Construction method, scheduling method, system and storage medium of single-track scheduling model

Abstract

The present application provides a method for constructing a monorail scheduling model, a scheduling method, a system and a storage medium, and belongs to the technical field of rail transit. The method for constructing the monorail scheduling model includes: constructing an objective function, the objective function is used to minimize the delay time of all trains running on the double track to arrive at the terminal station; constructing a scheduling judgment constraint condition, which is used to detect whether any train is a train object for monorail scheduling; constructing a safe driving constraint condition, which is used to make the operation of any train meet the target safety condition; based on the objective function, the scheduling judgment constraint condition and the safe driving constraint condition, a monorail scheduling model is constructed, and the monorail scheduling model is used to determine the target departure time of each train at the stations at both ends of the faulty line segment when there is a faulty line segment in the line segment of the double track. The present application aims to reduce train delays on double-track railways when a single track fails.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of rail transit, and in particular, to a method for constructing a single-track scheduling model, a scheduling method, a system, and a storage medium. Background Art

[0002] There are a large number of uncertainties in the operation of trains, which can easily cause trains to deviate from the original schedule. For example, uncertainties include natural disasters, abnormal weather, emergencies, equipment failures, operation delays and human factors. Uncertainties have spatial randomness, temporal randomness and duration randomness, which pose a hidden danger to high-speed railways traveling within a given time and space. Therefore, in abnormal circumstances, the normal operation of high-speed railways is disturbed or blocked. In order to deal with abnormalities in a timely manner and reduce losses in the railway system, it is very necessary to design a fast and efficient real-time rescheduling method for high-speed railways.

[0003] Current railway tracks generally include double tracks, that is, each line generally has two parallel tracks for the upward and downward directions. When a single track fails in the line section between two stations, for example, when the upward track of a certain line section fails, the train that needs to go up at the previous station on the line will be in a waiting state for a long time until the track failure is restored. However, the fault recovery process takes a long time from detecting the fault point to repairing, which will not only cause delays for the train that needs to go up at the previous station, but may even cause delays for trains on the entire upward line. Summary of the invention

[0004] The embodiments of the present application provide a method for constructing a single-track scheduling model, a scheduling method, a system and a storage medium, which are intended to reduce train delays on a double-track railway when a single track fails.

[0005] In a first aspect, an embodiment of the present application provides a method for constructing a single-track scheduling model, the method comprising:

[0006] Constructing an objective function, the objective function is used to minimize the delay time of all trains running on the double tracks arriving at the terminal station;

[0007] Constructing a scheduling judgment constraint condition, wherein the scheduling judgment constraint condition is used to detect whether any train is a train object for single-track scheduling;

[0008] Constructing safe driving constraint conditions, wherein the safe driving constraint conditions are used to ensure that the operation of any train meets target safety conditions;

[0009] Based on the objective function, the scheduling judgment constraint condition and the safe driving constraint condition, the single-track scheduling model is constructed. The single-track scheduling model is used to determine the target departure time of each train at the stations at both ends of the faulty line segment to run on another line segment where the fault does not occur when there is a faulty line segment in the double-track line segment.

[0010] Optionally, the formula of the objective function is:

[0011]

[0012] Among them, a in is the arrival time of train i in the upward direction at the terminal n; is the original arrival time of train i in the upward direction at the terminal n; a i1 is the arrival time of train i in the down direction at the terminal; is the original arrival time of train i in the down direction at the terminal station; O is the set of down trains; I is the set of up trains.

[0013] Optionally, constructing scheduling judgment constraint conditions includes:

[0014] Constructing a fault scheduling causal constraint condition, wherein the fault scheduling causal constraint condition is used for single track scheduling after a fault occurs;

[0015] A fault dispatch judgment constraint condition is constructed, wherein the fault dispatch judgment constraint condition is used to determine whether to perform single-track dispatch on any train.

[0016] Optionally, constructing safe driving constraints includes:

[0017] Constructing a safety distance constraint condition, wherein the safety distance constraint condition is used to satisfy a safety distance condition between two adjacent trains in an upward direction or a downward direction;

[0018] Constructing a stop time constraint condition, wherein the stop time constraint condition is used to satisfy the planned stop time of any train at each station;

[0019] Constructing a travel speed constraint condition, wherein the travel speed constraint condition is used to satisfy a safe speed condition of any train on a line segment;

[0020] Constructing an arrival time constraint condition, wherein the arrival time constraint condition is used to restrict any train to arrive at any station no earlier than the originally scheduled arrival time at the station;

[0021] Constructing anti-collision constraints, the anti-collision constraints are used to satisfy the requirement that when each train at the stations at both ends of the faulty line segment runs on another line segment where the fault has not occurred, only trains in the upward or downward direction run on the line segment where the fault has not occurred.

[0022] In a second aspect, an embodiment of the present application provides a double-track railway fault dispatching method, the method comprising:

[0023] Obtaining the faulty line section on the target double track, the fault time corresponding to the faulty line section, and the original arrival time of each train corresponding to the stations at both ends of the faulty line section;

[0024] Inputting the faulty line segment, the fault time corresponding to the faulty line segment, and the original arrival time of each train corresponding to the stations at both ends of the faulty line segment into a monorail scheduling model, wherein the monorail scheduling model is constructed based on the method for constructing the monorail scheduling model described in the first aspect of the embodiment;

[0025] Solving the single-track scheduling model based on a heuristic solution algorithm to obtain the target departure time corresponding to each train at the stations at both ends of the faulty line segment;

[0026] According to the target departure time corresponding to each train at the stations at both ends of the faulty line segment, each train is allowed to run on the normal single track corresponding to the faulty line segment according to the target departure time corresponding to each train.

[0027] Optionally, the single-track scheduling model is solved based on a heuristic solution algorithm to obtain the target departure time corresponding to each train at the stations at both ends of the faulty line segment, including:

[0028] Based on the first scheduling algorithm, determining an initial batch configuration of the single-track scheduling model;

[0029] Based on the neighborhood search algorithm and the simulated annealing algorithm, the initial batch configuration of the single-track scheduling model is optimized and adjusted to obtain the final batch configuration of the single-track scheduling model;

[0030] A target departure schedule is determined according to the final batch configuration, wherein the target departure schedule includes the target departure time corresponding to each train at the stations at both ends of the faulty line segment.

