The optimization of the speed curve of the permanent magnet maglev trains is of utmost importance for the automatic train operation. This work proposes a weight-adaptive genetic algorithm to effectively solve the problems of low efficiency, poor robustness, and vulnerability to falling into local optimum in the traditional biological evolutionary algorithm in the automatic train driving speed curve. Based on the traditional genetic algorithm process, the improvement of this algorithm lies in setting the weight of the penalty function, the value of the crossover factor, and the value of the mutation factor to be variable in real-time. First, the weight of the penalty function of the unsatisfied item should be doubled when the constraints are not met; otherwise, its weight remains unchanged. Second, smaller crossover and mutation factor values should be chosen when the solution obtained in this round is better than that in the previous round; otherwise, larger crossover and variation factor values should be used. Simulation experiments show that the improved algorithm in this work has the advantages of fast convergence and high robustness compared with the more widely used traditional genetic algorithm.
Optimization of the Speed Curve of Permanent Magnetic Maglev Trains Based on Improved Genetic Algorithm
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2021 October 21, 2021 - October 23, 2021
Proceedings of the 5th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2021 ; Chapter : 53 ; 504-514
2022-02-19
11 pages
Article/Chapter (Book)
Electronic Resource
English
British Library Conference Proceedings | 2022
|Noise from High Speed Maglev Trains
British Library Conference Proceedings | 1993
|Aerodynamics of Magnetic Levitation (Maglev) Trains
NTIS | 1996
|