KR102127916B1 - Autonomous collaboration based train control method - Google Patents

Abstract

In an autonomous collaboration-based train control method performed by an onboard device of each train in a train autonomous driving environment based on inter-train communication, a) the onboard device of the first train is at least one to re-adjust its route and schedule Setting a driving arrangement range including the above-described areas, and updating driving state information at each predetermined update cycle; b) When driving reorganization event information occurs in the update cycle, all trains located within the reorganization range are set as a target train, train priority for the target train is calculated, and neighboring trains except the first train among the target trains Gathering the operation status information of; c) determining a route and a schedule of the first train based on the determined route and schedule information for the neighboring train when the route and schedule for the neighboring train are determined according to the priority of the train; d) Perform a collaborative algorithm to form a neighbor coalition between the first train and neighboring trains, and simultaneously perform the driving arrangement of the target train according to route and schedule information determined for each train through collaboration between trains in the neighbor union. To do; And e) the on-board device of the target train includes updating route and schedule information according to a result of performing the collaboration algorithm, and updating driving state information while operating according to the updated route and schedule.

Description

Autonomous collaboration-based train control method {AUTONOMOUS COLLABORATION BASED TRAIN CONTROL METHOD}

The present invention relates to an autonomous collaboration-based train control method that enables each train to perform driving theorem on its own without the intervention of an administrator in real time.

In the railway network, due to the characteristics of trains operating on a fixed track, delays in some trains may affect the schedules of other trains, which can lead to races between trains, which can spread across the entire network and cause confusion. When a train in the same direction overtakes a preceding train or when multiple routes converge into one, the train can be operated by rescheduling the schedule, such as determining the train's operating sequence.

Recently, interest in an efficient train scheduling method has increased. Conventional scheduling has relied heavily on expert experience in railroad operations rather than optimization or simulation-based. If a railroad operator prepares a schedule for train operation in advance, the train operator and the controller will operate the train in strict accordance with the train schedule.

However, in the event of an unexpected situation, such as a failure of the train or track or non-compliance with the arrival time due to a schedule, delays or accidents on the platform, occupy the same track at the same time, deadlock between two directions, non-compliance with safety intervals, etc. There will be race contention.

At this time, the controller of the central control center performs driving arrangements such as re-adjusting the route and schedule of the train, that is, solving the contention of the train to ensure the on-time and safety of the train.

In the conventional method of creating a train schedule, the central control center collects all train-related operation information to make a decision, and the central control center transmits the decision to each on-site train. At this time, human error occurs in the communication process between the controller and the engineer. There is a risk of occurrence.

In addition, in the conventional train schedule creation method, it is not only realistic to collect the operation information of all trains in real time from the central control center, but also it takes a lot of time to resolve train contention in a large and complex railway network, and the controller of the central control center There are limitations in determining timely action.

As described above, the conventional method for creating a train schedule may re-adjust the train route and schedule depending on the experience of the controller to resolve the contention of the train, which may lead to a risk of human error, and is based on a uniform standard without considering the current state of the train operation. There is a problem in that the efficiency of the overall train operation is deteriorated due to the elimination of train contention. In addition, in the case of assigning train routes between a plurality of railway operators, there is a problem in that, even if a train route is assigned to a plurality of operators through any procedure, it is not possible to smoothly perform train route assignment in the absence of an effective scheduling method.

Republic of Korea Registered Patent No. 10-1214567 (Name of invention: Method and device for establishing train operation plan)

Republic of Korea Patent Publication No. 10-2016-159746 (Invention name: operation plan preparation device, method and program)

In order to solve the above-mentioned problems, the object of the present invention is to enable the train to self-adjust its own route and schedule based on real-time wireless communication between trains in the event of a train failure or natural disaster. have.

However, the technical problem to be achieved by the present embodiment is not limited to the technical problem as described above, and other technical problems may exist.