[0031] Optionally, based on the first scheduling algorithm, determining the initial batch configuration of the single-track scheduling model includes:

[0032] The first scheduling algorithm determines the initial batch configuration corresponding to each train in the upward and downward directions during monorail operation according to the original arrival time of each train corresponding to the stations at both ends of the faulty line segment and according to preset rules, wherein the preset rules include the preset batch number and the number of trains in each batch.

[0033] Optionally, based on a neighborhood search algorithm and a simulated annealing algorithm, the initial batch configuration of the single-track scheduling model is optimized and adjusted to obtain a final batch configuration of the single-track scheduling model, including:

[0034] When the current temperature in the simulated annealing algorithm is greater than the minimum temperature threshold and the number of iterations is less than the iteration threshold, the number of batches in the initial batch configuration and the number of trains in each batch are adjusted based on the neighborhood search algorithm to obtain an optimized batch configuration, and the current temperature is reduced, and the number of iterations is increased by 1;

[0035] Until the current temperature is equal to the minimum temperature threshold, or the number of iterations is equal to the iteration threshold, the currently optimized batch configuration is used as the final batch configuration of the single-track scheduling model.

[0036] In a third aspect, an embodiment of the present application provides a double-track railway fault dispatching system, the system comprising:

[0037] An acquisition module, used to acquire a faulty line section on a target double track, a fault time corresponding to the faulty line section, and the original arrival time of each train corresponding to the stations at both ends of the faulty line section;

[0038] An input module, used to input the faulty line segment, the fault time corresponding to the faulty line segment, and the original arrival time of each train corresponding to the stations at both ends of the faulty line segment into a monorail scheduling model, wherein the monorail scheduling model is constructed based on the method for constructing the monorail scheduling model described in the first aspect of the embodiment;

[0039] A solution module, used for solving the single-track scheduling model based on a heuristic solution algorithm to obtain the target departure time corresponding to each train at the stations at both ends of the faulty line segment;

[0040] The scheduling module is used to make each train run on the normal single track corresponding to the faulty line section according to the target departure time corresponding to each train at the stations at both ends of the faulty line section.

[0041] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the double-track railway fault scheduling method as described in the second aspect of the embodiment is implemented.

[0042] Beneficial effects:

[0043] The single-track scheduling model constructed by this method is used to minimize the objective function of the delay time of all trains running on the double track to the terminal station. The constructed scheduling judgment constraint conditions are used to detect whether any train is a train object for single-track scheduling; the constructed safe driving constraint conditions can determine that the operation of any train meets the target safety conditions; the single-track scheduling model can determine the target departure time of each train at the stations at both ends of the faulty line segment when there is a faulty line segment in the double-track line segment.

[0044] Therefore, when a single track fault occurs in a certain line section of a double-track railway, the trains at the stations at both ends of the faulty line section can continue to run based on the other line section where the fault has not occurred, reducing the overall delay of trains running on the double tracks caused by long waiting times for trains in the direction of the faulty line section. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] Figure 1 It is a flowchart of the steps of a method for constructing a single-track scheduling model proposed in an embodiment of the present application;

[0047] Figure 2 is a flowchart of the steps of a double-track railway fault dispatching method proposed in one embodiment of the present application;

[0048] Figure 3 It is a functional module diagram of a double-track railway fault dispatching system provided by an embodiment of the present application;

[0049] Figure 4 It is a schematic diagram of a computer-readable storage medium proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] The rescheduling problem is generally understood as a job-shop scheduling problem and is proven to be an NP-complete mixed integer programming problem. The problem scenarios mainly include practical needs such as delay recovery, conflict detection and resolution, and the solution objects include but are not limited to: (i) minimizing the number of delayed trains; (ii) minimizing the total passenger delay time; (iii) minimizing operating costs; (iv) minimizing the total delay time; and (v) minimizing the total travel time.

[0052] At present, the research on train operation plan adjustment can be roughly divided into three categories: operations research methods for precise modeling and solving, a variety of machine learning methods, and simulation methods close to real systems. Common operations research models are mathematical models such as mixed integer programming; artificial intelligence machine learning, heuristic algorithms and other methods, combined with artificially specified single-line faults, station paralysis and other interference response strategies, can realize non-precise search for adjustment plans.

[0053] At present, train scheduling problems are generally divided into two categories: precision priority and efficiency priority; precision priority refers to establishing a strict optimization model for a certain optimization goal, such as minimizing total error, minimizing passenger waiting time, minimizing energy consumption, etc.; the precision priority method usually establishes the rescheduling scenario as a mixed integer programming model, and applies operations research solution methods, such as column generation, branch and bound method, etc., or directly applies LINGO, CPLEX, GAMS and other optimization software to solve; compared with the precision priority method, the efficiency priority method sacrifices accuracy for calculation speed. In practical applications, rescheduling in response to interference requires shorter computing time; in order to speed up the solution, a certain degree of accuracy needs to be sacrificed. Related non-exact solution algorithms include simulation, deep learning simulation expert system, simulated annealing algorithm and genetic algorithm.

[0054] However, there is no research on the scheduling problem of two-way traffic on a single track of a double-track railway. In a double-track railway, the track is divided into two directions: inbound and outbound. There are multiple stations unevenly distributed on the line of the double-track railway. The line between each station is called a line segment. The train can only choose the up or down track at will when leaving the station, and cannot change tracks again when running on a line segment.

[0055] If a single track fault occurs on a certain line section, such as a fault on the up track and a normal down track, or a fault on the up track and a normal down track, trains in the direction of the single track fault at stations on both sides of the faulty line section will have to wait until the faulty line section is restored. However, the fault recovery process takes a long time from detecting the fault point to repairing it, which will not only cause delays in the train that needs to go up at the previous station, but may even cause delays in trains on the entire up line.

[0056] Based on this, this embodiment provides a method for constructing a single-track scheduling model and a double-track railway fault scheduling method, which can reduce train delays on double-track railways when a single-track fault occurs. A single-track fault may occur on a certain line segment. For example, if the up track fails and the down track is normal, the trains at the stations at both ends of the line segment can travel in both directions based on the normal down track single track within the fault occurrence time; or if the up track is normal and the down track fails, the trains at the stations at both ends of the line segment can travel in both directions based on the normal up track single track within the fault occurrence time.

