A rail transit virtual marshalling train operation scheme optimization method and device

Abstract

The application discloses a kind of optimization method and device of rail transit virtual marshalling train operation scheme, the method includes: obtaining line information, train operation information, train vehicle parameter and passenger flow information, line information, train operation information, train vehicle parameter and passenger flow information are all input into virtual marshalling train optimization model, and virtual marshalling train operation optimization scheme is generated.This method not only can effectively improve line transport efficiency, meet the transport demand of urban rail transit in different periods, but also can effectively shorten passenger travel time, improve rail transit service quality, and has guiding significance for the planning and construction of urban rail transit line.

Description

Technical Field

[0001] This invention relates to the field of rail transit technology, specifically to a method and apparatus for optimizing virtual train formation operation schemes in rail transit. Background Technology

[0002] Virtual coupling technology (also known as virtual coupling, virtual connection, etc.) allows for more flexible transportation modes because there are no physical couplers between vehicles. This enables the adaptation to the real-time changes in passenger flow in urban rail transit. Typical transportation organization modes for urban rail transit include express and local trains, long and short routes, cross-line operation, and flexible coupling. By combining one or more of these methods, different operation schemes can be formed, effectively solving the problem of uneven distribution of passenger flow in time and space and improving the transportation efficiency of the line.

[0003] Currently, most urban rail transit systems use fixed-formation trains, whose passenger capacity remains constant during operation. Adjusting train operation plans can improve transport capacity to some extent, but during peak hours, severe overcrowding often leads to reduced passenger comfort, while during off-peak hours, the significant mismatch between transport capacity and passenger load results in energy waste. Flexible-formation trains adapt to changes in passenger flow by adjusting the number of cars in each formation, but their formation requires empty-car operations at the originating or intermediate stations, resulting in low flexibility. This approach offers only a minor improvement in passenger travel time.

[0004] Virtual train formations, through online dynamic passenger formation operations, can achieve more efficient and flexible transportation services. Research on virtual train formation operation schemes has included using mathematical optimization models to optimize the number of virtual train formations for specific scenarios to avoid unnecessary capacity. However, these models do not consider time costs and train skipping stops, limiting the advantages of virtual formation technology. There have also been comparative analyses of virtual train formations using "express" and "local" trains under specific stopping schemes with traditional operation schemes, but no rules for formulating virtual train formation operation schemes have been provided. Furthermore, existing technologies provide an algorithm for generating virtual train formation operation schemes, but in this algorithm, trains stop according to a periodic pattern, and the stopping pattern does not consider the impact of passenger flow differences at different stations, making it impractical. Summary of the Invention

[0005] Therefore, the technical problem to be solved by the present invention is to overcome the shortcomings of existing virtual train formation operation schemes that do not take into account the impact of transportation modes such as time cost and train skipping stations, as well as the differences in passenger flow at different stations, and are therefore not practical. Thus, the present invention provides an optimization method and apparatus for virtual train formation operation schemes in rail transit.

[0006] This invention provides an optimization method for virtual train formation operation schemes in rail transit, comprising:

[0007] Obtain route information, train operation information, train vehicle parameters, and passenger flow information;

[0008] The route information, train operation information, train vehicle parameters and passenger flow information are all input into the virtual train formation optimization model to generate a virtual train formation operation optimization scheme.

[0009] This invention provides an optimization method for virtual train formation operation schemes in rail transit. By acquiring line information, train operation information, train vehicle parameters, and passenger flow information, and inputting these information into a virtual train formation optimization model, the model can fully consider the impact of passenger flow, trains, and lines on the virtual train formation operation scheme. Based on passenger travel patterns, the generated virtual train formation operation optimization scheme can not only effectively improve line transportation efficiency and meet the transportation needs of urban rail transit at different times, but also effectively shorten passenger travel time and improve the quality of rail transit services. It has guiding significance for the planning and construction of urban rail transit lines.

[0010] Optionally, passenger travel time, train travel time, and average passenger load factor across the entire train line are determined based on route information, train operation information, train vehicle parameters, and passenger flow information, including:

[0011] Extract the distance between two adjacent stations from the route information, the train departure interval, train stop variable values ​​and train stop time from the train operation information, the average train speed from the train vehicle parameters, and the number of passengers from the departure station to the destination station from the passenger flow information. Based on the train departure interval, train stop variable values, train stop time, the distance between two adjacent stations, the average train speed, and the number of passengers from the departure station to the destination station, use a virtual train formation optimization model to determine the passenger travel time.

[0012] Based on the distance between two adjacent stations, the average train speed, the train stopping time, and the train stopping variables, the train running time is determined using a virtual train formation optimization model.

[0013] Extract the train passenger capacity from the train vehicle parameters and the number of passengers boarding and alighting at stations from the passenger flow information. Based on the train stop variable values, train passenger capacity, number of passengers boarding and alighting at stations, and the virtual train formation optimization model, determine the average passenger load factor of the entire train line.

[0014] A virtual train formation operation optimization scheme is generated based on passenger travel time, train running time, and the average passenger load factor of the entire train line.

[0015] Optionally, based on train departure intervals, train stop variables, train stop times, distances between adjacent stations, average train speed, and the number of passengers from the departure station to the destination station, a virtual train formation optimization model is used to determine passenger travel time, including:

[0016] The passenger waiting time is determined based on the train stop variable values ​​and the train departure interval.

[0017] Determine passenger loss time based on train stop variable values ​​and train stop time;

[0018] Passenger travel time is determined based on the distance between two adjacent stations and the average train speed.

[0019] Passenger travel time is generated based on passenger waiting time, passenger loss time, passenger travel time, and the number of passengers from the departure station to the destination station.

[0020] The above-mentioned inclusion of passenger waiting time, passenger loss time, and passenger travel time as part of passenger travel time fully considers the impact of passenger flow on train operation plans and improves the operating efficiency of virtual train formations.

[0021] Optionally, passenger travel time is generated based on passenger waiting time, passenger loss time, passenger travel time, and the number of passengers from the departure station to the destination station. The formula for calculating passenger travel time is as follows:

[0022]

[0023] In the above formula, t p Let N represent the total number of stations on the line, x represent the departure station, y represent the destination station, and ζ represent the passenger travel time. i (x) represents the value of the stop variable of train i at the departure station, ζ i (y) represents the value of the stop variable for train i at the destination station, h x,y (i,j) / 2 represents the passenger waiting time, h x,y (i,j) represents the train departure interval. Indicates the passenger's lost time, ζ i (r) represents the value of the stop variable of train i at station r, t s Indicates the train's stopping time at the station. Indicates the passenger's travel time. v represents the distance between two adjacent stations. avg The average speed of the train is expressed in meters (m). x,y This indicates the number of passengers traveling from the departure station to the destination station.

