Research On Energy-saving Optimization Algorithms For High-speed Automatic Train Operation

With the increasing growth of China's economy,rail transit has entered a new period of rapid development in recent yean.Aceording to the public display of the China Railway Network,as of the end of 2019.China's high-speed nil operating mileage has exceeded 35,000 kilomelers,China's high-speed railway has accumulated mure than 10 billion passengers and completed a total passenger tumover of 3,34 trillion passenger kilometers.This shows that high-spced rail has become the main route for passenger transportation in China.Increasing transportation demand hasi brought huge energy consimption,so researching energy-saving driving strategies for high-speed railways bas become in urgent problem to be solved.In view of this problem,this paper studies the energy-soving optimization algorthms for high-speed trains.The research content is aas follows:1)Aiming at the problem of repeatedly adjusting the speed and traction in The trnsfitional train automatic driving system(ATO)control algorithm,which leads to the loss of eoergy consumption,an energy-saving optimization algorithm is proposed.Based on the train traction energy consumption model and operating constraints,based on the Pandrisgin maximum principle and Hamilton function,five driving strategies for optimal energy consumption control were solved,and based on this,an optimization algorithm was proposed to ensure the accuracy of time by controlling the distance between idle and cruise.Through two sets of operatingintervals at different times,it is verified that the algorithm can reduce energy consumption by aminimum of 5.7%compared with the traditional algorithm under the premise of ensuring comfort,punctuality and accurate parking,and has a good energy saving effect.2)the traditional genetic algorithm is used in tht automatic driving optimization algorithm of trains,and there are problems such as convergence speed mitigation and poor population optimization ability.An improved genetic algorithm is proposed for the above problems.The improved genetic algorithm is the optimal method based on the maximum value principle.On the basis of the control algorithm,the inertia condition conversion point is taken as the variable,the energy consumption is the objective function,the time constraint is converted into the penalty function,and the adaptive variation is added to the variation factor and the cross factor to achieve better results.It is verified through experiments that the improved genetic algorithm has a shorter convergence time than the simple genetic algorithm and the adaptive genetic algorithm,and the energy saving effect is better(the energy saving effect is increased by 3%compared with the former,Compared with the latter,the energy-saving effect is increased by 1.7%),and the ability of seeking for better is stronger.