Imbalanced Fault Diagnosis of Electrical Submersible Pumps Using a Graph Regularized Weighted Extreme Learning Machine
Scientific Journal of Technology · 20.10.2026 · 8 (10) · 43-53
DOI: 10.54691/bqfwp120 ↗Kurz gefasst
Fachartikel in der Zeitschrift Scientific Journal of Technology, online erschienen am 20.10.2026. Verfasst von Wen Zhang und 1 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
To address class imbalance in spectrum-based fault diagnosis of electrical submersible pumps, a graph regularized weighted extreme learning machine is developed. Fixed features are obtained using random wavelet kernels and kernel group selection. The reciprocal of class frequency is used as the sample weight to balance the contributions of different classes to the supervised error. A graph Laplacian regularization term based on same-class neighbors is introduced to constrain the consistency of local predictions. The output weights are then obtained by solving a system of linear equations. Under a 32-fold protocol compatible with the dataset used, the method achieves an accuracy of 91.80%, a macro-averaged F1 score of 0.7500, and a balanced accuracy of 0.7810. Its macro-averaged F1 score exceeds that of the weighted extreme learning machine by 0.0496. Under controlled downsampling of the normal class and capped sampling of selected fault classes, the absolute improvement in macro-averaged F1 over WELM ranges from 0.0486 to 0.0575. The results indicate that class weighting and constraints on local structure within each class can jointly improve class-balanced diagnosis using fixed spectral features.
Zitieren
APA
Zhang, W., & Deng, L. (2026). Imbalanced Fault Diagnosis of Electrical Submersible Pumps Using a Graph Regularized Weighted Extreme Learning Machine. Scientific Journal of Technology, 8(10), 43-53. https://doi.org/10.54691/bqfwp120
Vancouver
Zhang W, Deng L. Imbalanced Fault Diagnosis of Electrical Submersible Pumps Using a Graph Regularized Weighted Extreme Learning Machine. Scientific Journal of Technology. 2026;8(10):43-53. doi:10.54691/bqfwp120
BibTeX
@article{Zhang2026,
author = {Zhang, Wen and Deng, Li},
title = {Imbalanced Fault Diagnosis of Electrical Submersible Pumps Using a Graph Regularized Weighted Extreme Learning Machine},
journal = {Scientific Journal of Technology},
year = {2026},
volume = {8},
number = {10},
pages = {43--53},
doi = {10.54691/bqfwp120}
}
EUVIMED