Train operation control method and system and information execution method

Abstract

The invention provides a train operation control method and system and an information execution method, and can be applied to the technical field of train operation control. The train operation control method comprises the following steps: receiving first environment data sent by trackside equipment, and train state data and second environment data sent by vehicle-mounted equipment of each train in an operation state in a train cluster; processing the first environment data, the second environment data of each train and the train state data based on the lines where each train and the trackside equipment are located, and obtaining the line running states of the lines; determining an abnormal line from the plurality of lines based on the respective line operation states of the plurality of lines; and on the basis of the line operation state of the abnormal line, operation control information of at least one target train which is running or is about to run on the abnormal line in the train cluster is determined, and the operation control information is sent to the at least one target train, so that cooperative control over the at least one target train is achieved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of train operation control, in particular to a train operation control method, system and information execution method. BACKGROUND

[0002] With the continuous improvement of the intelligent demand of rail transit, the train operation control system is also constantly iterated and upgraded, which has evolved from the traditional communication-based train control system (CBTC, Communication Based Train Control System) to the more efficient train autonomous operation system based on vehicle-to-vehicle communication (TACS, Train Autonomous Circumambulate System).

[0003] However, in the research process, it is found that in the intelligent upgrading process of the current train operation system, there is still a technical problem that the train has weak perception ability to the environment, and it is difficult to realize the cooperative control between trains based on the change of the environment. SUMMARY

[0004] In view of the above problems, the present disclosure provides a train operation control method, system, information execution method, system, device, medium and program product.

[0005] According to a first aspect of the present disclosure, a train operation control method is provided, comprising: receiving first environment data sent by a trackside device, and train state data and second environment data sent by a vehicle-mounted device of each train in a running state in a train cluster; based on the respective lines of each train and the trackside device, processing the first environment data, and the second environment data and the train state data of each train, to obtain the respective line operation states of the multiple lines; based on the respective line operation states of the multiple lines, determining an abnormal line from the multiple lines; based on the line operation state of the abnormal line, determining the operation control information of at least one target train in the train cluster which is running or to be running on the abnormal line, and sending the operation control information to the at least one target train, so as to realize the cooperative control of the at least one target train.

[0006] According to an embodiment of the present disclosure, the trackside devices are multiple; the first environment data is collected by the multiple trackside devices; and the first environment data, the second environment data and the train state data of each train are processed based on the lines on which the trains and the trackside devices are respectively located to obtain the line operation states of the multiple lines respectively, including: based on the lines on which the trains are operated and the lines on which the multiple trackside devices are located, the first environment data, the second environment data and the train state data of each train are divided into first environment sub-data sets, second environment sub-data sets and state sub-data sets respectively matched with the multiple lines; for each line, the first environment sub-data set, the second environment sub-data set and the state sub-data set matched with the line are subjected to data analysis based on the multiple sections included in the line to determine the section operation states of the multiple sections respectively; and the state marking of each section is performed on a preset line map based on the section operation states of the multiple sections of each line to obtain the operation states of the multiple lines respectively; wherein the first environment sub-data set includes first environment sub-data of the multiple sections of the line respectively, the second environment sub-data set includes second environment sub-data of the multiple sections of the line respectively, and the state sub-data set includes train state sub-data of the multiple sections of the line respectively.

[0007] According to an embodiment of the present disclosure, the first environment sub-data includes a first weather condition and a first section track condition; the second environment sub-data includes a second weather condition and a second section track condition; and the train state sub-data represents the operation of the train in the section; wherein, based on the multiple sections included in the line, the first environment sub-data set, the second environment sub-data set and the state sub-data set matched with the line are subjected to data analysis to determine the section operation states of the multiple sections respectively, including: for each section, based on the first weather condition and the second weather condition, a target weather condition is determined; based on the first section track condition and the second section track condition, a target section track condition is determined; and based on the target weather condition, the target section track condition and the train state sub-data, the section operation state of the section is determined.

[0008] According to an embodiment of the present disclosure, the line operation state of the abnormal line includes the track adhesion states of the sections and the operation state of a target train running on the abnormal line; and based on the line operation state of the abnormal line, the operation control information of at least one target train running on or to be running on the abnormal line in the train cluster is determined, including: based on a preset weather prediction model, the track adhesion states of the sections and the operation state of the target train running on the abnormal line, the abnormal degree of the abnormal line is determined; in the case that the abnormal degree is a first abnormal degree, a train operation plan of the at least one target train is generated; and based on the train operation plan and the track adhesion states of the sections, the operation control information is generated.

[0009] According to an embodiment of the present disclosure, the train state sub-data comprises: a train idling detection result; the train idling detection result comprises an idling state value, an idling occurrence time period, an idling occurrence position, and an idling acceleration; the idling acceleration is one of parameters for reflecting a track adhesion state; the train idling detection result is obtained by detecting the train as follows: in a case where a speed of the train is in a first speed range, acceleration or speed difference detection is performed on a wheel shaft driven by a traction motor in the train to obtain a first detection result, the speed difference being a speed difference between the wheel shaft and any wheel shaft in the train; in a case where a first acceleration of a target wheel shaft represented by the first detection result is greater than a preset acceleration threshold or a first speed difference is greater than a preset speed difference threshold, it is determined that the train idles, and an actual output traction force is changed from a first traction force to a second traction force, the first traction force being greater than the second traction force; in a case where a second acceleration of the target wheel shaft is less than or equal to the preset acceleration threshold or a second speed difference is less than or equal to the preset speed difference threshold, the second traction force is updated at a preset gradient until the updated second traction force is consistent with a target traction force; and a difference between the first acceleration and the preset acceleration threshold is taken as the idling acceleration.

