.png){kind=icon}
.png){kind=icon}
Return
Energy-efficient train trajectory optimization based on improved differential evolution algorithm and multi-particle model
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jclepro.2021.127163.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Urban rail transit is an efficient public transport, and reducing their energy consumption is beneficial to climate change and sustainable development. Current researches in metro train trajectory optimization are mainly based on the single-particle train operation model, and the selection of energy-saving operation strategy under time-varying passenger flow is not taken into consideration. Therefore, considering the practical line environment and uncertain trainload simultaneously, this paper establishes a multi-particle operation model and develops a new optimization method based on mutated dichotomy and differential evolutionary algorithm to solve the model. Then, the influence of various passenger flow and line information on the train trajectory optimization is analyzed from the perspective of trainload capacity based on the proposed method, and the selection basis of the optimal energy-saving train operation strategy was determined. Finally, a case study was conducted in the Nanning Rail Transit Line 1 and Line 5, respectively. The results show that the proposed method has strong efficiency for energy conservation and better optimization performance than the conventional differential evolution algorithm in solving train trajectory optimization problem. And the simulation results of the Line 5, which is a fully automatic operation line, also verified the reliability of the selection basis . (c) 2021 Elsevier Ltd. All rights reserved.
Keywords:
Energy-saving train operation
Urban rail transit
Passenger flow
Improved evolution algorithm
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
10
Papers:
4.6W
Citations:
36.8W