A vehicle base planning method, device, equipment and storage medium

Abstract

The application relates to the field of urban rail transit, in particular to a vehicle depot planning method, device and equipment and a storage medium. According to operation organization information of a target urban rail line network, train operation stages are divided, a vehicle depot planning model of the target urban rail line network is constructed, a target function of the vehicle depot planning model is constructed with the target of minimizing the sum of train empty mileage cost and vehicle depot investment cost, constraint conditions of the vehicle depot planning model are set based on the operation organization information and each train operation stage, the vehicle depot planning model is solved according to the target function and the constraint conditions, a vehicle depot planning scheme is obtained, the site selection information and the number of the vehicle depot are comprehensively and accurately planned and optimized, the obtained vehicle depot planning scheme is more realistic and reasonable due to the combination of the operation organization information, the operation cost is reduced, the operation efficiency is improved, and the resource utilization rate of the vehicle depot construction is improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of urban rail transit, and particularly relates to a vehicle base planning method, device, equipment and storage medium. BACKGROUND

[0002] As an important part of the urban rail system, the vehicle base plays a key role in the stable, safe and efficient operation of the urban rail train. The site selection of the vehicle base in the urban rail network directly affects the operation path and the maintenance path of the train. The total empty mileage and the total cost of the train in the urban rail network also differ under different numbers, different sites and different scales of the vehicle base plan. Therefore, a scientific and reasonable site selection and scale determination scheme of the vehicle base not only helps to reduce the total empty mileage of the train in the urban rail network, save land resources and planning and construction cost, and efficiently and reasonably utilize various resources, but also significantly improves the network operation efficiency of the urban rail network, and provides good and sustainable economic benefits for the urban rail operator.

[0003] The existing urban rail transit vehicle base planning method mainly aims at the layout and design of the vehicle base, and less considers the site selection and scale optimization of the vehicle base, which leads to unreasonable vehicle base planning, and thus makes the operation cost of the urban rail network high and the operation efficiency low, and the resource utilization rate of the vehicle base construction low. SUMMARY

[0004] To solve the above technical problems of the prior art, the present application provides a vehicle base planning method, device, equipment and storage medium, and the technical scheme is as follows:

[0005] In a first aspect, the embodiments of the present application provide a vehicle base planning method, comprising:

[0006] obtaining a train running phase according to preset operation organization information of a target urban rail network, the train running phase comprising a pre-operation concentrated departure phase, a dispersed departure phase during operation, a dispersed return phase during operation and a post-operation concentrated return phase, and the target urban rail network being provided with a plurality of stations;

[0007] constructing a vehicle base planning model of the target urban rail network;

[0008] constructing an objective function of the vehicle base planning model with the objective of minimizing the sum of the train empty mileage cost of the target urban rail network and the vehicle base investment cost of the target urban rail network;

[0009] setting a constraint condition of the vehicle base planning model;

[0010] Solving the vehicle depot planning model according to the objective function and the constraint condition, a vehicle depot planning scheme of the target urban rail line network is obtained, and the vehicle depot planning scheme comprises vehicle depot site selection information and a vehicle depot quantity.

[0011] In an implementation, the vehicle depot planning model of the target urban rail line network comprises:

[0012] The mixed integer linear programming model is constructed as the vehicle depot planning model.

[0013] In an implementation, solving the vehicle depot planning model according to the objective function and the constraint condition comprises:

[0014] Solving the vehicle depot planning model according to the objective function and the constraint condition by using a tabu search algorithm, a vehicle depot planning scheme of the target urban rail line network is obtained.

[0015] In an implementation, the train empty mileage cost is equal to a product of a train running mileage and a preset unit mileage empty cost, the train running mileage is calculated according to the to-be-determined vehicle depot site selection information, the operation organization information and the station of the target urban rail line network, and the vehicle depot investment cost is equal to a product of a preset single vehicle depot investment cost and the to-be-determined vehicle depot quantity.

[0016] The constraint condition comprises a continuity constraint of a train running path in the target urban rail line network, a uniqueness constraint of the train running path in the target urban rail line network, a train quantity constraint from the vehicle depot to a starting station of the target urban rail line network in a centralized departure stage before operation, a train quantity constraint from the vehicle depot in a decentralized departure stage during operation, a train quantity constraint returning to the vehicle depot in a decentralized return stage during operation and a centralized return stage after operation, a constraint that a train quantity from the vehicle depot in each train running stage is equal to a train quantity returning to the vehicle depot in each train running stage, a vehicle depot departure quantity constraint, a vehicle depot departure capacity constraint, a turn-back capacity constraint of a turn-back station of the target urban rail line network, a vehicle depot track connection scheme constraint, a station site constraint reached by a train from the vehicle depot in the decentralized departure stage during operation, and a vehicle depot quantity constraint.

[0017] In an implementation, solving the vehicle depot planning model according to the objective function and the constraint condition comprises:

[0018] Solving the vehicle depot planning model according to the objective function and the constraint condition by using a preset improved tabu search algorithm, a vehicle depot planning scheme of the target urban rail line network is obtained.

[0019] In an embodiment, the vehicle depot planning model is solved by using a preset improved tabu search algorithm according to the objective function and the constraint condition, and a vehicle depot planning scheme of the target urban rail line network is obtained, including:

[0020] determining a plurality of tabu search tasks of the vehicle depot planning model;

[0021] solving each of the tabu search tasks in parallel by using the tabu search algorithm, and outputting a plurality of solving results;

[0022] selecting the solving results according to the objective function and the constraint condition, and obtaining a target initial solution;

[0023] initializing a first iteration number as 0;

[0024] taking the target initial solution as a current solution;

[0025] generating an empty first tabu table, and storing the current solution in the first tabu table;

[0026] increasing the first iteration number by 1, and obtaining a plurality of candidate solutions according to the current solution, a preset transformation rule and a preset random operator;

[0027] selecting the candidate solutions according to the objective function and the constraint condition, and obtaining an optimal candidate solution;

[0028] if the optimal candidate solution satisfies a contempt criterion, taking the optimal candidate solution as the current solution, replacing an earliest stored solution in the first tabu table with the current solution, and determining whether the first iteration number is greater than or equal to a preset second threshold value, if yes, outputting the current solution as the vehicle depot planning scheme; if no, returning to the step of increasing the first iteration number by 1 and obtaining the plurality of candidate solutions according to the current solution, the preset transformation rule and the preset random operator;

[0029] if the optimal candidate solution does not satisfy the contempt criterion, taking the optimal candidate solution that is not tabu as the current solution, replacing the earliest stored solution in the first tabu table with the current solution, and determining whether the first iteration number is greater than or equal to the second threshold value, if yes, outputting the current solution as the vehicle depot planning scheme; if no, returning to the step of increasing the first iteration number by 1 and obtaining the plurality of candidate solutions according to the current solution, the preset transformation rule and the preset random operator.