[0024] Optionally, based on the values ​​of train stop variables, train capacity, number of passengers boarding at stations, and number of passengers alighting at stations, a virtual train formation optimization model is used to determine the average passenger load factor for the entire train line, including:

[0025] The passenger capacity of a train at departure is determined based on the number of passengers boarding and disembarking at the station.

[0026] The average passenger load factor for the entire train line is determined based on the values ​​of train stop variables, the passenger load at the time of train departure, and the train's capacity.

[0027] Optionally, a virtual train formation operation optimization scheme is generated based on passenger travel time, train running time, and the average passenger load factor of the entire train line, including:

[0028] A virtual train formation operation optimization function is constructed based on passenger travel time, train running time, and average passenger load factor of the entire train line.

[0029] The travel demand of all passengers along the line and the average passenger load factor of each train are used as constraints for the virtual train operation optimization function.

[0030] A genetic algorithm is used to solve the virtual train operation optimization function and generate a virtual train operation optimization scheme.

[0031] Optionally, a virtual train formation operation optimization function is constructed based on passenger travel time, train running time, and the average passenger load factor of the entire train line. The calculation formula for the virtual train formation operation optimization function is as follows:

[0032]

[0033] In the above formula, t p Indicates passenger travel time, t c Indicates train travel time. represents the average passenger load factor across the entire train line, and minZ represents the virtual train formation operation optimization function.

[0034] The aforementioned virtual train formation operation optimization function is applicable to both the design of existing line operation schemes and planned lines, and has strong application value. Its virtual train formation operation optimization scheme has guiding significance for the planning and construction of urban rail transit lines.

[0035] In a second aspect of this application, a device for optimizing the operation scheme of virtual train formation in rail transit is also proposed, comprising:

[0036] The acquisition module is used to acquire route information, train operation information, train vehicle parameters, and passenger flow information.

[0037] The generation module is used to input route information, train operation information, train vehicle parameters and passenger flow information into the virtual train formation optimization model to generate a virtual train formation operation optimization scheme.

[0038] Optionally, the generation module includes:

[0039] The first determining submodule is used to extract the distance between two adjacent stations from the line information, the train departure interval, the train stop variable value and the train stop time from the train operation information, the average train speed from the train vehicle parameters and the number of passengers from the departure station to the destination station from the passenger flow information, and to determine the passenger travel time based on the train departure interval, the train stop variable value, the train stop time, the distance between two adjacent stations, the average train speed and the number of passengers from the departure station to the destination station;

[0040] The second determining submodule is used to determine the train travel time based on the distance between two adjacent stations, the average train speed, the train stop time, and the train stop variable values.

[0041] The third determination submodule is used to extract the train passenger capacity from the train vehicle parameters and the number of passengers boarding and alighting at stations from the passenger flow information, and to determine the average passenger load factor of the entire train line based on the train stop variable value, the train passenger capacity, the number of passengers boarding and alighting at stations;

[0042] The generation submodule is used to generate virtual train formation operation optimization schemes based on passenger travel time, train running time, and the average passenger load factor of the entire train line.

[0043] Optionally, the first determined submodule includes:

[0044] The first determining unit is used to determine the passenger waiting time based on the train stop variable value and the train departure interval.

[0045] The second determining unit is used to determine the passenger loss time based on the train stop variable value and the train stop time.

[0046] The third determining unit is used to determine the passenger travel time based on the distance between two adjacent stations and the average train speed, and to generate the passenger travel time based on the passenger waiting time, passenger loss time, passenger travel time and the number of passengers from the departure station to the destination station.

[0047] Optionally, the third determining unit includes:

[0048] The formula for calculating passenger travel time is as follows:

[0049]

[0050] In the above formula, t pLet N represent the total number of stations on the line, x represent the departure station, y represent the destination station, and ζ represent the passenger travel time. i (x) represents the value of the stop variable of train i at the departure station, ζ i (y) represents the value of the stop variable for train i at the destination station, h x,y (i,j) / 2 represents the passenger waiting time, h x,y (i,j) represents the train departure interval. Indicates the passenger's lost time, ζ i (r) represents the value of the stop variable of train i at station r, t s Indicates the train's stopping time at the station. Indicates the passenger's travel time. v represents the distance between two adjacent stations. avg The average speed of the train is expressed in meters (m). x,y This indicates the number of passengers traveling from the departure station to the destination station.

[0051] Optionally, the third determining submodule includes:

[0052] The fourth determining unit is used to determine the passenger capacity of the train at departure based on the number of passengers boarding and disembarking at the station.

[0053] The fifth determining unit is used to determine the average passenger load factor of the entire train line based on the train stopping variable values, the passenger load at the time of train departure, and the train's capacity.

[0054] Optionally, a submodule is generated, including:

[0055] The building unit is used to construct a virtual train operation optimization function based on passenger travel time, train running time, and the average passenger load factor of the entire train line.

[0056] The constraint unit is used to take the travel demand of all passengers on the line and the average passenger load factor of each train as the constraint conditions of the virtual train formation operation optimization function;

[0057] The solution unit is used to solve the virtual train operation optimization function using a genetic algorithm to generate a virtual train operation optimization scheme.

[0058] Optionally, the building unit includes:

[0059] The calculation formula for the virtual train formation operation optimization function is as follows:

[0060]

[0061] In the above formula, t p Indicates passenger travel time, t c Indicates train travel time. represents the average passenger load factor across the entire train line, and minZ represents the virtual train formation operation optimization function.

[0062] In a third aspect of this application, a computer device is also proposed, including a processor and a memory, wherein the memory is used to store a computer program, the computer program including a program, and the processor is configured to call the computer program to execute the above-described method for optimizing the virtual train formation operation scheme of rail transit.