An autonomous collaboration-based train control method according to an embodiment of the present invention as a technical means for achieving the above technical problem is autonomous collaboration performed by onboard devices of each train in a train autonomous driving environment based on inter-train communication. In the train control method based on: a) the on-board device of the first train sets a driving arrangement range including at least one area to re-adjust its route and schedule, and updates driving status information at each preset update cycle To do; b) When driving reorganization event information occurs in the update cycle, all trains located within the reorganization range are set as target trains, train priority is calculated for the target trains, and neighboring trains except the first train among the target trains Gathering the operation status information of; c) determining a route and a schedule of the first train based on the determined route and schedule information for the neighboring train when the route and schedule for the neighboring train are determined according to the priority of the train; d) Forming a neighbor coalition between the first train and neighboring trains, and performing a collaborative algorithm that simultaneously performs the driving arrangement of the target train according to route and schedule information determined for each train through collaboration between trains in the neighboring union. To do; And e) the on-board device of the target train includes updating route and schedule information according to a result of performing the collaboration algorithm, and updating driving state information while operating according to the updated route and schedule.

According to the above-described problem solving means of the present invention, by inter-train collaboration based on real-time wireless communication, the entire driving arrangement can be distributed in units of trains, so that the role of the central control center can be minimized to the supervision range, and the central control center Even in the event of an error, each train can make its own decision-making for its operation, thus enabling stable system operation.

In addition, the present invention is effective in a large-scale network including a large number of operating entities or transportation because the ability to cope with system changes is not affected by system scale when some of the system information, such as additional organization of vehicles or extension of routes, is changed. It can be operated with, and it is possible to shorten the calculation time of the algorithm for resolving the competition between trains by using only the operation status information of the neighboring train, not the operation status information of the entire train, so as to shorten the calculation time and manage data. It can be easy in terms.

1 is a view for explaining a train control system for implementing an autonomous collaboration-based train control method according to an embodiment of the present invention.
2 is a flowchart illustrating a method for autonomous collaboration based train control according to an embodiment of the present invention.
3 is a view for explaining an example of setting the driving clearance range according to an embodiment of the present invention.
4 is a diagram illustrating a priority management state for a target train according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art to which the present invention pertains may easily practice. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. In addition, in order to clearly describe the present invention in the drawings, parts irrelevant to the description are omitted, and like reference numerals are assigned to similar parts throughout the specification.

Throughout the specification, when a part is "connected" to another part, this includes not only "directly connected" but also "electrically connected" with other elements in between. . Also, when a part is said to "include" a certain component, it means that the component may further include other components, not exclude other components, unless specifically stated otherwise. However, it should be understood that the existence or addition possibilities of numbers, steps, actions, components, parts or combinations thereof are not excluded in advance.

The following examples are detailed descriptions to help understanding of the present invention, and do not limit the scope of the present invention. Therefore, the same scope of the invention performing the same function as the present invention will also belong to the scope of the present invention.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

1 is a view for explaining a train control system for implementing an autonomous collaboration-based train control method according to an embodiment of the present invention.

First, the train control system efficiently manages resources shared by multiple trains, such as track sections and track changers, in a train autonomous driving environment that performs safe spacing and branch control through direct communication between trains without relying on ground control commands. Make it operational.

To this end, each train includes an onboard equipment 100 for implementing a train autonomous driving system based on direct wireless communication between trains. The on-board device 100 acts as an agent for reorganizing each route and schedule through train collaboration between trains and performing driving arrangements.

Next, referring to FIG. 1, the onboard device 100 includes a communication module 110, a memory 120, a processor 130, and a database 140.

The communication module 110 provides a communication interface required to transmit and receive signals between trains in conjunction with a wireless communication network. Here, the communication module 110 may be a device including hardware and software necessary for transmitting and receiving a signal such as a control signal or a data signal through a wired or wireless connection with another network device.