[0057] In the scenario of single-track two-way traffic scheduling on a double-track railway where this method is applied, the train capacity of the station is large enough, and there is a fixed loss time for trains to enter and exit the station; a safe distance needs to be maintained between trains on the line section, and there is a fixed loss time for trains to enter and exit the station, and the single-track two-way traffic scheduling only affects the passing trains after the fault occurs, and has no effect on the trains that are running on the track when the fault occurs.

[0058] In the method for constructing a single-rail scheduling model provided in this embodiment, the single-rail scheduling model is a mixed integer programming mathematical model, and the parameters of the single-rail scheduling model include:

[0059] t s : The time when a single track failure occurs in any line section; t r : Fault recovery time for a single-track fault in any line section; I: Upward train set; O: Downward train set; m: Number of line sections of a double-track railway; l k : the length of the kth line segment; h 0 : The driving time corresponding to the minimum vehicle distance; M: A sufficiently large number; The planned duration of train i's stop at station k; The original arrival time of train i at station k in the original timetable; The original departure time of train i at station k in the original timetable; E: line segment set; K: station set; W: faulty line segment.

[0060] The decision variables of the single-track scheduling model include:

[0061] a ik : The arrival time of train i at station k; d ik : departure time of train i at station k; S i : If the value is 0, the train has passed the line section where the fault will occur before the fault occurs, otherwise it is 1; ijk : The value is 1 if the up train i passes the faulty line section k before the down train j, otherwise it is 0.

[0062] In this embodiment, i or j is a train subscript variable. {ij} is used only when the interaction between two trains needs to be represented. i can be used when only one train is represented. That is, in the formula for distinguishing an up train from a down train, i usually represents an up train and j usually represents a down train. However, in order to avoid formula redundancy, in some formulas, i represents both an up train and a down train, such as the train arrival time a. ik It represents the arrival time of all up and down vehicles at each station. Please make judgments based on the value range in the formula during actual implementation.

[0063] Reference Figure 1 , shows a flowchart of the steps of a method for constructing a single-track scheduling model in an embodiment of the present application, and the method may specifically include the following steps:

[0064] S101: Construct an objective function, wherein the objective function is used to minimize the delay time of all trains running on the double tracks arriving at the terminal station.

[0065] In the scenario of scheduling of two-way traffic on a single track of a double-track railway, the goal is to restore the train schedule to a state where no failure occurs. Therefore, the objective function of the single-track scheduling model of this embodiment is mainly to minimize the delay time of all trains running on the double track arriving at the terminal.

[0066] In a feasible implementation manner, the difference between the arrival time of all trains at the terminal station and the arrival time at the terminal station in the original schedule is calculated, that is, the train delay time.

[0067] For example, the objective function is formulated as follows:

[0068]

[0069] Among them, a in is the arrival time of train i in the upward direction at the terminal n; is the original arrival time of train i in the upward direction at the terminal n; a i1 is the arrival time of train i in the down direction at the terminal; is the original arrival time of train i in the down direction at the terminal station; O is the set of down trains; I is the set of up trains.

[0070] Solving the single-track scheduling model is to minimize the objective function.

[0071] S102: Constructing scheduling judgment constraint conditions to detect whether any train is a train object for single-track scheduling.

[0072] When dispatching a single track, the first thing to do is to dispatch the trains after the fault occurs, and to determine whether any train faces the problem of two-way traffic on the single track in the faulty line section.

[0073] Therefore, in a feasible implementation, constructing the scheduling judgment constraint condition may include:

[0074] A1: Construct a fault scheduling causal constraint condition, which is used to perform single-track scheduling after a fault occurs. For example, the formula of the fault scheduling causal constraint condition is:

[0075]

[0076]

[0077] That is, if: the original arrival time of train i at station k in the original schedule is and the original departure time of train i at station k If the fault time of the faulty line section k is smaller or earlier than that of the faulty line section k, then train i will continue to operate according to the original schedule. S Subsequent trains will be dispatched on single track.

[0078] A2: Construct fault dispatch judgment constraints, which are used to determine whether to perform single-track dispatch on any train. That is, considering that not all trains will be affected by the faulty line section, in the problem scenario on which this method is based, it can be considered that the train capacity of the station is large enough.

[0079] Assuming that the faulty line section is the monorail in either direction of the 4th line section between station 4 and station 5, line section 1 between station 1 and station 2, line section 2 between station 2 and station 3, and line section 3 between station 3 and station 4 are still normal, and the up and down trains running between station 1, station 2, station 3 and station 3 still run according to the original schedule, without having to face the problem of bidirectional operation of the monorail on the faulty line section 4.

[0080] In the actual implementation process, if the station capacity is limited, a constraint condition on the number of trains that a station can accommodate can be set to limit the maximum number of trains that each station can accommodate. It is also possible to fine-tune the timetable of each train on the entire double-track railway line after a fault occurs. This embodiment does not impose any restrictions.

[0081] The decision variables S in the single-track scheduling model i Indicates whether the faulty line segment k has been restored to normal when train i arrives at station k before the faulty line segment k. i When S is 1, it means that the fault of the faulty line section k has been restored, and train i does not need to face the problem of avoiding conflict with the oncoming train in the two-way traffic of the single track; iA value of 0 indicates that the fault of the faulty line segment k has not been restored. When train i departs from station k before the faulty line segment k, it faces the problem of two-way traffic on a single track. At this time, for the sake of operational safety, it is necessary to consider avoiding collisions with oncoming trains.

[0082] In short, the S variable is used to check whether the train faces a single-track two-way traffic condition based on whether the departure time of the train from the station before the faulty line section is greater than the time point of fault recovery. This embodiment also proposes a T variable, which is used to check whether the train faces a single-track two-way traffic condition at the time point of the fault. Based on the values ​​of the S variable and the T variable of a train, it can be determined whether a train needs to perform avoidance processing.

