Fuzzy-logic controlled genetic algorithm for the rail-freight crew-scheduling problem

KHMELEVA, Elena, HOPGOOD, A. A., TIPI, Lucian and SHAHIDAN, Malihe (2017). Fuzzy-logic controlled genetic algorithm for the rail-freight crew-scheduling problem. KI - Künstliche Intelligenz, 32 (1), 61-75.

13218_2017_Article_516.pdf - Published Version
Creative Commons Attribution.

Download (2MB) | Preview
Official URL: https://link.springer.com/article/10.1007%2Fs13218...
Link to published version:: https://doi.org/10.1007/s13218-017-0516-6
Related URLs:


AbstractThis article presents a fuzzy-logic controlled genetic algorithm designed for the solution of the crew-scheduling problem in the rail-freight industry. This problem refers to the assignment of train drivers to a number of train trips in accordance with complex industrial and governmental regulations. In practice, it is a challenging task due to the massive quantity of train trips, large geographical span and significant number of restrictions. While genetic algorithms are capable of handling large data sets, they are prone to stalled evolution and premature convergence on a local optimum, thereby obstructing further search. In order to tackle these problems, the proposed genetic algorithm contains an embedded fuzzy-logic controller that adjusts the mutation and crossover probabilities in accordance with the genetic algorithm’s performance. The computational results demonstrate a 10% reduction in the cost of the schedule generated by this hybrid technique when compared with a genetic algorithm with fixed crossover and mutation rates.

Item Type: Article
Additional Information: ** From Springer Nature via Jisc Publications Router. ** History: received 07-03-2017; accepted 13-10-2017; epub 27-10-2017; ppub 02-2018. ** Licence for this article: http://creativecommons.org/licenses/by/4.0/
Uncontrolled Keywords: Technical Contribution, Fuzzy logic, Genetic algorithm, Hybrid, Crew scheduling, Rail freight
Identification Number: https://doi.org/10.1007/s13218-017-0516-6
Page Range: 61-75
SWORD Depositor: Margaret Boot
Depositing User: Margaret Boot
Date Deposited: 08 Feb 2018 12:01
Last Modified: 18 Mar 2021 01:23
URI: https://shura.shu.ac.uk/id/eprint/18541

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics