Bibliographic citations
Benites, A., Apaza, A., Céspedes, J., Ampuero, D. (2024). IDENTIFICACIÓN DE ZONAS DE RIESGO ELÉCTRICO POTENCIAL EN REDES DE MEDIA TENSIÓN EN EL PERÚ EMPLEANDO ALGORITMOS DE VISIÓN POR COMPUTADORA Y APRENDIZAJE AUTOMÁTICO EN NUBES DE PUNTOS LIDAR 3D [Trabajo de investigación, Universidad Peruana de Ciencias Aplicadas (UPC)]. http://hdl.handle.net/10757/682910
Benites, A., Apaza, A., Céspedes, J., Ampuero, D. IDENTIFICACIÓN DE ZONAS DE RIESGO ELÉCTRICO POTENCIAL EN REDES DE MEDIA TENSIÓN EN EL PERÚ EMPLEANDO ALGORITMOS DE VISIÓN POR COMPUTADORA Y APRENDIZAJE AUTOMÁTICO EN NUBES DE PUNTOS LIDAR 3D [Trabajo de investigación]. PE: Universidad Peruana de Ciencias Aplicadas (UPC); 2024. http://hdl.handle.net/10757/682910
@mastersthesis{renati/1032111,
title = "IDENTIFICACIÓN DE ZONAS DE RIESGO ELÉCTRICO POTENCIAL EN REDES DE MEDIA TENSIÓN EN EL PERÚ EMPLEANDO ALGORITMOS DE VISIÓN POR COMPUTADORA Y APRENDIZAJE AUTOMÁTICO EN NUBES DE PUNTOS LIDAR 3D",
author = "Ampuero Cutty, Diego Alonso",
publisher = "Universidad Peruana de Ciencias Aplicadas (UPC)",
year = "2024"
}
In Peru, there is a little-known risk in public opinion that poses a serious threat to public safety, particularly in urban areas. This risk refers to non-compliance with minimum safety distances (MSD) in proximity to overhead medium voltage grids, which represents a potential and enduring electrical risk if corrective actions are not implemented. These incidents affect individuals through service interruptions, accidents resulting from electrified elements in public spaces, and fires due to short circuits. Furthermore, they affect electricity companies with economic losses due to unbilled hours, damage to their infrastructure, payments for customer compensations and monetary penalties. The presence of elements close to these networks, such as buildings, metallic structures, trees or communications cables, is due to a complex problem in our country, implicating economic and social factors, inefficient supervision, negligent or no urban planning, informality, limited culture about risk prevention and even political or judicial factors. This project focuses on the problem within the framework of the OSINERGMIN supervisory process of electrical companies where on-site inspections are stipulated in which manual tasks are carried out that could be optimized using technology and data science. To this end, it is proposed to automatize the identification of potential electrical risk zones using mobile LiDAR technology and applying computer vision and machine learning algorithms, a model will be designed to identify medium voltage wiring and the closest objects. The outcomes may be complemented with photographs and geolocation of each scene, which will provide more precise and reliable evidences.
This item is licensed under a Creative Commons License