[0063] In a fourth aspect of this application, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which is executed by a processor to implement the above-described method for optimizing the operation scheme of virtual train formation in rail transit. Attached Figure Description

[0064] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0065] Figure 1 This is a flowchart of a method for optimizing the operation scheme of virtual train formation in rail transit according to Embodiment 1 of the present invention;

[0066] Figure 2 This is a schematic diagram of the dynamic formation of a virtual train in Embodiment 1 of the present invention;

[0067] Figure 3 This is a schematic diagram of the dynamic de-staging of a virtual train in Embodiment 1 of the present invention;

[0068] Figure 4 This is a schematic diagram of the virtual train formation operation scheme in Embodiment 1 of the present invention;

[0069] Figure 5 This is a schematic diagram of the virtual train formation state in Embodiment 1 of the present invention;

[0070] Figure 6 This is a flowchart of step S102 in Embodiment 1 of the present invention;

[0071] Figure 7 This is a flowchart of step S1021 in Embodiment 1 of the present invention;

[0072] Figure 8 This is a flowchart of step S1023 in Embodiment 1 of the present invention;

[0073] Figure 9This is a flowchart of step S1024 in Embodiment 1 of the present invention;

[0074] Figure 10 This is a schematic diagram of the Beijing Subway Batong Line in Embodiment 1 of the present invention;

[0075] Figure 11 This is a schematic diagram of the train operation scheme coding in Embodiment 1 of the present invention;

[0076] Figure 12 This is a schematic diagram of the Pareto front in Embodiment 1 of the present invention;

[0077] Figure 13 This is a schematic diagram of the operation of a virtual train formation in Embodiment 1 of the present invention;

[0078] Figure 14 This is a schematic diagram of a virtual train formation operation scheme optimization device for rail transit in Embodiment 2 of the present invention. Detailed Implementation

[0079] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0080] In the description of this invention, it should be noted that the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0081] Furthermore, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0082] Example 1

[0083] This embodiment provides a method for optimizing the operation scheme of virtual train formation in rail transit, such as... Figure 1 As shown, it includes:

[0084] S101. Obtain route information, train operation information, train vehicle parameters and passenger flow information, and determine passenger travel time, train running time and average passenger load factor of the entire train line based on the above route information, train operation information, train vehicle parameters and passenger flow information.

[0085] The route information includes data such as section length, number of stations, and route layout; train operation information includes data such as section travel time, train stop time, and train departure interval; train vehicle parameters include data such as average train speed and train passenger capacity; and passenger flow information includes data such as station names, entry and exit times, and number of passengers.

[0086] S102. Input the above-mentioned route information, train operation information, train vehicle parameters and passenger flow information into the virtual train formation optimization model to generate a virtual train formation operation optimization scheme.

[0087] Among them, such as Figure 2-3 As shown, the virtual train formation achieves formation through high-performance car-to-car wireless communication, without physical connection, thus enabling real-time dynamic formation and de-formation operations. To better adapt to the uneven distribution of passenger flow at different stations, a convoy consisting of several cars is taken as the research object. A convoy departs from the originating station in the form of virtual formation, where each car has a different stopping plan. The stopping plans of all cars in the convoy constitute a running plan, and the next virtual train formation will repeat the running plan of the previous convoy; for example... Figure 4 As shown, the operation plan of train fleet B1-B2-B3 corresponds one-to-one with the operation plan of the previous train fleet A1-A2-A3. For each car in the fleet, its stopping plan for the entire line is generated by the virtual train operation optimization function mentioned above. At the same time, for each station, the number of trains stopping within a certain period of time will also be different. In order to meet the overtaking needs of trains, some stations need to have a passing track.

[0088] Furthermore, the number of cars in a virtual train formation departing from the originating station is determined by both passenger demand and platform length. Currently, most subway platforms are around 140m long. Taking a Type A train as an example, which is 22m long, during peak hours, trains are formed according to the maximum platform length limit, resulting in a virtual train formation of 6 cars. During off-peak hours, trains are formed according to passenger demand, ranging from 1 to 6 cars. The number of cars in the virtual train formation will also dynamically change during operation due to different stopping plans. Each car is an independent transport unit during operation and can be formed and deformed according to its own operating plan to create different combinations. Figure 5 As shown, taking a 6-car train as an example, this illustrates some possible train formation configurations when the train is running on the line.

[0089] Assuming all trains have the same stopping time, trains can be assembled upon entering or leaving stations, and the assembly time is negligible. Assuming passenger arrival times are evenly distributed across stations, and all passengers board the nearest direct train without transfers, and since trains can virtually assemble at the same speed on the line and overtake in platform areas, trains on the line do not interfere with each other under normal circumstances, and each train's stopping plan can be designed independently. However, different stopping plans will significantly impact passenger travel. For example, if fewer trains stop at a station, passengers at that station or traveling to that station will experience longer waiting times. Therefore, it is necessary to comprehensively consider the stopping plans of each train to meet the diverse travel needs of passengers. Thus, based on line information, train operation information, train vehicle parameters, and passenger flow information, a virtual train assembly operation optimization function is constructed.

[0090] The aforementioned optimization method for virtual train formation operation schemes in rail transit acquires line information, train operation information, train vehicle parameters, and passenger flow information. These information are then input into the virtual train formation optimization model, allowing the model to fully consider the impact of passenger flow, trains, and lines on the virtual train formation operation scheme. Based on passenger travel patterns, the generated virtual train formation operation optimization scheme can not only effectively improve line transportation efficiency and meet the transportation needs of urban rail transit at different times, but also effectively shorten passenger travel time and improve the quality of rail transit services. This method has guiding significance for the planning and construction of urban rail transit lines.

[0091] Preferably, such as Figure 6 As shown, in step S102, the aforementioned route information, train operation information, train vehicle parameters, and passenger flow information are all input into the virtual train formation optimization model to generate a virtual train formation operation optimization scheme, including:

[0092] S1021. Extract the distance between two adjacent stations from the above-mentioned line information, the train departure interval, train stop variable values ​​and train stop time from the above-mentioned train operation information, the average train speed from the above-mentioned train vehicle parameters, and the number of passengers from the departure station to the destination station from the above-mentioned passenger flow information. Based on the above-mentioned train departure interval, the above-mentioned train stop variable values, the above-mentioned train stop time, the above-mentioned distance between two adjacent stations, the above-mentioned average train speed, and the above-mentioned number of passengers from the departure station to the destination station, determine the passenger travel time using the above-mentioned virtual train formation optimization model.

[0093] S1022. Based on the distance between the two adjacent stations, the average train speed, the train stopping time, and the train stopping variable values, the train running time is determined using the virtual train formation optimization model.

