A multi-line oriented urban rail train delay adjustment method and device

Abstract

The application discloses a kind of urban rail train delay adjustment method and device for multi-interchange diagram, it is related to train operation organization and control technical field, the method is by obtaining the basic line operation data of urban rail system, multi-interchange planned diagram information and train delay information;The basic line operation data, the multi-interchange planned diagram and the train delay information are input to the train delay adjustment model for multi-interchange diagram, and the adjusted urban rail multi-interchange diagram is output, the automation, intelligent adjustment of multi-interchange diagram is realized, the influence of train delay on passenger travel is reduced, and the actual diagram realization rate is improved to adapt to the fine management of urban rail system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of train operation organization and control, in particular to a city rail train delay adjustment method and device for multi-interchange diagram. BACKGROUND

[0002] In recent years, China's urban rail transit has developed rapidly and plays an indispensable role in meeting residents' travel needs and alleviating urban traffic congestion. As of the end of 2023, there are 59 cities with 338 operating lines, with a total length of 11224.54 kilometers. Due to the diversity of urban area planning, the passenger flow time-space distribution of some city rail lines connecting urban and suburban areas is extremely uneven, and the single interchange operation mode is difficult to adapt to complex passenger flow demand. Therefore, many urban rail transit systems in China have adopted a multi-interchange operation organization mode, allowing trains to run in different sections to share passenger flow. This mode can improve train operation efficiency, shorten passenger waiting time, and reduce operating costs.

[0003] However, the multi-interchange operation organization mode presents new challenges to dispatchers, especially in the face of train delays caused by failures or emergency conditions. In the traditional single-interchange operation mode, train delay propagation is mainly limited within a single line, and the subsequent train operation state is relatively easy to predict, and the conditions and timing of applying dispatch measures are also relatively easy to control. However, in the multi-interchange operation organization mode, train operation between different interchanges is mutually restrictive, and the propagation of delays has changed significantly. This makes the application conditions and timing of the original dispatch measures more complex and introduces new dispatch strategies such as extending train operation interchanges, increasing the difficulty of train operation adjustment. Therefore, after a train delay occurs on a line using a multi-interchange diagram, it is important to develop a reasonable adjustment strategy as soon as possible to reduce the impact of train delays, which has become one of the key research directions for current urban rail systems.

[0004] Currently, train delay adjustment under the multi-interchange operation organization mode still mainly relies on manual processing, and this process has not yet been automated and intelligentized. SUMMARY

[0005] The purpose of the present application is to provide a city rail train delay adjustment method and device for multi-interchange diagrams, which can automatically and intelligently adjust the multi-interchange diagram based on city rail train delay information, reduce the impact of train delays on passenger travel, and improve the actual diagram realization rate to adapt to the fine management of urban rail systems.

[0006] To achieve the above purpose, the present application provides the following solutions:

[0007] In a first aspect, the present application provides a city rail train delay adjustment method for a multi-interchange diagram, comprising:

[0008] obtain basic line operation data, multi-interchange planned running graph information and train delay information of the urban rail transit system;

[0009] input the basic line operation data, the multi-interchange planned running graph information and the train delay information into a train delay adjustment model for a multi-interchange running graph, and output an adjusted urban rail multi-interchange running graph, wherein the train delay adjustment model comprises a target function and a constraint condition set for a multi-interchange running graph, the target function is a function constructed with the objective of minimizing a function value, the function value is a numerical value calculated according to a timetable offset, a number of canceled services and a tracking interval change, and the constraint condition set comprises a set of timetable adjustment constraints and a set of train turnaround adjustment constraints.

[0010] In a second aspect, the present application provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the urban rail train delay adjustment method for a multi-interchange running graph.

[0011] In a third aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the urban rail train delay adjustment method for a multi-interchange running graph.

[0012] In a fourth aspect, the present application provides a computer program product comprising a computer program, wherein the computer program is executed by a processor to implement the urban rail train delay adjustment method for a multi-interchange running graph.

