Grounding of electrical substations for safety and neutral point by ground rods and grid provides the lowest economical feasible ground resistance in the path of the expected fault current to ground. In the recent years Artificial Neural Networks (ANNs) have attracted much attention and many interesting ANN applications have been reported in power system areas, due to their computational speed, the ability to handle complex non-linear functions, robustness and great efficiency, even in cases where full information for the studied problem is absent. In this study several ANNs were addressed to evaluate apparent soil resistivity and design parameters of ground system for the predetermined grounding resistance value and soil resistivity without any need of complex calculations. These ANN are used to select the optimum dimensions and geometry of grounding system required for obtaining satisfactory ground resistance, and step and touch potentials.