Back to Search Start Over

Estimation of Effective Length of Type-A Grounding System According to IEC 62305-3 Using a Machine Learning Regression Model.

Authors :
Lovrić, Dino
Krolo, Ivan
Jurić-Grgić, Ivica
Source :
Applied Sciences (2076-3417); Aug2024, Vol. 14 Issue 16, p6945, 15p
Publication Year :
2024

Abstract

Two types of grounding systems are recommended for use in the international standard IEC 62305-3, Part 3: Physical damage to structures and life hazard. One of these is a radial-based grounding system (type-A), which is used in soil resistivities of up to 3000 Ω m and is considered in this paper. It is a well-known fact that during lightning strikes, only a part of the grounding wire contributes to dissipating the lightning current into the surrounding soil. This effective part of the grounding system depends on several features, such as soil resistivity, burial depth, and rise time of the dissipated lightning current. The effect of all of these features on the effective length of the type-A grounding system is explored in this paper. A suitable supervised machine learning regression model is developed, which will enable readers to accurately approximate the effective length of the type-A grounding system for realistic values of input features. The trained model in the paper yielded an R 2 value of 0.99998 on the test set. In addition, two simple mathematical formulas are also provided, which produce similar but less accurate results ( R 2 values of 0.989883 and 0.998557, respectively). [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
20763417
Volume :
14
Issue :
16
Database :
Complementary Index
Journal :
Applied Sciences (2076-3417)
Publication Type :
Academic Journal
Accession number :
179350973
Full Text :
https://doi.org/10.3390/app14166945