[0013] According to the embodiments provided in the present application, the following technical effects are disclosed:

[0014] The present application provides an urban rail train delay adjustment method and device for a multi-interchange running graph, which inputs basic line operation data, multi-interchange planned running graph and train delay information into a train delay adjustment model for a multi-interchange running graph, and outputs an adjusted urban rail multi-interchange running graph, thereby realizing automatic and intelligent adjustment of the multi-interchange running graph, reducing the impact of train delay on passenger travel, and improving the actual running graph realization rate to adapt to the fine management of the urban rail system. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed in the embodiments will be briefly introduced as follows. Obviously, the accompanying drawings in the following description only only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained based on these drawings without creative labor.

[0016] Figure 1 The application environment diagram of a city rail train delay adjustment method for a multi-interchange running diagram in Embodiment 1 of the present application;

[0017] Figure 2 The flowchart of a city rail train delay adjustment method for a multi-interchange running diagram provided in Embodiment 1 of the present application;

[0018] Figure 3 The line topology structure diagram considered in Embodiment 1 of the present application;

[0019] Figure 4 The structure diagram of a multi-layer perception machine classifier in Embodiment 1 of the present application;

[0020] Figure 5 The adjusted city rail multi-interchange running diagram in Embodiment 1 of the present application;

[0021] Figure 6 The structure diagram of a computer device provided in Embodiment 2 of the present application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0023] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0024] Embodiment 1

[0025] The city rail train delay adjustment method for a multi-interchange running diagram provided in the embodiments of the present application can be applied to, for example, Figure 1The application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data required by the server 104 to process. The data storage system can be set up separately, or integrated on the server 104, or placed on the cloud or other servers. The data storage system sends the basic line operation data of the urban rail transit system and the multi-interchange planned running graph to the server 104, and the terminal 102 sends the train delay information to the server 104. After receiving the basic line operation data of the urban rail transit system, the multi-interchange planned running graph and the train delay information, the server 104 inputs them into the train delay adjustment model facing the multi-interchange running graph, and obtains the adjusted urban rail multi-interchange running graph according to the train delay adjustment model facing the multi-interchange running graph. The server 104 can feed back the obtained adjusted urban rail multi-interchange running graph to the terminal 102.

[0026] Among them, the terminal 102 can be but not limited to passenger information system equipment (such as LED screen, LCD display in the station or the car), train operation control system equipment, power and environmental control equipment, etc. The server 104 can be realized by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0027] Through research, it is found that the related art about train delay adjustment under the multi-interchange operation organization mode still mainly relies on manual processing: after obtaining the delay information, the train dispatcher needs to predict the delay propagation and issue scheduling instructions such as car withdrawal, change of running interchange, return to the vehicle depot through the phone. This process has not been automated and intelligentized, and the dispatcher needs to consider scheduling instruction optimization and issuance at the same time, and the work intensity and pressure increase sharply. In addition, the line using the multi-interchange running graph has the ability to flexibly change the train running interchange, and the demand for train turnaround at intermediate stations increases significantly. Since the number of turnaround tracks configured at the intermediate station is relatively limited, the dispatcher faces great difficulties in ensuring the feasibility of the adjusted running graph. Finally, the scheduling work under the complex condition of the multi-interchange running graph often requires high professional knowledge and instant decision-making ability, and it is easy to cause prediction and decision-making errors due to insufficient experience and adaptability of the dispatcher, which may issue incorrect instructions, further expanding the impact of the delay; or the train running interchange is changed without timely notification to the station, resulting in passenger organization confusion.

[0028] In summary, the above-mentioned train delay adjustment method facing the multi-interchange running graph has the following defects:

[0029] 1) The train dispatcher needs to manually adjust the multi-interchange running graph, and issues scheduling instructions through the phone, which is high in work intensity and pressure;

[0030] 2) In the train delay adjustment for multi-route diagram, there is a contradiction between the large increase of turnaround demand of the train at the intermediate station and the relatively limited turnaround track capacity of the intermediate station, and it is difficult for the manual to ensure the feasibility of the adjusted diagram;

[0031] 3) The manual adjustment is prone to decision-making errors and untimely dispatching instructions, resulting in further expansion of the delay impact and passenger organization confusion.

