Determination of Rail Voltage Depending on Operational Datas in a 1500 V DC Subway Line With Artificial Intelligence Methods

Abstract

In this study, the determination of the rail voltage for a 1500 V DC-fed rail system by means of the adaptive neuro-fuzzy inference system (ANFIS), support vector machines (SVM) and artificial neural networks (ANN). The distance occurring on the line was calculated with regard to the operating parameters by means of the ANFIS, SVM and ANN. The ANFIS, SVM and ANN were explained and a comparison was made. The electrification system in the rail systems is designed with regard to the operating data and design parameters. While the electrification system is formed, the maximum rail voltage needs to be provided in the limits of the touch voltage limits during the operation. The highest value of the rail voltage occurring on the line determined by the line characteristic properties. This value needs to be kept within certain limits for the continuity of the operation. The data created regarding one-way and two-way supply conditions were examined for simulation.