[0030] In an embodiment, the solving each of the tabu search tasks in parallel by using the tabu search algorithm, and outputting the plurality of solving results includes:

[0031] initializing a second iteration number as 0;

[0032] generating an initial solution corresponding to each of the tabu search tasks and an empty second tabu table corresponding to each of the tabu search tasks;

[0033] store each initial solution as a current solution of each tabu search task, and store each current solution to a corresponding second tabu table;

[0034] increment a second iteration number by 1, and obtain a plurality of candidate solution sets according to the current solution and a preset transformation rule, each candidate solution set including a plurality of candidate solutions;

[0035] filter the candidate solutions in each candidate solution set according to the objective function and the constraint condition, and obtain an optimal candidate solution of each tabu search task;

[0036] if the optimal candidate solution satisfies the contempt criterion, the optimal candidate solution is taken as the current solution, the earliest stored solution in the tabu table is replaced by the current solution, and it is judged whether the second iteration number is greater than or equal to a preset first threshold value, if yes, the current solution is output as a solving result; if no, the step of incrementing the second iteration number by 1 and obtaining a plurality of candidate solution sets according to the current solution and a preset transformation rule is returned;

[0037] if the optimal candidate solution does not satisfy the contempt criterion, the non-tabu optimal candidate solution is taken as the current solution, the earliest stored solution in the tabu table is replaced by the current solution, and it is judged whether the second iteration number is greater than or equal to the first threshold value, if yes, the current solution is output as a solving result; if no, the step of incrementing the second iteration number by 1 and obtaining a plurality of candidate solution sets according to the current solution and a preset transformation rule is returned.

[0038] In a second aspect, an embodiment of the present application provides a vehicle depot planning device, comprising:

[0039] a running phase division module configured to obtain a train running phase according to preset operation organization information of a target urban rail line network, the train running phase including a pre-operation concentrated departure phase, a dispersed departure phase during operation, a dispersed return phase during operation, and a post-operation concentrated return phase, and the target urban rail line network being provided with a plurality of stations;

[0040] a modeling module configured to construct a vehicle depot planning model of the target urban rail line network;

[0041] a target function construction module configured to construct a target function of the vehicle depot planning model with a target of minimizing a sum of a train empty mileage cost and a vehicle depot investment cost of the target urban rail line network, the train empty mileage cost being equal to a product of a train mileage and a preset unit mileage empty cost, the train mileage being calculated according to vehicle depot site selection information to be determined, operation organization information, and the stations of the target urban rail line network, and the vehicle depot investment cost being equal to a product of a preset single vehicle depot investment cost and a vehicle depot quantity to be determined;

[0042] The constraint setting module is configured to set constraints of the vehicle depot planning model, and the constraints include continuity constraints of a travel path of a train in a target urban rail line network, uniqueness constraints of the travel path of the train in the target urban rail line network, a constraint of a number of trains traveling from the vehicle depot to a starting station of the target urban rail line network in a centralized departure stage before operation, a constraint of a number of trains departing from the vehicle depot in a decentralized departure stage during operation, a constraint of a number of trains returning to the vehicle depot in a decentralized return stage during operation and a centralized return stage after operation, a constraint of a number of trains departing from the vehicle depot in each train operation stage being equal to a number of trains returning to the vehicle depot in each train operation stage, a constraint of a number of departures of the vehicle depot, a constraint of a departure capacity of the vehicle depot, a constraint of a turnaround capacity of a turnaround station of the target urban rail line network, a constraint of a rail connection scheme of the vehicle depot, a constraint of stations reached by trains departing from the vehicle depot in the decentralized departure stage during operation, and a constraint of a number of vehicle depots.

[0043] The model solving module is configured to solve the vehicle depot planning model according to the objective function and the constraints, to obtain a vehicle depot planning scheme of the target urban rail line network, the vehicle depot planning scheme including vehicle depot site selection information and a number of vehicle depots.

[0044] In a third aspect, an embodiment of the present application provides a vehicle depot planning device, which includes a memory and a processor. The memory and the processor communicate with each other through an internal connection path. The memory is configured to store instructions, and the processor is configured to execute the instructions stored in the memory. When the processor executes the instructions stored in the memory, the processor executes the method in any one of the embodiments of the above aspects.

[0045] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program. When the computer program runs on a computer, the method in any one of the embodiments of the above aspects is executed.

[0046] The beneficial effects of the present application are embodied in that, by dividing train operation stages according to operation organization information of a target urban rail line network, then constructing a vehicle depot planning model of the target urban rail line network, constructing a target function of the vehicle depot planning model with the goal of minimizing the sum of train empty mileage cost of the target urban rail line network and vehicle depot investment cost of the target urban rail line network, setting constraint conditions of the vehicle depot planning model based on the operation organization information and constraints such as train driving path, train departure quantity, train return quantity, departure capacity, rail connection scheme and turn-back capacity under each train operation stage, and then solving the vehicle depot planning model according to the target function and the constraint conditions to obtain a vehicle depot planning scheme of the target urban rail line network, the vehicle depot site selection information and the vehicle depot quantity are comprehensively and accurately planned and optimized, and since the train operation stages are divided in combination with the operation organization information, the obtained vehicle depot planning scheme is more realistic, the rationality of the vehicle depot planning is improved, the operation cost of the urban rail line network is reduced, the operation efficiency of the urban rail line network is improved, and the resource utilization rate of the vehicle depot construction is improved. BRIEF DESCRIPTION OF DRAWINGS

[0047] In the drawings, like reference numerals refer to like elements throughout the various drawings. The drawings are not necessarily to scale, emphasis instead being placed on illustrating principles of the application. It should be understood that the drawings are merely depictions of some embodiments of the application and should not be construed as limiting the scope of the application.

[0048] Figure 1 A flowchart of a vehicle depot planning method of an embodiment of the present application;

[0049] Figure 2 A structure diagram of a target urban rail line network of a vehicle depot planning method of an embodiment of the present application;

[0050] Figure 3 A route structure diagram of a target urban rail line network of a vehicle depot planning method of an embodiment of the present application;

[0051] Figure 4 An iteration result diagram of an improved tabu search algorithm of a vehicle depot planning method of an embodiment of the present application;

[0052] Figure 5 A structure diagram of a vehicle depot planning device of an embodiment of the present application;

[0053] Figure 6 A structure diagram of a vehicle depot planning device of an embodiment of the present application. DETAILED DESCRIPTION

[0054] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by those skilled in the art without creative effort belong to the scope of the present application.

[0055] Figure 1 A flow chart of a vehicle depot planning method according to an embodiment of the present application is shown. As shown in the figure, the vehicle depot planning method can include: Figure 1

[0056] S101, obtaining a train running phase according to preset operation organization information of a target urban rail line network.

[0057] The train running phase includes a pre-operation concentrated departure phase, an operation time dispersed departure phase, an operation time dispersed return phase and a post-operation concentrated return phase, and the target urban rail line network is provided with a plurality of stations.

[0058] It can be understood that the operation organization information of the target urban rail line network is an actual operation organization scheme and the like set for the line network, and the train running phase of the embodiment of the present application is each running phase of the whole-day operation of the urban rail train. Among them:

[0059] The pre-operation concentrated departure phase: before operation, the train departs from the vehicle depot, and is driven to the starting station of the target urban rail line network through a direct path or a return path for empty running, so as to wait for passenger operation.

[0060] The operation time dispersed departure phase and the operation time dispersed return phase: after the target urban rail line network starts operation, the number of trains required to be operated is different at different time periods, so before the time period when passenger travel demand is relatively strong, such as morning peak and evening peak, the train needs to depart from the vehicle depot, drive into the main line, and arrive at the vehicle depot junction station to carry passengers for operation; before the time period when passenger travel demand decreases, such as flat peak and low peak, the train needs to transport passengers to the terminal station, and then return to the vehicle depot for empty running. The operation time dispersed departure phase includes a pre-morning peak charging stage and a pre-evening peak charging stage, and the operation time dispersed return phase includes a post-morning peak return stage and a post-evening peak return stage.

[0061] The post-operation concentrated return phase: after operation, the train completes passenger cleaning at the terminal station of the target urban rail line network, and returns to the vehicle depot through a direct path or a return path for empty running.

