Exportar Publicação

Seman, L. O., Stefenon, S. F., Leithardt, V. R. Q., de Paz Santana, J. F. & Yow, K.-C. (2026). Feature-engineered ensemble learning methods for insulator fault detection based on ultrasound signals. Egyptian Informatics Journal. 35

L. O. Seman et al.,  "Feature-engineered ensemble learning methods for insulator fault detection based on ultrasound signals", in Egyptian Informatics Journal, vol. 35, 2026

@article{seman2026_1788306362891,
	author = "Seman, L. O. and Stefenon, S. F. and Leithardt, V. R. Q. and de Paz Santana, J. F. and Yow, K.-C.",
	title = "Feature-engineered ensemble learning methods for insulator fault detection based on ultrasound signals",
	journal = "Egyptian Informatics Journal",
	year = "2026",
	volume = "35",
	number = "",
	doi = "10.1016/j.eij.2026.101038",
	url = "https://www.sciencedirect.com/journal/egyptian-informatics-journal"
}

TY  - JOUR
TI  - Feature-engineered ensemble learning methods for insulator fault detection based on ultrasound signals
T2  - Egyptian Informatics Journal
VL  - 35
AU  - Seman, L. O.
AU  - Stefenon, S. F.
AU  - Leithardt, V. R. Q.
AU  - de Paz Santana, J. F.
AU  - Yow, K.-C.
PY  - 2026
SN  - 1110-8665
DO  - 10.1016/j.eij.2026.101038
UR  - https://www.sciencedirect.com/journal/egyptian-informatics-journal
AB  - This paper presents a feature-engineered ensemble method for fault detection in medium-voltage insulator ultrasound signals. We develop a feature extraction framework that captures time-domain, frequency-domain, wavelet-domain, and envelope characteristics of ultrasonic emissions from porcelain insulators under various conditions: normal operation, artificial contamination, and simulated lightning damage. A robust signal augmentation methodology enhances classification robustness while preserving class-discriminative properties. We evaluate standard ensemble approaches (random forest, extreme gradient boosting, and light gradient boosting) and introduce two novel algorithms: EvoBagging, which employs evolutionary operators to optimize bootstrap samples, and proximal policy optimization bagging (PPOBagging), which leverages reinforcement learning through proximal policy optimization to construct ensembles via sequential decision-making. Experimental results demonstrate that our feature engineering approach significantly outperforms raw signal classification (91.67% vs. 55.00% accuracy). The proposed PPOBagging algorithm achieves the highest performance with 94.17% accuracy and a macro-F1 score of 0.9412, surpassing conventional methods. Comparative analysis against convolutional kernel transforms (standard, mini, and multi random convolutional kernels) reveals that while these methods offer competitive accuracy (up to 88.33%), they fall short of our feature-engineered ensemble approach in both performance and interpretability. Comparison against deep learning methods also reaffirms the usefulness of the proposed feature engineering technique. This work contributes practical tools for non-destructive monitoring of power distribution systems, enabling proactive maintenance strategies to prevent failures.
ER  -