1887

Abstract

Summary

This study explores the application of SqueezeNet, a lightweight deep learning architecture, for fault diagnosis in sucker rod pumps within the oil and gas industry. Initially, SqueezeNet encountered challenges in accurately classifying fault conditions. To address this, the integration of Error-Correcting Output Codes (ECOC) classifiers, specifically Support Vector Machines (SVM) and k-Nearest Neighbors (k-NN), was implemented, resulting in a significant improvement in accuracy and a reduction in misclassifications. Additionally, data augmentation techniques were employed to enhance the diversity and robustness of the training data, further boosting the model’s generalization capabilities.

Our findings highlight the transformative potential of combining deep learning with advanced machine learning techniques for predictive maintenance in critical infrastructure. The improved fault diagnosis accuracy can optimize asset management, leading to increased operational efficiency and enhanced reliability. These advancements can guide decision-making processes, resulting in substantial cost savings and improved asset reliability for sucker rod pump operations and other applications. This study underscores the value of innovative approaches in the oil and gas sector, paving the way for more efficient and reliable operations through the adoption of cutting-edge technologies.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202477004
2024-10-15
2026-02-10

  • From This Site

    /content/papers/10.3997/2214-4609.202477004
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Hari, S., Krishna, S., Gurrala, L. N., Singh, S., Ranjan, N., Vij, R. K., and Shah, S. N. [2021]. Impact of reservoir, fracturing fluid and proppant characteristics on proppant crushing and embedment in sandstone formations. Journal of Natural Gas Science and Engineering, 95 (November). https://doi.org/10.1016/j.jngse.2021.104187
     [Google Scholar]
  2. Kini, A. S., Prema, K. V., and Pai, S. N. [2024]. Early stage black pepper leaf disease prediction based on transfer learning using ConvNets. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-51884-0
     [Google Scholar]
  3. Krishna, S., Sreenivasan, H., and Nair, R. R. [2018]. Hydraulic fracture studies of reservoirs with an emphasis on pore fracture geometry studies by developing fracture and microseismic estimations. Annals of Geophysics, 61(5), 1–14. https://doi.org/10.4401/ag-7638
     [Google Scholar]
  4. Patel, S., Wilson, I., Sreenivasan, H., and Krishna, S. [2024]. Numerical simulations of proppant transportation in cryogenic fluids: Implications on liquid helium and liquid nitrogen fracturing for subsurface hydrogen storage. International Journal of Hydrogen Energy, 56(October 2023), 924–936. https://doi.org/10.1016/j.ijhydene.2023.12.268
     [Google Scholar]
  5. Patel, S., Wilson, I., Sreenivasan, H., Naveen, P., Gupta, P., and Krishna, S. [2023]. Proppant transportation and placement in fractures by water and liquid nitrogen : a numerical simulation. Computational Particle Mechanics. https://doi.org/10.1007/s40571-023-00649-z
     [Google Scholar]
  6. Temizel, C., Canbaz, C. H., Betancourt, D., Ozesen, A., Acar, C., Krishna, S., and Saputelli, L. [2020]. A comprehensive review and optimization of artificial lift methods in unconventionals. Annual Technical Conference and Exhibition. https://doi.org/10.2118/201692-ms
     [Google Scholar]
  7. Temizel, C., Canbaz, C. H., Saracoglu, O., Putra, D., Baser, A., Erfando, T., Krishna, S., and Saputelli, L. [2020]. Production forecasting in shale reservoirs using LSTM method in deep learning. Unconventional Resources Technology Conference. https://doi.org/10.15530/urtec-2020-2878
     [Google Scholar]
/content/papers/10.3997/2214-4609.202477004
Loading
SqueezeNet-Based Fault Diagnosis and Predictive Maintenance for Sucker Rod Pumps using ECOC Classifiers for Asset Management
Conference Proceedings 2024, 1 (2024); https://doi.org/10.3997/2214-4609.202477004
/content/papers/10.3997/2214-4609.202477004
/content/papers/10.3997/2214-4609.202477004
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error