SciELO - Scientific Electronic Library Online

 
vol.35 número1Control de un restaurador dinámico de tensión basado en la transformada de Fourier del Vector EspacialSistemas Integrados de energías con fuentes renovables, requisitos y opciones índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Servicios Personalizados

Revista

Articulo

Indicadores

  • No hay articulos citadosCitado por SciELO

Links relacionados

  • No hay articulos similaresSimilares en SciELO

Compartir


Ingeniería Energética

versión On-line ISSN 1815-5901

Resumen

MARTINEZ LOZANO, Miguel. Methodology based on neural networks for earth resistivity interpretation in congested urban areas. Energética [online]. 2014, vol.35, n.1, pp.59-69. ISSN 1815-5901.

One of the main troubles for grounding system design in an electrical installation on congested urban areas is obtaining the soil parameters, since the traditional measurements techniques are not applicable due to the limited space. In the present work, an alternative procedure based on introducing a driven rod into the soil and registering the variation of ground resistance versus the depth, is presented; with the field measurements obtained, a procedure were evaluated to estimate the soil parameters in a simplified bi-stratified model (two vertical layers) using a trained neural network to minimize the effort and time to obtain the respective results. The trouble about the measurement and estimation of electrical soil properties in congested urban areas is solved with the detailed methodology presented, based on non conventional measurement techniques and computational processing.The results obtained during both digital simulation and field measurements, demonstrates the validity of the proposed procedure and making feasible its application to engineering projects.

Palabras clave : soil resistivity estimation on congested urban areas; grounding systems; neural networks.

        · resumen en Español     · texto en Español     · Español ( pdf )

 

Creative Commons License Todo el contenido de esta revista, excepto dónde está identificado, está bajo una Licencia Creative Commons