Fault diagnosis of a mixed-flow pump under cavitation condition based on deep learning techniques

被引:2
|
作者
Tan, Yangyang [1 ]
Wu, Guoying [2 ]
Qiu, Yanlin [3 ]
Fan, Honggang [4 ]
Wan, Jun [5 ]
机构
[1] Jiangxi Port & Waterway Construct Investment Grp C, Jian, Peoples R China
[2] China Water Resources Pearl River Planning Surveyi, Guangzhou, Peoples R China
[3] Shanghai Chongming Dist Miao Town Water Affairs Ma, Shanghai, Peoples R China
[4] Tsinghua Univ, Dept Energy & Power Engn, State Key Lab Hydrosci & Engn, Beijing, Peoples R China
[5] Jiangxi Jiepai Nav & Elect Hub Management Off, Yingtan, Peoples R China
基金
中国国家自然科学基金;
关键词
fault diagnosis; mixed-flow pump; deep learning; convolution neural network; cavitation condition;
D O I
10.3389/fenrg.2022.1109214
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Deep learning technique is an effective mean of processing complex data that has emerged in recent years, which has been applied to fault diagnosis of a wide range of equipment. In the present study, three types of deep learning techniques, namely, stacked autoencoder (SAE) network, long short term memory (LSTM) network, and convolutional neural network (CNN) are applied to fault diagnosis of a mixed-flow pump under cavitation conditions. Vibration signals of the mixed-flowed pump are collected from experiment measurements, and then employed as input datasets for deep learning networks. The operation status is clarified into normal, minor cavitation, and severe cavitation conditions according to visualized bubble density. The techniques of FFT and dropout algorithms are also applied to improve diagnosis accuracy. The results show that the diagnosis accuracy based on SAE and LSTM networks is lower than 50%, while is higher than 68% when using CNN. The maximum accuracy can reach 87.2% by mean of a combination of CNN, BN, MLP, and using frequency domain data by FFT as inputs, which validates the feasibility of applying CNN in mixed-flow pumps.
引用
收藏
页数:10
相关论文
共 50 条
  • [31] Study on transient hydrodynamic performance and cavitation characteristic of high-speed mixed-flow pump
    Chen, T.
    Sun, Y. B.
    Liu, Y. L.
    Wu, D. Z.
    Wang, L. Q.
    [J]. 6TH INTERNATIONAL CONFERENCE ON PUMPS AND FANS WITH COMPRESSORS AND WIND TURBINES (ICPF2013), 2013, 52
  • [32] Experiment on pressure fluctuation in mixed-flow pump under different flow rate conditions
    Li W.
    Ji L.
    Shi W.
    Zhou L.
    Ping Y.
    [J]. Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery, 2016, 47 (12): : 70 - 76
  • [33] Multi-condition optimization and experimental study of impeller blades in a mixed-flow pump
    Liu, Houlin
    Chen, Xinxiang
    Wang, Kai
    Tan, Minggao
    Zhou, Xiaohua
    [J]. ADVANCES IN MECHANICAL ENGINEERING, 2016, 8 (06)
  • [34] Mixed-flow pump cavitation characteristics extraction based on power spectrum density through pressure pulsation signal analysis
    Xu, Wentao
    Cheng, Li
    Lei, Shuaihao
    Yu, Lei
    Jiao, Weixuan
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2024, 208
  • [35] PIV measurement of internal flow in mixed-flow pump under different flow rate conditions
    Li W.
    Ji L.
    Shi W.
    Zhou L.
    Zhang Y.
    [J]. 2016, Chinese Society of Agricultural Engineering (32): : 82 - 88
  • [36] Numerical simulation of flow in centrifugal pump under cavitation and sediment condition
    Guo, P. C.
    Lu, J. L.
    Zheng, X. B.
    Zhao, Q.
    Luo, X. Q.
    [J]. 26TH IAHR SYMPOSIUM ON HYDRAULIC MACHINERY AND SYSTEMS, PTS 1-7, 2013, 15
  • [37] Numerical Simulation on the Performance of a Mixed-Flow Pump under Various Casing Structures
    Wu Dazhuan
    Hu Fangfang
    Wang Leqin
    [J]. ADVANCES IN MECHANICAL ENGINEERING, 2013,
  • [38] A hybrid approach for gearbox fault diagnosis based on deep learning techniques
    Bessaoudi, Mokrane
    Habbouche, Houssem
    Benkedjouh, Tarak
    Mesloub, Ammar
    [J]. INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2024, 133 (5-6): : 2861 - 2874
  • [39] Optimum design on impeller blade of mixed-flow pump based on CFD
    Li, Jidong
    Zeng, Yongzhong
    Liu, Xiaobing
    Wang, Huiyan
    [J]. INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTATIONAL MODELING AND SIMULATION, 2012, 31 : 187 - 195
  • [40] Vehicle Turning Behavior Modeling at Conflicting Areas of Mixed-Flow Intersections Based on Deep Learning
    Sun, Jian
    Qi, Xiao
    Xu, Yiming
    Tian, Ye
    [J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2020, 21 (09) : 3674 - 3685