[0094] Since virtual train formations involve operations such as skipping stations, which significantly shortens train travel time, train travel time is used to measure operating costs. The formula for calculating train travel time is as follows:

[0095]

[0096] In the above formula, t c Indicates the train travel time, n t This indicates the number of cars in a virtual formation at the originating station. v represents the distance between two adjacent stations. avg The average speed of the train is represented by t. s ζ represents the train's stopping time at each station, N represents the total number of stations on the line, and ζ represents the total number of stations on the line. i (r) represents the value of the stop variable of train i at station r.

[0097] S1023. Extract the train passenger capacity from the above train vehicle parameters and the number of passengers boarding and alighting at stations from the above passenger flow information. Based on the above train stop variable values, the above train passenger capacity, the above number of passengers boarding and alighting at stations, the above virtual train formation optimization model is used to determine the average passenger load factor of the entire train line.

[0098] S1024. Based on the above passenger travel time, the above train running time, and the above average passenger load factor of the entire train line, generate the above virtual train formation operation optimization scheme.

[0099] Preferably, such as Figure 7 As shown, in step S1021, the determination of passenger travel time using the virtual train formation optimization model, based on the train departure interval, train stop variable values, train stop time, distance between adjacent stations, average train speed, and the number of passengers from the departure station to the destination station, includes:

[0100] S10211. Determine the passenger waiting time based on the above-mentioned train stop variable values ​​and the above-mentioned train departure interval.

[0101] Specifically, passenger waiting time is expressed as follows:

[0102] h x,y (i,j) / 2

[0103] In the above formula, h x,y(i,j) represents the departure interval between two adjacent trains that depart from the same departure station and arrive at the same destination station.

[0104] S10212. Determine the passenger loss time based on the above-mentioned train stop variable values ​​and the above-mentioned train stop time.

[0105] Specifically, the passenger loss time is expressed as follows:

[0106]

[0107] In the above formula, ζ i (r) represents the value of the stop variable of train i at station r, t s Indicates the train's stopping time at the station.

[0108] S10213. Determine passenger travel time based on the distance between two adjacent stations and the average train speed.

[0109] Specifically, passenger travel time is expressed as follows:

[0110]

[0111] In the above formula, v represents the distance between two adjacent stations. avg This indicates the average speed of the train.

[0112] The passenger travel time is generated based on the above passenger waiting time, the above passenger lost time, the above passenger boarding time, and the number of passengers from the departure station to the destination station.

[0113] Specifically, the formula for calculating the passenger travel time is as follows:

[0114]

[0115] In the above formula, t p Let N represent the total number of stations on the line, x represent the departure station, y represent the destination station, and ζ represent the passenger travel time. i (x) represents the value of the stop variable of train i at the departure station, ζ i (y) represents the value of the stop variable for train i at the destination station, h x,y (i,j) / 2 represents the passenger waiting time, h x,y (i,j) represents the train departure interval (i.e., the departure interval between two adjacent trains departing from the same departure station and arriving at the same destination station), m x,y The number of passengers is represented between the departure station and the destination station, and r represents any station between the departure station x and the destination station y.

[0116] Among them, the departure interval h between two adjacent trains whose passengers depart from the same departure station and arrive at the same destination station. x,y The formula for calculating (i,j) is as follows:

[0117] h x,y (i,j)=t i,x -t j,x i = 2, ..., n t x = 1, 2, ..., N, y = 1, 2, ..., N.

[0118] In the above formula, t i,x t represents the time when train i departs from departure station x. j,x This indicates the time when train j departs from departure station x, where train j is the preceding train of train i, and train i and train j have the same destination station.

[0119] h x,y (i,j)=h0,i=1

[0120] In the above formula, h0 represents the time interval between train departures at the originating station.

[0121] Furthermore, the more stations a train stops at, the shorter the average waiting time for passengers, but it also increases the passenger travel time. Therefore, it is necessary to comprehensively optimize train operation plans to shorten passenger travel time as much as possible.

[0122] Preferably, such as Figure 8 As shown, in step S1023, based on the aforementioned train stop variable values, the aforementioned train capacity, the aforementioned number of passengers boarding at the aforementioned stations, and the aforementioned number of passengers alighting at the aforementioned stations, the average passenger load factor of the entire train line is determined using the aforementioned virtual train formation optimization model, including:

[0123] S10231. Determine the passenger capacity of the train at departure based on the number of passengers boarding at the aforementioned stations and the number of passengers alighting at the aforementioned stations.

[0124] Among them, the number of people p boarding train i at station r i,r The calculation formula is as follows:

[0125]

[0126] In the above formula, m r,y h represents the number of passengers traveling from station r to destination station y. r,y (i,j) represents the time interval between the departure of train i from station r to destination station y and the previous train j from station r to destination station y.

[0127] Furthermore, the number of passengers q who disembark at station r on train i. i,r The calculation formula is as follows:

[0128]

[0129] In the above formula, m x,r h represents the number of passengers traveling from departure station x to station r. x,r (i,j) represents the time interval between the departure of train i from departure station x to station r and the previous train j from departure station x to station r.

[0130] Specifically, for the same train, a higher average passenger load factor results in higher utilization. Reducing the number of stops can effectively reduce passenger loss time, but at the same time, it may reduce the number of passengers that can be carried due to too few stops, thus reducing the train's transportation efficiency. Therefore, limiting the average passenger load factor of a train is used to ensure its transportation efficiency. The formula for calculating the passenger capacity of a train when it departs from a station is as follows:

[0131] C i,r =C i,r-1 +p i,r -q i,r r = 2, 3, ..., N, i = 1, 2, ..., n t

[0132] In the above formula, C i,r C represents the passenger capacity of train i at station r. i,r-1 This represents the passenger capacity of train i at station r-1, n t This indicates the number of virtual train sets at the originating station.

[0133] Wherein, the passenger capacity of train i at the originating station is represented by C. i,r =0, r=1, i=1,2,…,n t .

[0134] S10232. Based on the above-mentioned train stop variable values, the above-mentioned passenger volume at the time of train departure, and the above-mentioned train capacity, determine the average passenger load factor of the entire train line.

[0135] Specifically, the formula for calculating the average passenger load factor of train i across the entire line is as follows:

[0136]

[0137] In the above formula, C0 represents the average passenger load factor across the entire train line, and ω represents the train's capacity. i This represents the number of stops train i makes along the entire line, where ω i The calculation formula is as follows:

[0138]

[0139] When train i stops at station r, ζ i The value of (r) is 1, otherwise ζ i The value of (r) is 0.