In the memory 120, a program for performing a train control method based on autonomous collaboration is recorded. In addition, it performs a function of temporarily or permanently storing data processed by the processor 130. Here, the memory 120 may include volatile storage media or non-volatile storage media, but the scope of the present invention is not limited thereto.

The processor 130 controls the entire process of providing a train control method for reorganizing the driving by re-adjusting the route and schedule through autonomous collaboration between trains. Each step performed by the processor 130 will be described later with reference to FIG. 2.

Here, the processor 130 may include all kinds of devices capable of processing data, such as a processor. Here, the'processor (processor)', for example, may mean a data processing device embedded in hardware having physically structured circuits to perform functions represented by codes or instructions included in a program. As an example of such a data processing device embedded in hardware, a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, and an application-specific integrated ASIC circuit, a field programmable gate array (FPGA), or the like, but the scope of the present invention is not limited thereto.

The database 140 stores data accumulated while performing a train control method based on autonomous collaboration. For example, the database 140 may store driving state information that is updated every set period, a result of performing a collaboration algorithm, route and schedule information, and the like.

2 is a flowchart illustrating an autonomous collaboration-based train control method according to an embodiment of the present invention, and FIG. 3 is a view illustrating an example of setting a driving arrangement range according to an embodiment of the present invention, FIG. 4 Is a diagram illustrating a priority management state for a target train according to an embodiment of the present invention.

2 to 4, in the autonomous collaboration-based train control method, the on-board device of each train updates its current operating state information at every update cycle, and it is inefficient to re-adjust the route and schedule at every update cycle Therefore, it is possible to perform the driving clearance only when the driving clearance event information is generated in consideration of the dynamically changing surrounding situation (S1).

The driving clearance event information is at least one of a case in which a train enters a new area, a new train enters the area where the train is located, a failure in a train or a track, or a train delay time that is greater than the allowable delay time. When the above situation occurs, it is determined that an event that requires updating the train route and schedule has occurred.

At this time, the on-board device of each train limits the range of driving arrangements for re-adjusting its route and schedule to a certain area. In the railway network, a partial network between a station and a station is defined as a region, and the on-board device sets the area from the direction of the train to the current station and the next station as the driving clearance range.

That is, as shown in FIG. 3, when the train A is operating the upstream line, k station where the train A is currently located and k+1 station to stop next, and k station and k+1, k+2 station to the next stop Is set to the operation clearing range.

If, when the first train (X ₁ ) has the driving clearance event information in a specific update cycle, the corresponding on-board device updates the current driving state information and sets all trains located within the driving clearance range as the target train, For trains located in the region where the first train is located, before and after, the train priority for the target train is calculated by considering the class of the train type and the current location information of the train (S2, S3). The operation status information of neighboring trains other than the first train is collected (S4).

As shown in FIG. 4, since the first train is located in Region 2, the trains X ₂ , X ₃ , and X ₄ located in Region 1, Region 2, and Region 3 based on Region 2 It becomes a target train, and for example, priority can be managed in the order of the second train, the third train, and the fourth train based on the first train, that is, X ₁ > X ₂ > X ₃ > X ₄ .

In addition, each train defines trains other than itself as neighbor trains. At this time, the neighboring trains are symmetrical to each other. That is, when train j is a neighbor train of train i, train i also becomes a neighbor train of train j. As shown in Fig. 3, train A and train B become neighbor trains.

The autonomous collaboration-based train control method of the present invention is to enable the entire driving theorem to be decentralized in units of trains, so that when the event of the driving theorem occurs, each train can perform its own driving arrangement without the intervention of the manager. The goal is to determine the route and schedule (TRS _i ) to minimize the sum of the delay times of trains in a region, and to achieve this goal, each train manages neighboring trains and train priorities.

The on-board device determines the route and schedule of the first train based on the determined route and schedule information for the neighboring train (TRS _i ) when the route and schedule for the neighboring train having a higher priority is determined according to the train priority (TRS _i ) ( S5).