[0062] ​It can be understood that, according to the embodiments of the present application, the train operation stage is divided according to the operation organization information of the target urban rail line network, so that the constraint conditions set based on the train operation stage and the operation organization information are consistent with the actual conditions, thereby making the vehicle depot planning scheme calculated more reasonable and practical.

[0063] S102, a vehicle depot planning model of the target urban rail line network is constructed.

[0064] Specifically, the embodiments of the present application construct a vehicle depot planning model of the target urban rail line network, and the output value of the model is a vehicle depot planning scheme. Therefore, by solving the vehicle depot planning model, the vehicle depot planning scheme can be obtained.

[0065] Optionally, in some embodiments, an integer programming model is constructed as the vehicle depot planning model of the target urban rail line network. In these embodiments, the scale of the target urban rail line network is small, the vehicle depot site selection information and the number of vehicle depots are discretized as integer variables, and the optimal solution is solved by a linear programming model, and the vehicle depot site selection information and the number of vehicle depots output have high accuracy.

[0066] Optionally, in some embodiments, a mixed integer linear programming model is constructed as the vehicle depot planning model of the target urban rail line network. It can be understood that the mixed integer linear programming model adds some continuous variables on the basis of the integer programming model, can more flexibly describe the vehicle depot site selection information and the number of vehicle depots, can consider more actual situations, and has high solving efficiency.

[0067] Optionally, in some embodiments, a network flow-based model is constructed as the vehicle depot planning model of the target urban rail line network. In these embodiments, the vehicle depot planning problem is converted into a network flow problem, and the optimal solution of the model is solved by a minimum cost flow or maximum flow algorithm. It can be understood that the network flow-based model considers the flowability of the train and the transportation demand, and the vehicle depot planning scheme output in the scenario where the number of train operations needs to be considered is more accurate.

[0068] S103, a target function of the vehicle depot planning model is constructed with the objective of minimizing the sum of the train empty mileage cost of the target urban rail line network and the vehicle depot investment cost of the target urban rail line network.

[0069] The train empty mileage cost is equal to the product of the train mileage and the preset unit mileage empty cost, the train mileage is calculated according to the vehicle depot site selection information to be determined, the operation organization information and the station of the target urban rail line network, and the vehicle depot investment cost is equal to the product of the preset single vehicle depot investment cost and the number of vehicle depots to be determined.

[0070] It can be understood that the embodiments of the present application define the target of the vehicle depot planning by constructing the objective function of the vehicle depot planning model, guide the vehicle depot planning model to pay more attention to and optimize important indicators in the decision-making process, thereby improving the quality and efficiency of the vehicle depot planning scheme; at the same time, in the subsequent solving process of the vehicle depot planning model, the different vehicle depot planning schemes can be evaluated and compared by calculating the objective function value, and the scheme with the optimal objective function value is selected as the final vehicle depot planning scheme from multiple feasible solutions.

[0071] Specifically, the objective function is:

[0072]

[0073] Wherein, a represents a train operation stage, a = 1 represents a concentrated departure stage before operation, a = 2 represents a train adding stage before early peak, a = 3 represents a back to depot stage after early peak, a = 4 represents a train adding stage before late peak, a = 5 represents a train adding stage after late peak, and a = 6 represents a concentrated back to depot stage after operation; r a Different trains in different train operation stages; represents a 0-1 variable of a train in different train operation stages, if a train r a If a train continuously passes through i, j stations, then The value of is 1, otherwise 0; N represents a set of all nodes, including all stations in the target urban rail line network and the nodes corresponding to the to-be-determined vehicle depot site selection information; if i, j stations are adjacent and i can directly reach j, then G(i, j) = d, d is the distance between i, j stations, if i, j stations are not adjacent, then G(i, j) = M, M is a value of infinity; represents the train mileage; α represents the unit mileage empty running cost, that is, the average empty running cost per kilometer; x represents the to-be-determined number of vehicle depots; β represents the preset investment cost (annualized) of a single vehicle depot.

[0074] In some embodiments, the unit mileage empty running cost is:

[0075] α = n × (e × c1 + c2)

[0076] Wherein, n represents the number of marshalling of the trains in the target urban rail line network; e represents the average energy consumption per kilometer of each train; c1 represents the urban rail electricity charging standard of the place where the target urban rail line network is located; c2 represents the average repair cost per kilometer of each train.

[0077] In some embodiments, the investment cost of a single vehicle depot is:

[0078]

[0079] wherein c3 represents the total investment cost of a single vehicle depot; n ′ represents the design service life of the vehicle depot; represents the capital recovery coefficient, which can be understood as a ratio of the annual recovery amount to the investment amount considering compound interest in the fixed investment period, and essentially represents a conversion coefficient of the total investment cost into the annual annuity limit in the fixed period; and γ represents the capital recovery rate.

[0080] S104, setting a constraint condition of the vehicle depot planning model.

[0081] The constraint condition includes a continuity constraint of a travel path of a train in a target urban rail line network, a uniqueness constraint of the travel path of the train in the target urban rail line network, a constraint of a number of trains traveling from the vehicle depot to a departure station of the target urban rail line network in a concentrated departure stage before operation, a constraint of a number of trains departing from the vehicle depot in a dispersed departure stage during operation, a constraint of a number of trains returning to the vehicle depot in a dispersed return stage during operation and a concentrated return stage after operation, a constraint of a number of trains departing from the vehicle depot in each train operation stage being equal to a number of trains returning to the vehicle depot in each train operation stage, a constraint of a number of departures of the vehicle depot, a constraint of a departure capacity of the vehicle depot, a constraint of a turnaround capacity of a turnaround station of the target urban rail line network, a constraint of a rail connection scheme of the vehicle depot, a constraint of stations arrived at by the trains departing from the vehicle depot in the dispersed departure stage during operation, and a constraint of a number of the vehicle depots. It can be understood that the embodiments of the present application set the constraint condition of the vehicle depot planning model in combination with actual operation organization information and train operation stages, define the limitation condition of the vehicle depot planning model, so that the vehicle depot planning scheme calculated is feasible in actual operation and does not violate actual limitations and requirements; at the same time, the setting of the constraint condition narrows the search space when the vehicle depot planning model is solved subsequently, so that the solving process of the vehicle depot planning model is more efficient and accurate, that is, by excluding solutions that do not satisfy the constraint condition, more attention can be focused on solutions with greater potential, and the model solving speed is accelerated; in addition, the constraint condition provides specific constraint information of the vehicle depot planning problem, and converts the vehicle depot planning problem into a mathematical model solving.

[0082] Specifically, step S104 specifically includes steps S1041-S10412:

[0083] Step S1041, setting a continuity constraint of a travel path of a train in a target urban rail line network.

[0084] It can be understood that the travel path of the train between stations in the target urban rail line network is continuous. Therefore, in different train operation stages a, the train r aIf a train arrives at a station j in the target urban rail network, it must depart from the station j to reach other stations, which can be expressed as:

[0085]

[0086] In step S1042, the uniqueness constraint of the travel path of the train in the target urban rail network is set.

[0087] It can be understood that the travel path of the train in the target urban rail network is unique, and the number of times the train passes through the same station is less than or equal to 1, which represents the uniqueness of the travel path of the train, that is, in different train operation stages a, the train r a At most, each station is passed once, which can be expressed as:

[0088]

[0089] In step S1043, the number constraint of the train traveling from the vehicle depot to the starting station of the target urban rail network in the pre-operation concentrated departure stage is set.

