A Centrifugal Pump Fault Diagnosis Framework Based on Supervised Contrastive Learning

被引:14
作者
Ahmad, Sajjad [1 ]
Ahmad, Zahoor [1 ]
Kim, Jong-Myon [1 ,2 ]
机构
[1] Univ Ulsan, Dept Elect Elect & Comp Engn, Ulsan 44610, South Korea
[2] PD Technol Cooperat, Ulsan 44610, South Korea
关键词
centrifugal pumps; convolutional encoder; contrastive learning; fault diagnosis; deep learning; FEATURE-EXTRACTION; SPECTRAL KURTOSIS; AUTOENCODER; VIBRATION;
D O I
10.3390/s22176448
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
A novel intelligent centrifugal pump (CP) fault diagnosis method is proposed in this paper. The method is based on the contrast in vibration data obtained from a centrifugal pump (CP) under several operating conditions. The vibration signals data obtained from a CP are non-stationary because of the impulses caused by different faults; thus, traditional time domain and frequency domain analyses such as fast Fourier transform and Walsh transform are not the best option to pre-process the non-stationary signals. First, to visualize the fault-related impulses in vibration data, we computed the kurtogram images of time series vibration sequences. To extract the discriminant features related to faults from the kurtogram images, we used a deep learning tool convolutional encoder (CE) with a supervised contrastive loss. The supervised contrastive loss pulls together samples belonging to the same class, while pushing apart samples belonging to a different class. The convolutional encoder was pretrained on the kurtograms with the supervised contrastive loss to infer the contrasting features belonging to different CP data classes. After pretraining with the supervised contrastive loss, the learned representations of the convolutional encoder were kept as obtained, and a linear classifier was trained above the frozen convolutional encoder, which completed the fault identification. The proposed model was validated with data collected from a real industrial testbed, yielding a high classification accuracy of 99.1% and an error of less than 1%. Furthermore, to prove the proposed model robust, it was validated on CP data with 3.0 and 3.5 bar inlet pressure.
引用
收藏
页数:15
相关论文
共 32 条
  • [1] Multistage Centrifugal Pump Fault Diagnosis Using Informative Ratio Principal Component Analysis
    Ahmad, Zahoor
    Nguyen, Tuan-Khai
    Ahmad, Sajjad
    Nguyen, Cong Dai
    Kim, Jong-Myon
    [J]. SENSORS, 2022, 22 (01)
  • [2] A Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis
    Ahmad, Zahoor
    Rai, Akhand
    Hasan, Md Junayed
    Kim, Cheol Hong
    Kim, Jong-Myon
    [J]. IEEE ACCESS, 2021, 9 : 150128 - 150141
  • [3] Multistage Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Modes of Vibration and Using Pearson Linear Discriminant Analysis
    Ahmad, Zahoor
    Prosvirin, Alexander E.
    Kim, Jaeyoung
    Kim, Jong-Myon
    [J]. IEEE ACCESS, 2020, 8 : 223030 - 223040
  • [4] Alabied S., 2017, P 23 IEEE INT C AUTO, P7, DOI [10.23919/IConAC.2017.8082027, DOI 10.23919/ICONAC.2017.8082027]
  • [5] The spectral kurtosis: application to the vibratory surveillance and diagnostics of rotating machines
    Antoni, J
    Randall, RB
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2006, 20 (02) : 308 - 331
  • [6] Fast computation of the kurtogram for the detection of transient faults
    Antoni, Jerome
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2007, 21 (01) : 108 - 124
  • [7] Bachman P, 2019, ADV NEUR IN, V32
  • [8] Multi-fault Condition Monitoring of Slurry Pump with Principle Component Analysis and Sequential Hypothesis Test
    Chen, Hanxin
    Huang, Wenjian
    Huang, Jinmin
    Cao, Chenghao
    Yang, Liu
    He, Yibin
    Zeng, Li
    [J]. INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2020, 34 (07)
  • [9] A temporal-based SVM approach for the detection and identification of pollutant gases in a gas mixture
    Djeziri, Mohand A.
    Djedidi, Oussama
    Morati, Nicolas
    Seguin, Jean-Luc
    Bendahan, Marc
    Contaret, Thierry
    [J]. APPLIED INTELLIGENCE, 2022, 52 (06) : 6065 - 6078
  • [10] Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
    Dosovitskiy, Alexey
    Fischer, Philipp
    Springenberg, Jost Tobias
    Riedmiller, Martin
    Brox, Thomas
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (09) : 1734 - 1747