Urban rail transit networked train operation adjusting method

Abstract

The invention discloses an urban rail transit networked train operation adjustment method. The method comprises the following steps: 1) data preparation and preprocessing; 2) simulation environment modeling; 3) constructing an intelligent agent; 4) constructing an intelligent agent interaction mechanism; and 5) train operation adjustment. According to the invention, the multi-agent simulation system of the passenger agent, the train agent, the station agent and the line agent is constructed and cooperated, and the real-time interaction among the agents promotes the efficient flow and processing of information. According to the invention, dynamic optimization of train scheduling, passenger flow direction suggestion and route resource management is realized, and the system shows significant adaptability and recovery capability especially when coping with peak flow and emergencies. The method can effectively improve the defects of an existing traffic system, and improve the operation efficiency and the passenger travel experience.

Description

Technical Field

[0001] The present application belongs to the technical field of urban rail transit operation organization planning, and in particular, relates to a method for adjusting networked train operations in urban rail transit. Background Art

[0002] With the acceleration of urbanization, urban rail transit networks are carrying more and more passenger traffic. During peak hours and emergencies, urban rail transit systems are facing increasingly prominent challenges, especially operational disruptions, which may lead to large-scale passenger backlogs and affect the stability of the overall transportation system.

[0003] At present, relevant research at home and abroad focuses on accident cause analysis, emergency response, passenger route selection, etc., while research on adjacent line train adjustment strategies in the event of operation interruption is relatively insufficient. Therefore, an adjacent line train operation adjustment method that can effectively respond to emergencies has important practical significance. Summary of the invention

[0004] The purpose of this application is to overcome the problems of the prior art and disclose a method for adjusting the operation of urban rail transit network trains to solve the problem of passenger backlog on adjacent lines in the urban rail transit system under conditions of operational interruption.

[0005] The purpose of this application is achieved through the following technical solutions:

[0006] A method for adjusting the operation of a networked urban rail transit train, the method comprising:

[0007] S1: Data preparation, collecting urban rail transit network data, AFC card swiping data and timetable data;

[0008] S2: Simulation environment modeling, completing the train operation and personnel flow simulation modeling based on the data obtained in step S1;

[0009] S3: Agent construction, based on the data obtained in step S1, the agent construction is completed, including:

[0010] Constructing a passenger agent, which is configured to perceive the system environment and make path selection, transfer decisions, select the best travel plan or re-plan the trip;

[0011] Constructing a train intelligent agent, wherein the train intelligent agent is configured to make corresponding operation decisions based on the operation status obtained by real-time monitoring;

[0012] Constructing a line agent, which is configured to complete the coordination of various lines, optimize the train schedule and complete the collaborative operation between various stations and trains on the line;

[0013] Building a station agent, wherein the station agent is configured to complete the stop time and departure sequence control of trains in the station and manage the passenger flow in the station;

[0014] S4: constructing an agent interaction mechanism, constructing the interaction rules of each agent in step S3 under the simulation environment model framework obtained in step S2;

[0015] S5: Train operation adjustment. Each intelligent agent interacts with each other based on the interaction rules obtained in step S4 and outputs decision information respectively. According to the output decision information, the departure time, stop strategy and alternative routes of the train are adjusted.

[0016] According to a preferred embodiment, step S1 also includes data preprocessing, which is used to complete data processing of the collected data according to a preset format and store it.

[0017] According to a preferred embodiment, the simulation environment model constructed in step S2 includes the following contents: network topology, train operation parameters and passenger behavior.

[0018] According to a preferred embodiment, the network topology is configured to simulate the actual line layout of the subway network, including stations, transfer points and specific directions of the lines;

[0019] The train operation parameters include: train station stop time, maximum carrying capacity, and line capacity;

[0020] The passenger behavior: by collecting historical data, the passenger's behavioral response in various scenarios is simulated, including: the passenger's path selection, transfer behavior, and waiting time when the section is interrupted.