[0140] Preferably, such as Figure 9 As shown, step S1024, which generates the virtual train formation operation optimization scheme based on the passenger travel time, train running time, and average passenger load factor of the entire train line, includes:

[0141] S10241. Based on the above passenger travel time, the above train running time, and the above average passenger load factor of the entire train line, construct a virtual train formation operation optimization function.

[0142] Specifically, the formula for calculating the above objective function is as follows:

[0143]

[0144] In the above formula, t p Indicates passenger travel time, t c Indicates train travel time. denoted as the average passenger load factor across the entire train line, and minZ represents the objective function of the virtual train formation operation optimization model.

[0145] S10242. The travel demand of all passengers on the line and the average passenger load factor of each train are used as constraints for the above-mentioned virtual train formation operation optimization function.

[0146] Specifically, the travel demand of all passengers along the line and the average passenger load factor of each train are used as constraints on the objective function. This ensures that at least one train stops at any two stations, thus satisfying the travel demand of all passengers. Therefore, the constraint on the travel demand of all passengers is expressed as follows:

[0147]

[0148] The constraint on the average passenger load factor of each train is expressed as follows:

[0149]

[0150] S10243. Use a genetic algorithm to solve the above-mentioned virtual train formation operation optimization function to generate the above-mentioned virtual train formation operation optimization scheme.

[0151] Specifically, the objective function decision variable is the stop variable value for each vehicle, i.e., ζ. i (1), ζ i (2), ..., ζ i(N), using a genetic algorithm to solve the objective function, generate the full-line stopping scheme for different vehicles, i.e., the virtual train formation operation optimization scheme.

[0152] The following specific example illustrates an optimization method for a virtual train formation operation scheme in rail transit:

[0153] (1) As Figure 10 As shown, taking the Beijing Subway Batong Line as an example, the entire line has 15 stations. Currently, the vast majority of trains operate in the Sihui-Tuqiao section of the train schedule. Table 1 shows the OD (Origin-Destination) table for the Batong Line during peak hours (8:00-9:00), reflecting the travel patterns of passengers during this period.

[0154] Table 1:

[0155]

[0156]

[0157] As can be seen from Table 1 above, the vast majority of passenger flow moves from the suburbs towards the city center (towards Sihui Station). Therefore, the following steps mainly study and design the train operation plan for the Tuqiao-Sihui direction of the Batong Line during the morning peak hours. During off-peak hours, the number of trains can be reduced and optimized accordingly.

[0158] (2) Solving the virtual train formation optimization operation scheme based on NSGA-Ⅱ algorithm (genetic algorithm); Since the vehicle only has two states at each station, namely stopping and passing, the train state can be represented by 1 and 0 respectively. Thus, for each vehicle, its stopping scheme is encoded, that is, each operation scheme can be represented by a binary number, and the number of bits in the binary number is the number of stations. The current train operation scheme of Batong Line (Scheme 1) is shown in Table 2 below.

[0159] Table 2:

[0160]

[0161] The six-car trains depart one after another at 2-minute intervals, and it takes 39.45 minutes for one train to complete the entire line.

[0162] Because the train stopping scheme in the operation plan exhibits a significant combinatorial explosion trend with the increase in the number of trains and the number of stations they pass through, and because there are multiple optimization objectives, it is difficult to obtain the train stopping scheme using traditional optimization methods. Therefore, the Fast Non-Dominated Sorting Genetic Algorithm (NSGA-II) is used to solve the problem. This algorithm has low computational complexity and can guarantee population diversity. The specific solution process is as follows: Figure 11As shown, the stopping pattern of 6 trains in one operating cycle is regarded as a chromosome, and the stopping pattern of each train is the gene that makes up the chromosome. Figure 12 This represents the Pareto front after 100 iterations with an initial population size of 100. Figure 12 The passenger travel time is the ratio of the passenger travel time in the virtual formation optimization operation scheme to the time required by the current scheme (Scheme 1). As can be seen from the Pareto front, when the average passenger travel time increases, the train's transport efficiency will also increase accordingly. Railway operators can choose between passenger travel time and train transport efficiency according to demand. A set of optimization results in the operation scheme is shown in Table 3 below.

[0163] Table 3:

[0164]

[0165] As can be seen from Table 3 above, in this set of optimization results, the operation plan of each train in the virtual train formation is different, and they will carry out bypass operations at different stations. At the same time, the plan can still meet the travel needs of all passengers on the entire line. At this time, the average passenger load factor of the entire line is 49.05%. Compared with the current plan of stopping at every station, the average travel time of passengers on the entire line can be reduced by 6.61%.

[0166] Assuming that trains with corresponding numbers (such as A1 and B1) in two virtual train formations have the same operating plan, the trains will be dynamically formed into different small train formations according to the stopping plan during operation. At this time, it will take only 36.45 minutes for a train to run the entire line, which saves 3 minutes compared to the current plan 1. This can effectively reduce operating costs and improve line utilization.

[0167] Figure 13 The scene of each vehicle leaving each station is shown in turn. Taking Sihui East Station (Station 12) as an example, the 6 cars form three formations. Car 1 runs alone, while cars 5 and 2, and cars 6, 3 and 4 are respectively grouped into two virtual formations. From the perspective of the entire line, Batong Line only needs to set up six bypass stations to meet the requirements of this optimized operation scheme. Therefore, based on this optimization result, the line modification of Batong Line can be guided to be suitable for the operation of virtual formation trains.

[0168] (3) Comparative analysis of optimization schemes: In order to compare the advantages of the designed virtual train operation schemes, Table 4 below shows five train operation schemes, namely: Scheme 1, a station-by-station stopping scheme with a departure interval of 2 minutes; Scheme 2, a virtual train skipping station operation scheme with a departure interval of 2 minutes; Scheme 3, a fixed train skipping station scheme with a departure interval of 2 minutes; Scheme 4, a station-by-station stopping scheme with a departure interval of 1 minute; Scheme 5, a virtual train skipping station operation scheme with a departure interval of 1 minute. In order to meet the normal boarding and alighting of passengers, it is assumed that the stopping time of all trains is 30 seconds, and the skipping of all schemes adopts the same scheme as Scheme 2.

[0169] Table 4:

[0170]

[0171] The following conclusions can be drawn from the comparison:

[0172] A. Comparing Scheme 1 and Scheme 2, it can be seen that compared with the current fixed-station train transportation scheme, the virtual train transportation mode can shorten passenger travel time by 6.61%, with an average reduction of 1.5 minutes per person. It also significantly shortens train running time, which is beneficial to improving transportation efficiency.