[0010] According to an embodiment of the present disclosure, the train state sub-data comprises: a train idling detection result; the train idling detection result comprises an idling state value, an idling occurrence time period, an idling occurrence position, and an idling acceleration; the idling acceleration is one of parameters for reflecting a track adhesion state; the train idling detection result is obtained by detecting the train as follows: in a case where a speed of the train is in a first speed range, acceleration or speed difference detection is performed on a wheel shaft driven by a traction motor in the train to obtain a first detection result, the speed difference being a speed difference between the wheel shaft and any wheel shaft in the train; in a case where a first acceleration of a target wheel shaft represented by the first detection result is greater than a preset acceleration threshold or a first speed difference is greater than a preset speed difference threshold, it is determined that the train idles, and an actual output traction force is changed from a first traction force to a second traction force, the first traction force being greater than the second traction force; in a case where a second acceleration of the target wheel shaft is less than or equal to the preset acceleration threshold or a second speed difference is less than or equal to the preset speed difference threshold, the second traction force is updated at a preset gradient until the updated second traction force is consistent with a target traction force; and a difference between the first acceleration and the preset acceleration threshold is taken as the idling acceleration.

[0011] According to an embodiment of the present disclosure, the method further comprises: in a case where the coasting deceleration value or the coasting acceleration value of the first train in the train cluster is obtained, determining a second train that is on the same line as the first train and is located behind the first train; and sending the coasting deceleration value and the coasting occurrence position, or the coasting acceleration value and the coasting occurrence position to the second train, so that the second train performs train control based on the coasting deceleration value or the coasting acceleration value respectively when the second train travels to the coasting occurrence position or the coasting occurrence position.

[0012] According to a second aspect of the present disclosure, an information execution method applied to a train is provided, comprising: in response to the train receiving operation control information, determining a departure time point and a travel speed curve based on a train operation plan included in the operation control information, wherein the operation control information is obtained by the train operation control method described above; determining a braking parameter matched with a track adhesion state of each section based on the track adhesion state of each section included in the operation control information; and performing operation control on the train based on the departure time point, the travel speed curve and the braking parameter.

[0013] According to a third aspect of the present disclosure, a train operation control system is provided, comprising: a control center, a trackside device and an on-board device; the trackside device is configured to collect first environment data through a trackside sensor and send the first environment data to the control center; the on-board device is configured to collect second environment data through an on-board sensor, perform operation state detection on the train to obtain train state data, and send the second environment data and the train state data to the control center, wherein the on-board device is further configured to receive operation control information sent by the control center and perform train operation control based on the operation control information; and the control center is configured to execute the train operation control method described above.

[0014] According to an embodiment of the present disclosure, the control center comprises: a computing device, a storage device and a network device; the computing device is configured to provide computing resources; the storage device is configured to provide storage resources; and the network device is configured to provide network resources; the computing device is further configured to: determine a priority of a to-be-processed task based on a type of the to-be-processed task, wherein the to-be-processed task comprises a pre-prepared processing task for the first environment data, the second environment data and the train state data; and allocate computing resources, storage resources and network resources to the to-be-processed task based on the priority.

[0015] A fourth aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to perform the above method.

[0016] The fifth aspect of the present disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above method.

[0017] The sixth aspect of the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the above method.

[0018] According to the train operation control method of the present disclosure, by combining the train state data sent by the on-board equipment of each train in the train cluster in the running state and the second environment data with the first environment data sent by the trackside equipment, a more comprehensive cognition of the line surrounding environment and a more accurate grasp of the vehicle running state in each line are formed. And based on the lines where each device is located, these data are processed to obtain the running state of each line, and then the abnormal line is located. And based on the abnormal line state, the running control information of the target train running and to be running on the line is determined and issued, so that at least one target train makes a coordinated action based on the same abnormal environment state. Since this method not only performs more comprehensive and multi-dimensional autonomous perception of the line and the surrounding environment, but also generates running control information for dynamic coordinated adjustment of multiple target trains based on environmental changes. Therefore, at least part of the technical problems that the train has weak perception ability to the environment and is difficult to realize coordinated control between trains based on environmental changes are solved, and the train realizes more accurate perception of the environment, and the technical effect of coordinated and efficient response between trains around the environmental abnormal situation is realized. BRIEF DESCRIPTION OF DRAWINGS

[0019] The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure, taken in conjunction with the accompanying drawings, in which:

[0020] Figure 1 The application scenario diagram of the train operation control method, system and information execution method according to the embodiments of the present disclosure is schematically shown;

[0021] Figure 2 The flowchart of the train operation control method according to the embodiments of the present disclosure is schematically shown;

[0022] Figure 3 The flowchart of the information execution method according to the embodiments of the present disclosure is schematically shown;

[0023] Figure 4 The flowchart of the train idling detection according to the embodiments of the present disclosure is schematically shown;

[0024] Figure 5 The flowchart of the train coasting detection according to the embodiments of the present disclosure is schematically shown;

[0025] Figure 6 A flowchart of a train operation control method according to another embodiment of the present disclosure is schematically shown;

[0026] Figure 7 A schematic diagram of a train operation control system according to an embodiment of the present disclosure is schematically shown;

[0027] Figure 8 An architectural diagram of an on-board device according to an embodiment of the present disclosure is schematically shown;

[0028] Figure 9 A structural block diagram of a train operation control system implementing train-road-cloud collaboration according to an embodiment of the present disclosure is schematically shown;

[0029] Figure 10 A block diagram of an electronic device adapted to implement a train operation control method and an information execution method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0030] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it is to be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. However, it will be apparent to one skilled in the art that one or more embodiments can be practiced without these specific details. In other instances, well-known structures and techniques have been omitted in order to avoid obscuring the concepts of the present disclosure.