[0021] According to a preferred embodiment, in step S4, constructing an agent interaction mechanism includes:

[0022] The passenger agent perceives the operation of the train and the congestion of the station in real time. When it finds that the waiting time exceeds the preset value or the congestion of the station exceeds the preset value, the passenger agent communicates with the station agent and feedbacks the travel demand.

[0023] According to a preferred embodiment, in step S4, constructing an agent interaction mechanism includes:

[0024] Based on the feedback received from the passenger agents, the station agent dynamically adjusts the passenger flow management of the station, including: adjusting the departure frequency of trains, extending the stop time, and taking measures to limit the flow of passengers entering the station.

[0025] According to a preferred embodiment, in step S4, constructing an agent interaction mechanism includes:

[0026] Based on the feedback from the station agent and the passenger agent, the train agent adjusts the train's operating parameters in real time, including: accelerating, decelerating, extending the stop time or changing the departure time.

[0027] According to a preferred embodiment, in step S4, constructing an agent interaction mechanism includes:

[0028] Based on the information fed back by the station agents and train agents, the line agent coordinates the operation of each station and each train to achieve the overall deployment and operation of each line.

[0029] According to a preferred embodiment, step S5 also includes: simulation and deduction before train operation adjustment, which is used to analyze the impact of not adjusting the train operation on passengers, so as to evaluate and determine the timing of adjusting the train operation.

[0030] According to a preferred embodiment, step S5 further includes: simulation and deduction after the train operation adjustment, for analyzing the impact of the train operation adjustment on passengers, so as to evaluate and determine the duration of the train operation adjustment.

[0031] The aforementioned main scheme of the present application and its further options can be freely combined to form multiple schemes, all of which are schemes that can be adopted and claimed for protection in the present application. After understanding the scheme of the present application, those skilled in the art can understand that there are multiple combinations based on the prior art and common knowledge, all of which are technical schemes to be protected by the present application, and they are not exhaustively listed here.

[0032] Beneficial effects of this application:

[0033] The urban rail transit network train operation adjustment method of the present application builds a multi-agent simulation system, which can monitor passengers' path selection and transfer behavior in real time, and dynamically adjust the train departure interval and station stop time according to the passenger flow at the station, thereby solving the problem of passenger flow backlog on adjacent lines in the urban rail transit system under operation interruption conditions.

[0034] This application realizes dynamic optimization of train scheduling, passenger flow recommendations and line resource management. In particular, the system shows significant adaptability and recovery capabilities when dealing with peak traffic and emergencies. This method can effectively improve the shortcomings of the existing transportation system and improve operational efficiency and passenger travel experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flowchart of the application method. DETAILED DESCRIPTION

[0036] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0037] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0038] refer to Figure 1 As shown, a method for adjusting the operation of a networked urban rail transit train is shown in the figure, and the method for adjusting the operation of a networked urban rail transit train comprises the following steps.

[0039] Step S1: Data preparation, collecting urban rail transit network data, AFC card swiping data and timetable data.

[0040] Preferably, step S1 also includes data preprocessing, which is used to complete data processing of the collected data according to a preset format and store it.

[0041] Step S2: Simulation environment modeling, completing the train operation and personnel flow simulation modeling based on the data obtained in step S1.

[0042] Preferably, the simulation environment model constructed in step S2 includes the following contents: network topology, train operation parameters and passenger behavior.

[0043] The network topology is configured to simulate the actual line layout of the subway network, including stations, transfer points and specific directions of the lines;

[0044] The train operation parameters include: train station stop time, maximum carrying capacity, and line capacity;

[0045] The passenger behavior: by collecting historical data, the passenger's behavioral response in various scenarios is simulated, including: the passenger's path selection, transfer behavior, and waiting time when the section is interrupted.

[0046] Step S3: intelligent agent construction, based on the data obtained in step S1, the intelligent agent construction is completed, including: constructing passenger intelligent agents, constructing train intelligent agents, constructing line intelligent agents and constructing station intelligent agents.