[0083] Based on this, the fault dispatch judgment constraint conditions may include line segment restoration time constraint and line segment fault time constraint, specifically:

[0084] The line segment recovery time constraint (i.e., S variable) is 1 if the train arrives at the faulty line segment after the fault is restored; otherwise, it is 0. The formula for the line segment recovery time constraint is:

[0085]

[0086]

[0087]

[0088]

[0089] Where, d i，k is the departure time of train i at station k; d j，k+1 is the departure time of train i at station k+1.

[0090] The line segment failure time constraint (i.e., T variable) is 1 if the train arrives at the line segment that is about to fail before the line segment fails; otherwise, it is 0. The formula for the line segment failure time constraint is:

[0091]

[0092]

[0093]

[0094]

[0095] S103: Construct safe driving constraint conditions to ensure that the operation of any train meets the target safety conditions.

[0096] When scheduling two-way traffic on a single track, safe driving remains the most important basic principle.

[0097] In a feasible implementation, constructing safe driving constraint conditions may include the following steps:

[0098] B1: Constructing a safety distance constraint condition, where the safety distance constraint condition is used to satisfy a safety distance condition between two adjacent trains in an upward direction or a downward direction.

[0099] Whether the train is running on the track or arriving and departing at the station, there should be an appropriate safety interval between the departure and arrival times of two adjacent trains. 0 ; Because the train is assumed to travel at a constant speed on the line section and will not stop halfway, it is only necessary to constrain the minimum interval between the arrival and departure times of the train at the station to a fixed duration.

[0100] The safety distance condition only applies to trains traveling in the same direction. Under normal circumstances, trains in the two directions do not interfere with each other. In the case of single-track parallel operation, the safety distance between opposite trains will be guaranteed by other constraints. Therefore, the safety distance constraint condition can include the upward safety distance constraint condition and the downward safety distance constraint condition.

[0101] For an upward train, the stations it arrives at are from the first station to the last station, and the stations it departs from are from the 0th station to the second to last station. The main way to distinguish upward and downward trains is the train number. In this embodiment, the first n 0 The first train is an ascending train, and the subsequent train is a descending train. When ensuring the safe distance, it is only necessary to ensure the safe interval between the two trains with adjacent serial numbers.

[0102] Specifically, the formula for the uplink safety distance constraint is:

[0103] a i，k +h 0 ≤a i+1，k , i∈{0,...,n 0 -2}, k∈{1,...,m}

[0104] d i，k +h 0 ≤d i+1，k , i∈{0,...,n 0 -2}, k∈{0,...,m-1}

[0105] It is basically the same as the upward direction, but the range of train numbers and stations is slightly different. For upward trains, the stations they arrive at are from the 0th station to the second-to-last station, and the stations they depart from are from the 1st station to the last station.

[0106] Specifically, the formula for the downlink safety distance constraint is:

[0107] a i，k +h 0 ≤a i+1，k , i∈{n 0 , ..., n 0 +n 1 -2}, k∈{0,...,m-1}

[0108] d i，k +h 0 ≤d i+1，k , i∈{n 0 , ..., n 0 +n 1 -2}, k∈{1,...,m}

[0109] B2: Constructing a stop time constraint condition, which is used to satisfy the planned stop time of any train at each station.

[0110] Each train must stay at each station for a certain period of time. This minimum time is consistent with the planned stay time in the original timetable. Consistent.

[0111] Generally, the planned duration of the stop in the original timetable is calculated based on the length of the line section the train has just traveled. This time is used for train maintenance, material replenishment, and passenger transfers. In the new timetable, the stop time cannot be shorter than the planned duration of the stop to ensure the normal operation of the railway system.

[0112] Specifically, the formula for the stop time constraint is:

[0113]

[0114] B3: Constructing a travel speed constraint condition, which is used to satisfy a safe speed condition for any train on a line segment.

[0115] For safe operation, the running speed of the train may also be limited. For example, a maximum running speed V is set, and the average running speed of the train between two stations is less than the maximum running speed.

[0116] After a fault occurs, the train may stay too long after arriving at a station. Therefore, in order to avoid the train staying too long at any station, the train can reduce its speed in the previous line section. This constraint increases the search range of the model.

[0117] Specifically, the formula for the driving speed constraint is:

[0118] a i，k+1 -d i，k ≥l k / V,i∈I,k∈{0,1,...,m}

[0119] a j，k -d j，k+1 ≥l k / V,j∈O,k∈{1,2,...,m+1}

[0120] B4: Construct an arrival time constraint condition, which is used to restrict any train to arrive at any station no earlier than the originally scheduled arrival time at the station.

[0121] Because of the failure, trains in both directions cannot arrive at the terminal earlier than the original schedule. On the other hand, arriving early will cause passengers to miss the train, which is an unreasonable arrangement. Therefore, in this embodiment, the arrival time of the train at each station is not earlier than the original schedule.

[0122] Specifically, the formula for the arrival time constraint is:

[0123]

[0124]

[0125] B5: Constructing anti-collision constraints, which are used to satisfy the requirement that when trains at stations at both ends of the faulty line segment run on another line segment where no fault occurs, only trains in the upward or downward direction run on the line segment where no fault occurs.

[0126] Since up and down trains share one track in a double-track railway with single-track two-way traffic, it is necessary to ensure that trains going in opposite directions do not collide with each other.

[0127] In a feasible implementation, based on the explanation of S variables and T variables, this implementation proposes the concept of single-track space-time. Single-track space-time refers to the space-time where trains pass through the line section from the time when a single-track fault occurs in the faulty line section to the time when the fault is restored. Trains in the single-track space-time must pass the faulty line section by the single track. Therefore, it must be ensured that within the single-track space-time, there can only be trains in one direction on the line section with two-way traffic on the single track, that is, in the faulty line section, only one direction of trains can travel on the monotrack at the same time, so as to avoid collisions between opposite trains when the monotrack is in two-way traffic.

[0128] When the S and T variables of a train i are both 0, it means that it arrives at the stations at both ends of the faulty line segment at the fault time. At this time, it must be ensured that there is no oncoming train on the faulty line segment k. If the oncoming train j passes the faulty line segment k before the train i, then the train j must arrive at the kth station before the train i departs.