[0031] The terms used herein are merely used to describe specific embodiments and are not intended to limit the present disclosure. The terms "include", "comprise", and the like used herein indicate the presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0032] All terms used herein, including technical and scientific terms, have the same meanings as those generally understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of the specification, and should not be interpreted in an idealized or overly formal manner.

[0033] In the case of using expressions similar to "at least one of A, B, and C, etc.", it is generally to be interpreted as including one or more of the same as the meaning generally understood by one of ordinary skill in the art (for example, "a system having at least one of A, B, and C" should include but not be limited to a system having A alone, a system having B alone, a system having C alone, a system having both A and B, a system having both A and C, a system having both B and C, and / or a system having A, B, and C together, etc.).

[0034] It should be noted that the train operation control method, system and information execution method of the present disclosure can be used in the field of train operation control technology, and can also be used in any field other than the field of train operation control technology, such as the field of computer technology. The application field of the train operation control method, system and information execution method of the present disclosure is not limited.

[0035] In the technical solution of the present application, the user information (including but not limited to user personal information, user image information, user equipment information such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards of relevant countries and regions, necessary security measures are taken, public order and good customs are not violated, and appropriate operation portals are provided for users to choose authorization or refusal.

[0036] In the research process, it is found that the TACS system in the related art, compared with the traditional CBTC system, although the ground function is restructured, the regional controller is cancelled, and the ground interlocking logic controller is simplified. However, considering that the vehicle undertakes the fundamental task of passenger transportation in the urban rail automation system, the evolution of the train operation control system from the CBTC system to the TACS system has not really decoupled, restructured the whole vehicle system architecture, function, hardware computing power, etc. level, has not carried out system design from the starting point of train intelligent autonomous operation, has not taken environmental uncertainty factors as the control input of train autonomous operation, and in special extreme cases, it will affect the train driving safety.

[0037] In the traditional rail transit operation, signal control is mainly based on ground centralized control and individual train control, and lacks intelligent perception of train autonomous control and train cluster collaborative control mode characterized by information sharing. In terms of environmental perception, the rain and snow mode of the existing system is mainly set by the dispatcher through external information to understand the weather condition and manually set the rain and snow mode, and the automation and intelligent level is low. The dispatcher lacks more input for the judgment of rail surface sliding.

[0038] In the train operation control process, the train lacks the perception of the environment, the control input is less, the safety protection has blind spots, and the means to deal with extreme weather is scarce. In terms of train state perception, in the train operation control, the train lacks real-time grasp of the train traction, braking characteristics, real-time load of the train, train traction and braking capacity values, and the control mechanism of the train idling and sliding. When the track surface is affected by external conditions such as rain, snow, ice, frost, fallen leaves, and poor maintenance state, the adhesion between the train wheel and the track surface decreases, the train braking distance is extended, and the train safety braking distance cannot be guaranteed. At this time, the dispatch personnel need to manually intervene to set the corresponding strategy, and the automation and intelligent level is low. The dispatch personnel lack more input for the judgment of the track surface sliding condition, and cannot timely and accurately intervene in the train operation. In summary, the train lacks autonomous perception ability, and cannot realize real-time dynamic adjustment and active safety protection of the train operation control according to the changes of the external environment. It is urgent to improve the autonomous perception, autonomous operation and active protection ability of the train operation.

[0039] In addition, with the application of intelligent algorithms such as image processing, deep learning and neural network, the computing power and performance of the traditional control center and the vehicle-mounted hardware platform cannot meet the requirements. It is urgent to upgrade the control center and the vehicle-mounted hardware platform to improve the data storage and computing ability of the control center and the vehicle-mounted hardware platform. At the same time, the number of control center and vehicle-mounted control devices should be reduced as much as possible.

[0040] Therefore, the embodiment of the present disclosure provides a train operation control method, which comprises the following steps: receiving first environment data sent by a trackside device, and train state data and second environment data sent by a vehicle-mounted device of each train in a running state in a train cluster; processing the first environment data, and the second environment data and the train state data of each train based on the respective lines of each train and the trackside device, to obtain the respective line operation states of a plurality of lines; determining an abnormal line from the plurality of lines based on the respective line operation states of the plurality of lines; determining operation control information of at least one target train in the train cluster which is running on or to be running on the abnormal line based on the line operation state of the abnormal line, and sending the operation control information to the at least one target train, so as to realize the cooperative control of the at least one target train.

[0041] Figure 1 The application scenario diagram of the train operation control method, system and information execution method according to the embodiment of the present disclosure is schematically shown.

[0042] As Figure 1As shown, the application scenario 100 according to this embodiment can include a control center 101, a network 102, trackside equipment 103 and onboard equipment 104. The network 102 is a medium for providing communication links between the control center 101, the trackside equipment 103 and the onboard equipment 104. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0043] The control center 101 can be composed of a computing power network cloud platform, can receive first environment data sent by the trackside equipment, and train state data and second environment data sent by onboard equipment of each train in a running state in the train cluster, so as to realize train intelligent scheduling, train-road collaborative perception information fusion processing, environment perception data processing based on artificial intelligence (AI), and train cluster collaborative control, safety protection based on "train-road-cloud" collaboration, etc. based on the above data.

[0044] The trackside equipment 103 is installed at the roadside area of each line, used to collect first environment data, and send the first environment data to the control center 101 and the onboard equipment 104.