[0173] B. As shown in Schemes 2 and 3, although the fixed-formation train skipping-station scheme can shorten the travel time for express train passengers, overall, if the scheme is not optimized properly, resulting in excessively long waiting times for slow train passengers, it will increase the overall average travel time for passengers. In Scheme 2, trains with different stopping schemes can depart simultaneously through virtual formation technology, without waiting for a certain departure interval, thus effectively avoiding the problem of excessively long waiting times for passengers, while also meeting the needs of passengers for rapid travel.

[0174] C. Comparing Scheme 2 and Scheme 5, it can be seen that when the train departure interval is shortened from 2 minutes to 1 minute, the passenger travel time can be further reduced to 91.69%. However, as can be seen from Scheme 2 and Scheme 4, compared with shortening the train departure interval, the virtual train formation operation scheme has a more significant effect on shortening the passenger travel time.

[0175] Example 2

[0176] This embodiment provides an optimization device for virtual train formation operation schemes in rail transit, such as... Figure 14 As shown, it includes:

[0177] The acquisition module 141 is used to acquire route information, train operation information, train vehicle parameters and passenger flow information.

[0178] The generation module 142 is used to input the above-mentioned line information, train operation information, vehicle parameters and passenger flow information into the virtual train formation optimization model to generate a virtual train formation operation optimization scheme.

[0179] In this virtual train formation, the cars are grouped together via high-performance car-to-car wireless communication, without physical connections, thus enabling real-time dynamic grouping and degrouping. To better address the uneven passenger flow distribution at different stations, a convoy of several cars is used as the research object. A convoy departs from the originating station in a virtual formation, where each car has a different stopping plan. The stopping plans of all cars in the convoy constitute a running plan, and the next virtual train formation will repeat the running plan of the previous convoy. Figure 4 As shown, the operation plan of train fleet B1-B2-B3 corresponds one-to-one with the operation plan of the previous train fleet A1-A2-A3. For each car in the fleet, its stopping plan for the entire line is generated by the virtual train operation optimization function mentioned above. At the same time, the number of trains stopping at each station within a certain period of time will also be different. In order to meet the overtaking needs of trains, some stations need to have a passing track.

[0180] Furthermore, the number of cars in a virtual train formation departing from the originating station is determined by both passenger demand and platform length. Currently, most subway platforms are around 140m long. Taking a Type A train as an example, which is 22m long, during peak hours, trains are formed according to the maximum platform length limit, resulting in a virtual train formation of 6 cars. During off-peak hours, trains are formed according to passenger demand, ranging from 1 to 6 cars. The number of cars in the virtual train formation will also dynamically change during operation due to different stopping plans. Each car is an independent transport unit during operation and can be formed and deformed according to its own operating plan to create different combinations. Figure 5 As shown, taking a 6-car train as an example, this illustrates some possible train formation configurations when the train is running on the line.

[0181] Assuming all trains have the same stopping time, trains can be assembled upon entering or leaving stations, and the assembly time is negligible. Assuming passenger arrival times are evenly distributed across stations, and all passengers board the nearest direct train without transfers, and since trains can virtually assemble at the same speed on the line and overtake in platform areas, trains on the line do not interfere with each other under normal circumstances, and each train's stopping plan can be designed independently. However, different stopping plans will significantly impact passenger travel. For example, if fewer trains stop at a station, passengers at that station or traveling to that station will experience longer waiting times. Therefore, it is necessary to comprehensively consider the stopping plans of each train to meet the diverse travel needs of passengers. Thus, based on line information, train operation information, train vehicle parameters, and passenger flow information, a virtual train assembly operation optimization function is constructed.

[0182] The aforementioned optimization device for virtual train formation operation schemes in rail transit acquires line information, train operation information, train vehicle parameters, and passenger flow information. It then inputs these information into a virtual train formation optimization model, enabling the model to fully consider the impact of passenger flow, trains, and lines on the virtual train formation operation scheme. Based on passenger travel patterns, the generated virtual train formation operation optimization scheme not only effectively improves line transportation efficiency and meets the transportation needs of urban rail transit at different times, but also effectively shortens passenger travel time and improves the quality of rail transit services. This provides guidance for the planning and construction of urban rail transit lines.

[0183] Preferably, the above-mentioned generation module 142 includes:

[0184] The first determining submodule 1421 is used to extract the distance between two adjacent stations in the above-mentioned line information, the train departure interval, the train stop variable value and the train stop time in the above-mentioned train operation information, the average train speed in the above-mentioned train vehicle parameters and the number of passengers from the departure station to the destination station in the above-mentioned passenger flow information, and to determine the passenger travel time using the above-mentioned virtual train formation optimization model based on the above-mentioned train departure interval, the above-mentioned train stop variable value, the above-mentioned train stop time, the above-mentioned distance between two adjacent stations, the above-mentioned average train speed and the above-mentioned number of passengers from the departure station to the destination station.

[0185] The second determining submodule 1422 is used to determine the train running time based on the distance between the two adjacent stations, the average train speed, the train stopping time, and the train stopping variable values, using the virtual train formation optimization model.

[0186] Since virtual train formations involve operations such as skipping stations, which significantly shortens train travel time, train travel time is used to measure operating costs. The formula for calculating train travel time is as follows:

[0187]

[0188] In the above formula, t c Indicates the train travel time, n t This indicates the number of cars in a virtual formation at the originating station. v represents the distance between two adjacent stations. avg The average speed of the train is represented by t. s ζ represents the train's stopping time at each station, N represents the total number of stations on the line, and ζ represents the total number of stations on the line. i (r) represents the value of the stop variable of train i at station r.

[0189] The third determining submodule 1423 is used to extract the train passenger capacity from the train vehicle parameters and the number of passengers boarding and alighting at stations from the passenger flow information. Based on the train stop variable values, the train passenger capacity, the number of passengers boarding and alighting at stations, the virtual train formation optimization model is used to determine the average passenger load factor of the entire train line.

[0190] The generation submodule 1424 is used to generate the above-mentioned virtual train formation operation optimization scheme based on the above-mentioned passenger travel time, the above-mentioned train running time, and the above-mentioned average passenger load factor of the entire train line.

[0191] Preferably, the first determining submodule 1421 includes:

[0192] The first determining unit 14211 is used to determine the passenger waiting time based on the above-mentioned train stop variable value and the above-mentioned train departure interval.

[0193] Specifically, passenger waiting time is expressed as follows:

[0194] h x,y (i,j) / 2

[0195] In the above formula, h x,y (i,j) represents the departure interval between two adjacent trains that depart from the same departure station and arrive at the same destination station.