[0129] Based on this, the formula for the collision avoidance constraint is:

[0130] a i，k+1 -M.S. i -M.T i -M(1-od ijk )<d j，k+1 , i∈I, j∈O, k∈W

[0131] a j，k -M.S. j -M.T j -Mod ijk <d ik , i∈I, j∈O, k∈W

[0132] Train i leading train j means train j lagging behind train i:

[0133] od ijk +od jik =1, i∈I, j∈O, k∈W

[0134] S104: Based on the objective function, the scheduling judgment constraint condition and the safe driving constraint condition, construct the single-track scheduling model, wherein the single-track scheduling model is used to determine the target departure time of each train at the stations at both ends of the faulty line segment to run on another line segment without fault when there is a faulty line segment in the double-track line segment.

[0135] The single-track scheduling model constructed by the method includes an objective function that can minimize the delay time of all trains running on the double track to arrive at the terminal station. Whether any train is a train object for single-track scheduling can be detected through the constructed scheduling judgment constraint condition; the operation of any train can be determined to meet the target safety condition through the constructed safe driving constraint condition; the single-track scheduling model can determine the target departure time of each train at the stations at both ends of the faulty line segment when there is a faulty line segment in the double-track line segment to run on another line segment where the fault does not occur; therefore, in a double-track railway, if a single-track fault occurs in a line segment, each train at the stations at both ends of the faulty line segment can continue to run based on the other line segment where the fault does not occur, thereby reducing the overall delay of trains running on the double track caused by the long waiting period of trains in the direction where the faulty line segment is located, and realizing scheduling based on single-track two-way traffic.

[0136] Reference Figure 2 , shows a flowchart of the steps of a double-track railway fault dispatching method in an embodiment of the present application, and the method may specifically include the following steps:

[0137] S201: Acquire a faulty line section on a target double track, a fault time corresponding to the faulty line section, and the original arrival times of each train corresponding to stations at both ends of the faulty line section.

[0138] In actual application, it is possible to detect in real time whether a single-track fault exists in the faulty line section on the double track, and obtain the fault time corresponding to the faulty line section. The original arrival time of each train corresponding to the stations at both ends of the faulty line section can be directly obtained from the original timetable.

[0139] S202: Input the faulty line segment, the fault time corresponding to the faulty line segment, and the original arrival time of each train corresponding to the stations at both ends of the faulty line segment into a monorail scheduling model.

[0140] The single-rail scheduling model is constructed based on the single-rail scheduling model construction method described in the embodiment.

[0141] The monorail scheduling model can solve the problem of realizing the passage of up and down trains based on the single track when a single track fault occurs in a double track line section. Therefore, the faulty line section, the fault time corresponding to the faulty line section, and the original arrival time of each train corresponding to the stations at both ends of the faulty line section can be input into the monorail scheduling model. By solving the monorail scheduling model, the target departure time of each train at the stations at both ends of the faulty line section running on another line section where the fault does not occur can be obtained.

[0142] S203: Solving the monorail scheduling model based on a heuristic solution algorithm to obtain the target departure time corresponding to each train at the stations at both ends of the faulty line segment.

[0143] The single-track scheduling model is a mixed integer programming mathematical model, and CPLEX can be used to solve the model directly. However, CPLEX takes too long to solve. When the problem scale is large, the solution time is generally more than 4 hours. In the railway scheduling problem, in order to reduce train delays, the solution efficiency is also very important. In order to improve the solution efficiency, this embodiment solves the single-track scheduling model based on a heuristic solution algorithm.

[0144] In a feasible implementation manner, the monorail scheduling model is solved based on a heuristic solution algorithm to obtain the target departure time corresponding to each train at the stations at both ends of the faulty line segment. First, based on a first scheduling algorithm, an initial batch configuration of the monorail scheduling model is determined; then, based on a neighborhood search algorithm and a simulated annealing algorithm, the initial batch configuration of the monorail scheduling model is optimized and adjusted to obtain a final batch configuration of the monorail scheduling model; finally, a target departure schedule is determined based on the final batch configuration, and the target departure schedule includes the target departure time corresponding to each train at the stations at both ends of the faulty line segment.

[0145] Specifically, based on the first scheduling algorithm, when determining the initial batch configuration of the monorail scheduling model, the first scheduling algorithm determines the initial batch configuration corresponding to each train in the upward and downward directions during the operation of the monorail according to the original arrival time of each train corresponding to the stations at both ends of the faulty line segment and according to preset rules, wherein the preset rules include the preset batch number and the number of trains in each batch.

[0146] This embodiment also provides a first scheduling algorithm. Since the principle of the first scheduling algorithm is similar to that of an elevator, it can be called an "elevator algorithm". The core idea of ​​the elevator algorithm is to imitate the way an elevator carries passengers. During a fault, imagine that the faulty line section is an elevator shaft, and the stations at both ends are elevator entrances on two floors. The elevator has a rated number of passengers, and the monorail can carry a rated number of trains in one direction each time; up and down are alternating. The elevator will be called by the first person to arrive at the elevator entrance, and the direction of the first batch of transportation will be determined. Trains before the fault are not affected, and trains after the fault depart at their earliest departure time according to safety rules. After parameter adjustment testing, for a fixed train starting station departure interval, the elevator quota has an optimal value, and when the first batch of trains depart, the quota needs to be halved because there are not enough waiting trains and the elevator waiting time is long.

[0147] Specifically, the algorithm flow of the first scheduling algorithm is as follows:

[0148] 1. Initialize variables deptime, arrtime, batch, empty lists newdep, arrangement;

[0149] 2. Copy the train schedules not affected by the fault directly to the new schedule newdep;

[0150] 3. The direction first affected by the fault shall be regarded as the primary direction for one-way traffic;

[0151] 4. Batch trains are passed in turns in both directions, and this arrangement is written into the arrangement;

[0152] 5. Update the new timetable newdep according to arrangement;

[0153] 6. Output the new timetable newdep and the initial batch configuration arrangement through the single-track fault line section.

