计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220400128-8.doi: 10.11896/jsjkx.220400128

• 软件&交叉 • 上一篇    下一篇

基于核鲁棒流形非负矩阵分解和融合特征的柴油机故障诊断

刘弘毅1,2, 王瑞3, 吴贯锋1,2, 张阳1,2   

  1. 1 西南交通大学数学学院 成都 611756;
    2 系统可信性自动验证国家地方联合工程实验室 成都 611756;
    3 中国航天电子技术研究院 北京 100094
  • 出版日期:2023-06-10 发布日期:2023-06-12
  • 通讯作者: 吴贯锋(wgf1024@swjtu.edu.cn)
  • 作者简介:(905759310@qq.com)
  • 基金资助:
    国家自然科学基金(62106206)

Diesel Engine Fault Diagnosis Based on Kernel Robust Manifold Nonnegative Matrix Factorizationand Fusion Features

LIU Hongyi1,2, WANG Rui3, WU Guanfeng1,2, ZHANG Yang1,2   

  1. 1 School of Mathematics,Southwest Jiaotong University,Chengdu 611756,China;
    2 National-Local Joint Engineering Laboratory of System Credibility Automatic Verification,Chengdu 611756,China;
    3 China Academy of Aerospace Electronics Technology,Beijing 100094,China
  • Online:2023-06-10 Published:2023-06-12
  • About author:LIU Hongyi,born in 1998,postgra-duate,is a member of China Computer Federation.His main research interests include machine learning and fault diagnosis. WU Guanfeng,born in 1986,Ph.D,is a member of China Computer Federation.His main research interests include intelligent information processing and parallel computing.
  • Supported by:
    National Natural Science Foundation of China(62106206).

PDF (PC)

579

摘要： 柴油发动机作为工业生产上的重要动力源之一,若其产生故障,将对工业生产的效率和安全造成巨大的影响,因此对柴油机进行故障诊断具有重要意义。针对柴油发动机气门故障诊断中特征提取困难和准确率不高的问题,提出一种基于核鲁棒流形非负矩阵分解方法和融合特征的柴油机故障诊断方法。首先,对压力信号进行时域分析,提取压力特征;其次使用短时傅里叶变换对振动信号进行时频分析;然后用核鲁棒流形非负矩阵分解提取振动信号中的特征;再融合压力信号中的特征与振动信号中的特征;最后使用支持向量机实现故障诊断。与传统方法相比,该方法在采集的数据集上故障诊断准确率可达100%,证明该方法可以有效提取特征并显著提高诊断准确率。

关键词: 柴油机, 故障诊断, 非负矩阵分解, 特征提取, 融合特征

Abstract: The diesel engine is one of the important power sources in industrial production,its failure will cause a huge impact on the efficiency and safety of industrial production,it is of great significance to diagnose the fault of diesel engine.Aiming at the difficulty and low accuracy of feature extraction in diesel engine valve fault diagnosis,a diesel engine fault diagnosis method based on kernel robust manifold non-negative matrix factorization method and fusion feature is proposed.Firstly,the pressure signal is analyzed in the time domain to extract the pressure characteristics.Secondly,the time-frequency analysis of the vibration signal is carried out using the short-time flourier transform(STFT),and the features of the vibration signal are extracted by the kernel robust manifold nonnegative matrix factorization.Then the features of the pressure signal and vibration signal are fused.Finally,support vector machine is used to realize fault diagnosis.Compared with the traditional method,the fault diagnosis accuracy of this method can reach 100% on the collected data set,which proves that it can effectively extract features and significantly improve the diagnosis accuracy.

Key words: Diesel engine, Fault diagnosis, Nonnegative matrix factorization, Feature extraction, Fusion feature

中图分类号: 

  • TP206
[1]LV S G,YANG L,YANG Q.Research on the applications of infrared technique in the diagnosis and prediction of diesel engine exhaust fault[J].Journal of Thermal Science,2011,20(2):189-194.
[2]YANG T T.Investigation into the condition monitoring of in-cylinder combustion behaviours of diesel engines based on time-frequency analysis of vibration signals[D].Taiyuan:Taiyuan University of Technology,2019.
[3]YUE Y J,WANG X,CAI Y P,et al.A novel fault feature ex-traction scheme for diesel engine valves based on feature reduction of time-frequency images[J].Automotive Engineering,2018,40(1):114-120,126.
[4]LEE D D,SEUNG H S.Learning the parts of obj-ects by non-negative matrix factorization[J].Nature,1999,401(6755):788-791.
[5]WANG X,YUE Y J,CAI Y P.Fast sparse dec-omposition andtwo-dimensional feature encoding recognition method of diesel engine vibration signal[J].Journal of Vibration,Measurement &Diagnosis,2019,39(1):114-122,225.
[6]CAI Y P,FAN Y,CHEN W,et al.Application of improvedtime-frequency analysis and feature fusion in fault diagnosis of IC engines[J].China Mechanical Engineering,2020,31(16):1901-1911.
[7]WANG H Q,WANG M Y,SONG L Y,et al.Method of compound fault signal separation using double constraints non-negative factorization[J].Journal of Vibration Engineering,2020,33(3):590-596.
[8]MA C P,LIANG L,CHEN Y M,et al.Feature ext-raction for fault diagnosis of machine based on kernel nonnegative matrix factorization[C]//2020 IEEE 4th Information Technology,Networking,Electronic and Automation Control Conference(IT-NEC).IEEE,2020:1412-1416.
[9]ZHANG D,ZHOU Z H,CHEN S.Non-negative matrix factorization on kernels[C]//Pacific Rim International Conference on Artificial Intelligence.Berlin:Springer,2006:404-412.
[10]KONG D,DING C,HUANG H.Robust nonnegative matrix factorization using l21-norm[C]//Proceedings of the 20th ACM International Conference on Information and KnowledgeMana-gement.2011:673-682.
[11]DING C,ZHOU D,HE X F,et al.R1-pca:rotational invariant l1-norm principal component analysis for robust subspace facto-rization[C]//Proceedings of the 23rd International Conference on Machine Learning.2006:281-288.
[12]CAI D,HE X F,HAN J W,et al.Graph regular-ized nonnegative matrix factorization for data represen-tation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,33(8):1548-1560.
[13]WANG Y S,SUN T S,DING M T,et al.Actuator dynamicprocess fault detection using kernel robust non-negative matrix factorization[J/OL].Control Theory & Applications:1-9.http://kns.cnki.n-et/kcms/detail/44.1240.TP.20211117.1453.026.html.
[14]ZHU X J.Fault diagnosis of beards compound fault based on sparse no-negative matrix factorization[J].Chinese Journal of Construction Machinery,2018,16(6):553-558.
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