Denoising Autoencoder for Partial Discharge Identification in Instrument Transformers

Author(s)

Crivelaro, Matheus Goes ; Rodrigues, Douglas ; Gifalli, Andre ; Papa, Joao Paulo ; Gonzales, Carlos Guilherme ; de Souza, Andre Nunes ; da Silva, Gustavo Vinicius ; Silveira Neto, Erasmo

• Document type: Journal article
• Source: 2024 31ST INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING, IWSSIP 2024; v. N/A, p. 7-pg., 2024-01-01.

Abstract

Analyzing Partial Discharge (PD) signals is crucial to assessing the health of insulation in high-voltage systems. Nevertheless, noise often distorts these signals, hindering the ability to obtain precise information. This paper proposes a novel deep-learning approach using two denoising autoencoders (DAEs) to learn data representations and eliminate noise during reconstruction. By leveraging DAEs' capacity to capture essential features within the latent space, this method enhances the analysis of PD signals and yields more accurate results. This paper investigates the effectiveness of two deep-learning architectures for denoising partial discharge signals in high-voltage insulation systems. Experimental results carried out on a PD dataset demonstrated the efficiency of the Linear AE model in removing noise in sets A, B, and C suggesting that DAEs hold great promise in PD signal denoising. (AU)

• FAPESP's process: 23/03726-4 - On the Study and Development of Multi-method Multi-objective Algorithms
• Grantee: Douglas Rodrigues
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• FAPESP's process: 19/07665-4 - Center for Artificial Intelligence
• Grantee: Fabio Gagliardi Cozman
• Support Opportunities: Research Grants - Research Program in eScience and Data Science - Research Centers in Engineering Program
• FAPESP's process: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry
• Grantee: Francisco Louzada Neto
• Support Opportunities: Research Grants - Research, Innovation and Dissemination Centers - RIDC
• FAPESP's process: 23/14427-8 - Data Science for Smart Industry (CDII)
• Grantee: José Alberto Cuminato
• Support Opportunities: Research Grants - Applied Research Centers Program