[0045] The onboard equipment 104 is deployed on the train, which can perform environment perception and vehicle state perception, such as collecting second environment data, detecting the running state of the train to obtain train state data, and sending the second environment data and the train state data to the control center. The onboard equipment is also used to receive running control information sent by the control center, and perform train running control based on the running control information. Among them, the onboard equipment 104 located in different vehicles can perform real-time transmission of data, such as transmission of position, speed, idling detection result, and coasting detection result.

[0046] It should be noted that the train running control method provided by the embodiment of the present disclosure can generally be executed by the control center 101. The train running control method provided by the embodiment of the present disclosure can also be executed by a server or a server cluster different from the control center 101 and capable of communicating with the trackside equipment 103 and the onboard equipment 104. The information execution method provided by the embodiment of the present disclosure can generally be executed by the onboard equipment 104. The train running control method provided by the embodiment of the present disclosure can also be executed by a server or a server cluster different from the onboard equipment 104 and capable of communicating with the control center 101 and the onboard equipment 104.

[0047] It should be understood that Figure 1 The number of control centers, trackside equipment and onboard equipment in the above description is only illustrative. According to the needs of implementation, there can be any number of control centers, trackside equipment and onboard equipment.

[0048] The following will be based onFigure 1 The described scenario is achieved by Figures 2-7 The method of the disclosed embodiment is described in detail.

[0049] Figure 2 The flowchart of the train operation control method according to the embodiment of the present disclosure is schematically shown.

[0050] As Figure 2 shown, the method includes operations S210-S240, which can be performed by the control center.

[0051] In operation S210, the first environment data sent by the trackside device, and the train state data and the second environment data sent by the on-board device of each train in the running state in the train cluster are received.

[0052] In operation S220, the first environment data, and the second environment data and the train state data of each train are processed based on the respective lines on which each train and the trackside device are located, to obtain the respective line operation states of the multiple lines.

[0053] In operation S230, the abnormal line is determined from the multiple lines based on the respective line operation states of the multiple lines.

[0054] In operation S240, the operation control information of at least one target train in the train cluster that is running or to be running on the abnormal line is determined based on the line operation state of the abnormal line, and the operation control information is sent to the at least one target train, so as to realize the cooperative control of the at least one target train.

[0055] The trackside device includes a wayside perception module, a train-ground communication module, etc. The trackside device can be used to detect the environment data and vehicle operation data within the detection range of the device; the first environment data can include the environment data and vehicle operation data within the detection range of each trackside device. The environment data can be, for example, track surface condition data or weather state data, etc. The vehicle operation data can be, for example, vehicle speed, vehicle position, etc.

[0056] The train-ground communication module can be used to send the acquired sensor data to the control center and the on-board device. The trackside device can be, for example, a track state sensor, an environmental camera, a temperature and humidity sensor, a water accumulation sensor, a speed sensor, etc.

[0057] The multiple trackside devices can be deployed at the trackside through a preset deployment strategy to cover the road condition perception of key areas such as turnouts, curves, tunnel entrances, etc. The perception information is transmitted to the on-board operation control platform and the control center through the train-ground wireless network.

[0058] The vehicle-mounted device can be used to collect environmental data around the train or detect train operation state to obtain train state data. The vehicle-mounted device can include a perception device and a detection device, etc. The perception device can be, for example, a camera, a laser radar, a millimeter wave radar, a combined inertial navigation, a speed sensor, a running gear sensor, etc. The state detection device can be, for example, a coasting detection device, an idling detection device, etc.

[0059] In determining the respective line operation state of each line, the first environmental data, and the second environmental data and the train state data of each train can be processed. For example, the first environmental data, and the second environmental data and the train state data of each train can be divided into different line data pools based on the line information included in each of them, so as to avoid confusion between different lines.

[0060] The data pool of each line can determine whether the line state of each line is abnormal based on the data content included in each data pool, so as to determine the line operation state of each line.

[0061] The line operation state of each line can be used to reflect whether the line is abnormal, which can include the following aspects, such as the track surface state of the line and the operation state of the train running on the line, specifically, the track surface state is that there is snow in multiple sections, and the overall line is slippery. The operation state of the train can be that the train has a skid phenomenon, or the train has a fault, etc.

[0062] In some embodiments, the Simultaneous Localization and Mapping (SLAM) technology can be used to determine the line operation state of different lines based on the first environmental data, the second environmental data and the train state data obtained in real time.

[0063] In determining the abnormal line, the line operation state can be analyzed to determine whether each line is an abnormal line. And / or for each line, the track adhesion coefficient of each section in the line and the train state running on the line are used to determine whether the line is an abnormal line. Alternatively, the weather condition, the train operation state and the track surface state can be compared with the respective preset rules respectively, and the comparison results of the three aspects are combined to determine whether it belongs to an abnormal state.

[0064] For the abnormal line, the abnormal degree of the abnormal line can be determined based on the line operation state of the abnormal line, and the operation control information for at least one target train can be generated based on the generation strategy matched with the abnormal degree, so as to realize the cooperative control of the at least one target train.

[0065] According to the train operation control method of the present disclosure, by combining the train state data and the second environment data sent by the on-board equipment of each train in the train cluster in the running state with the first environment data sent by the trackside equipment, a more comprehensive understanding of the line surrounding environment and a more accurate grasp of the vehicle running state in each line are formed. And based on the lines of each device, these data are processed to obtain the running state of each line, and then the abnormal line is located. And based on the abnormal line state, the running control information of the target train running and to be running on the line is determined and issued, so that at least one target train makes a coordinated action based on the same abnormal environment state. Since this method not only performs more comprehensive and multi-dimensional autonomous perception of the line and the surrounding environment, but also generates running control information for dynamic coordinated adjustment of multiple target trains based on environmental changes. Therefore, at least part of the technical problems that the train has weak perception ability to the environment, and it is difficult to realize the coordinated control between trains based on environmental changes are solved, the more accurate perception of the train to the environment is realized, and the technical effect of the coordinated and efficient response of the trains around the environmental abnormal situation is realized.

