Research on fault diagnosis technology of pumping units based on multi-modal information fusion
Journal of Mechanical StrengthVol. 48, Issue 6, Pages: 62-69(2026)
作者机构:
1.西南石油大学 计算机与软件学院,成都 610500
2.绵阳师范学院,绵阳 621000
作者简介:
WANG Xin, E-mail: xinwang@swpu.edu.cn
基金信息:
Excellent Young Scientists Fund of National Natural Science Foundation of China(52222402);Open Research Project of State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation Engineering(PLN 2022-33);Nanchong Science and Technology Plan Project(23XNSYSX0111)
ZHAO Xiangdong,JIANG Wei,GAO Guohai,et al. Research on fault diagnosis technology of pumping units based on multi-modal information fusion[J]. Journal of Mechanical Strength,2026,48(6):62-69.
ZHAO Xiangdong,JIANG Wei,GAO Guohai,et al. Research on fault diagnosis technology of pumping units based on multi-modal information fusion[J]. Journal of Mechanical Strength,2026,48(6):62-69.DOI: 10.16579/j.issn.1001.9669.2026.06.007.
Research on fault diagnosis technology of pumping units based on multi-modal information fusion
A fault diagnosis method based on multimodal information fusion was proposed. It addressed the issues of sample imbalance and limited diagnostic information in rod pump fault diagnosis. The goal was to improve the accuracy and reliability of fault diagnosis.
Methods
2
Firstly
data augmentation techniques were applied to address sample imbalance. This enhanced the diagnostic accuracy of minority class samples. Secondly
features were extracted from dynamometer cards and dynamic production data. These features were then fused. Finally
a transformer-based fault diagnosis framework was constructed. This framework achieved precise diagnosis of rod pump faults.
Results
2
The test results show that the proposed method performs well in accuracy and
F
1
-score. It offers a more reliable and effective solution for rod pump fault diagnosis.
LÜ Xiaoxiao , WANG Hanxiang , LIU Yanxin , et al . Study on operating performance and indicator diagram of rod pump production system under fault conditions [J]. Journal of China University of Petroleum (Edition of Natural Science) , 2020 , 44 ( 2 ): 117 - 126 . (In Chinese)
WU W , XING X , WEI H X , et al . Fault diagnosis of pumping system based on multimodal attention learning (CBMA Learning) [J]. Journal of Process Control , 2023 , 128 : 103006 .
ZHAO Xinyu , FAN Jun , HE Fang , et al . Fault diagnosis of pumping unit based on global and local features [J]. Journal of Mechanical Strength , 2023 , 45 ( 6 ): 1286 - 1292 . (In Chinese)
GIBBS S G . Predicting the behavior of sucker-rod pumping systems [J]. Journal of Petroleum Technology , 1963 , 15 ( 7 ): 769 - 778 .
DEREK H J , JENNINGS J W , MORGAN S M . Sucker rod pumping unit diagnostics using an expert system [C]// Proceedings of the Permian Basin Oil and Gas Recovery Conference . Richardson : Society of Petroleum Engineers , 1988 :SPE-17318-MS.
FENG K , JIANG Z N , HE W , et al . A recognition and novelty detection approach based on Curvelet transform,nonlinear PCA and SVM with application to indicator diagram diagnosis [J]. Expert Systems with Applications , 2011 , 38 ( 10 ): 12721 - 12729 .
WANG X , SHAO Z W , SHEN Y C , et al . Research on fast marking method for indicator diagram of pumping well based on K-means clustering [J]. Heliyon , 2023 , 9 ( 10 ): e20468 .
TANG Liwen , FAN Jun , ZHAO Xinyu , et al . Research on measurement method based on fault types and strength characteristics of power diagram [J]. Machinery Design & Manufacture , 2024 ( 9 ): 164 - 168 . (In Chinese)
LI J N , SHAO J , WANG W , et al . An evolutional deep learning method based on multi-feature fusion for fault diagnosis in sucker rod pumping system [J]. Alexandria Engineering Journal , 2023 , 66 : 343 - 355 .
ZHOU Xuan , WU Weili . Transformer fault diagnosis method based on improved SMOTE unbalanced sample processing and IHPO-DBN [J]. Power System Protection and Control , 2024 , 52 ( 11 ): 21 - 30 . (In Chinese)
KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 .
ZHANG Zhaolin , FAN Yugang . Fault diagnosis of a bearing using feature extraction method based on CEEMD algorithm and CNN [J]. Mechanical Science and Technology for Aerospace Engineering , 2019 , 38 ( 2 ): 178 - 183 . (In Chinese)
SUN Qifeng , LI Kehao , DUAN Youxiang , et al . Fluorescent thin section analysis method based on convolutional neural network and feature clustering [J]. Acta Petrolei Sinica , 2024 , 45 ( 3 ): 548 - 558 . (In Chinese)
VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [C]// Proceedings of the 31st International Conference on Neural Information . New York : Curran Associates Inc. , 2017 : 6000 - 6010 .
CHEN Junying , XI Yueyun , LI Zhaoyang . Prediction of aeroengine remaining life by combining multi-scale local features and transformer global learning [J]. Acta Automatica Sinica , 2024 , 50 ( 9 ): 1818 - 1830 . (In Chinese)
FARRAHI M R , CHERIET M . AdOtsu:an adaptive and parameterless generalization of Otsu’s method for document image binarization [J]. Pattern Recognition , 2012 , 45 ( 6 ): 2419 - 2431 .
SHI Hongbo , CHEN Yuwen , CHEN Xin . Summary of research on SMOTE oversampling and its improved algorithms [J]. CAAI Transactions on Intelligent Systems , 2019 , 14 ( 6 ): 1073 - 1083 . (In Chinese)
LI Kang , LI Shuang , GAO Xiaoyong , et al . Multivariate time series tokenized Transformer and its application in fault diagnosis of electric submersible pump [J]. Control and Decision , 2025 , 40 ( 4 ): 1145 - 1153 . (In Chinese)
Fault diagnosis of motor rolling bearings based on dual⁃channel information fusion and VCC-FuseNet
Research on fault diagnosis of rotating machinery based on deep learning and SMOTE data enhancement
THE REVIEW OF MECHANICAL FAULT DIAGNOSIS METHODS BASED ON CONVOLUTIONAL NEURAL NETWORK
Study on remaining useful life prediction method of grinding wheel based on CEEMDAN-LSTM-MHSA
Uncertainty analysis of simplified spline coupling model and its impact on rotor dynamic characteristics
Related Author
HE Yuling
ZHENG Hai
DAI Derui
ZHI Jiahe
WANG Nana
WANG Xiaolong
LI Wenzan
LIU Qinming
Related Institution
Hebei Key Laboratory of Electric Machinery Health Maintenance & Failure Prevention, North China Electric Power University
Hebei Engineering Research Center for Advanced Manufacturing & Intelligent Operation and Maintenance of Electric Power Machinery, North China Electric Power University
Binzhou Weiqiao Park Operation and Management Co., Ltd.
Business School, University of Shanghai for Science and Technology
Business School, University of Shanghai for Science & Technology