The on-board device uses the hydraulic model to sequentially determine the train's route and the departure and arrival times of each point on the route according to the train priority, and there is no competition between trains based on the determined route and schedule information for neighboring trains. To avoid this, decide the order of operation with neighboring trains.

At this time, the mathematical model provides the objective function represented by Equation 1 to minimize the total delay time of train i, and configures at least one constraint condition such as Equations 2 to 6 to prevent train contention.

[Equation 1]

[Equation 2]

인 경우, 목적함수가 지연 시간의 최소화가 되므로 최적해는 제약식을 항상 등호로 만족시키고,

인 경우, 최적해는

을 만족시킨다. The constraint in Equation 2 is to check how long train i is delayed compared to the scheduled schedule on each platform,

In the case of, the objective function minimizes the delay time, so the optimal solution always satisfies the constraint with the equal sign,

If is, the optimal solution is

Satisfies

[Equation 3]

The constraints in Equation (3) ensure that trains following in order of operation maintain a given safety interval. Through Equation 3, it is possible to secure a safe distance from neighboring trains using the same section, thereby preventing collisions between trains.

Equation 3 is a constraint for keeping the distance in the section running in the same direction as the neighboring train, and maintaining the distance in the section running in a different direction from the neighboring train is as in Equation 4.

[Equation 4]

[Equation 5]

는 입력받은 값이다.Equation 5 is a constraint that train i shares with the neighboring train in the hydraulic model, so that the order of operation between train i and the neighboring train is determined consistently as a whole. At this time,

Is the input value.

[Equation 6]

Equation (6) is a constraint expression that satisfies the case where the departure time is restricted in the platform.

[Equation 7]

Equation 7 above is a constraint that determines the stop time at each node. Trains will stop on platforms where the minimum stop time is greater than zero. When stopping at a node, the speed at the node must be 0. Conversely, when passing through the node, the time to arrive at the end of the previous section and the time to leave the next section must be the same in two consecutive sections.

[Equation 8]

Equation 8 is a travel time constraint expression of train i in section p, and the travel time is determined according to the operation pattern for each section.

[Equation 9]

Equation (9) is a constraint for selecting the movement type of train i in section p. In each section, the train must select only one movement type, and the arrival speed and departure speed at each node must be the same.

In this way, the constraints are the delay time of arrival time (Equation 2), the restriction on the maintenance of the train's distance (Equation 3), the order of operation with neighboring trains (Equation 5), and the departure time constraint of trains at each station ( Equation 6), at least one of the stop time at each node (Equation 7), the travel time constraint of the train in the section (P) (Equation 8), or the constraint on the movement type selection (Equation 9) do. Accordingly, the on-board device can obtain a detailed schedule satisfying the above-described constraints through the hydraulic model.

에 대해서 열차 i가 고려하는 이웃 열차 집합과 열차 i가 선택한 경로에 포함되는 구간 및 플랫폼의 집합을 각각 N_i, P_i, Q_i로 나타낸다. 각 열차는 구간을 상행 혹은 하행 방향으로 이동할 수 있는데, P_i 를 보다 세분화하여 열차 i가 방향 d로 지나갈 수 있는 구간의 집합을

로 나타내고, 이를 정리하면 하기한 표 1및 표 2와 같다.The set of trains operating in the entire railway network is represented by I, and the set of sections and platforms is represented by P and Q, respectively. Each train considers a partial rail network, each train

For N, the set of neighbor trains considered by train i and the set of sections and platforms included in the route selected by train i are denoted by N _i , P _i , Q _i , respectively. Each train can move a section in the up or down direction, but by subdividing P _i , a set of sections where train i can pass in direction d

It is shown in Table 1 and Table 2 below.