[0090] It can be understood that in the pre-operation concentrated departure stage, the train needs to be empty from the vehicle depot to the starting station of the target urban rail network in a specified time period for passenger operation, which can be expressed as:

[0091]

[0092]

[0093] Wherein, r1 represents the train in the pre-operation concentrated departure stage; R1 represents the train set in the pre-operation concentrated departure stage; S represents the set of all stations of the target urban rail network; D represents the set of nodes corresponding to the vehicle depot site information; v represents a virtual station (starting station); n1 represents the number of trains in the pre-operation concentrated departure stage; O i represents the preset number of trains departing from the starting station of the target urban rail network.

[0094] In step S1044, the number constraint of the train departing from the vehicle depot in the operation dispersed departure stage is set.

[0095] It can be understood that in the operation dispersed departure stage (pre-peak early morning and pre-peak late evening), the train in the vehicle depot needs to be dispersed to be loaded. In the operation dispersed departure stage, there are already some trains running on the target urban rail network, and the train departing from the vehicle depot for loading does not need to be empty to the starting station, but can directly run to the junction station of the target urban rail network to start passenger operation, which can be expressed as:

[0096]

[0097]

[0098] wherein r2 represents a train in the pre-early peak stage of adding cars; r4 represents a train in the pre-late peak stage of adding cars; R2 represents a set of trains in the pre-early peak stage of adding cars; R4 represents a set of trains in the pre-late peak stage of adding cars; n2 represents the number of trains in the pre-early peak stage of adding cars; n4 represents the number of trains in the pre-late peak stage of adding cars; and v represents a virtual station (a junction station).

[0099] In step S1045, the number of trains returning to the vehicle depot in the pre-early peak stage of dispersing and the post-operation stage of concentrating is set.

[0100] It can be understood that in the pre-early peak stage of dispersing and the post-operation stage of concentrating, the train first travels to the terminal station of the target urban rail line network, completes the last passenger carrying task, and then returns to the vehicle depot after emptying the passengers at the terminal station. The terminal station is the terminal station of each line in the target urban rail line network, and the number of arriving trains at different terminal stations is related to the operation organization information, which can be specifically expressed as:

[0101]

[0102]

[0103]

[0104]

[0105]

[0106]

[0107] wherein v represents a virtual station (a terminal station); r3 represents a train in the post-early peak stage of returning; r5 represents a train in the post-late peak stage of returning; r6 represents a train in the post-operation stage of concentrating; R3 represents a set of trains in the post-early peak stage of returning; R5 represents a set of trains in the post-late peak stage of returning; R6 represents a set of trains in the post-operation stage of concentrating; D i represents the number of trains running to the terminal station of the target urban rail line network in the post-early peak stage of returning; D i ′ represents the number of trains running to the terminal station of the target urban rail line network in the post-late peak stage of returning; D i ″n3 represents the number of trains in the early morning peak after the departure stage; n5 represents the number of trains in the late peak after the departure stage; and n6 represents the number of trains in the post-operation concentrated return stage.

[0108] Step S1046, setting a constraint that the number of trains departing from the vehicle depot in each train operation stage is equal to the number of trains returning to the vehicle depot in each train operation stage.

[0109] It can be understood that the scale of the vehicle depot is conserved after being set, and for a certain vehicle depot, the number of trains received and sent in different train operation stages should be balanced, that is, the number of trains sent in the pre-operation concentrated departure stage and the operation time dispersed departure stage should be equal to the number of trains returned in the post-operation concentrated return stage and the operation time dispersed return stage, which can be specifically represented as:

[0110]

[0111] Step S1047, setting a vehicle depot departure number constraint.

[0112] Specifically, the vehicle depot departure number constraint indicates that in different train operation stages, the number of trains departing from a certain vehicle depot cannot be greater than the number of trains stored in the vehicle depot in the train operation stage, and the sum of the number of trains returned from a certain vehicle depot and the number of trains stored in the vehicle depot cannot be greater than the scale of the vehicle depot, which can be specifically represented as:

[0113]

[0114] Step S1048, setting a vehicle depot departure capacity constraint.

[0115] It can be understood that after the daily operation is completed, the vehicle depot needs to carry out tasks such as cleaning, detection, and maintenance of trains to ensure the safe operation of the trains. Therefore, before operation, the vehicle depot needs to send the trains within a limited time so as not to occupy the window time. For a certain vehicle depot, the number of trains that can be sent in the pre-operation concentrated departure stage is affected by its departure capacity, which can be specifically represented as:

[0116]

[0117] C 1,t represents the uplink departure capacity of the vehicle depot t.

[0118] Step S1049, setting a turnaround station turnaround capacity constraint of the target city rail line network.

[0119] It can be understood that the number of turnable trains of the turnback station per unit time has an upper limit, which is affected by the turnback capacity of the turnback station, and can be specifically represented as:

[0120]

[0121] Wherein, T represents a set of turnback stations of the target urban rail line network; η i represents the turnback capacity of the turnback station i; m1 represents the number of stations of the target urban rail line network.

[0122] Step S10410, setting a vehicle depot track connection scheme constraint.

[0123] It can be understood that the vehicle depot track connection scheme includes single-station double-line track connection, two-station track connection and interval track connection, wherein the single-station double-line track connection scheme is more common. The embodiments of the present application take the single-station double-line track connection scheme as an example. Under the single-station double-line track connection scheme, the vehicle depot is connected to one station through double lines. In addition, one line connected between the vehicle depot and the station is used for departure, and the other line is used for train back. Under the single-station double-line track connection scheme, the vehicle depot track connection scheme constraint can be specifically represented as:

[0124]

[0125]

[0126]

[0127]

[0128]

[0129]

[0130]

[0131] Wherein, z i,j represents a 0-1 variable of vehicle depot site selection information, if the site selection of the vehicle depot i is at the j station, then z i,j is 1, otherwise 0; u i represents an outgoing line 0-1 variable, if it is an outgoing line, then u i is 1, otherwise 0.

[0132] Step S10411, setting a constraint that the train departing from the vehicle depot in the dispersed departure stage reaches a station during operation.

[0133] It can be understood that when the number of trains connected by a station of the target urban rail line network is greater than a certain value, the vehicle depot cannot add trains to the main line, that is, during the pre-early peak and pre-late peak train adding stages, when the number of trains connected by the vehicle depot connection station is small, the vehicle depot can add trains to the main line, which can be specifically represented as:

[0134]

[0135]

[0136] H1 represents a set of stations with limited train adding during the pre-early peak train adding stage; H2 represents a set of stations with limited train adding during the pre-late peak train adding stage.

[0137] Step S10412, setting a vehicle depot quantity constraint.

[0138] It can be understood that due to factors such as cost and land use, the number of vehicle depots in the urban rail line network should not be too large, so it is necessary to determine the upper limit of the number of vehicle depots in the model, which can be specifically represented as:

[0139]

[0140] m2 represents the maximum number of vehicle depots.

[0141] S105, solving the vehicle depot planning model according to the objective function and the constraint condition, to obtain a vehicle depot planning scheme of the target urban rail line network.

[0142] The vehicle depot planning scheme includes vehicle depot site selection information and the number of vehicle depots.

[0143] Specifically, in the embodiments of the present application, a heuristic algorithm can be used to solve the vehicle depot planning model, such as a tabu search algorithm, a genetic algorithm, and a simulated annealing algorithm. The heuristic algorithm adjusts and optimizes the vehicle depot site selection information and the number of vehicle depots through search and optimization strategies to achieve better results. The heuristic algorithm has good robustness and adaptability when dealing with large-scale and high-complexity vehicle depot planning problems.

[0144] Optionally, in some embodiments, the tabu search algorithm is used to solve the vehicle depot planning model according to the objective function and the constraint condition, to obtain a vehicle depot planning scheme of the target urban rail line network.