[0196] The second determining unit 14212 is used to determine the passenger loss time based on the above-mentioned train stop variable value and the above-mentioned train stop time.

[0197] Specifically, the passenger loss time is expressed as follows:

[0198]

[0199] In the above formula, ζ i (r) represents the value of the stop variable of train i at station r, t s Indicates the train's stopping time at the station.

[0200] The third determining unit 14213 is used to determine the passenger travel time based on the distance between the two adjacent stations and the average train speed.

[0201] Specifically, passenger travel time is expressed as follows:

[0202]

[0203] In the above formula, v represents the distance between two adjacent stations. avg This indicates the average speed of the train.

[0204] The passenger travel time is generated based on the passenger waiting time, the aforementioned passenger lost time, the aforementioned passenger boarding time, and the number of passengers from the aforementioned departure station to the destination station.

[0205] Specifically, the formula for calculating the passenger travel time is as follows:

[0206]

[0207] In the above formula, t p Let N represent the total number of stations on the line, x represent the departure station, y represent the destination station, and ζ represent the passenger travel time. i (x) represents the value of the stop variable of train i at the departure station, ζ i (y) represents the value of the stop variable for train i at the destination station, h x,y (i,j) / 2 represents the passenger waiting time, h x,y (i,j) represents the departure interval between two adjacent trains that depart from the same departure station and arrive at the same destination station, m x,y The number of passengers is represented between the departure station and the destination station, and r represents any station between the departure station x and the destination station y.

[0208] Among them, the departure interval h between two adjacent trains whose passengers depart from the same departure station and arrive at the same destination station. x,y The formula for calculating (i,j) is as follows:

[0209] h x,y (i,j)=t i,x -t j,x i = 2, ..., n t j = 1, 2, ..., i-1, x = 1, 2, ..., N, y = 1, 2, ..., N. In the above formula, t i,x t represents the time when train i departs from departure station x.j,x This indicates the time when the train preceding train i, which has the same destination station as train i, departs from the departure station x.

[0210] h x,y (i,j)=h0,i=1

[0211] In the above formula, h0 represents the time interval between train departures at the originating station.

[0212] Furthermore, the more stations a train stops at, the shorter the average waiting time for passengers, but it also increases the passenger travel time. Therefore, it is necessary to comprehensively optimize train operation plans to shorten passenger travel time as much as possible.

[0213] Preferably, the third determining submodule 1423 includes:

[0214] The fourth determining unit 14231 is used to determine the passenger capacity of the train at the time of departure based on the number of passengers boarding at the aforementioned stations and the number of passengers alighting at the aforementioned stations.

[0215] Among them, the number of people p boarding train i at station r i,r The calculation formula is as follows:

[0216]

[0217] In the above formula, m r,y h represents the number of passengers traveling from station r to destination station y. r,y (i,j) represents the time interval between the departure of train i from station r to destination station y and the previous train j from station r to destination station y, i.e., the train departure interval.

[0218] Furthermore, the number of passengers q who disembark at station r on train i. i,r The calculation formula is as follows:

[0219]

[0220] In the above formula, m x,r h represents the number of passengers traveling from departure station x to station r. x,r (i,j) represents the time interval between the departure of train i from departure station x to station r and the previous train j from departure station x to station r.

[0221] Specifically, for the same train, a higher average passenger load factor results in higher utilization. Reducing the number of stops can effectively reduce passenger loss time, but at the same time, it may reduce the number of passengers that can be carried due to too few stops, thus reducing the train's transportation efficiency. Therefore, limiting the average passenger load factor of a train is used to ensure its transportation efficiency. The formula for calculating the passenger capacity of a train when it departs from a station is as follows:

[0222] C i,r =C i,r-1 +p i,r -q i,r r = 2, 3, ..., N, i = 1, 2, ..., n t

[0223] In the above formula, C i,r C represents the passenger capacity of train i at station r. i,r-1 This represents the passenger capacity of train i at station r-1, n t This indicates the number of virtual train sets at the originating station.

[0224] Wherein, the passenger capacity of train i at the originating station is represented by C. i,r =0, r=1, i=1,2,…,n t .

[0225] The fifth determining unit 14232 is used to determine the average passenger load factor of the entire train line based on the above-mentioned train stop variable values, the above-mentioned passenger load at the time of train departure and the above-mentioned train passenger capacity.

[0226] Specifically, the formula for calculating the average passenger load factor of train i across the entire line is as follows:

[0227]

[0228] In the above formula, C0 represents the average passenger load factor across the entire train line, and ω represents the train's capacity. i This represents the number of stops train i makes along the entire line, where ω i The calculation formula is as follows:

[0229]

[0230] When train i stops at station r, ζ i The value of (r) is 1, otherwise ζ i The value of (r) is 0.

[0231] Preferably, the above-mentioned generation submodule 1424 includes:

[0232] Construction unit 14241 is used to construct a virtual train operation optimization function based on the above-mentioned passenger travel time, the above-mentioned train running time, and the above-mentioned average passenger load factor of the entire train line.

[0233] Specifically, the formula for calculating the above objective function is as follows:

[0234]

[0235] In the above formula, t pIndicates passenger travel time, t c Indicates train travel time. denoted as the average passenger load factor across the entire train line, and minZ represents the objective function of the virtual train formation operation optimization model.

[0236] Constraint unit 14242 is used to use the travel demand of all passengers on the line and the average passenger load factor of each train as constraints for the above-mentioned virtual train formation operation optimization function.

[0237] Specifically, the travel demand of all passengers along the line and the average passenger load factor of each train are used as constraints on the objective function. This ensures that at least one train stops at any two stations, thus satisfying the travel demand of all passengers. Therefore, the constraint on the travel demand of all passengers is expressed as follows:

[0238]

[0239] The constraint on the average passenger load factor of each train is expressed as follows:

[0240]

[0241] The solver unit 14243 is used to solve the above-mentioned virtual train formation operation optimization function using a genetic algorithm, and generate the above-mentioned virtual train formation operation optimization scheme.

[0242] Specifically, the objective function decision variable is the stop variable value for each vehicle, i.e., ζ. i (1), ζ i (2), ..., ζ i (N), using a genetic algorithm to solve the objective function, generate the full-line stopping scheme for different vehicles, i.e., the virtual train formation operation optimization scheme.