[0066] According to an embodiment of the present disclosure, the trackside equipment is multiple; the first environment data is obtained by the multiple trackside equipment; based on the lines of each train and the trackside equipment, the first environment data, and the second environment data and the train state data of each train are processed to obtain the line running state of each of the multiple lines, which can include the following operations.

[0067] Based on the lines on which each train runs and the lines on which the multiple trackside equipment is located, the first environment data, and the second environment data and the train state data of each train are divided into first environment sub-data sets, second environment sub-data sets and state sub-data sets respectively matched with the multiple lines; for each line, based on the multiple sections included in the line, the first environment sub-data set, the second environment sub-data set and the state sub-data set matched with the line are subjected to data analysis to determine the section running state of each of the multiple sections; based on the section running state of each of the multiple sections of each line, the state marking of each section is performed on the preset line diagram to obtain the running state of each of the multiple lines; wherein the first environment sub-data set includes the first environment sub-data of each of the multiple sections of the line, the second environment sub-data set includes the second environment sub-data of each of the multiple sections of the line, and the state sub-data set includes the train state sub-data of each of the multiple sections of the line.

[0068] The multiple trackside equipment can be arranged in the corresponding sections of each line, therefore, by sorting the first environment data, the first environment sub-data of each of the multiple sections can be obtained.

[0069] In the operation state determination of multiple lines, the disordered data can be divided into respective matching lines through line division to obtain the first environment sub-data set, the second environment sub-data set and the state sub-data set respectively matched with each line.

[0070] For the first environment sub-data set, the second environment sub-data set and the state sub-data set of each line, the section operation state of each section can be determined by the first environment sub-data, the second environment sub-data and the train state sub-data corresponding to each section in each data set, for example, the first environment sub-data indicates that there is snow in section 1, the second environment sub-data indicates that there is snow and obstacle in section 1, and the train state sub-data indicates that the train is slipping in section 1, then section 1 can be marked as slippery, and the adhesion coefficient of section 1 can be calculated.

[0071] The adhesion coefficient of section 1 can be calculated and sent by the train passing through the section 1, or can be calculated by the control center. When multiple trains pass through the section 1, the train state sub-data, the first environment sub-data and the second environment sub-data of multiple trains can be integrated to obtain the state sub-data of the section. In some embodiments, on the basis of the above, the state sub-data can also be determined in combination with the adhesion coefficients of multiple trains.

[0072] Based on the operation state of each section of each line, the visualization marking can be completed on the preset line map to generate the overall operation state of the line.

[0073] For example, the color and icon can be rendered in the corresponding section area through the pre-drawn line map, for example, if section 1 is normal, the position of section 1 in the map is filled with a green block.

[0074] When the overall operation state of the line is determined, the preset line state evaluation standard can be combined to determine whether the overall line is abnormal, for example, if the normal section ratio is greater than 80%, the overall state of the line is normal.

[0075] According to the embodiments of the present disclosure, the perception layer can realize train autonomous positioning and external environment perception, which improves the train's perception ability of the external environment, and through the fusion of the first environment data collected by the trackside equipment and other train perception data, the automatic marking of the line state under adverse weather such as rain, snow, ice and frost can be realized, and the autonomous perception of the front and rear trains and track foreign objects can be realized. Based on the satellite navigation system, vision, inertial navigation, radar and other multi-source information fusion, the real-time generation and update of the operation state map of different lines and different sections are realized, and the precise positioning of the line operation state is realized.

[0076] According to an embodiment of the present disclosure, the first environment sub-data includes a first weather condition and a first section track surface condition; the second environment sub-data includes a second weather condition and a second section track surface condition; the train state sub-data represents a running condition of the train on the section; based on a plurality of sections included in the line, performing data analysis on the first environment sub-data set, the second environment sub-data set and the state sub-data set matched with the line to determine a section running state of each of the plurality of sections can include the following operations.

[0077] For each section, a target weather condition is determined based on the first weather condition and the second weather condition; a target section track surface condition is determined based on the first section track surface condition and the second section track surface condition; and a section running state of the section is determined based on the target weather condition, the target section track surface condition and the train state sub-data.

[0078] For each section, when determining the target weather condition, the first weather condition and the second weather condition can be cross-verified. For example, the trackside equipment of Section 1 detects continuous light rain and a wind speed of 2 m / s, and the train passing through the section feeds back that the rain is slightly larger within a range of 50 meters in front of the train head and the visibility is 600 meters, so the target weather condition is determined to be light rain, slightly larger local rain and a visibility of 600 meters, thereby retaining the overall monitoring result of the trackside equipment and supplementing the dynamic details captured by the train.

[0079] When determining the target section track surface condition, the first section track surface condition and the second section track surface condition can be fused and cross-verified with each other, so as to obtain a more complete and accurate target section track surface condition.

[0080] The section running state can be determined in combination with the target weather condition, the target section track surface condition, the train state sub-data and an evaluation model. Alternatively, the section running state can be obtained by fusing the target weather condition, the target section track surface condition and the train state sub-data, and performing semantic analysis on the description sentence obtained after the fusion.

[0081] For example, the evaluation model can be pre-trained, and the section running state can be obtained by inputting the target weather condition, the target section track surface condition and the train state sub-data into the evaluation model.

[0082] According to an embodiment of the present disclosure, by fusing multi-source information, the target weather and the target track surface condition of the section are more accurately determined, and then the above information is combined with the train running condition to comprehensively determine the section running state, so as to more accurately position the section running state.

