Auxiliary Decision-making Engine For Train Operation Adjustment Of High-speed Railway

With the vigorous development of high-speed railways in recent years,the high-speed railway network has been gradually built and perfected,and high-speed railways have also become the preferred mode of transportation for people to travel long and medium distances.However,when the high-speed railway train is interfered by random factors during operation,the train is delayed to varying degrees,and the dispatcher issues a dispatch instruction to hope to resume normal operation as soon as possible.At present,the operation adjustment work of high-speed railways mainly depends on the experience of dispatchers.If there is a system that can assist dispatchers to complete the dispatching work,it can guarantee the punctuality of high-speed railway trains and improve the quality of high-speed railway transportation services.In recent years,big data mining has provided good ideas for solving the problem of operation adjustment.Therefore,it is of far-reaching significance to study the auxiliary decision engine for train operation adjustment of high-speed railways.This article focuses on the characteristics of high-speed railway,combined with existing research results,from the following aspects of research.First,introduce the definition of the train operation diagram and the factors that affect the actual performance operation diagram.Analysis of interference factors during driving.Explain the principles and measures of train operation adjustment.Secondly,define the model parameters and pre-process the data obtained from the planned operation chart and the actual operation chart to obtain the late train data information.The quantitative determination methods of train overtaking,organizational interval hurrying and compression stop time are studied,and then separately Mark the parameters in the respective scene.Thirdly,according to the characteristics of the train operation adjustment problem,this article describes the principle of the random forest algorithm and the characteristics of random sampling and random selection of attributes.The two methods for selecting the optimal characteristics of random forest are discussed,and the independent and dependent variable factors of the auxiliary decision model based on random forest are given.By analyzing the prediction results of calculation examples,the random forest algorithm can compare the actual operation graph with the planned operation graph.Once the late information occurs,it can effectively predict the auxiliary decision suggestions.Finally,C# programming is used to design the auxiliary decision-making engine for high-speed railway train operation adjustment,including the operation diagram viewing module,statistical analysis module,and auxiliary decision-making suggestion module,and the Sql Server database management system information is also used.Finally,an example of running data construction in the upward direction of the Baolan passenger train is selected to analyze the prediction results.The calculation example shows that the random forest algorithm can give reasonable operation adjustment suggestions for the dispatcher to choose,update the acceptance probability optimization engine of each strategy,achieve the purpose of helping the dispatcher to make operation adjustment,and prove the effectiveness of the corresponding function of the auxiliary decision engine.The research results of this paper show that after matching the existing strategies in the historical sample data with the actual operating conditions,the best matching adjustment strategy or combination strategy is found and provided to the dispatcher to avoid solving the total delay of each train at each station The minimum time is the complex problem of optimizing the target,guiding practice with practice,and providing the basis for the automation and intelligentization of operation adjustment.The auxiliary decision engine for train operation adjustment prepared in this paper can realize all design functions and can achieve good human-computer interaction effects.