[0032] In order to overcome the above technical defects, in an exemplary embodiment, as shown in Figure 2 , a city rail train delay adjustment method for multi-route diagram is provided, which is executed by a computer device, specifically can be executed by a server or the like computer device alone, or can be executed by a terminal and a server together, in the embodiment of the application, taking the server 104 in Figure 1 as an example for illustration, including the following steps A to step D. Among them:

[0033] A. Obtain the basic line operation data of the city rail system, the multi-route planned diagram and the train delay information.

[0034] Step A specifically includes:

[0035] A.1, according to the actual situation of the city rail system, configure the basic line operation data required for diagram adjustment, including line station set, shortest stopping time of each station in line station set, longest stopping time of each station in line station set, shortest running time between each station in uplink direction, longest running time between each station in uplink direction, shortest running time between each station in downlink direction, longest running time between each station in downlink direction, configuration of turnaround track station set, number of turnaround tracks in each station in the configuration of turnaround track station set, station set connected with the vehicle depot, number of standby vehicles in the vehicle depot connected with each station in the station set connected with the vehicle depot, train shortest tracking interval, train shortest turnaround time and standby vehicle shortest on-line time.

[0036] As shown in Figure 3 , the representation of the basic line operation parameter is: the set of all stations on the line (i.e. line station set) The shortest stopping time q min and the longest stopping time q max of the station s in this set, the stations 1 to S end are defined as the uplink direction, the stations S end to 1 are defined as the downlink direction, the shortest running time and the longest running time from station s to station s+1 in the uplink direction, the shortest running time and the longest running time Configuration of turn-back track station set The number of turn-back tracks r configured at station s in the set s Station set connected with the car depot The number of standby cars c in the car depot connected with station s in the set s The minimum headway h of trains min The minimum turn-back time u of trains min The minimum on-line time l of standby cars min .

[0037] A.2, Obtain multi-interchange plan diagram information, including: all up train set in the multi-interchange plan diagram Down train set The set of stations where train n is planned to run in the two sets Train At station The planned arrival time And the planned departure time

[0038] A.3, Obtain train delay information, including: train delay occurrence time t start , Delay duration t duration , Train number of train delay And station The type of delay δ and the set of stations where all trains have run through when the delay occurs Wherein,

[0039]

[0040] B, The objective is to minimize the schedule deviation, the number of canceled services and the change in headway, combined with the actual operation constraints (i.e. the constraint condition set for the multi-interchange diagram), to establish a train delay adjustment model for the multi-interchange diagram.

[0041] Step B specifically includes:

[0042] B.1, In order to ensure the feasibility of the arrival and departure time of the train after adjustment, establish a schedule adjustment constraint set for the multi-interchange diagram, including determined time constraints, stop time constraints, running time constraints, headway constraints, turn-back time constraints and standby car on-line time constraints, as follows:

[0043] Before the train delay occurs, each train strictly follows the plan diagram, so for train The actual arrival and departure time at station Is equal to the planned time. In addition, for the train If it leaves station If a delay occurs at the departure time (i.e. δ = 1), a departure delay is set; if a delay occurs at the arrival time (i.e. δ = 0), an additional arrival delay is set. Thus, the arrival time constraint is expressed as:

[0044]

[0045] To facilitate passengers' boarding and alighting and prevent traffic congestion, a threshold of dwell time is needed. Since the dwell time constraint is only valid at the stations where train n stops, the dwell time constraint is expressed as:

[0046]

[0047] where a n,s and d n,s are the actual arrival and departure times of train n at station s, y n,s is a 0-1 variable, and y n,s = 1 indicates that train n stops at station s.

[0048] The running time of a train in a section should also be limited within a certain range. For the up-train the running time constraint is valid when train n stops at stations s and s+1; for the down-train the running time constraint is valid when train n stops at stations s and s-1, and is expressed as:

[0049]

[0050] To ensure the safety of operation, a headway constraint is introduced to limit the interval between the departure time of the previous train and the arrival time of the next train. Due to the diversity of running routes, the running order of trains cannot be directly determined by the index, so train n and all trains n' < n need to maintain the headway constraint, i.e.:

[0051]

[0052] After executing a train, if it is to continue running, the train needs to be reversed on the turnaround track before executing the reverse train, and the duration of this process must be greater than the minimum turnaround time. Therefore, the turnaround time constraint is expressed as:

[0053]

[0054] where ξ n′,n,s is a 0-1 variable, and ξ n′,n,s = 1 indicates that the train enters the turnaround track configured at station s after executing train n' and executes the reverse train n.