[Table 1]

[Table 2]

는 선택한 경로의 각 구간별로 시작마디에서의 출발 시각

및 끝마디에서의 도착시간

을 결정하게 된다. 이 때, 플랫폼

까지의 도착 지연 시간은 종속적으로 주어진다. 또한, 각 구간별로 이웃열차와의 운행 순서를 결정하게 된다. 각 열차는 절점별로 속도 및 정차 여부를 결정하게 된다. 각 절점별로 열차가 가질 수 있는 속도값을 이산화하여 수리 모형에 반영한다. 수리 모형에서는 속도를 세 단계로 나눌수 있는데, s는 정지, c는 서행 속도, p는 최대 속도를 나타낸다. 이를 정리하면 하기한 표 3과 같다.Each train

Is the departure time at the start node for each section of the selected route

And arrival time at the end

Will decide. At this time, the platform

The arrival delay time until is given dependently. In addition, the order of operation with neighboring trains is determined for each section. Each train determines the speed and stop for each node. The speed value that the train can have for each node is discretized and reflected in the hydraulic model. In the hydraulic model, the speed can be divided into three stages: s for stop, c for slow speed, and p for maximum speed. This is summarized in Table 3 below.

[Table 3]

Referring again to FIG. 2, the first train forms a neighboring association with a neighboring train (S6), and simultaneously performs a driving arrangement of a target train according to route and schedule information determined for each train through collaboration between trains in the neighboring union. To perform a collaborative algorithm (S7).

과정을 반복한다. 이때, 협업 알고리즘은 어떠한 이웃 연합도 열차 지연시간을 개선시킬 수 없을 경우에 종료된다.At this time, the collaborative algorithm initializes the route and schedule of each train as a result of TRS _i , transmits the information to the neighboring train, and each train i forms a neighbor association {i, j} for each neighboring train j.

Repeat the process. At this time, the collaboration algorithm ends when no neighboring association can improve the train delay time.

과정은, 먼저 TRS_ij를 MILP solver로 풀고, 최적해

,

와, 이때의 목적함수 변화량(

)을 수학식 10과 같이 계산한다.

The process is, first, solve the TRS _ij with the MILP solver,

,

Wow, the amount of change in the objective function at this time (

) Is calculated as in Equation 10.

[Equation 10]

) 정보를 전송하고, 이웃 연합의 목적함수 변화량 정보(

)를 얻은 후에

가 모든

보다 클 경우, 결정 변수를

,

로 변경하고, 해당 정보를 이웃 연합에게 전달한다. The collaborative algorithm tells the neighboring coalition how much of its objective function

) Information, and information about the change in the objective function of the neighboring union (

)

There all

If greater than

,

Change it to, and send the information to the neighboring union.

는 수학식 11과 같이 정의된다. 여기서

는

제외한 나머지 이웃열차들간의 순서로 입력값이다.If W _i is the solution set of TRS _i ,

Is defined as Equation 11. here

The

The input values are in the order of the remaining neighboring trains.

[Equation 11]

The on-board device of the target train updates the route and schedule information according to the result of performing the collaboration algorithm (S8), and the first train updates the driving state information while operating according to the updated route and schedule (S9).

As described above, the autonomous collaboration-based train control method of the present invention can minimize the role of the central control center as the supervisory scope by distributing the entire driving arrangement in train units through inter-train collaboration based on real-time wireless communication. Even when an error occurs in the control center, each train can make its own decision-making for its operation, enabling stable system operation.

In addition, the present invention is effective in a large-scale network including a large number of operating entities or transportation because the ability to cope with system changes is not affected by the system scale when a part of system information such as additional organization of a vehicle or extension of a route is changed. Can operate as

The autonomous collaboration-based train control method according to the embodiment of the present invention described above may be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Such recording media include computer readable media, which can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, computer readable media includes computer storage media, which are volatile and nonvolatile implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. , Removable and non-removable media.

The above description of the present invention is for illustration only, and a person having ordinary knowledge in the technical field to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the above detailed description, and it should be interpreted that all changes or modified forms derived from the meaning and scope of the claims and equivalent concepts thereof are included in the scope of the present invention. do.

