Gustavo Fardo Armênio

Gustavo Fardo Armênio

Auto-generated profile, based on publicly available information

Gustavo Fardo Armênio

Universidade Tecnolgica Federal do Paran UTFPR, Av. Sete de Setembro, Curitiba, PR, Brazil

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 December 2024 in IEEE Access
Verified
Journal Article
Open access
JAJosé Mário Nishihara De Albuquerque
José Mário Nishihara De Albuquerque
ONOswaldo Ramos Neto
Oswaldo Ramos Neto
GAGustavo Fardo Armênio
Gustavo Fardo Armênio
VCVinicius Miranda Correa
Vinicius Miranda Correa
DVDavi Riiti Goto Do Valle
Davi Riiti Goto Do Valle
Andre Schneider De OliveiraAndre Schneider De Oliveira
Andre Schneider De Oliveira
This study presents an innovative technique for the predictive inspection of power lines utilizing an autonomous line-crawling inspection robot equipped with multimodal sensors. The system enhances the robot’s capabilities by integrating comprehensive analyses of power line conditions and correlating these assessments with historical data to predict the future state of power infrastructure. The inspection framework is organized into three modules: a frontal multimodal sensor module for examining key power components, such as dampers, wire markers, and insulators; a cable inspection module for detailed analysis of power cables; and a perpendicular perception module to evaluate power elements in the lower plane and monitor vegetation encroachment. The results demonstrate a significant enhancement in the robot’s ability to accurately identify and categorize power line components, leveraging the advantages of various techniques. The system generates composite inspection data that offers a comprehensive assessment of the power line condition in a consolidated multimodal inspection map by standardizing and correlating information collected from multiple viewpoints. This synthesis of diverse sensor data enables early detection of issues and supports proactive maintenance strategies. The proposed method represents a significant advancement in power line inspection, providing enhanced reliability, safety, and operational efficiency.