[0154] For example, according to the preset rules, the number of batches in each direction can be stipulated as 6 batches in the upward or downward direction, the number of departures in each batch is 3, and the train in the upward direction is the first to be affected by the fault. Therefore, the initial batch configuration obtained based on the first scheduling algorithm is as follows: in order, upward trains 1, 2, and 3 pass through the faulty line section based on the single track, and then downward trains 1, 2, and 3 pass through the faulty line section based on the single track, and then upward trains 4, 5, and 6 pass through the faulty line section based on the single track, and thus the upward batches and the downward batches are switched.

[0155] The rough rescheduling supported by the first scheduling algorithm needs further optimization. In this embodiment, the neighborhood search algorithm is combined with a simulated annealing algorithm to optimize the initial batch configuration of the first scheduling algorithm, expand the search space, and match or exceed the solver effect.

[0156] Based on the neighborhood search algorithm and the simulated annealing algorithm, the initial batch configuration of the single-track scheduling model is optimized and adjusted to obtain the final batch configuration of the single-track scheduling model, including: when the current temperature in the simulated annealing algorithm is greater than the minimum temperature threshold and the number of iterations is less than the iteration threshold, the number of batches and the number of trains in each batch in the initial batch configuration are adjusted based on the neighborhood search algorithm to obtain the optimized batch configuration, and the current temperature is lowered, and the number of iterations is increased by 1; until the current temperature is equal to the minimum temperature threshold, or the number of iterations is equal to the iteration threshold, the current optimized batch configuration is used as the final batch configuration of the single-track scheduling model.

[0157] Specifically, this embodiment proposes a neighborhood structure based on batch arrangement according to the scheduling idea of ​​the rule algorithm. The core idea is to adjust the existing batch arrangement and then generate the new batch arrangement as a timetable. Since the first scheduling algorithm has generated an initial batch configuration, it is necessary to adjust the batch number and the number of trains in each batch.

[0158] The steps of the neighborhood search algorithm are as follows:

[0159] 1. Input the initial batch configuration arrangement of the first scheduling algorithm;

[0160] 2. Add an empty batch after multiple non-empty batches in arrangement;

[0161] 3. Randomly select an adjustment direction dir (up / down);

[0162] 4. Randomly select a non-empty batch in this direction;

[0163] 5. Randomly select an operation: add / delete;

[0164] 6. Perform the operation on the non-empty batch, where add: add the first train of the following batch to the end of the current batch; delete: add the tail train of the current batch to the head of the next batch;

[0165] 7. Return the optimized batch configuration arrangement.

[0166] Multiple iterations are performed based on the simulated annealing algorithm, and the batch configuration is optimized using a neighborhood search algorithm during each iteration, ultimately obtaining the final batch configuration of the single-track scheduling model.

[0167] The temperature function is the main content of simulated annealing. In one iteration, the temperature function calculates the probability of accepting a new solution based on the current simulation temperature and the difference between the old and new solutions. The simulated annealing algorithm first sets a higher current temperature, which is continuously cooled in the iteration until the current temperature reaches the minimum temperature threshold or the number of iterations reaches the iteration threshold. When the temperature is high, according to the definition of the temperature function, the possibility of accepting a worse solution is greater. Therefore, the temperature cooling mechanism of the simulated annealing algorithm realizes the gradual convergence and stabilization of the current solution. The temperature cooling method is to multiply a hyperparameter. It is found in experiments that if the algorithm searches multiple times at a certain temperature, the objective function decreases faster. Therefore, the temperature cooling is fine-tuned in this embodiment, and cooling is performed every 20 rounds.

[0168] In actual implementation, the settings of the minimum temperature threshold and the iteration threshold can be customized, and are not limited in this embodiment.

[0169] In a feasible implementation, the specific steps of the simulated annealing algorithm are as follows:

[0170] 1. Input: the initial schedule newdep and initial batch configuration arrangement given by the first scheduling algorithm (elevator algorithm);

[0171] 2. Initialize the new timetable Timetable and the objective function value obj, the best objective function value bestObj;

[0172] 3. Initialize simulated annealing parameters: current temperature T, iteration threshold iter;

[0173] 4. If the current number of iterations is less than iter and T is greater than the minimum temperature threshold Tmin, execute 5, otherwise return bestTimetable, bestObj;

[0174] 5. Generate optimized batch configuration arrangement based on neighborhood search algorithm; and calculate the corresponding schedule and objective function value;

[0175] 6. Randomly obtain a number R (0-1), and calculate the accepted new solution Pacc based on the current temperature and the objective function value. If R is greater than Pacc, update the arrangement and objective function value of the algorithm, otherwise remain unchanged;

[0176] 7. If the result of the update in 6 is bestObj, then record the current schedule and the objective function value as the best schedule bestTimtable and bestObj;

[0177] 8. The current temperature T decreases, and the current iteration round increases by 1 and returns to 4.

[0178] After obtaining the final batch configuration, according to the actual operation requirements of the train, for example, a target departure schedule can be determined according to the final batch configuration, and the target departure schedule includes the target departure time corresponding to each train at the stations at both ends of the faulty line segment. For example, after each train in the final batch configuration meets the planned stay time at the station, it can leave the station as soon as possible, and minimize the delay time of all trains while meeting the parking requirements, safe driving speed and safety distance.

[0179] The target departure schedule determined according to the final batch configuration can be determined based on the needs of trains and stations according to actual applications, and this embodiment does not impose any restrictions.

[0180] S204: According to the target departure time of each train at the stations at both ends of the faulty line segment, each train is allowed to run on the normal single track corresponding to the faulty line segment according to the target departure time.

[0181] Based on the target departure schedule determined by the final batch configuration, the control center of the target double track can order each train to run on the normal single track corresponding to the faulty line section according to its corresponding target departure time, so that up and down trains can alternately travel in both directions on the single track, avoiding congestion and large delays for trains in either direction when the single track in either direction fails.

[0182] In a feasible implementation, under different scale examples, the single-rail scheduling model provided in this embodiment and the heuristic solution algorithm based on the first scheduling algorithm, the neighborhood search algorithm and the simulated annealing algorithm are tested for solving the single-rail scheduling model. The single-rail scheduling model of this embodiment and the commercial solver CPLEX are compared in terms of solution time and solution quality. Finally, the performance of the proposed model is analyzed. The test results are shown in Table 1.