[0055] ​For the train service using the backup train, its arrival and departure time should be arranged after the earliest time that the backup train can reach the main line. Therefore, the backup train online time constraint is expressed as:

[0056]

[0057] where, is a 0-1 variable, denotes that train service n is performed by the backup train in the depot connected to station s.

[0058] B.2, In order to ensure the feasibility of the adjusted train connection and the entry and exit depot plan, train turnaround adjustment constraints are established for multi-interchange diagram, including binary decision variable constraints, train service and train correspondence constraints, and turnaround track capacity constraints, as follows:

[0059] In order to establish the relationship between the timetable and the train turnaround, the intermediate variable y n,s is calculated (i.e., the expression of the binary decision variable constraint) as follows:

[0060]

[0061] where, n,s is a 0-1 variable, and β n,s = 1 indicates that the train returns to the depot connected to station s after performing train service n. The above formula indicates that for the up train service if it starts from the station with index less than or equal to s and ends at the station with index greater than or equal to s, train service n will stop at station s. For the down train service if it starts from the station with index greater than or equal to s and ends at the station with index less than or equal to s, train service n will stop at station s.

[0062] Train turnaround adjustment must ensure one-to-one correspondence between trains and train services. A train service can be performed in one of the following two ways, and the train service and train correspondence constraint includes:

[0063] On-line train turnaround or calling backup train in the depot, i.e.,

[0064]

[0065] At the same time, after performing a train service, the train also has two choices: turnaround to perform the opposite direction train service or return to the depot, which is expressed as:

[0066]

[0067] The number of backup trains called during multi-interchange diagram adjustment should not exceed the number of existing backup trains in the depot, which is expressed as:

[0068]

[0069] The number of turnaround tracks in urban rail transit system is relatively limited, so the turnaround track capacity constraint is introduced to ensure the feasibility of train operation diagram when the train operation diagram is flexibly changed. At least one idle turnaround track is needed when the train is turning back, and the number of idle turnaround tracks is related to the number of times that all trains enter and exit the turnaround track. Therefore, the calculation formula of the number of times that all trains enter and exit the turnaround track needs to be given before the turnaround track capacity constraint is formally established. First, the 0-1 variable γ n′,n,s is introduced, which is expressed as the following IF-THEN rule:

[0070]

[0071] Then, the number of times π n,s that all trains leave the station s equipped with turnaround track before train n performs turnaround can be calculated as:

[0072]

[0073] Meanwhile, the number of times σ n,s that all trains enter the station s equipped with turnaround track before train n performs turnaround can be calculated as:

[0074]

[0075] Based on the above variables, the turnaround track capacity constraint can be expressed as:

[0076]

[0077] B.3, In order to evaluate the effect of multi-loop train operation diagram adjustment, three operation indexes, including timetable offset, number of canceled services and tracking interval change, are introduced, and linear weighting is used for trade-off, as follows:

[0078] The timetable offset is calculated as:

[0079]

[0080] The number of canceled services is calculated as:

[0081]

[0082] The tracking interval change is calculated as:

[0083]

[0084] Where, p n′,n,s is a 0-1 variable, and p n′,n,s = 1 indicates that train n' and n are continuous at station s. The calculation formula of the variable is:

[0085]

[0086] The objective function can be calculated as:

[0087] min Z = λ1Z deviation + λ2Z cancel + λ3Z headway ;

[0088] Wherein, λ1, λ2, λ3 are weights corresponding to the three operation indexes, representing the importance of the operation indexes, and the train dispatchers can input different weight values according to the specific on-site situation.

[0089] C. The prediction of the 0-1 variable (i.e. binary decision variable) in the model is regarded as a binary classification task, a data set containing multiple train delay adjustment schemes is constructed, a variable prediction method based on data driving is proposed, and the solving efficiency of the subsequent model is improved.