[0083] According to an embodiment of the present disclosure, the line operation state of the abnormal line comprises track adhesion states of each section and an operation state of a target train running on the abnormal line; and determining the operation control information of at least one target train running on or to be running on the abnormal line in the train cluster based on the line operation state of the abnormal line can comprise the following operations.

[0084] Based on the preset weather prediction model, the track adhesion states of each section, and the operation state of the target train running on the abnormal line, the abnormal degree of the abnormal line is determined; in the case that the abnormal degree is a first abnormal degree, a train operation plan of the at least one target train is generated; and based on the train operation plan and the track adhesion states of each section, the operation control information is generated.

[0085] The preset weather prediction model can be used to predict the weather conditions of each section of each line at different time periods, so as to determine the line operation state of each abnormal line at different future time based on the predicted weather conditions, the track adhesion states of each section, and the operation state of the target train running on the abnormal line.

[0086] The implementation of the preset weather prediction model is not limited, and can be implemented based on a neural network model, such as a Long Short-Term Memory (LSTM), a pre-trained language model, etc.

[0087] The abnormal degree can be divided into different levels, such as a first abnormal degree, a second abnormal degree, and a third abnormal degree, etc. Further, different abnormal degrees can represent different line states, such as that the first abnormal degree can be that the abnormal line has a mild abnormality, and the second abnormal degree can be that the abnormal line has a severe abnormality. Specifically, the first abnormal degree can be that the sliding degree of the abnormal line is mild sliding.

[0088] When the abnormal degree is determined as the first abnormal degree, an adapted operation plan can be generated for the target train running and to be running. For example, the arrival time is optimized, the acceleration and deceleration time is fine-tuned to ensure that the train punctuality rate is not affected. For the target train to be running, the departure time is re-planned to avoid the current peak pressure of the abnormal line, for example, a train originally planned to depart after 10 minutes is delayed to depart after 15 minutes to relieve congestion; if multiple target trains to be running need to enter the abnormal line, the departure interval is staggered to reduce the train density in the section, etc.

[0089] The train operation plan and the track adhesion states of each section can be packaged as the operation control information and sent to each target train.

[0090] According to an embodiment of the present disclosure, by combining the preset weather prediction model and the line operation state of the abnormal line, the segment operation state of each target train when arriving at each segment of the abnormal line is further analyzed, so as to realize the abnormal prediction and real-time detection of the abnormal line, and the cooperative operation plan of each train is made. The operation control information is generated by the train operation plan and the track adhesion state, so that the cooperative operation of each train can be realized, and the real-time state of each segment can also be grasped.

[0091] According to an embodiment of the present disclosure, the real-time perception and interaction of the information such as speed, position, track adhesion state, etc. between vehicles in the train cluster can be realized by relying on the existing signal system communication network, the optimal scheduling, cooperative control and safety protection of the train cluster are realized, and the train efficiency and safety are improved.

[0092] According to an embodiment of the present disclosure, through the information sharing between the train individuals and groups, the overall management of the traction and braking forces between different constituent units of the train can be realized, the influence of different frames and axle idling and slipping on the train operation control is reduced, the communication delay between the core functions of the train operation control is shortened through the deep fusion and interaction of the train core operation control system, the train response time and control accuracy are improved, and the train braking distance is shortened.

[0093] According to an embodiment of the present disclosure, by fusing the perception information of the vehicle and the trackside facility, the information in the cloud is shared in real time to the train that is driving, the train operation environment cooperative perception is realized through the fusion of the autonomous perception information and the cloud sharing information, the beyond-visual-range perception of the train is realized, and the car-car and car-ground cooperative decision is realized.

[0094] According to an embodiment of the present disclosure, through the AI perception algorithm, the ability of the deep neural network in data expression can be excavated, the network design and parameter optimization are combined, the recognition of different traffic objects and road surface environments can be realized, and the control input information is provided for the individual and group control of the train.

[0095] According to an embodiment of the present disclosure, the train cluster cooperative control layer can start from the global, realize the train operation curve planning and tracking control, use the control center to calculate the energy consumption optimal driving strategy online, dynamically regulate and control the whole vehicle power system, and realize the large-range multi-train cooperative control energy-saving driving.

[0096] Figure 3 A flowchart of an information execution method according to an embodiment of the present disclosure is schematically shown.

[0097] As shown in Figure 3 , the method comprises operations S310-S330.

[0098] At operation S310, in response to the train receiving the operation control information, a departure time point and a running speed curve are determined based on a train operation plan included in the operation control information, wherein the operation control information is obtained by using the train operation control method described above.

[0099] At operation S320, braking parameters matched with track adhesion states of each section are determined based on the track adhesion states of each section included in the operation control information.

[0100] At operation S330, the train is controlled based on the departure time point, the running speed curve, and the braking parameters.

[0101] After the train receives the operation control information, the train operation plan included in the operation control information can be parsed, and relevant parameters such as basic information such as planned departure time, estimated passing time of each section, section speed limit threshold, and station stopping time length are extracted.

[0102] In combination with the current state of the train, the actual departure time point of the train during operation can be determined by whether the train is in standby state, whether the on-board equipment is normal, and passenger boarding and alighting progress. For the train to be operated, the departure time in the operation plan can be used as a reference, and the station dispatching situation, such as whether the previous train is delayed, can be used to fine-tune the departure time point to ensure that the departure time point matches the overall scheduling demand of the line.

[0103] In determining the running speed curve, the section speed limit in the operation plan can be used as a reference, and the train performance parameters, track adhesion states of each section, and line slope information can be used to generate a continuous speed change trajectory.

