An ATO Multi-objective Optimization Control Strategy Based on Genetic Algorithm

Abstract

Aiming at the multi-objective optimization of punctuality, precise parking, comfort and energy consumption in the train operation, an ATO control strategy based on genetic algorithm optimization is proposed. Because the train operation process is multi-objective, complex and non-linear, and there are internal contradictions in the evaluation index, there is no optimal control strategy for all indicators. This paper establishes an evaluation index model based on the performance evaluation system of automatic train operation curve. Design an optimization algorithm of velocity-displacement curve (V-S curve) based on genetic algorithm. The algorithm enables the train to automatically give the optimal curve which is most suitable for the given operating environment. While ensuring the safe and smooth operation of the train, it also meets the requirements of punctuality, parking accuracy, energy saving and comfort. The simulation results show that the algorithm is effective, under the designed optimal train operation sequence, the punctuality error is 0 and the position error is 0.09 meters for 33.769 kilometers.