[0090] Step C specifically comprises:

[0091] C.1. In the model established in step B, β n,s and ξ n,n′,s play a key role. Once the values of β n,s and ξ n,n′,s are determined, the train turnaround can be determined, thereby reducing the solution space of the model. Considering the mutual restrictive relationship between β n,s and ξ n,n′,s , it is not necessary to predict each variable separately. Here, two intermediate variables and are introduced to represent whether train n starts and ends at station s, which is expressed as:

[0092]

[0093]

[0094] The prediction of and is regarded as a binary classification task.

[0095] C.2, The binary classification task is to predict the start and end stations of the train for the train delay adjustment model of the multi-line train diagram. For the binary classification task, it is essential to build a reliable data set to find the correlation between the classification task and the label. For the above task, the data set used to train the classifier is a plurality of train delay instances and the corresponding optimal adjustment scheme, which is represented by a set of features and their labels. Specifically, the features of the train delay instance are represented as e = (e1, e2, …, e K ), including the spatiotemporal distribution (the time and location when the train is delayed), the duration, the standby distribution of the vehicle depot, and the label is the value of and in the corresponding optimal adjustment scheme. Among them, the train delay instance is generated from historical data, and the optimal adjustment scheme is obtained by a solver such as CPLEX or GUROBI.

[0096] C.3, A multilayer perceptron is used as a classifier, as shown in Figure 4 , the multilayer perceptron includes an input layer, a hidden layer, and an output layer. The feature vector e is taken as the input layer, and after a series of linear weighting and nonlinear activation, the predicted values of and are output. This mapping from the input layer to the output layer can be represented by the function f(e; θ), where θ is the weight of the multilayer perceptron. The predicted value of the output layer can be represented as or and a threshold of 0.5 is used to determine the classification label. In order to make the predicted value as close to the true value as possible, the training of the multilayer perceptron uses the cross-entropy loss function, that is:

[0097]

[0098] where J is the number of training instances. The weights of the multilayer perceptron are updated continuously during the training process to minimize the cross-entropy loss.

[0099] D, Use the trained classifier to predict the value of the intermediate variable, and solve the train delay adjustment model after narrowing the solution space to obtain the adjusted urban rail multi-line train diagram.

[0100] Step D specifically includes:

[0101] D.1, Sort the trained classifiers according to the prediction accuracy, and use the classifiers with higher than the acceptable prediction accuracy threshold. According to the basic operation parameters and train delay information obtained in step A, determine the feature vector value of the input layer, input it into the multilayer perceptron in order according to the sorting, and determine the predicted value of the corresponding variable according to the output layer. If there is a constraint conflict between the predicted values of the two classifiers, skip the output of the classifier with lower prediction accuracy. After traversing all available classifiers, the train delay adjustment model with narrowed solution space is obtained;

[0102] D.2, using a solver such as CPLEX or GUROBI to solve the train delay adjustment model after reducing the solution space, and obtaining the adjusted urban rail multi-interchange diagram within a specified time. Figure 5 The adjustment diagram of the 092037 train of Beijing subway line 19 is shown when a 5-minute delay occurs at Niujie station. The gray color represents the planned arrival and departure time, the red color represents the adjusted arrival and departure time, the green color represents the adjusted train turnaround, and the yellow color represents the canceled train.

[0103] The embodiment realizes the adjustment of the multi-interchange diagram of the urban rail transit system, and has the following advantages:

[0104] 1. The intelligent method is used to replace the existing manual adjustment method of the dispatcher under the condition of the multi-interchange diagram train delay, and the working intensity of the dispatcher is reduced;

[0105] 2. The operation constraints such as turnaround line capacity, tracking interval, stopping time and turnaround time can be met, and the feasibility of the adjusted diagram can be ensured;

[0106] 3. A variety of scheduling measures such as adjusting train arrival and departure time, canceling / adding train, putting standby train on line and changing running route are comprehensively applied, and scheduling instructions are automatically issued, the realization rate of the diagram is improved, and the situation that the decision-making is wrong or the scheduling instruction is not issued in time due to the lack of experience of the dispatcher is avoided.