100: onboard device
110: communication module 120: memory
130: processor 140: database

Claims (18)

In the autonomous vehicle-based train control method performed by the onboard device of each train in a train autonomous driving environment based on inter-train communication,
a) the in-vehicle device of the first train sets a driving arrangement range including at least one area to re-adjust its route and schedule, and updates driving state information at each preset update cycle;
b) When driving reorganization event information occurs in the update cycle, all trains located within the reorganization range are set as a target train, train priority for the target train is calculated, and neighboring trains except the first train among the target trains Gathering the operation status information of;
c) determining a route and a schedule of the first train based on the determined route and schedule information for the neighboring train when the route and schedule for the neighboring train are determined according to the priority of the train;
d) Perform a collaborative algorithm to form a neighbor coalition between the first train and neighboring trains, and simultaneously perform the driving arrangement of the target train according to route and schedule information determined for each train through collaboration between trains in the neighbor union. To do; And
e) the on-board device of the target train includes updating route and schedule information according to a result of performing the collaboration algorithm, and updating driving state information while operating according to the updated route and schedule, autonomous collaboration Based train control method. According to claim 1,
Step a) is,
An autonomous collaboration-based train control method for setting up or descending areas leading to the current station (k) and the next station (k+1) in the driving direction of the first train as a driving clearance range. According to claim 1,
Step b),
The first train enters a new area, a new train enters an area where the first train is located, a train or a track failure in an area within the driving clearance range, the first allowable delay time 1 The driving control event information is generated in at least one of the situations in which the delay time of the train increases, the autonomous collaboration-based train control method. According to claim 1,
Step b),
Based on the region where the first train is located, priority is managed based on the class of the train type and the current location information of the train for neighboring trains located in the previous region and neighboring trains located in the subsequent region. Train control method. According to claim 1,
Step c),
According to the train priority, determine the schedule for the route of the neighboring train and the departure and arrival times of each point on the route in the order of the train with the highest priority, and repair to prevent train contention based on the determined schedule for the neighboring train. A vehicle control method based on autonomous collaboration, in which a sequence of operations with the neighboring train is determined using a model. The method of claim 5,
The hydraulic model provides an objective function for minimizing the delay time of individual trains, and constitutes at least one constraint for preventing train contention,
The above constraints are the delay time of arrival time, the maintenance of the train's distance, the order of operation with neighboring trains, the departure time limit of each train at each station, the stop time at each node, and the travel time of the train in section (p) Or it includes at least one or more of the constraints on the movement type selection, autonomous collaboration based train control method. The method of claim 6,
The objective function (g _i ) of the hydraulic model is represented by Equation 1 below to minimize the total delay time of the train i, an autonomous collaboration-based train control method.
[Equation 1]

Q _i : Set of platforms where train i passes
C _i : delay cost of train i

: Platform of train i

Delay time from The method of claim 6,
The delay time constraint of the arrival time is that train i is represented by Equation 2 below to obtain a delay time value based on a schedule planned on each platform, an autonomous collaboration-based train control method.
[Equation 2]

: Section of train i

Arrival time at the end node

: Scheduled arrival time at the end node in section p of train i

: Platform of train i

Delay time from The method of claim 6,
The train maintenance limit of the train is shown in Equation 3 to maintain a preset safety interval in a section in which the neighboring trains that follow in the order of operation operate in the same direction, the autonomous collaboration-based train control method.
[Equation 3]

: Section of train i

Arrival time at the end node

: Section of train i

Departure time at the end node

: 1 if train i starts before j in section p, 0 otherwise
H _q : Safety clearance at node q
H _r : Safety test at node r The method of claim 6,
The constraint for maintaining the distance of the train is shown in Equation 4 to maintain a predetermined safety interval in a section in which the neighboring trains that follow in the order of operation operate in different directions, an autonomous collaboration-based train control method.
[Equation 4]