[0145] It can be understood that the tabu search algorithm has global search capability, and can jump out of the limitation of local optimal solution when solving the vehicle depot planning model, search multiple solutions in the search space, and thus find a better solution. In addition, the tabu search algorithm has high flexibility and robustness, and can adapt to different objective functions and constraint conditions when solving the vehicle depot planning model, and can process multiple search tasks in parallel.

[0146] Optionally, in some embodiments, since the tabu search algorithm can be combined with other heuristic algorithms, a hybrid algorithm combining the tabu search algorithm with other heuristic algorithms (such as genetic algorithm, simulated annealing algorithm) is used to solve the vehicle depot planning model.

[0147] Further, according to the objective function and the constraint condition, the tabu search algorithm is used to solve the vehicle depot planning model to obtain a vehicle depot planning scheme of the target urban rail line network, which specifically includes the following steps:

[0148] 1-1, initialize the iteration number to 0;

[0149] 1-2, generate an initial solution and an empty tabu table, and the tabu table is used to store the accessed solutions;

[0150] 1-3, take the initial solution as the current solution, and store the current solution in the tabu table;

[0151] 1-4, increase the iteration number by 1, and obtain a plurality of candidate solutions according to the current solution and a preset transformation rule;

[0152] 1-5, screen the candidate solutions according to the objective function and the constraint condition to obtain an optimal candidate solution;

[0153] 1-6, if the optimal candidate solution meets the contempt criterion, the optimal candidate solution is taken as the current solution, the earliest stored solution in the tabu table is replaced by the current solution, and it is judged whether the iteration number is greater than or equal to a preset first threshold value, if yes, the current solution is output as the vehicle depot planning scheme; if no, return to step 1-4;

[0154] 1-7, if the optimal candidate solution does not meet the contempt criterion, the non-tabu optimal candidate solution is taken as the current solution, the earliest stored solution in the tabu table is replaced by the current solution, and it is judged whether the iteration number is greater than or equal to the first threshold value, if yes, the current solution is output as the vehicle depot planning scheme; if no, return to step 1-4.

[0155] It can be understood that the contempt criterion (special pardon criterion) is: (1) a rule based on evaluation value, if a solution has a better target value than any previous best candidate solution, it can be pardoned; (2) a rule based on minimum error, if all objects are tabu, a solution with the minimum evaluation value is pardoned.

[0156] In step 1-4, the preset transformation rule is a neighborhood operator designed by the embodiment of the application, and a plurality of candidate solutions are obtained after generating a neighborhood space according to the current solution and the neighborhood operator. The neighborhood operator includes a sequence number increasing operator, a sequence number decreasing operator, and an insertion operator and a deletion operator. For the sequence number increasing operator and the sequence number decreasing operator, the algorithm adaptively changes the increasing or decreasing amplitude according to the current solution evaluation function value.

[0157] Optionally, in some embodiments, the preset improved tabu search algorithm is used to solve the vehicle depot planning model according to the objective function and the constraint condition, and a vehicle depot planning scheme of the target urban rail line network is obtained.

[0158] Specifically, the improved tabu search algorithm is designed on the basis of the tabu search algorithm. The improved tabu search algorithm includes two stages. In the first stage, the tabu search algorithm is used to process a plurality of determined tabu search tasks in parallel, a plurality of solution results are output, and then an evaluation function is used to select a solution with the highest evaluation value from the solution results as an initial solution of the second stage. In the second stage, the solution with the highest evaluation value output in the first stage is used as the initial solution, and the tabu search algorithm is used for solving. When a neighborhood solution (a candidate solution) is solved, a random operator is added to improve the diversity of the candidate solution and improve the solving speed and performance of the tabu search algorithm.

[0159] Further, the preset improved tabu search algorithm is used to solve the vehicle depot planning model according to the objective function and the constraint condition, and a vehicle depot planning scheme of the target urban rail line network is obtained, which specifically includes the following steps:

[0160] 2-1, determining a plurality of tabu search tasks of the vehicle depot planning model;

[0161] 2-2, using the tabu search algorithm to solve each tabu search task in parallel, and outputting a plurality of solution results;

[0162] 2-3, selecting the solution results according to the objective function and the constraint condition, and obtaining a target initial solution;

[0163] 2-4, initializing the first iteration number as 0;

[0164] 2-5, taking the target initial solution as a current solution;

[0165] 2-6, generating an empty first tabu table, and storing the current solution to the first tabu table;

[0166] 2-7, increasing the first iteration number by 1, and obtaining a plurality of candidate solutions according to the current solution, a preset transformation rule, and a preset random operator;

[0167] 2-8, selecting the candidate solutions according to the objective function and the constraint condition, and obtaining an optimal candidate solution;

[0168] 2-9, if the optimal candidate solution satisfies the contempt criterion, the optimal candidate solution is taken as the current solution, the earliest stored solution in the first tabu table is replaced by the current solution, and it is judged whether the first iteration number is greater than or equal to a preset second threshold value, if yes, the current solution is output as the vehicle base planning scheme; if no, return to step 2-7;

[0169] 2-10, if the optimal candidate solution does not satisfy the contempt criterion, the non-tabu optimal candidate solution is taken as the current solution, the earliest stored solution in the first tabu table is replaced by the current solution, and it is judged whether the iteration number is greater than or equal to the second threshold value, if yes, the current solution is output as the vehicle base planning scheme; if no, return to step 2-7.

[0170] It can be understood that the first stage of the improved tabu search algorithm preset in the embodiment of the application is steps 2-1 to 2-3, and the second stage is steps 2-4 to 2-10.

[0171] It is worth noting that in step 2-7, the random operator is added when the tabu search algorithm solves the neighborhood solution (candidate solution), and the random operator specifically refers to replacing the sequence number of the vehicle base site selection information in the current solution with a random sequence number. Based on the candidate solution generated by the random operator, each candidate solution only replaces the sequence number of one vehicle base site selection information, thereby improving the diversity of the candidate solution and improving the solving speed and performance of the second stage tabu search algorithm. In addition, the transformation rule preset in step 2-7 is the same as the transformation rule in step 1-4, which is not described here.

[0172] Further, in the embodiment of the application, step 2-2 specifically includes:

[0173] 1) initialize the second iteration number to 0;

[0174] 2) generate the initial solution corresponding to each tabu search task and the empty second tabu table corresponding to each tabu search task;

[0175] 3) take each initial solution as the current solution of each tabu search task, and store each current solution to the corresponding second tabu table;

[0176] 4) increase the second iteration number by 1, obtain a plurality of candidate solution sets according to the current solution and the transformation rule, and each candidate solution set includes a plurality of candidate solutions;

[0177] 5) screen the candidate solutions in each candidate solution set according to the objective function and the constraint condition to obtain the optimal candidate solution of each tabu search task;

[0178] 6) If the optimal candidate solution satisfies the contempt criterion, the optimal candidate solution is taken as the current solution, the earliest stored solution in the tabu table is replaced by the current solution, and it is judged whether the second iteration number is greater than or equal to the preset first threshold value. If yes, the current solution is output as the solving result; if no, step 4) is returned.

[0179] 7) If the optimal candidate solution does not satisfy the contempt criterion, the non-tabu optimal candidate solution is taken as the current solution, the earliest stored solution in the tabu table is replaced by the current solution, and it is judged whether the second iteration number is greater than or equal to the first threshold value. If yes, the current solution is output as the solving result; if no, step 4) is returned. It can be understood that, when the tabu search algorithm or the improved tabu search algorithm is used to solve the vehicle depot planning model, the solution of the algorithm is first encoded to determine the covered content and the encoding mode of the solution, as the iteration basis of the subsequent algorithm. In the embodiment of the present application, the partial determined variables of the solution are encoded, and the remaining determined variables of the solution will be obtained by solving the sub-model in the candidate solution screening step. In the embodiment of the present application, the encoding length of the solution represents the number of vehicle depots, and each element / number in the encoding represents the vehicle depot site selection information. The lower limit of the encoding length is 1, and the upper limit is the maximum value of the number of vehicle depots. Within this range, the encoding length of the solution can be changed according to the design of the random operator at each iteration.