[0243] Example 3

[0244] This embodiment provides a computer device, including a memory and a processor. The processor is used to read instructions stored in the memory to execute an optimization method for a virtual train formation operation scheme in rail transit according to any of the above method embodiments.

[0245] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0246] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0247] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0248] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0249] Example 4

[0250] This embodiment provides a computer-readable storage medium storing computer-executable instructions that can execute an optimization method for a virtual train formation operation scheme in rail transit, as described in any of the above method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium may also include combinations of the above types of memory.

[0251] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A method for optimizing a virtual marshalling train operation scheme of rail transit, characterized in that, The method comprises the following steps: acquiring line information, train operation information, train vehicle parameters and passenger flow information; inputting the line information, the train operation information, the train vehicle parameters and the passenger flow information into a virtual marshalling train optimization model to generate a virtual marshalling train operation optimization scheme; the step of inputting the line information, the train operation information, the train vehicle parameters and the passenger flow information into the virtual marshalling train optimization model to generate the virtual marshalling train operation optimization scheme comprises the following steps: extracting the distance between two adjacent stations in the line information, the train departure interval in the train operation information, the train stop variable value and the train stop time, the train average running speed in the train vehicle parameters and the passenger quantity from the departure station to the destination station in the passenger flow information, and determining the passenger travel time by using the virtual marshalling train optimization model based on the train departure interval, the train stop variable value, the train stop time, the distance between the two adjacent stations, the train average running speed and the passenger quantity from the departure station to the destination station; determining the train running time by using the virtual marshalling train optimization model based on the distance between the two adjacent stations, the train average running speed, the train stop time and the train stop variable value; extracting the train fixed number of passengers in the train vehicle parameters and the boarding number and the alighting number of passengers at the station in the passenger flow information, and determining the train full-line average passenger load rate by using the virtual marshalling train optimization model based on the train stop variable value, the train fixed number of passengers, the boarding number of passengers at the station and the alighting number of passengers at the station; generating the virtual marshalling train operation optimization scheme based on the passenger travel time, the train running time and the train full-line average passenger load rate.

2. The optimization method for virtual marshalling train operation scheme of rail transit according to claim 1, characterized in that, the step of determining the passenger travel time by using the virtual marshalling train optimization model based on the train departure interval, the train stop variable value, the train stop time, the distance between the two adjacent stations, the train average running speed and the passenger quantity from the departure station to the destination station comprises the following steps: determining the passenger waiting time based on the train stop variable value and the train departure interval; determining the passenger loss time based on the train stop variable value and the train stop time; determining the passenger travel time based on the distance between the two adjacent stations and the train average running speed; generating the passenger travel time based on the passenger waiting time, the passenger loss time, the passenger travel time and the passenger quantity from the departure station to the destination station.

3. The method of claim 2, wherein, the step of generating the passenger travel time based on the passenger waiting time, the passenger loss time, the passenger travel time and the passenger quantity from the departure station to the destination station, and the calculation formula of the passenger travel time is as follows: In the above formula, Indicates the passenger's travel time. Indicates the total number of stations on the line. Indicates the departure station. Indicates the destination station. Indicates train The value of the stop variable at the departure station. Indicates train The value of the stop variable at the destination station. Indicates passenger waiting time Indicates the train departure interval. This indicates that passengers have lost time. Indicates train At the station The value of the stop variable, Indicates the train's stopping time at the station. Indicates the passenger's travel time. This indicates the distance between two adjacent stations. Indicates the average speed of the train. This indicates the number of passengers traveling from the departure station to the destination station.

4. The method of claim 1, wherein, the step of determining the train full-line average passenger load rate by using the virtual marshalling train optimization model based on the train stop variable value, the train fixed number of passengers, the boarding number of passengers at the station and the alighting number of passengers at the station comprises the following steps: determining the passenger load at the departure time of the train based on the boarding number of passengers at the station and the alighting number of passengers at the station; Determine the train average passenger load rate based on the train stop variable value, the train departure passenger load and the train fixed number of passengers.

5. The method of claim 1, wherein, The generating the virtual marshalling train operation optimization scheme based on the passenger travel time, the train operation time and the train average passenger load rate comprises: Construct a virtual marshalling train operation optimization function based on the passenger travel time, the train operation time and the train average passenger load rate; Take the passenger travel demand and the average passenger load rate of each train as the constraint conditions of the virtual marshalling train operation optimization function; Solve the virtual marshalling train operation optimization function by using a genetic algorithm to generate the virtual marshalling train operation optimization scheme.

6. The optimization method for virtual marshaling of rail transit trains according to claim 5, characterized in that, The virtual marshalling train operation optimization function is constructed based on the passenger travel time, the train operation time and the train average passenger load rate, and a calculation formula of the virtual marshalling train operation optimization function is as follows: In the above formula, denotes the passenger travel time, denotes the train running time, denotes the average passenger load rate of the train, denotes the virtual marshalling train running optimization function.

7. A device for optimizing a running scheme of a virtual marshaled train of a rail transit, characterized in that, Comprise: An acquisition module is configured to acquire line information, train operation information, train vehicle parameters and passenger flow information; A generation module is configured to input the line information, the train operation information, the train vehicle parameters and the passenger flow information into a virtual marshalling train optimization model to generate a virtual marshalling train operation optimization scheme; The generation module comprises: A first determination submodule is configured to extract the distance between adjacent stations in the line information, the train departure interval in the train operation information, the train stop variable value and the train stop time, the average train running speed in the train vehicle parameters and the passenger quantity from the departure station to the destination station in the passenger flow information, and determine the passenger travel time based on the train departure interval, the train stop variable value, the train stop time, the distance between adjacent stations, the average train running speed and the passenger quantity from the departure station to the destination station; A second determination submodule is configured to determine the train operation time based on the distance between adjacent stations, the average train running speed, the train stop time and the train stop variable value; A third determination submodule is configured to extract the train fixed number of passengers in the train vehicle parameters and the boarding passengers and the alighting passengers in the passenger flow information, and determine the train average passenger load rate based on the train stop variable value, the train fixed number of passengers, the boarding passengers and the alighting passengers; A generation submodule is configured to generate a virtual marshalling train operation optimization scheme based on the passenger travel time, the train operation time and the train average passenger load rate.

8. A computer device, comprising: The computer program is stored in the memory and configured to instruct the processor to perform the steps of the method according to any one of claims 1-6.

9. A computer readable storage medium having stored thereon computer instructions, wherein, The computer program is stored in the memory and configured to instruct the processor to perform the steps of the method according to any one of claims 1-6.

Images