[0047] Preferably, the passenger agent is configured to be able to perceive the system environment and make path selection, transfer decisions, select the best travel plan or re-plan the itinerary.

[0048] Specifically, each passenger is an independent intelligent agent with personal travel goals, route selection, transfer needs and other behavioral decisions. The passenger agent can perceive the system environment (such as station passenger flow, train arrival time, congestion, etc.), and make route selection and transfer decisions, select the best travel plan or re-plan the itinerary.

[0049] Passenger agents can communicate with station agents and train agents to report their location, waiting time, travel needs and other information. Station agents can make adjustments based on this information to improve the train service level.

[0050] For example, when the passenger agent waits too long at the platform, it will send a request to the station agent, prompting the station agent to collaborate with the train agent to optimize the train arrival time and stop strategy. The passenger agent can also dynamically adjust its path selection according to the real-time status of the train, such as arrival time or congestion, and choose a more comfortable or faster travel mode.

[0051] Preferably, the train agent is configured to be able to make corresponding operation decisions based on the operation status obtained through real-time monitoring.

[0052] Specifically, each train acts as an independent intelligent agent, responsible for its own driving control. By monitoring the train operation status (such as train delays, station conditions, etc.) in real time, corresponding decisions (such as speeding up, delaying departure, skipping stations, etc.) can be made. The train agent can communicate with the station agent and the passenger agent, and make flexible adjustments based on passenger needs and station passenger flow to ensure the train's operating efficiency and passenger experience.

[0053] Preferably, the line agent is configured to complete the coordination of various lines, optimize the train schedule and complete the collaborative operation between various stations and trains on the line.

[0054] The line agent is responsible for the coordination of the entire line, optimizing the train schedule and ensuring the coordination between the stations and trains on the line. It monitors the traffic conditions of the entire line in real time, including train density, sudden failures, operational interruptions and other events, to ensure that the trains can be flexibly adjusted according to the passenger flow and train operation status of each station. When the station agent or passenger agent reports a large-scale passenger flow, the line-level agent can optimize the operation of the entire line by adding trains or adjusting the departure interval.

[0055] Preferably, the station agent is configured to complete the stop time and departure sequence control of trains in the station, and manage the passenger flow in the station.

[0056] By collaborating with train agents and passenger agents, station agents can sense passenger flow pressure in stations and coordinate train stops and departures, especially during peak hours to optimize passenger organization and management in stations. When receiving a large number of demands reported by passenger agents, station agents can send adjustment requests to train agents to extend stop times or increase train frequencies.

[0057] Step S4: construct an agent interaction mechanism, and construct the interaction rules of each agent in step S3 under the simulation environment model framework obtained in step S2.

[0058] Preferably, constructing an agent interaction mechanism includes:

[0059] The passenger agent perceives the operation of the train and the congestion of the station in real time. When it finds that the waiting time exceeds the preset value or the congestion of the station exceeds the preset value, the passenger agent communicates with the station agent and feedbacks the travel demand.

[0060] Based on the feedback received from the passenger agents, the station agent dynamically adjusts the passenger flow management of the station, including: adjusting the departure frequency of trains, extending the stop time, and taking measures to limit the flow of passengers entering the station to ensure the safety and comfort of passengers.

[0061] Based on the feedback from the station agent and the passenger agent, the train agent adjusts the train's operating parameters in real time, including: acceleration, deceleration, extended stop time or changed departure time. In particular, at some severely congested stations, the train agent can respond first to reduce the overall waiting time of passengers.

[0062] Based on the information fed back by the station agents and train agents, the line agent coordinates the operation of each station and each train to achieve the overall deployment and operation of each line, ensuring that when multiple stations face congestion or large passenger flow at the same time, they can respond and guide traffic quickly and effectively.

[0063] Step S5: Train operation adjustment. Each agent interacts with each other based on the interaction rules obtained in step S4 and outputs decision information respectively. According to the output decision information, the departure time, stop strategy and alternative routes of the train are adjusted.