[0183] Table 1 Comparison of the results of the hybrid algorithm and the commercial solver CPLEX for 1 hour under different scale examples and parameter settings

[0184]

[0185] As can be seen from Table 1, in large, medium and small scale examples, the heuristic solution algorithm provided by this embodiment solves the delay of the single-rail scheduling model. Compared with the delay of the single-rail scheduling model solved by the commercial solver CPLEX, it can greatly improve the solution speed in large-scale examples and obtain a higher quality scheduling solution, which significantly reduces the delay of the train. In terms of the model, this embodiment maintains the single-rail scheduling model as a linear mixed integer programming model by introducing 0-1 variables. In small and medium scale examples, this model can obtain the optimal solution or approximate optimal solution through a commercial solver within an acceptable time range.

[0186] Reference Figure 3 , shows a functional module diagram of a double-track railway fault dispatching system in an embodiment of the present application, the system comprising:

[0187] The acquisition module 100 is used to acquire the faulty line section on the target double track, the fault time corresponding to the faulty line section, and the original arrival time of each train corresponding to the stations at both ends of the faulty line section;

[0188] An input module 200, used to input the faulty line segment, the fault time corresponding to the faulty line segment, and the original arrival time of each train corresponding to the stations at both ends of the faulty line segment into a monorail scheduling model, wherein the monorail scheduling model is constructed based on the method for constructing a monorail scheduling model according to any one of claims 1 to 4;

[0189] A solution module 300 is used to solve the single-track scheduling model based on a heuristic solution algorithm to obtain the target departure time corresponding to each train at the stations at both ends of the faulty line segment;

[0190] The scheduling module 400 is used to enable each train to run on the normal single track corresponding to the faulty line section according to the target departure time corresponding to each train at the stations at both ends of the faulty line section.

[0191] Optionally, the solution module includes:

[0192] An initial solution unit, used for determining an initial batch configuration of the single-track scheduling model based on a first scheduling algorithm;

[0193] An optimization solving unit, used for optimizing and adjusting the initial batch configuration of the single-track scheduling model based on a neighborhood search algorithm and a simulated annealing algorithm to obtain a final batch configuration of the single-track scheduling model;

[0194] A schedule determination unit is used to determine a target departure schedule according to the final batch configuration, wherein the target departure schedule includes the target departure time corresponding to each train at the stations at both ends of the faulty line segment.

[0195] Optionally, the initial solution unit includes:

[0196] The preset rule solving subunit is used to determine the initial batch configuration corresponding to each train in the upward and downward directions during monorail operation according to the original arrival time of each train corresponding to the stations at both ends of the faulty line segment based on the first scheduling algorithm and the preset rules, wherein the preset rules include the preset batch number and the number of trains in each batch.

[0197] Optionally, the optimization solution unit includes:

[0198] An optimization iteration subunit, configured to adjust the number of batches and the number of trains in each batch in the initial batch configuration based on a neighborhood search algorithm to obtain an optimized batch configuration, reduce the current temperature, and increase the number of iterations by 1 when the current temperature in the simulated annealing algorithm is greater than a minimum temperature threshold and the number of iterations is less than an iteration threshold;

[0199] The final batch configuration determination subunit is used to use the currently optimized batch configuration as the final batch configuration of the single-track scheduling model until the current temperature is equal to the minimum temperature threshold, or the number of iterations is equal to the iteration threshold.

[0200] Reference Figure 4 , shows a schematic diagram of a computer-readable storage medium provided in an embodiment of the present application, wherein the computer-readable storage medium 400 stores a computer program 401, and when the computer program 401 is executed by a processor, the double-track railway fault scheduling method as described in the embodiment is implemented.

[0201] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0202] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, devices, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented 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.

[0203] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0204] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0205] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0206] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0207] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including a..." do not exclude the presence of other identical elements in the process, method, article or terminal device including the elements.

[0208] Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A double-track railway fault dispatching method, characterized in that: The method comprises: Obtaining the faulty line section on the target double track, the fault time corresponding to the faulty line section, and the original arrival time of each train corresponding to the stations at both ends of the faulty line section; The faulty line section, the fault time corresponding to the faulty line section, and the original arrival time of each train corresponding to the stations at both ends of the faulty line section are input into a monorail scheduling model, wherein the monorail scheduling model is used to realize the passage of up and down trains based on the single track when a single track fault occurs in a double track line section; Solving the monorail scheduling model based on a heuristic solution algorithm to obtain the target departure time corresponding to each train at the stations at both ends of the faulty line segment, including: determining the initial batch configuration of the monorail scheduling model based on an elevator algorithm; performing multiple iterations based on a simulated annealing algorithm, optimizing the batch configuration using a neighborhood search algorithm during each iteration, and finally obtaining the final batch configuration of the monorail scheduling model; determining a target departure schedule based on the final batch configuration, wherein the target departure schedule includes the target departure time corresponding to each train at the stations at both ends of the faulty line segment; the elevator algorithm uses the faulty line segment as an elevator shaft, and the stations at both ends of the faulty line segment as elevator entrances of two floors; using the rated number of trains passing in one direction of the monorail each time as the rated number of passengers of the elevator; using the elevator going up and down alternately as the switching between the up batch and the down batch, wherein the up batch refers to: multiple up-direction trains passing up on the faulty line segment based on the monorail, and the down batch refers to: multiple down-direction trains passing down on the faulty line segment based on the monorail; According to the target departure time of each train at the stations at both ends of the faulty line section, each train is allowed to run on the normal monorail corresponding to the faulty line section according to the target departure time, so as to realize the alternating bidirectional passage of up and down trains on the monorail, and avoid the congestion and delay of trains in any direction when the monorail in that direction fails; The method for constructing the single-track scheduling model at least includes: Constructing an objective function, the objective function is used to minimize the delay time of all trains running on the double tracks arriving at the terminal station; Constructing a scheduling judgment constraint condition, wherein the scheduling judgment constraint condition is used to detect whether any train is a train object for single-track scheduling; Constructing safe driving constraint conditions, wherein the safe driving constraint conditions are used to ensure that the operation of any train meets target safety conditions; Based on the objective function, the scheduling judgment constraint condition and the safe driving constraint condition, the single-track scheduling model is constructed. The single-track scheduling model is used to determine the target departure time of each train at the stations at both ends of the faulty line segment to run on another line segment where the fault does not occur when there is a faulty line segment in the double-track line segment.

