Journal on Communications,2020,41(6):152-160.
[14]SHEN Y H,JIANG X H,WANG Y Z,et al.A review of infe-rence research on temporal knowledge graph[J].Journal of Computing,2023,46(6):1272-1301.
[15]QUAN T,ZHU F,LING X,et al.Learning fair representations by separating the relevance ofpotential information[J].Information Processing & Management,2022,59(6):103103.
[16]SEO Y,DEFFERRARD M,VANDERGHEYNST P,et al.Structured sequence modeling with graph convolutional recurrent networks[C]//The 25th International Conference on Neural Information Processing(ICONIP 2018).ICONIP,2018:362-373.
[17]HE M,WEI Z,WEN J R.Convolutional neural networks ongraphs with chebyshev approximation,revisited[C]//Advances in Neural Information Processing Systems.NIPS,2022,35:7264-7276.
[18]YU B,YIN H,ZHU Z.Spatio-temporal graph convolutional networks:a deep learning framework for traffic forecasting[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence(IJCAI 2018).IJCAI,2018:3634-3640.
[19]CHEN D,HUANG T,SONG Z,et al.AGG-Net:AttentionGuided Gated-convolutional Network for Depth Image Completion[C]//Proceedings of the IEEE/CVF International Confe-rence on Computer Vision.IEEE,2023:8853-8862.
[20]WU Z,PAN S,LONG G,et al.Graphwavenet for deep spatial-temporal graph modeling[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence.2019:1907-1913.
[21]BI J,YUAN H,XU K,et al.Large-scale Network Traffic Prediction With LSTM and Temporal Convolutional Networks[C]//2022 International Conference on Robotics and Automation(ICRA).IEEE,2022:3865-3870.
[22]ZHENG C,FAN X,WANG C,et al.Gman:A graph multi-at-tention network for traffic prediction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.AAAI,2020:1234-1241.
[23]LEIK,QIN M,BAI B,et al.GCN-GAN:A non-linear temporal link prediction model for weighted dynamic networks[C]//IEEE INFOCOM 2019-IEEE Conference on Computer Communications.IEEE,2019:388-396.
[24]DE BRUIN G J,VEENMAN C J,VAN DEN HERIK H J,et al.Supervised temporal link prediction in large-scale real-world networks[J].Social Network Analysis and Mining,2021,11(1):80.
[25]LV L,BARDOU D,HU P,et al.Graph regularized nonnegative matrix factorization for link prediction in directed temporal networks using PageRank centrality[J].Chaos,Solitons & Fractals,2022,159:112107.
[26]CASOLA S,LAURIOLA I,LAVELLI A.Pre-trained trans-formers:an empirical comparison[J].Machine Learning with Applications,2022,9:100334.
[27]JI S,PAN S,CAMBRIA E,et al.A survey on knowledgegraphs:Representation,acquisition,and applications[J].IEEE Transactions on Neural Networks and Learning Systems,2021,33(2):494-514.
[28]BOSAGHZADEH A,DORNAIKA F.Incremental and dynamic graph construction with application to image classification[J].Expert Systems with Applications,2020,144:113117.
[29]XU D,RUAN C,KORPEOGLU E,et al.Inductive representation learning on temporal graphs[C]//8th International Confe-rence on Learning Representations(ICLR 2020).ICLR,2020:1-19.
[30]YAROTSKY D.Error bounds for approximations with deepReLU networks[J].Neural Networks,2017,94:103-114.
[31]XU Y,HUANG H,FENG C,et al.A supervised multi-head self-attention network for nested named entity recognition[C]//Proceedings of the AAAI Conference on Artificial Intelligence.AAAI,2021:14185-14193.
[32]LIU S,LIN T,HE D,et al.Paint transformer:Feed forward neural painting with stroke prediction[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.IEEE,2021:6598-6607.
[33]XU J,SUN X,ZHANG Z,et al.Understanding and improving layer normalization[C]//Proceedings of the 33rd International Conference on Neural Information Processing Systems(NIPS 2019).NIPS,2019:4381-4391.
[34]TA H T,RAHMAN A B,MAJUMDER N,et al.WikiDes:A Wikipedia-based dataset for generating short descriptions from paragraphs[J].Information Fusion,2023,90:265-282.
[35]LIU M,LIU Y.Inductive representation learning in temporal networks via mining neighborhood and community influences[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.ACM,2021:2202-2206.
[36]JIANG X,WANG Q,WANG B.Adaptive convolution for multi-relational learning[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.ACL,2019:978-987.
[37]TRIVEDI R,FARAJTABAR M,BISWAL P,et al.Dyrep:Learning representations over dynamic graphs[C]//Interna-tional Conference on Learning Representations(ICLR 2019).ICLR,2019:1-25.
[38]SONG C,SHU K,WU B.Temporally evolving graph neural network for fake news detection[J].Information Processing & Management,2021,58(6):102712.
[39]LIU J,LI D,GU H,et al.Parameter-free Dynamic Graph Embedding for Link Prediction[J].Advances in Neural Information Processing Systems(NIPS 2022).NIPS,2022:27623-27635.
[40]HAN Z,YANG F,HUANG J,et al.Multimodal dynamics:Dynamical fusion for trustworthy multimodal classification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2022:20707-20717.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发