[0180] Optionally, in some embodiments, when the vehicle depot planning model is solved, the basic parameters of the vehicle depot planning model (objective function) are first determined according to the operation organization information of the target urban rail line network, then the basic parameters of the tabu search algorithm / improved tabu search algorithm are determined according to the constraint conditions of the vehicle depot planning model, and finally the tabu search algorithm / improved tabu search algorithm is used to quantitatively solve the vehicle depot planning model to obtain the vehicle depot site selection information and the number of vehicle depots.

[0181] Reference Figure 2 In one specific embodiment of the present application, the target urban rail line network has 4 urban rail lines, 74 stations, 3 transfer stations, and 135 trains. In the target urban rail line network, line 1 includes stations S1-S24; line 2 includes stations S25-S39 and station S18; line 3 includes stations S39-S64, which consists of a trunk line and a straight line; and line 4 includes stations S65-S74 and station S27. The target urban rail line network has 8 interchanges, such as Figure 3As shown, the route 1 includes stations S1-S18, S38-S43, S57-S64; the route 2 includes stations S1-S21; the route 3 includes stations S25-S39, S18; the route 4 includes stations S29-S56, S18; the route 5 includes stations S29-S43, S57-S64, S18; the route 6 includes stations S27-S37, S65-S74, S18; the route 7 includes stations S8-S24; and the route 8 includes stations S43-S56, S57-S64. The trains on the routes 2, 3, 7 and 8 all operate in different lines, while the routes 1, 4, 5 and 6 are composed of part stations of two or more lines, so that the trains on the routes 1, 4, 5 and 6 can realize cross-line operation, which not only can reduce the passenger flow pressure of the transfer stations to a certain extent and meet the fast and direct travel demand of passengers, but also can improve the utilization rate of the trains in the line network and reduce the operation cost. The train operation numbers of each period on different routes are shown in Table 1. In the specific embodiments of the present application, 7:00-9:00 and 17:00-19:00 are respectively the morning and evening peak hours, and the total train operation numbers of the line network in this period are the most. 6:00-7:00, 9:00-17:00 and 19:00-24:00 are the flat peak hours, and the total train operation numbers in the line network in this period are less, but the train operation numbers are different due to different demands in different periods. Considering the needs of construction and maintenance, the window time cannot be too short, and the train operation starts 1 hour before the operation. Therefore, 5:00-6:00 is the concentrated train operation stage before the operation, 6:00-7:00 is the dispersed train operation stage before the morning peak, 9:00-10:00 is the back stage after the morning peak, 16:00-17:00 is the dispersed train operation stage before the evening peak, 19:00-24:00 is the back stage after the evening peak, and 24:00 onwards is the concentrated back stage after the operation.

[0182] Table 1

[0183]

[0184]

[0185] For step S105, first, the basic parameters of the vehicle depot planning model (objective function) are determined according to the operation organization information of the target urban rail line network, wherein the average energy consumption of each train per kilometer is 2.23 kw·h / vehicle·km, the urban rail electricity charging standard of the city where the target urban rail line network is located is 0.7601 yuan / kw·h, the average repair cost of each train per kilometer is 2.75 yuan / vehicle·km, the total investment cost of a single vehicle depot is 300 million yuan, the design service life of the vehicle depot is 50 years, and the capital recovery coefficient is 0.02; then, the basic parameters of the improved tabu search algorithm are determined, wherein the length of the tabu list is set to 4, the first threshold is 5, the number of tabu search tasks processed in parallel in the first stage is 2 (executed by parallel algorithm 1 and parallel algorithm 2), and the sum of the first threshold and the second threshold is less than or equal to 50; finally, the vehicle depot planning model is quantitatively solved by using the improved tabu search algorithm to obtain the vehicle depot site selection information and the number of vehicle depots. The iteration results of the improved tabu search algorithm are shown in Table 1. Figure 4 Figure 4 It can be seen that the "parallel competition" proposed in the embodiment of the present application to some extent makes up for the defect that the result of the tabu search algorithm is highly dependent on the initial value. With the increase of the iteration number of the algorithm, the reduction amplitude of the objective function value is smaller and smaller, but it will not stay at a certain value for too long. This is because the setting of the tabu list and the "self-adaptive" improvement proposed in the present application make the algorithm not only unable to jump out of the local optimal solution, but also can realize the "refinement" of the gradual approximation to the optimal solution. The total iteration number of the algorithm is 28, which indicates that the search efficiency of the improved tabu search algorithm proposed in the embodiment of the present application is high, and the optimal solution can be found in an effective time and the algorithm is terminated.

[0186] The vehicle depot planning scheme of the specific embodiment of the present application is shown in Table 2. Among them, the number of vehicle depots is 5, and the sites are located near stations S8, S21, S27, S56 and S64. Except for station S27, the remaining stations are all starting stations and route end point stations (i.e. terminal stations). This means that part of the trains can directly drive from the vehicle depot to the starting station before operation, and directly return to the vehicle depot from the terminal station after operation without passing through other stations, so the empty running of this part of the trains only occurs in the vehicle depot access line part. Station S27 is a transfer station of line 2 and line 4, and the vehicle depot site located here can facilitate the train to undertake the passenger transport task of the two lines, and keep the empty running mileage at a low level.

[0187] Table 2

[0188] ​

[0189] The algorithm solves the problem and obtains the annual idle mileage and cost of the target urban rail network, which are 2.0313 million km and 154.402 million yuan, respectively. Furthermore, the vehicle base investment cost of the target urban rail network is also calculated. The vehicle base investment cost accounts for 53.22% of the target urban rail network, while the idle mileage cost accounts for 46.78%. The annual idle mileage cost is also divided into six components based on different operating phases. The idle mileage cost during the concentrated departure phase before operations accounts for 18.26% of the idle mileage cost; the idle mileage cost during the pre-peak rush hour addition phase accounts for 1.08% of the idle mileage cost; the idle mileage cost during the pre-peak rush hour addition phase accounts for 0.71% of the idle mileage cost; the idle mileage cost during the post-peak rush hour return phase accounts for 6.72% of the idle mileage cost; the idle mileage cost during the post-peak rush hour return phase accounts for 12.85% of the idle mileage cost; and the idle mileage cost during the concentrated return phase after operations accounts for 7.17% of the idle mileage cost.

[0190] In summary, the above steps S101-S105 of the embodiment of the present application divide the train operation phases according to the operation organization information of the target city rail network, and then construct a vehicle base planning model for the target city rail network. The objective function of the vehicle base planning model is constructed with the goal of minimizing the sum of the train empty mileage cost of the target city rail network and the vehicle base investment cost of the target city rail network. The constraints of the vehicle base planning model are set based on the operation organization information and the train travel path, number of train departures, number of train returns, departure capacity, connection plan and return capacity in each train operation phase. Then, the vehicle base planning model is solved according to the objective function and the constraints to obtain the vehicle base planning scheme for the target city rail network, thereby realizing comprehensive and accurate planning and optimization of the vehicle base site selection information and the number of vehicle bases. At the same time, since the train operation phases are divided in combination with the operation organization information, the obtained vehicle base planning scheme is more in line with reality, improves the rationality of the vehicle base planning, reduces the operation cost of the urban rail network, improves the operation efficiency of the urban rail network, and improves the resource utilization rate of the vehicle base construction.