[0064] Preferably, step S5 also includes: simulation and deduction before train operation adjustment, for analyzing the impact of not adjusting the train operation on passengers, so as to evaluate and determine the timing of adjusting the train operation.

[0065] The simulation after train operation adjustment is used to analyze the impact of train operation adjustment on passengers and to evaluate and determine the duration of train operation adjustment.

[0066] Example

[0067] The processing flow of the method for compiling a plan for the use of the undercarriage of urban rail transit provided by the first embodiment of the present invention is as follows: Figure 1 As shown, the following steps are included:

[0068] Step S1: Data preparation and preprocessing.

[0069] The line network data is received and preprocessed. The data of some stations in the line network are shown in the following table.

[0070]

[0071]

[0072] Some transfer relationships are shown in the following table.

[0073]

[0074] Some AFC card swiping data are shown below.

[0075]

[0076] Some timetable data is shown in the table below.

[0077]

[0078]

[0079] Step S2: Simulation environment modeling. The constructed simulation environment model includes:

[0080] Network topology: simulates the actual line layout of the subway network, including stations, transfer points and the specific direction of the line.

[0081] Train operation parameters: initial operation parameters such as train stop time, maximum carrying capacity, line capacity, etc. The simulation simulates the optimized operation effect by dynamically adjusting the departure interval.

[0082] Passenger behavior: Passengers’ path selection, transfer behavior, and waiting time during interval interruptions are all important factors affecting system dynamics. The simulation model collects historical data to simulate passengers’ behavioral responses in different scenarios.

[0083] Step S3: Multi-agent construction

[0084] S31: Build passenger agent. S32: Build train agent. S33: Build line agent. S34: Build station agent.

[0085] Step S4: Agent interaction mechanism construction

[0086] Step S5: Train operation adjustment: According to the decision information output by the agent interaction, the train departure time, stop strategy and alternative routes are adjusted to optimize resource allocation.

[0087] Taking Chengdu Metro Line 5 and Line 8 as cases, the impact of the interruption of the "Gaoshengqiao-Provincial Orthopedic Hospital" section of Line 5 on Line 8 during the evening peak period of "18:00-19:00" was analyzed, and the simulation model proposed in this application was used for simulation optimization.

[0088] Simulation and analysis of the impact on passengers caused by not optimizing.

[0089] When Line 5 broke down, the number of passengers entering Jiuxing Avenue Station, a transfer station on Line 8, and the number of passengers transferring from other lines increased dramatically, from the normal passenger flow of less than 500 to 1,767. The number of passengers transferring also increased from the normal passenger flow of less than 500 to 2,142.

[0090] Due to the influx of a large number of passengers into Line 8, a large number of passengers were accumulated at the stations on the downward direction of Line 8, especially at Jiuxing Avenue Station and the next station Gaopeng Avenue Station, where the number of waiting and remaining passengers increased sharply. The peak numbers of waiting and remaining passengers reached 983 and 321 passengers respectively.

[0091] After the interruption of Line 5, the passenger flow and full load rate of Line 8 in the downward direction were analyzed, and it was found that the peak passenger flow of the section was close to 3,000, and the maximum full load rate reached 114.36%.

[0092] Based on the decision information output by the intelligent agent interaction, the train departure time, stop strategy and alternative routes are adjusted to optimize resource allocation and analyze the impact on passengers.

[0093] After simulation optimization, the operation diagram of Line 8 was adjusted. The peak number of people waiting at each station in the down direction of Line 8 was reduced from 983 to 736, and the number of people staying was reduced to 0, which alleviated the passenger backlog problem of Line 8 caused by the interruption of the section of Line 5. In addition, after simulation optimization, the maximum value of the full load rate of the down direction section of Line 8 was also reduced to 85.59%.

[0094] The simulation results show that after optimizing the train schedule, the operating efficiency of Line 8 has been greatly improved. The number of waiting people and the full load rate have been significantly reduced, especially the passenger flow pressure at Jiuxing Avenue Station and Gaopeng Avenue Station has been effectively alleviated. By shortening the departure interval, the average waiting time of passengers has been reduced, and the detention phenomenon in the station has also been improved.