[0107] The application also provides an application scenario of the above-mentioned urban rail train delay adjustment method for a multi-interchange diagram. Specifically, the urban rail train delay adjustment method for a multi-interchange diagram provided in the embodiment can be applied in the train scheduling and operation management scenario of the urban rail transit system. The train scheduling and operation management scenario of the urban rail transit system includes train operation monitoring, delay prediction and adjustment, passenger information release and other links. The urban rail train delay adjustment method for a multi-interchange diagram provided in the embodiment belongs to the intelligent optimization link in the delay prediction and adjustment. By using the urban rail train delay adjustment method for a multi-interchange diagram provided in the embodiment, the operation efficiency and service quality of the urban rail transit system are improved through intelligent optimization and dynamic adjustment, and the negative impact of the delay on passengers is reduced.

[0108] Embodiment 2

[0109] The computer device provided in the embodiment can be a server or a terminal, and the internal structure diagram thereof can be as shown in Figure 6The computer device shown in the figure includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store any data in the urban rail train delay adjustment method facing the multi-interchange running graph. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with the terminal outside through network connection. The computer program is executed by the processor to realize the urban rail train delay adjustment method facing the multi-interchange running graph provided in embodiment 1.

[0110] Those skilled in the art can understand that, Figure 6 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0111] Embodiment 3

[0112] The embodiment provides a computer device including a memory and a processor, and the memory stores a computer program. The processor executes the computer program to realize the urban rail train delay adjustment method facing the multi-interchange running graph provided in the above embodiment 1.

[0113] Embodiment 4

[0114] The embodiment provides a computer readable storage medium storing a computer program. The computer program is executed by a processor to realize the urban rail train delay adjustment method facing the multi-interchange running graph provided in the above embodiment 1.

[0115] Embodiment 5

[0116] The embodiment provides a computer program product including a computer program. The computer program is executed by a processor to realize the urban rail train delay adjustment method facing the multi-interchange running graph provided in the above embodiment 1.

[0117] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0118] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments of each method. In the embodiments provided in the present application, any reference to memory, database or other medium can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc.

[0119] The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a blockchain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0120] The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, not all possible combinations of the technical features in the above embodiments are described, but as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0121] The principles and implementations of the present application are described in the specific examples herein, and the above examples are only used to help understand the method of the present application and its core idea; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation and application range will be changed. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A method for adjusting delay of a metro train oriented to a multi-route working diagram, characterized in that, The urban rail train delay adjustment method faces a multi-line operation diagram, and comprises the following steps: Obtain basic line operation data, multi-line planned operation diagram information, and train delay information of an urban rail system; Input the basic line operation data, the multi-line planned operation diagram information, and the train delay information into a train delay adjustment model facing a multi-line operation diagram, and output an adjusted urban rail multi-line operation diagram, wherein the train delay adjustment model comprises a target function and a constraint condition set facing a multi-line operation diagram, the target function is a function constructed with the objective of minimizing a function value, the function value is a numerical value calculated according to a timetable offset, a number of canceled services, and a tracking interval change value, and the constraint condition set comprises a set of timetable adjustment constraints and a set of train turnaround adjustment constraints; The expression of the target function is as follows: Wherein, Z represents function value; Z deviation represents schedule offset; Z cancel represents number of canceled services; Z headway represents tracking interval change; n represents train number; represents up-train set; represents down-train set; a n,s represents actual arrival time of train n at station s; represents planned arrival time of train n at station s; d n,s represents actual departure time of train n at station s; represents planned departure time of train n at station s; S represents line station set; S n represents station set planned to be run by train n; represents station set run by train n when delay occurs; y n,s represents whether train n stops at station s; n' and n" both represent train number; S turn represents station set configured with turn-back track; p n',n,s represents whether train n' and train n are continuous at station s; p n,n”,s represents whether train n and train n" are continuous at station s; d n',s represents actual departure time of train n' at station s; y n',s represents whether train n' stops at station s; p n”,n,s represents whether train n" and train n are continuous at station s; λ1, λ2, λ3 all represent weight.