[0191] Figure 5 FIG. 1 shows a structural block diagram of a vehicle base planning device according to an embodiment of the present application. Figure 5 As shown, the device may include:

[0192] The running phase division module 501 is configured to obtain a train running phase according to preset operation organization information of the target urban rail line network, the train running phase including a pre-operation concentrated departure phase, a during-operation dispersed departure phase, a during-operation dispersed return phase, and a post-operation concentrated return phase, and the target urban rail line network being provided with a plurality of stations;

[0193] The modeling module 502 is configured to construct a vehicle depot planning model of the target urban rail line network.

[0194] The objective function construction module 503 is configured to construct an objective function of the vehicle depot planning model with a target of minimizing a sum of a train empty mileage cost and a vehicle depot investment cost of the target urban rail line network, the train empty mileage cost being equal to a product of a train mileage and a preset unit mileage empty cost, the train mileage being calculated according to the to-be-determined vehicle depot site selection information, the operation organization information, and the stations of the target urban rail line network, and the vehicle depot investment cost being equal to a product of a preset single vehicle depot investment cost and a to-be-determined vehicle depot quantity.

[0195] The constraint condition setting module 504 is configured to set a constraint condition of the vehicle depot planning model, the constraint condition including a continuity constraint of a train travel path in the target urban rail line network, a uniqueness constraint of the train travel path in the target urban rail line network, a train quantity constraint of a train traveling from the vehicle depot to a starting station of the target urban rail line network in the pre-operation concentrated departure phase, a train quantity constraint of a train departing from the vehicle depot in the during-operation dispersed departure phase, a train quantity constraint of a train returning to the vehicle depot in the during-operation dispersed return phase and the post-operation concentrated return phase, a constraint that a train quantity departing from the vehicle depot in each train running phase is equal to a train quantity returning to the vehicle depot in each train running phase, a vehicle depot departure quantity constraint, a vehicle depot departure capacity constraint, a turn-back capacity constraint of a turn-back station of the target urban rail line network, a vehicle depot track connection scheme constraint, a station constraint of a train arriving at a station from the vehicle depot in the during-operation dispersed departure phase, and a vehicle depot quantity constraint.

[0196] The model solving module 505 is configured to solve the vehicle depot planning model according to the objective function and the constraint condition, to obtain a vehicle depot planning scheme of the target urban rail line network, the vehicle depot planning scheme including the vehicle depot site selection information and the vehicle depot quantity.

[0197] The functions of each module in each device in the embodiments of the present application can be referred to the corresponding description in the above method, which will not be repeated here.

[0198] Figure 6 A structure block diagram of a vehicle depot planning device according to an embodiment of the present application is shown. As shown in FIG. 5, the vehicle depot planning device includes a running phase division module 501, a modeling module 502, an objective function construction module 503, a constraint condition setting module 504, and a model solving module 505. Figure 6As shown, the vehicle base planning device includes a memory 610 and a processor 620, and the memory 610 stores a computer program executable on the processor 620. The processor 620 implements the vehicle base planning method in the above embodiment when executing the computer program. The number of the memory 610 and the processor 620 can be one or more.

[0199] The vehicle base planning device further includes:

[0200] A communication interface 630 is configured to communicate with external devices and transmit data.

[0201] If the memory 610, the processor 620 and the communication interface 630 are implemented independently, the memory 610, the processor 620 and the communication interface 630 can be connected to each other through a bus and complete communication therebetween. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus.

[0202] Optionally, in a specific implementation, if the memory 610, the processor 620 and the communication interface 630 are integrated on a chip, the memory 610, the processor 620 and the communication interface 630 can complete communication therebetween through an internal interface.

[0203] The embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the method provided in the embodiment of the present application.

[0204] The embodiment of the present application further provides a chip, which includes a processor, is configured to call and execute instructions stored in a memory, and makes a communication device installed with the chip execute the method provided in the embodiment of the present application.

[0205] The embodiment of the present application further provides a chip, which includes an input interface, an output interface, a processor and a memory, and the input interface, the output interface, the processor and the memory are connected through an internal connection path. The processor is configured to execute code in the memory, and when the code is executed, the processor is configured to execute the method provided in the embodiment of the present application.

[0206] It is to be understood that the above-described processor can be a central processing unit (CPU), but can also be other general purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general purpose processor can be a microprocessor or any conventional processor, etc. It is to be noted that the processor can be an advanced RISC machine (ARM) architecture processor.

[0207] Further, the memory described above can include a read-only memory and a random access memory, and can also include a non-volatile random access memory. The memory can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. The non-volatile memory can include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can include a random access memory (RAM) used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static random access memory (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM) can be used.

[0208] In the above-described embodiments, all or part can be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded on a computer, all or part generates the flow or function according to the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium.

[0209] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. Also, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction.

[0210] In addition, the terms "first", "second", etc. are used only for the purpose of description and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly specified.

[0211] Any process or method descriptions or descriptions in flow charts or otherwise described herein can be understood as representing code modules, segments, or portions of code that include one or more executable instructions for implementing specific logic functions or steps in the process. And the scope of the preferred embodiments of the present application includes additional implementation in which the functions can be performed in different order, including substantially concurrently or in reverse order, according to the functions involved.

[0212] The logic and / or steps represented in the flow chart or otherwise described herein, for example, can be considered as a list of executable instructions for implementing the logic function, which can be specifically implemented in any computer-readable medium for instruction execution system, device or equipment, such as computer-based system, system including processor or other system that can take instructions from instruction execution system, device or equipment and execute instructions, or in conjunction with these instructions execution system, device or equipment.

[0213] It should be understood that each part of the present application can be realized by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be realized by software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above-mentioned embodiment methods can be completed by a program instructing the relevant hardware, which can be stored in a computer readable storage medium and includes one or a combination of the steps of the embodiment methods when executed.

[0214] In addition, each functional unit in each embodiment of the present application can be integrated in one processing module, or each unit can be physically present separately, or two or more units can be integrated in one module. The above-mentioned integrated module can be realized in the form of hardware or in the form of a software functional module. The above-mentioned integrated module, if realized in the form of a software functional module and sold or used as an independent product, can also be stored in a computer readable storage medium. The storage medium can be a read-only memory, a magnetic disk or an optical disk, etc.

[0215] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of various changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A vehicle base planning method characterized by comprising: The method comprises the following steps: obtaining a train operation stage according to preset operation organization information of a target urban rail line network, wherein the train operation stage comprises a pre-operation centralized departure stage, a during-operation dispersed departure stage, a during-operation dispersed return stage and a post-operation centralized return stage, and the target urban rail line network is provided with a plurality of stations; constructing a vehicle depot planning model of the target urban rail line network; constructing an objective function of the vehicle depot planning model with the objective of minimizing the sum of a train empty mileage cost and a vehicle depot investment cost of the target urban rail line network; setting a constraint condition of the vehicle depot planning model; solving the vehicle depot planning model according to the objective function and the constraint condition to obtain a vehicle depot planning scheme of the target urban rail line network, wherein the vehicle depot planning scheme comprises vehicle depot site selection information and a vehicle depot quantity; the step of constructing the vehicle depot planning model of the target urban rail line network comprises: constructing a mixed integer linear programming model as the vehicle depot planning model; the constraint condition comprises a continuity constraint of a train driving path in the target urban rail line network, a uniqueness constraint of the train driving path in the target urban rail line network, a train quantity constraint of a train driving from a vehicle depot to a starting station of the target urban rail line network in the pre-operation centralized departure stage, a train quantity constraint of a train departing from the vehicle depot in the during-operation dispersed departure stage, a train quantity constraint of a train returning to the vehicle depot in the during-operation dispersed return stage and the post-operation centralized return stage, a constraint that a train quantity departing from the vehicle depot in each train operation stage is equal to a train quantity returning to the vehicle depot in each train operation stage, a vehicle depot departure quantity constraint, a vehicle depot departure capacity constraint, a turn-back capacity constraint of a turn-back station of the target urban rail line network, a vehicle depot track connection scheme constraint, a station constraint of a train arriving at a station from the vehicle depot in the during-operation dispersed departure stage, and a vehicle depot quantity constraint.