[0095] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for adjusting train operation in urban rail transit network, characterized in that: The urban rail transit network train operation adjustment method comprises: S1: Data preparation, collecting urban rail transit network data, AFC card swiping data and timetable data; S2: Simulation environment modeling, completing the train operation and personnel flow simulation modeling based on the data obtained in step S1; S3: Agent construction, based on the data obtained in step S1, the agent construction is completed, including: Constructing a passenger agent, which is configured to perceive the system environment and make path selection, transfer decisions, select the best travel plan or re-plan the trip; Constructing a train intelligent agent, wherein the train intelligent agent is configured to make corresponding operation decisions based on the operation status obtained by real-time monitoring; Constructing a line agent, which is configured to complete the coordination of various lines, optimize the train schedule and complete the collaborative operation between various stations and trains on the line; Building a station agent, wherein the station agent is configured to complete the stop time and departure sequence control of trains in the station and manage the passenger flow in the station; S4: constructing an agent interaction mechanism, constructing the interaction rules of each agent in step S3 under the simulation environment model framework obtained in step S2; S5: Train operation adjustment. Each intelligent agent interacts with each other based on the interaction rules obtained in step S4 and outputs decision information respectively. According to the output decision information, the departure time, stop strategy and alternative routes of the train are adjusted.

2. The urban rail transit network train operation adjustment method according to claim 1, characterized in that: Step S1 also includes data preprocessing, which is used to complete data processing of the collected data according to a preset format and store it.

3. The urban rail transit network train operation adjustment method according to claim 1, characterized in that: The simulation environment model constructed in step S2 includes the following contents: network topology, train operation parameters and passenger behavior.

4. The urban rail transit network train operation adjustment method according to claim 3, characterized in that: The network topology is configured to simulate the actual line layout of the subway network, including stations, transfer points and specific directions of the lines; The train operation parameters include: train station stop time, maximum carrying capacity, and line capacity; The passenger behavior: by collecting historical data, the passenger's behavioral response in various scenarios is simulated, including: the passenger's path selection, transfer behavior, and waiting time when the section is interrupted.

5. The urban rail transit network train operation adjustment method according to claim 1, characterized in that: In step S4, constructing the agent interaction mechanism includes: The passenger agent perceives the operation of the train and the congestion of the station in real time. When it finds that the waiting time exceeds the preset value or the congestion of the station exceeds the preset value, the passenger agent communicates with the station agent and feedbacks the travel demand.

6. The urban rail transit network train operation adjustment method according to claim 1, characterized in that: In step S4, constructing the agent interaction mechanism includes: Based on the feedback received from the passenger agents, the station agent dynamically adjusts the passenger flow management of the station, including: adjusting the departure frequency of trains, extending the stop time, and taking measures to limit the flow of passengers entering the station.

7. The urban rail transit network train operation adjustment method according to claim 1, characterized in that: In step S4, constructing an agent interaction mechanism includes: Based on the feedback from the station agent and the passenger agent, the train agent adjusts the train's operating parameters in real time, including: accelerating, decelerating, extending the stop time or changing the departure time.

8. The urban rail transit network train operation adjustment method according to claim 1, characterized in that: In step S4, constructing the agent interaction mechanism includes: Based on the information fed back by the station agents and train agents, the line agent coordinates the operation of each station and each train to achieve the overall deployment and operation of each line.

9. The urban rail transit network train operation adjustment method according to claim 1, characterized in that: Step S5 also includes: simulation and deduction before train operation adjustment, which is used to analyze the impact of not adjusting the train operation on passengers, so as to evaluate and determine the timing of train operation adjustment.

10. The urban rail transit network train operation adjustment method according to claim 9, characterized in that: Step S5 also includes: simulation and deduction after the train operation adjustment, which is used to analyze the impact of the train operation adjustment on passengers, so as to evaluate and determine the duration of the train operation adjustment.

Images