A method for short-term prediction of the number of people gathered at urban rail transit platforms

Abstract

The invention relates to the field of urban rail transit control, and discloses a short-term prediction method for the number of people gathered at an urban rail transit platform. This method predicts the flow of passengers entering the station, the number of train passengers and the train timetable, and fuses the above prediction results to obtain the final prediction result. For each prediction, first predict a round of train timetable, and then predict the flow of passengers entering the station and the number of passengers on the train within the scope of the timetable, and deduce the flow prediction results and passenger number prediction results according to the train timetable prediction results to obtain the timetable The prediction results of the number of people gathered within the range, and then update the real train timetable to continue the next round of prediction. The prediction algorithm of the invention has the characteristics of high prediction accuracy and strong practicability.

Description

technical field [0001] The invention relates to the field of urban rail transit control, in particular to a method for short-term prediction of the number of people gathered at an urban rail transit platform. Background technique [0002] Because rail transit not only has the characteristics of fast speed, accurate time, large transportation volume, long transportation distance, high comfort, and little influence from the outside world, but also can better solve the problems of large urban public traffic flow and road congestion. Therefore, rail transit Transportation has gradually become the main way of public transportation for citizens in big cities. [0003] With the rapid increase of rail transit passenger flow, the platform often appears in a state of passenger flow oversaturation, especially in the morning and evening peak hours of weekdays, large passenger flow events and emergencies. Due to the lack of detailed passenger flow distribution information and accurate p...

AI Technical Summary

Problems solved by technology

[0004] 1. The existing prediction algorithm based on the fixed number of people getting off the train assumes that the number of passengers left on the platform after each train leaves is 0 during the prediction process, which is inconsistent with the common phenomenon on the platform during peak hours, resulting in a large error;

[0005] 2. The existing prediction algorithms based on the fixed alighting ratio and the fixed boarding ratio all believe that the ratio of passengers getting on and off within an hour is fixed, but in actual operation, the ratio of getting on and off within an hour will vary greatly. caused a large error;

[0006] 3. When the existing algorithms predict the flow of passengers entering the station, they all use the time granularity of 1 hour to predict. The time granularity is too large, resulting in large errors in the prediction results of the flow of passengers entering the station, and further causing the prediction error of the number of people gathered on the platform ;

[0007] 4. The existing algorithms all recognize that the arrival and departure time of the train strictly abides by the planned train timetable and can be known in advance, so the timetable prediction is not included, and the actual running timetable of the train is unstable and inconsistent with the planned train timetable , which further increases the prediction error of the number of people gathered

Images