2. The urban rail train delay adjustment method for multi-line oriented working diagram according to claim 1, characterized in that, The basic line operation data comprises a set of line stations, a shortest stopping time of each station in the set of line stations, a longest stopping time of each station in the set of line stations, a shortest running time between each station in the uplink direction, a longest running time between each station in the uplink direction, a shortest running time between each station in the downlink direction, a longest running time between each station in the downlink direction, a set of stations configured with a turnaround track, a number of turnaround tracks configured at each station in the set of stations configured with a turnaround track, a set of stations connected with a vehicle depot, a number of standby vehicles in the vehicle depot connected with each station in the set of stations connected with the vehicle depot, a shortest train tracking interval, a shortest train turnaround time, and a shortest standby vehicle online time; The multi-line planned operation diagram information comprises a set of uplink trains, a set of stations planned to be run by each train in the set of uplink trains, a set of downlink trains, a set of stations planned to be run by each train in the set of downlink trains, a planned arrival time at each station, and a planned departure time at each station; The train delay information comprises a train delay occurrence time, a delay duration, a train number of a delayed train, a station of a delayed train, a delay type, and a set of stations that have been run by all trains at the time of the delay.

3. The urban rail train delay adjustment method for multi-line oriented working diagram according to claim 1, characterized in that, Input the basic line operation data, the multi-line planned operation diagram information, and the train delay information into a train delay adjustment model facing a multi-line operation diagram, and output an adjusted urban rail multi-line operation diagram, specifically comprising the following steps: Determine a feature vector value according to the basic line operation data and the train delay information; Use the trained classifier to output an intermediate variable value in the optimal adjustment scheme by taking the feature vector value as input, wherein the intermediate variable is a variable determined according to a set of binary decision variables in the train delay adjustment model facing a multi-line operation diagram, the set of binary decision variables comprises a variable used to represent whether a train returns to a vehicle depot connected with a station after executing a train, a variable used to represent whether a train enters a turnaround track configured at a station to change the direction and execute a reverse train after executing a train, and a variable used to represent whether a train is executed by a standby vehicle in a vehicle depot connected with a station. Solving the train delay adjustment model according to the basic line operation data, the multi-interchange plan diagram information, the train delay information and the intermediate variable value, to obtain an adjusted urban rail multi-interchange operation diagram.

4. The urban rail train delay adjustment method for multi-line oriented working diagram according to claim 1, characterized in that, The time adjustment constraint set includes determined time constraints, stop time constraints, running time constraints, tracking interval constraints, turnaround time constraints and spare car online time constraints; the train turnaround adjustment constraint set includes binary decision variable constraints, train number and train corresponding relationship constraints and turnaround track capacity constraints.

5. The urban rail train delay adjustment method for multi-line oriented working diagram according to claim 3, characterized in that, The training process of the classifier specifically includes: constructing a sample data set, wherein the sample data set includes a sample feature vector and label data, the sample feature vector is determined according to historical basic line operation data and historical train delay information in a historical train delay instance, and the label data is a real intermediate variable value in an optimal adjustment scheme corresponding to the historical train delay instance; training a classifier according to the sample feature vector and the label data; when the cross-entropy loss function value between the predicted variable value output by the classifier and the real intermediate variable value is the minimum, the training of the classifier is completed.

6. The urban rail train delay adjustment method for multi-line oriented working diagram according to claim 3, characterized in that, The expression of the intermediate variable is: wherein, represents an intermediate variable for characterizing whether the train n starts at station s; n' and n both represent train numbers; represents a set of down trains; ξ n,n′,s represents whether the train, after performing train n', enters the turnaround track configured at station s and performs the reverse train n; represents whether train n is performed by a standby train in the depot connected to station s; represents a set of stations configured with turnaround tracks; represents a set of up trains; represents a set of stations connected to the depot; represents an intermediate variable for characterizing whether the train n ends at station s; β n,s represents whether the train, after performing train n, returns to the depot connected to station s.

7. A computer device comprising: A memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the urban rail train delay adjustment method for a multi-interchange operation diagram according to any one of claims 1-6.

8. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the urban rail train delay adjustment method for a multi-interchange operation diagram according to any one of claims 1-6.

9. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the urban rail train delay adjustment method for a multi-interchange operation diagram according to any one of claims 1-6.

Images