Estimation of seasonal variation of ground resistance using Artificial Neural Networks

Objective of this paper is the development of a methodological approach for estimating the ground resistance by using Artificial Neural Network. The value of the ground resistance greatly depends on the grounding system and the properties of the soil, where the system is embedded. Given that the value of soil resistivity fluctuates during the year, the ground resistance does not have one single value. The approach proposed in this paper, takes advantage of the capability of Artificial Neural Networks (ANNs) to recognize linear and non-linear relationships between various parameters. By taking into account measurements of resistivity and rainfall data accrued for previous days, the ground resistance is estimated. On that purpose ANNs have been trained and validated by using experimental data in order to examine their ability to predict the ground resistance. The results prove the effectiveness of the proposed methodology.

► Soil resistivity and ground resistance seasonal variation measurements. ► Ground resistance estimation using field measurements and Artificial Neural Network. ► Artificial Neural Networks training by using different training algorithms. ► Sensitivity analysis of Artificial Neural Network results.