: Section of train i

Arrival time at the end node

: Section of train i

Departure time at the end node

: 1 if train i starts before j in section p, 0 otherwise

: Set of sections where train i can pass in the up direction

: Set of sections where train j can pass in the down direction
N _i : Set of neighbor trains of train i
H _q : Safety clearance at node q
H _r : Safety test at node r The method of claim 6,
The operation order matching constraint with the neighboring train is shown in Equation 5 below to be determined by sharing with the neighboring train, the autonomous collaboration based train control method.
[Equation 5]

: Input value
N _i : Set of neighbor trains of train i
P _i : Set of sections that train i can pass
P _j : Set of sections that train j can pass The method of claim 6,
A train control method based on autonomous collaboration, wherein the departure time constraints of trains at each station are shown in Equation 6 below.
[Equation 6]

: Section of train i

Departure time at the end node

: When the departure time is restricted from the platform, the section of train i

Planned departure time at the end of the bar
Q _i : set of platforms on which train i passes The method of claim 6,
The stop time constraint at each node is shown in Equation 7 below to determine the stop time at each node, the autonomous collaboration based train control method.
[Equation 7]

: Minimum stop time of train i at node r

: Section of train i

Arrival time at the end node

: Section of train i

Departure time at the end node

: section

At the beginning of the train, the speed of train i

Is a step, and if the velocity at the end node is n steps, 1 or 0 The method of claim 6,
In the section (p), the travel time limitation of the train is shown in Equation (8) to determine the travel time according to the operation pattern for each section.
[Equation 8]

: Section of train i

Arrival time at the end node

: Section of train i

Departure time at the end node
P _i : Set of sections that train i can pass

: The train i has the speed step of the node starting at p

Is the step, and the maximum value of the time it takes to move to the form where the end node's velocity step is n

: The train i has the speed step of the node starting at p

Is a step, and the minimum value of the time it takes to move to the form where the end node's velocity step is n.

: section

At the beginning of the train, the speed of train i

Is a step, and if the velocity at the end node is n steps, 1 or 0 The method of claim 6,
In the section (p), the constraint on the movement type selection of the train is represented by Equation 9 below, and the autonomous collaboration based train control method.
[Equation 9]

: section

At the beginning of the train, the speed of train i

Is a step, and if the velocity at the end node is n steps, 1 or 0
P _i : Set of sections that train i can pass According to claim 1,
Step d),
d-1) initializing with the route and schedule information (TRS _i ) for each train determined in step c) and sharing with the neighboring train;
d-2) each train i forms a neighbor association {I, j} for each neighbor train j, and performs the collaboration algorithm; And
d_3) if it is determined that there is no improvement in train delay time with all neighboring associations after repeatedly performing the collaboration algorithm, the step of ending the collaboration algorithm,
The collaboration algorithm

Autonomous collaboration based train control method that is a process. The method of claim 16,
remind

The process is,
To minimize the total delay time of train i, the objective function (g _i ) defined by Equation (1) is calculated based on the mixed-integer linear programming (MILP) solver to calculate the optimal solution (

,

) And the amount of change in the objective function expressed by the following equation (10)

);
The amount of change in his objective function to the neighboring union (

) Information, and information about the change in the objective function of the neighboring association (

);
The amount of change in the objective function of train i (

) Is the amount of change in the objective function of all neighboring unions (

), the optimal solution

,

), and passing the changed information to a neighboring union, autonomous collaboration based train control method.
[Equation 1]

[Equation 10]

Q _i : Set of platforms where train i passes
C _i : delay cost of train i

: Platform of train i

Delay time from The method of claim 17,
If the solution set of the TRS _i W _i

Is defined by the following equation 11, autonomous collaboration based train control method.
[Equation 11]

:

Input values in the order of the neighboring trains except

Images