Urban Rail Transit Network Planning Based on Adaptive Neural Network

Authors

  • Yuan Lu School of Architecture and Design, Beijing Jiao tong University, Beijing 100044, China
  • Jinyan Shao Beijing Urban Construction Design & Development Group Co. Limited, Beijing 100037, China
  • Lin Zhou School of Automotive Engineering, Beijing Polytechnic, Beijing 100176, China

Abstract

An adaptive neural network, also referred to as ANN, is an artificial neural network with adaptive learning ability. The purpose of this paper is to study an adaptive neural network-based method, and apply this algorithm to the planning of an urban rail transit network. In this paper, several important railway stations in a certain city are used as data nodes. The network planning is simulated according to these nodes, and the calculation time and energy consumption of the proposed system are compared with those using traditional calculation methods. The experimental results show that the calculation time of the ANN neural network for a certain node is about 8s, while the traditional algorithm takes more than 15s. The CPU ratio of the ANN algorithm is 35%, while the traditional algorithm CPU ratio is about 50%. By using the algorithm proposed in this paper, the CPU is reduced by
15%, which shows that the urban road traffic network planning method based on ANN is faster and consumes less power.

Keywords: adaptive neural network, urban rail, traffic planning, factors related to line network planning

Cite As

Y. Lu, J. Shao, L. Zhou, "Urban Rail Transit Network Planning Based on Adaptive Neural Network", Engineering
Intelligent Systems, vol. 31 no. 1, pp. 65-76, 2023.



Downloads

Published

2023-01-01

Issue

Vol. 31 No. 1 (2023): International Journal of Engineering Intelligent Systems

Section

General Submission

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.