2. The vehicle base planning method according to claim 1, characterized by, the step of solving the vehicle depot planning model according to the objective function and the constraint condition to obtain the vehicle depot planning scheme of the target urban rail line network comprises: solving the vehicle depot planning model by using a tabu search algorithm according to the objective function and the constraint condition to obtain the vehicle depot planning scheme of the target urban rail line network.

3. The vehicle base planning method according to claim 1, characterized by, the train empty mileage cost is equal to a product of a train driving mileage and a preset unit mileage empty cost, the train driving mileage is calculated according to the vehicle depot site selection information to be determined, the operation organization information and the stations of the target urban rail line network, and the vehicle depot investment cost is equal to a product of a preset single vehicle depot investment cost and the vehicle depot quantity to be determined.

4. The vehicle base planning method according to claim 1, characterized by, the step of solving the vehicle depot planning model according to the objective function and the constraint condition to obtain the vehicle depot planning scheme of the target urban rail line network comprises: Solving the vehicle depot planning model according to the objective function and the constraint condition by using a preset improved tabu search algorithm to obtain a vehicle depot planning scheme of the target urban rail line network.

5. The vehicle base planning method according to claim 4, characterized by, The solving the vehicle depot planning model according to the objective function and the constraint condition by using a preset improved tabu search algorithm to obtain a vehicle depot planning scheme of the target urban rail line network includes: determining a plurality of tabu search tasks of the vehicle depot planning model; solving each of the tabu search tasks in parallel by using a tabu search algorithm and outputting a plurality of solving results; screening the solving results according to the objective function and the constraint condition to obtain a target initial solution; initializing a first iteration number as 0; taking the target initial solution as a current solution; generating an empty first tabu table and storing the current solution in the first tabu table; incrementing the first iteration number by 1 and obtaining a plurality of candidate solutions according to the current solution, a preset transformation rule and a preset random operator; screening the candidate solutions according to the objective function and the constraint condition to obtain an optimal candidate solution; if the optimal candidate solution meets a contempt criterion, taking the optimal candidate solution as the current solution, replacing an earliest-stored solution in the first tabu table with the current solution and judging whether the first iteration number is greater than or equal to a preset second threshold value, if yes, outputting the current solution as the vehicle depot planning scheme, and if no, returning to the step of incrementing the first iteration number by 1 and obtaining a plurality of candidate solutions according to the current solution and the preset random operator; if the optimal candidate solution does not meet the contempt criterion, taking a non-tabu optimal candidate solution as the current solution, replacing an earliest-stored solution in the first tabu table with the current solution and judging whether the first iteration number is greater than or equal to the second threshold value, if yes, outputting the current solution as the vehicle depot planning scheme, and if no, returning to the step of incrementing the first iteration number by 1 and obtaining a plurality of candidate solutions according to the current solution and the preset random operator.

6. The vehicle base planning method according to claim 5, characterized by, The solving each of the tabu search tasks in parallel by using a tabu search algorithm and outputting a plurality of solving results includes: initializing a second iteration number as 0; generating an initial solution corresponding to each of the tabu search tasks and an empty second tabu table corresponding to each of the tabu search tasks; taking each of the initial solutions as a current solution of each of the tabu search tasks and storing each of the current solutions in the corresponding second tabu table; incrementing the second iteration number by 1, obtaining a plurality of candidate solution sets according to the current solutions and the transformation rule, each of the candidate solution sets including a plurality of candidate solutions; screening the candidate solutions in each of the candidate solution sets according to the objective function and the constraint condition to obtain an optimal candidate solution of each of the tabu search tasks; If the optimal candidate solution satisfies the contempt criterion, the optimal candidate solution is taken as the current solution, the earliest solution stored in the tabu list is replaced by the current solution, and it is determined whether the second iteration number is greater than or equal to a preset first threshold value; if yes, the current solution is output as the solving result; if no, the second iteration number is increased by 1, and the step of obtaining a plurality of candidate solution sets according to the current solution and a preset transformation rule is returned; If the optimal candidate solution does not satisfy the contempt criterion, the optimal candidate solution that is not tabu is taken as the current solution, the earliest solution stored in the tabu list is replaced by the current solution, and it is determined whether the second iteration number is greater than or equal to the first threshold value; if yes, the current solution is output as the solving result; if no, the second iteration number is increased by 1, and the step of obtaining a plurality of candidate solution sets according to the current solution and a preset transformation rule is returned.

7. A vehicle base planning device characterized by comprising: Comprise: A running phase division module is configured to obtain train running phases according to preset operation organization information of a target urban rail line network, wherein the train running phases comprise a pre-operation concentrated departure phase, a during-operation scattered departure phase, a during-operation scattered return phase, and a post-operation concentrated return phase; and the target urban rail line network is provided with a plurality of stations. A modeling module is configured to construct a vehicle depot planning model of the target urban rail line network. A target function construction module is configured to construct a target function of the vehicle depot planning model, with a target of minimizing a sum of a train empty mileage cost and a vehicle depot investment cost of the target urban rail line network; the train empty mileage cost is equal to a product of a train mileage and a preset unit mileage empty cost; the train mileage is calculated according to vehicle depot site selection information to be determined, the operation organization information, and the stations of the target urban rail line network; and the vehicle depot investment cost is equal to a product of a preset single vehicle depot investment cost and a vehicle depot quantity to be determined. A constraint condition setting module is configured to set constraint conditions of the vehicle depot planning model, wherein the constraint conditions comprise a continuity constraint of a train travel path in the target urban rail line network, a uniqueness constraint of the train travel path in the target urban rail line network, a train quantity constraint from a vehicle depot to a starting station of the target urban rail line network in the pre-operation concentrated departure phase, a train quantity constraint from the vehicle depot in the during-operation scattered departure phase, a train quantity constraint returning to the vehicle depot in the during-operation scattered return phase and the post-operation concentrated return phase, a constraint that a train quantity from the vehicle depot in each train running phase is equal to a train quantity returning to the vehicle depot in each train running phase, a vehicle depot departure quantity constraint, a vehicle depot departure capacity constraint, a turn-back capacity constraint of a turn-back station of the target urban rail line network, a vehicle depot track connection scheme constraint, a station constraint arrived at by a train from the vehicle depot in the during-operation scattered departure phase, and a vehicle depot quantity constraint. A model solving module is configured to solve the vehicle depot planning model according to the objective function and the constraint condition, and obtain a vehicle depot planning scheme of the target urban rail line network, the vehicle depot planning scheme including the vehicle depot site selection information and the number of vehicle depots.

8. A vehicle base planning device characterized by comprising: Comprise: A processor and a memory, the memory storing instructions which are loaded and executed by the processor to implement the vehicle depot planning method according to any one of claims 1-6. 9.A computer readable storage medium, the computer readable storage medium storing a computer program, the computer program being executed by a processor to implement the vehicle depot planning method according to any one of claims 1-6.

Images