Volume 23, Issue 1 (JIAEEE Vol.23 No.1 2026)                   Journal of Iranian Association of Electrical and Electronics Engineers 2026, 23(1): 0-0 | Back to browse issues page

XML Persian Abstract Print

Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Fadaei Tehrani M R, Dehghani M. The application of neural network to estimate the specific resistance of the soil in the ground system of the electricity distribution network. Journal of Iranian Association of Electrical and Electronics Engineers 2026; 23 (1)
URL: http://jiaeee.com/article-1-1783-en.html
The application of neural network to estimate the specific resistance of the soil in the ground system of the electricity distribution network
Mohamad Reza Fadaei Tehrani * , Mina Dehghani
Niro Research Institute
Abstract:   (3 Views)
Soil resistivity, as a key parameter in grounding systems, indicates the soil's ability to conduct electric current and directly impacts the performance of grounding systems. This research aims to provide a practical and cost-effective method for estimating soil-resistivity through limited measurements and training a neural network for optimal design of the distribution network grounding system. In this study, soil resistivity was measured at 70 points in Isfahan at three different depths and used to train a neural network in MATLAB. Considering the scattered distribution of measurement points, for better estimation, the data was subjected to statistical analysis using two sequential k-means clustering before being applied as input to the neural network. The first clustering was based on the geographical location of the points, and the second clustering was based on depth. The cluster resulting from this analysis was fed into the neural network as input. According to the results of this research, the correlation coefficient R2 between the actual and estimated values by the model was 0.9567, which is completely satisfactory and confirms that the application of the proposed method is a useful tool for estimating the performance of ground-resistance over a wide geographical area and at different depths.
Keywords: specific resistance, ground connection, two consecutive clustering, k-means
     
Type of Article: Research | Subject: Power
Received: 2024/12/28 | Accepted: 2025/12/6
Add your comments about this article : Your username or Email:
CAPTCHA
Send email to the article author

Rights and permissions
Creative Commons License This Journal is an open access Journal Licensed under the Creative Commons Attribution-NonCommercial 4.0 International License. (CC BY NC 4.0)