Imbalanced Fault Diagnosis of Electrical Submersible Pumps Using a Graph Regularized Weighted Extreme Learning Machine
DOI:
https://doi.org/10.54691/bqfwp120Keywords:
Electrical Submersible Pump; Fault Diagnosis; Class Imbalance; Weighted Extreme Learning Machine; Graph Laplacian Regularization; Vibration Spectrum.Abstract
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.
Downloads
References
[1] Liu, R., Yang, B., Zio, E., et al. (2018). Artificial intelligence for fault diagnosis of rotating machinery: A review. Mechanical Systems and Signal Processing, 108, 33–47.
[2] He, H., & Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263–1284.
[3] Krawczyk, B. (2016). Learning from imbalanced data: Open challenges and future directions. Progress in Artificial Intelligence, 5(4), 221–232.
[4] Guo, H., Li, Y., Shang, J., et al. (2017). Learning from class-imbalanced data: Review of methods and applications. Expert Systems with Applications, 73, 220–239.
[5] Chawla, N. V., Bowyer, K. W., Hall, L. O., et al. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357.
[6] Li, K., Li, S., Gao, X. Y., et al. (2025). Multivariate time-series tokenization Transformer and its application to fault diagnosis of electrical submersible pumps. Control and Decision, 40(4), 1145–1153. (in Chinese)
[7] Mello, L. H. S., Oliveira-Santos, T., Varejão, F. M., et al. (2022). Ensemble of metric learners for improving electrical submersible pump fault diagnosis. Journal of Petroleum Science and Engineering, 218, 110875.
[8] Varejão, F. M., Mello, L. H. S., Ribeiro, M. P., et al. (2024). An open source experimental framework and public dataset for vibration-based fault diagnosis of electrical submersible pumps used on offshore oil exploration. Knowledge-Based Systems, 288, 111452.
[9] Feng, Y., Zheng, C., Chen, J., et al. (2025). Beyond deep features: Fast random wavelet kernel convolution for weak-fault feature extraction of rotating machinery. Mechanical Systems and Signal Processing, 224, 112057.
[10] Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2004). Extreme learning machine: A new learning scheme of feedforward neural networks. In Proceedings of the 2004 IEEE International Joint Conference on Neural Networks (Vol. 2, pp. 985–990).
[11] Huang, G. B., Zhu, Q. Y., & Siew, C. K. (2006). Extreme learning machine: Theory and applications. Neurocomputing, 70(1–3), 489–501.
[12] Zong, W., Huang, G. B., & Chen, Y. (2013). Weighted extreme learning machine for imbalance learning. Neurocomputing, 101, 229–242.
[13] Belkin, M., Niyogi, P., & Sindhwani, V. (2006). Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. Journal of Machine Learning Research, 7, 2399–2434.
[14] Huang, G., Song, S., Gupta, J. N. D., et al. (2014). Semi-supervised and unsupervised extreme learning machines. IEEE Transactions on Cybernetics, 44(12), 2405–2417.
[15] von Luxburg, U. (2007). A tutorial on spectral clustering. Statistics and Computing, 17(4), 395–416.
[16] Zelnik-Manor, L., & Perona, P. (2004). Self-tuning spectral clustering. In Advances in Neural Information Processing Systems 17 (pp. 1601–1608).
[17] Sokolova, M., & Lapalme, G. (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4), 427–437.
[18] Brodersen, K. H., Ong, C. S., Stephan, K. E., et al. (2010). The balanced accuracy and its posterior distribution. In Proceedings of the 20th International Conference on Pattern Recognition (pp. 3121–3124).
[19] Kubat, M., Holte, R. C., & Matwin, S. (1998). Machine learning for the detection of oil spills in satellite radar images. Machine Learning, 30(2–3), 195–215.
[20] Demšar, J. (2006). Statistical comparisons of classifiers over multiple data sets. Journal of Machine Learning Research, 7, 1–30.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Scientific Journal of Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