[0104] For example, in the departure phase, the initial acceleration can be set according to the adhesion state of the starting section; in the section running phase, the transition nodes of acceleration, constant speed, and deceleration are planned according to the speed limit values of different sections to ensure smooth transition of the speed curve.

[0105] The track adhesion state can be divided into different state levels, including dry track condition, wet track condition, and low adhesion condition. Different state levels can correspond to different braking parameters. When the train senses changes in environmental temperature, humidity, and wheel-rail adhesion state through autonomous sensing capability, the braking parameters can be adjusted autonomously, and the train safety braking distance can be automatically adjusted under the action of the safety braking model to realize safety protection in the individual and group automatic driving process of the train. The braking parameter can be a guaranteed emergency brake rate (GEBR).

[0106] The braking parameters corresponding to different state levels can be constructed in advance, such as: for common low adhesion working condition scenes such as rain, snow, ice, frost, gear box oil, etc., a list of guaranteed emergency braking rates under corresponding typical different adhesion coefficient working conditions is formed through tests, and when the train is running, through on-board sensing, vehicle-road cooperative sensing, central weather forecasting, and identification through the control center sensing fusion model, the guaranteed emergency braking rate (GEBR) is accurately matched.

[0107] According to the embodiments of the present disclosure, the departure time point and the running speed curve are determined based on the operation control information, so that the train control is performed through the departure time point and the running speed curve, and the section congestion or the waste of transport capacity caused by time deviation is reduced. In combination with the matching of the braking parameters under the adhesion state of each section track, the train can adopt an adaptive braking strategy under different adhesion conditions to avoid the risks of slipping, sliding and the like caused by insufficient braking or excessive braking, and the train safety is ensured. That is, through the cooperative control of the departure time, the speed curve and the braking parameters, the train can not only be efficiently operated according to the plan in the complex line environment, but also dynamically adjust the operation mode according to the track adhesion change, reduce the operation failure caused by the environment or the track surface problem, and reduce unnecessary energy consumption and wheel-rail wear.

[0108] According to the embodiments of the present disclosure, the train state sub-data includes: a train idling detection result; the train idling detection result includes an idling state value, an idling occurrence period, an idling occurrence position, and an idling acceleration; the idling acceleration is one of the parameters for reflecting the track adhesion state; and the train idling detection result is obtained by detecting the train as follows.

[0109] In a case where the speed of the train is in a first speed range, an acceleration or a speed difference of a wheel shaft driven by a traction motor in the train is detected to obtain a first detection result, and the speed difference is a speed difference between the wheel shaft and any wheel shaft in the train; in a case where a first acceleration of a target wheel shaft represented by the first detection result is greater than a preset acceleration threshold or a first speed difference is greater than a preset speed difference threshold, it is determined that the train idles, and an actual output traction force is changed from a first traction force to a second traction force, and the first traction force is greater than the second traction force; in a case where a second acceleration of the target wheel shaft is less than or equal to the preset acceleration threshold or a second speed difference is less than or equal to the preset speed difference threshold, the second traction force is updated at a preset gradient until the updated second traction force is consistent with a target traction force; and a difference between the first acceleration and the preset acceleration threshold is taken as an idling acceleration.

[0110] The detection side for the idling detection is not limited, and can be realized by a train traction force management module in the train or by a control center based on data sent by the train.

[0111] The first speed range can be a low speed range, and a specific value thereof can be determined according to actual conditions.

[0112] Figure 4 A flowchart of performing train idling detection according to an embodiment of the present disclosure is shown schematically;

[0113] As shown in Figure 4 , performing train idling detection can include operation S410~operation S408.

[0114] In operation S401, wheel shaft speed acquisition and calculation are performed on the traction system.

[0115] Speed acquisition can be performed on the wheel shaft driven by the traction motor in the traction system, and speed difference and acceleration are calculated.

[0116] In operation S402, it is determined whether there is a target wheel shaft with a first acceleration greater than a preset acceleration threshold or a target wheel shaft with a first speed difference greater than a preset speed difference threshold. If the determination is yes, operation S403 is performed; if the determination is no, operation S401 is returned.

[0117] In operation S403, it is determined that the train idles, and an idling state value is fed back.

[0118] In operation S404, the actual output traction force is reduced.

[0119] That is, the actual output traction force is changed from a first traction force to a second traction force, and the first traction force is greater than the second traction force.

[0120] In operation S405, it is determined whether the second acceleration of the target wheel shaft is less than or equal to the preset acceleration threshold or the second speed difference is less than or equal to the preset speed difference threshold. If the determination is yes, operation S406 is performed. If the determination is no, operation S404 is returned.

[0121] In operation S406, the second traction force is updated at a preset gradient until the updated second traction force is consistent with the target traction force.

[0122] The actual output traction force can be gradually increased to follow the target traction force until the actual traction force is consistent with the target traction force.

[0123] In operation S407, the idling acceleration is calculated.

[0124] The idling acceleration is calculated when the actual traction force is consistent with the target traction force.

[0125] In operation S408, the idling state value or the idling state value and the idling acceleration are fed back.

[0126] At the same time, information such as the idling occurrence period and the idling occurrence position can be fed back.

[0127] In the case where the above idle running detection is implemented by the train traction force management module, the above information is fed back to the train operation control platform and the control center; in the case where the above idle running detection is implemented by the control center, the above information is fed back to the train operation control platform.

[0128] The idle running state value can be a preset value representing whether idle running occurs, for example, 0 can be set for the idle running state, and 1 can be set for the non-idle running state.

[0129] According to an embodiment of the present disclosure, by idle running detection when the train speed is in the first speed range, the idle running occurrence position, idle running acceleration and other data are determined, and the train and the control center both hold the above data through communication transmission, which on the one hand realizes real-time detection and modification of the train abnormal situation, and on the other hand can reflect the line condition through the train state to realize train cooperative control.

