Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Anne Carolina Rodrigues Klaar; Laio Oriel Seman; Viviana Cocco Mariani; Leandro Dos Santos Coelho

doi:10.3390/s24041113

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Sensors (Basel). 2024 Feb 8;24(4):1113. doi: 10.3390/s24041113.

Authors

Anne Carolina Rodrigues Klaar¹, Laio Oriel Seman², Viviana Cocco Mariani^{3

4}, Leandro Dos Santos Coelho^{4

5}

Affiliations

¹ Graduate Program in Education, University of Planalto Catarinense, Lages 88509-900, Brazil.
² Department of Automation and Systems Engineering, Federal University of Santa Catarina, Florianópolis 88040-535, Brazil.
³ Mechanical Engineering Graduate Program, Pontifical Catholic University of Parana, Curitiba 80215-901, Brazil.
⁴ Department of Electrical Engineering, Federal University of Parana, Curitiba 81530-000, Brazil.
⁵ Industrial and Systems Engineering Graduate Program, Pontifical Catholic University of Parana, Curitiba 80215-901, Brazil.

Abstract

The electrical energy supply relies on the satisfactory operation of insulators. The ultrasound recorded from insulators in different conditions has a time series output, which can be used to classify faulty insulators. The random convolutional kernel transform (Rocket) algorithms use convolutional filters to extract various features from the time series data. This paper proposes a combination of Rocket algorithms, machine learning classifiers, and empirical mode decomposition (EMD) methods, such as complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), empirical wavelet transform (EWT), and variational mode decomposition (VMD). The results show that the EMD methods, combined with MiniRocket, significantly improve the accuracy of logistic regression in insulator fault diagnosis. The proposed strategy achieves an accuracy of 0.992 using CEEMDAN, 0.995 with EWT, and 0.980 with VMD. These results highlight the potential of incorporating EMD methods in insulator failure detection models to enhance the safety and dependability of power systems.

Keywords: electric power system; empirical mode decomposition; rocket algorithm; time series classification.

Grants and funding

The authors Mariani and Coelho thank the National Council of Scientific and Technologic Development of Brazil—CNPq (Grants numbers: 314389/2023-7-PQ, 313169/2023-3-PQ, 407453/2023-7-Universal, and 442176/2023-6-Peci), and Fundação Araucária PRONEX Grant 042/2018 for its financial support of this work. The author Seman thanks the National Council of Scientific and Technologic Development of Brazil—CNPq (Grant number: 308361/2022-9).