Multi-objective Optimization Of Train Speed Based On Hierarchical Learning Golden Sine-whale Algorithm

Train urban rail transit system is an important facility to relieve the pressure of urban public transport operation,with many advantages such as convenience,high cost performance,punctuality,speed and so on.The automatic train operation system(ATO)is of great significance in improving the ride comfort and energy-saving operation of the urban rail transit system.The research of ATO system mainly includes the optimization of train speed curve and the design of train tracking controller.The optimization of the train speed curve is to improve the safety,energy saving,punctuality,parking accuracy and comfort of the train under the condition of ensuring the safe operation of the train.This paper mainly studies the optimization of train speed curve.First of all,the current research status of ATO system is understood by consulting relevant domestic and foreign literatures and materials.The structure,function and operation process of the ATO system are deeply analyzed,and the dynamic model of the train is established by analyzing the traction characteristics,braking characteristics and basic resistance of the train.On this basis,the operating condition conversion principle and operation control strategy during train operation are clarified,which provides a theoretical basis for the automatic operation optimization of the train.Secondly,based on the optimization objective of train operation,combined with the constraints of accuracy,speed protection and comfort,the multi-objective optimization problem of the train is transformed into a single-objective optimization problem by the weighted average method,and a mathematical model for the optimization of the train speed curve is established.Thirdly,in view of the shortcomings of the whale optimization algorithm,such as low convergence accuracy and easy to fall into local optimum,combined with the golden sine algorithm,a Golden Sine-Whale Optimization Algorithm Based on Hierarchical Learning(Whale Optimization Algorithm Based on Hierarchical Learning,HLGS-WOA)to solve the optimization model of the train speed curve.Compared with the whale optimization algorithm,the algorithm has been greatly improved in terms of population structure and parameter selection,and increased population diversity.The benchmark function is tested,and the results show that compared with the traditional whale optimization algorithm,the algorithm has greatly improved the convergence speed and accuracy.Finally,according to the train’s own properties and line parameters,an optimization algorithm of train speed curve based on HLGS-WOA algorithm is designed,and Matlab simulation software is used to simulate the optimization process of the speed curve of the ATO system,and the optimal operation environment and operating line are obtained.speed curve.Experiments show that the punctuality,energy consumption and other indicators of the train operating system have achieved satisfactory results.