The study of fault-diagnosis method of reciprocating compressor based on fuzzy fault tree theory

被引:0
|
作者
Gong, Jian-Chun [1 ]
Tian, PENG-Fei [1 ]
机构
[1] PanZhiHua Univ, Panzhihua 617000, Peoples R China
关键词
reciprocating compressor; fuzzy set theory; fault tree; diagnosis;
D O I
10.4028/www.scientific.net/AMM.217-219.2649
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Since working condition of reciprocating compressor is awfully bad and it has bigger risk in operation and higher fault rate, it is of importance to study reciprocating compressor fault. Fault tree has been established in this paper by analyzing factors leading reciprocating compressor fault based on the method of fault tree. 21 minimum cut sets leading to reciprocating compressor fault can be gotten through qualitative analyses on this fault tree, the happening probability of the top event can be calculated and the importance of the basic event s can be analyzed through quantitative analysis. The expert inquiry method combined with fuzzy sets theory is adopted to assess the happening probability of the basic events and top events. Reciprocating compressor is extensively used in many petroleum and chemical enterprises for high compression ratio of single stage and high work efficiency. Once the machines are abnormal and fault,it will affect the normal production, bring huge economic loss.Development of reciprocating compressor fault diagnosis, fault elimination can be invisible, the normal operation of the machine can be ensured, economic benefit be improved. ([1]) Application of fuzzy fault tree theory can effectively diagnose reciprocating compressor failure probability, and quickly identify the predisposing factors causing failure.
引用
收藏
页码:2649 / 2653
页数:5
相关论文
共 50 条
  • [41] Fault diagnosis of reciprocating compressor based on group self-attention network
    Bao, Ganchao
    Zhang, Hongli
    Wei, Yuan
    Gu, Dan
    Liu, Shulin
    [J]. MEASUREMENT SCIENCE AND TECHNOLOGY, 2020, 31 (06)
  • [42] Fault-diagnosis for reciprocating compressors using big data and machine learning
    Qi, Guanqiu
    Zhu, Zhiqin
    Erqinhu, Ke
    Chen, Yinong
    Chai, Yi
    Sun, Jian
    [J]. SIMULATION MODELLING PRACTICE AND THEORY, 2018, 80 : 104 - 127
  • [43] FAULT-DIAGNOSIS BASED ON QUALITATIVE REASONING
    YAMASHITA, Y
    SHOJI, S
    SUZUKI, M
    [J]. KAGAKU KOGAKU RONBUNSHU, 1988, 14 (03) : 387 - 394
  • [44] Fault Diagnosis Method of Reciprocating Compressor Based on Domain Adaptation under Multi-working Conditions
    Zhang, Lijun
    Duan, Lixiang
    Hong, Xiaocui
    Zhang, Xinyun
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION (IEEE ICMA 2021), 2021, : 588 - 593
  • [45] Fuzzy Bayesian Network Fault Diagnosis Method Based on Fault Tree for Coal Mine Drainage System
    Shi, Xiaojuan
    Gu, Huabei
    Yao, Bing
    [J]. IEEE SENSORS JOURNAL, 2024, 24 (06) : 7537 - 7547
  • [46] FAULT DIAGNOSIS OF RECIPROCATING COMPRESSOR VALVE USING ACOUSTIC EMISSION
    Wang, Y. F.
    Peng, X. Y.
    [J]. INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION - 2012, VOL 6, PTS A AND B, 2013, : 101 - 106
  • [47] Using working progress simulation for fault diagnosis of reciprocating compressor
    Liu, BY
    Liu, ML
    Chang, HB
    [J]. PROGRESS IN SAFETY SCIENCE AND TECHNOLOGY, VOL 4, PTS A and B, 2004, 4 : 1970 - 1974
  • [48] Applications of Machine Learning to Reciprocating Compressor Fault Diagnosis: A Review
    Lv, Qian
    Yu, Xiaoling
    Ma, Haihui
    Ye, Junchao
    Wu, Weifeng
    Wang, Xiaolin
    [J]. PROCESSES, 2021, 9 (06)
  • [49] A Fault Diagnosis Method for Information Systems Based on Weighted Fault Diagnosis Tree
    Duan, Liming
    Wang, Fenghai
    Guo, Ruifeng
    Gai, Rongli
    [J]. 2017 IEEE 19TH INTERNATIONAL CONFERENCE ON E-HEALTH NETWORKING, APPLICATIONS AND SERVICES (HEALTHCOM), 2017,
  • [50] Fault diagnosis method for reciprocating machine based on local wave theory and neural network
    Bie Fengfeng
    Ma Xiaojiang
    [J]. Proceedings of the First International Symposium on Test Automation & Instrumentation, Vols 1 - 3, 2006, : 1060 - 1064