2. The method according to claim 1, characterized in that The single-track scheduling model is solved based on a heuristic solution algorithm to obtain the target departure time corresponding to each train at the stations at both ends of the faulty line segment, including: Based on the elevator algorithm, determining the initial batch configuration of the monorail scheduling model; Based on the neighborhood search algorithm and the simulated annealing algorithm, the initial batch configuration of the single-track scheduling model is optimized and adjusted to obtain the final batch configuration of the single-track scheduling model; A target departure schedule is determined according to the final batch configuration, wherein the target departure schedule includes the target departure time corresponding to each train at the stations at both ends of the faulty line segment.

3. The method according to claim 2, characterized in that Based on the elevator algorithm, determining the initial batch configuration of the monorail scheduling model includes: The elevator algorithm determines the initial batch configuration corresponding to each train in the upward and downward directions during monorail operation according to the original arrival time of each train corresponding to the stations at both ends of the faulty line segment and the preset rules, wherein the preset rules include the preset batch number and the number of trains in each batch.

4. The method according to claim 2 or 3, characterized in that: Based on the neighborhood search algorithm and the simulated annealing algorithm, the initial batch configuration of the single-track scheduling model is optimized and adjusted to obtain the final batch configuration of the single-track scheduling model, including: When the current temperature in the simulated annealing algorithm is greater than the minimum temperature threshold and the number of iterations is less than the iteration threshold, the number of batches in the initial batch configuration and the number of trains in each batch are adjusted based on the neighborhood search algorithm to obtain an optimized batch configuration, and the current temperature is reduced, and the number of iterations is increased by 1; Until the current temperature is equal to the minimum temperature threshold, or the number of iterations is equal to the iteration threshold, the currently optimized batch configuration is used as the final batch configuration of the single-track scheduling model.

5. The method according to claim 1, characterized in that The formula of the objective function is: in, is the arrival time of train i in the upward direction at the terminal n; is the original arrival time of train i in the upward direction at the terminal n; is the arrival time of train i in the down direction at the terminal; is the original arrival time of train i in the down direction at the terminal station; O is the set of down trains; I is the set of up trains.

6. The method according to claim 1 or 5, characterized in that: The construction of scheduling judgment constraints includes: Constructing a fault scheduling causal constraint condition, wherein the fault scheduling causal constraint condition is used for single track scheduling after a fault occurs; A fault dispatch judgment constraint condition is constructed, wherein the fault dispatch judgment constraint condition is used to determine whether to perform single-track dispatch on any train.

7. The method according to claim 1 or 5, characterized in that: The construction of safe driving constraints includes: Constructing a safety distance constraint condition, wherein the safety distance constraint condition is used to satisfy a safety distance condition between two adjacent trains in an upward direction or a downward direction; Constructing a stop time constraint condition, wherein the stop time constraint condition is used to satisfy the planned stop time of any train at each station; Constructing a travel speed constraint condition, wherein the travel speed constraint condition is used to satisfy a safe speed condition of any train on a line segment; Constructing an arrival time constraint condition, wherein the arrival time constraint condition is used to restrict any train to arrive at any station no earlier than the originally scheduled arrival time at the station; Constructing anti-collision constraints, the anti-collision constraints are used to satisfy the requirement that when each train at the stations at both ends of the faulty line segment runs on another line segment where the fault has not occurred, only trains in the upward or downward direction run on the line segment where the fault has not occurred.

8. A double-track railway fault dispatching system, characterized in that: The system comprises: An acquisition module, used to acquire a faulty line section on a target double track, a fault time corresponding to the faulty line section, and the original arrival time of each train corresponding to the stations at both ends of the faulty line section; An input module, used to input the faulty line section, the fault time corresponding to the faulty line section, and the original arrival time of each train corresponding to the stations at both ends of the faulty line section into a monorail scheduling model, wherein the monorail scheduling model is used to realize the passage of up and down trains based on the single track when a single track fault occurs in a double track line section; A solution module is used to solve the monorail scheduling model based on a heuristic solution algorithm to obtain the target departure time corresponding to each train at the stations at both ends of the faulty line segment, and is specifically used to determine the initial batch configuration of the monorail scheduling model based on the elevator algorithm; perform multiple iterations based on the simulated annealing algorithm, and optimize the batch configuration using a neighborhood search algorithm during each iteration to finally obtain the final batch configuration of the monorail scheduling model; determine the target departure schedule according to the final batch configuration, and the target departure schedule includes the target departure time corresponding to each train at the stations at both ends of the faulty line segment; the elevator algorithm uses the faulty line segment as the elevator shaft, and the stations at both ends of the faulty line segment as the elevator entrances of two floors; the rated number of trains passing in one direction on the monorail each time is used as the rated number of passengers of the elevator; the elevator goes up and down alternately as the switching between the up batch and the down batch, wherein the up batch refers to: multiple up-direction trains pass through the faulty line segment based on the monorail up, and the down batch refers to: multiple down-direction trains pass through the faulty line segment based on the monorail down; A scheduling module is used to make each train run on the normal monorail corresponding to the faulty line section according to the target departure time of each train at the stations at both ends of the faulty line section, so as to realize the alternating bidirectional passage of up and down trains based on the monorail, and avoid the congestion and delay of trains in any direction when the monorail in either direction fails; A construction module is used to construct an objective function, wherein the objective function is used to minimize the delay time of all trains running on the double track to arrive at the terminal station; construct a scheduling judgment constraint condition, wherein the scheduling judgment constraint condition is used to detect whether any train is a train object for single-track scheduling; construct a safe driving constraint condition, wherein the safe driving constraint condition is used to make the operation of any train meet the target safety condition; based on the objective function, the scheduling judgment constraint condition and the safe driving constraint condition, the single-track scheduling model is constructed, wherein the single-track scheduling model is used to determine the target departure time of each train at the stations at both ends of the faulty line segment when there is a faulty line segment in the double-track line segment.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the double-track railway fault dispatching method according to any one of claims 1 to 7 is implemented.

Images