Comparison of ANN and ANFIS Methods for the Voltage-Drop Prediction on an Electric Railway Line


Creative Commons License

Kocaarslan İ., Akcay M. T., Akgündoğdu A., Tiryaki H.

ELECTRICA, vol.18, no.1, pp.26-35, 2018 (Peer-Reviewed Journal) identifier identifier

  • Publication Type: Article / Article
  • Volume: 18 Issue: 1
  • Publication Date: 2018
  • Doi Number: 10.5152/iujeee.2018.1805
  • Journal Name: ELECTRICA
  • Page Numbers: pp.26-35
  • Keywords: ANFIS, ANN, electrification, railway, traction, ARTIFICIAL NEURAL-NETWORK, SIMULATION, SYSTEM, MODEL
  • Istanbul Technical University Affiliated: No

Abstract

Railway electrification systems are designed with regard to the operating data and design parameters. The minimum voltage rating required by traction during the operation should be provided. The maximum voltage drop on a line determines the minimum traction voltage. This voltage should be maintened within certain limits for the continuity of operation. In this study, the maximum voltage drop generated via traction was determined using artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) for a 25-kV AC-supplied railway.The voltage drop on line was calculated with regard to the operating data using ANN and ANFIS. ANN and ANFIS were explained, and the results were compared.The Levenberg-Marquardt (LM) algorithm was used for the ANN model. The LM algorithm is preferred because of the speed and stability it provides for the training of ANNs. The data created for one-way supply status were examined for simulation.