[0130] According to an embodiment of the present disclosure, the train state sub-data includes: train coasting detection results; the train coasting detection results include a coasting state value, a coasting occurrence time period, a coasting occurrence position and a coasting deceleration value; the coasting deceleration value is one of parameters reflecting the track adhesion state; the train idle running detection results are obtained by detecting the train as follows: the train coasting detection results are obtained by the following method.

[0131] In the case where the speed of the train is in the second speed range, the rotational shaft speed deviation detection is performed on a plurality of wheels in the same brake unit of the train to obtain a second detection result, the rotational shaft speed deviation detection is to subtract the rotational shaft speeds of the plurality of wheels from a rotational shaft speed threshold value, and to compare the plurality of rotational speed differences with a preset rotational speed difference threshold value, the rotational shaft speed threshold value is determined from the rotational shaft speeds of the plurality of wheels; in the case where it is determined that the second detection result represents that there is a rotational speed difference greater than the preset rotational speed difference threshold value, it is determined that there is a target wheel in the brake unit that is in a coasting state, and the brake force output mode is switched from unit control to wheel control, so as to switch the first brake force output to the target wheel to a second brake force, the first brake force being greater than the second brake force; in the case where it is determined that the target wheel switched to the second brake force is still in the coasting state and the coasting duration is greater than a preset duration, the electric brake function for the target wheel is turned off, and the pressure in the air brake cylinder for the target wheel is released; in the case where it is determined that the rotational shaft speed of the target wheel is in an ascending state, the air brake cylinder for the target wheel is inflated; in the case where it is determined that the target wheel is in a normal state, the coasting deceleration value is determined based on the current rotational shaft speed of the target wheel, the rotational shaft speed at the coasting start time and the coasting duration.

[0132] The detection method for the coasting detection is not limited, and can be implemented by a train brake force management module in the train, or can be implemented by the control center based on the data sent by the train.

[0133] The second speed range can be a high speed range, and a specific value thereof can be determined according to actual conditions.

[0134] Figure 5 A flowchart of train coasting detection according to an embodiment of the present disclosure is schematically shown.

[0135] As shown in Figure 5 The train coasting detection can include the following operations S501-S507.

[0136] In operation S501, the rotational shaft speed in the braking system is collected and calculated.

[0137] The rotational shaft speeds of multiple wheels in the train under the same braking unit are collected and calculated. In the calculation process, the rotational shaft speeds of the multiple wheels are subtracted from a rotational speed threshold value, and the multiple rotational speed differences are compared with a preset rotational speed difference threshold value. The rotational speed threshold value is the highest rotational speed from the rotational speeds of the multiple wheels.

[0138] In operation S502, whether there is a target wheel with a rotational speed difference greater than the preset rotational speed difference threshold value. If yes, operation S503 is performed. If no, operation S501 is returned.

[0139] In operation S503, it is determined that the target wheel is coasting, and the coasting state values of the multiple wheels are fed back.

[0140] In operation S504, the braking force of the target rotational shaft for the target wheel is reduced.

[0141] When coasting occurs, in order to fully utilize the braking force, the coasting control can be converted to shaft control on the basis of the frame control, and the braking force output to the target rotational shaft is reduced. When the coasting exceeds the specified time, the air brake request cuts off the electric brake, and the corresponding shaft air brake starts to gradually release the brake cylinder pressure to restore the shaft speed. When the shaft speed shows a trend of recovery, the brake cylinder pressure starts to charge, but the recovered brake cylinder pressure is not more than the brake cylinder pressure required by the current level and load.

[0142] In operation S505, it is determined whether the rotational speed difference of the target wheel is less than or equal to the preset rotational speed difference threshold value. If yes, operation S505 is performed. If no, operation S504 is performed.

[0143] In operation S506, a coasting deceleration value is calculated.

[0144] In operation S507, the coasting state values of the multiple wheels or the coasting state values and the coasting deceleration values of the multiple wheels are fed back.

[0145] At the same time, information such as the coasting occurrence period and the idling coasting position can be fed back.

[0146] When the multiple different braking units or the multiple target wheels are in the sliding, the average of the multiple sliding deceleration values can be taken as the sliding deceleration value of the whole vehicle, and the feedback is performed.

[0147] When the sliding detection is realized by the train braking force management module, the information is fed back to the train operation control platform and the control center, and the online main valve can be used for sending when sending; when the idling detection is realized by the control center, the information is fed back to the train operation control platform.

[0148] The sliding state value can be a preset value representing whether the train is in the sliding state, for example, the train in the sliding state can be set to 0, and the train not in the sliding state can be set to 1.

[0149] The train operation control platform can use the sliding deceleration value to perform automatic train control, and the control center can use the sliding deceleration value to perform train cluster optimization control.

[0150] According to the embodiments of the present disclosure, the threshold deceleration in the sliding state of the vehicle can be calculated through the sliding detection and the deceleration calculation, and sent to the control center. The control center can issue the sliding state to the train cluster through comprehensive analysis of the sliding states of different regions and different trains. The train can automatically adjust the driving and deceleration according to the sliding instruction, and can automatically select the emergency braking rate. When the rain and snow disaster weather causes large-area sliding on the whole line, the train can automatically adjust the operation plan, and mainly adjusts the interval operation time and other parameters on the train diagram level. When the sliding is serious, the system is degraded, and the manual driving mode is recommended.

[0151] According to the embodiments of the present disclosure, through the sliding detection when the train speed is in the second speed range, the sliding occurrence position, the sliding acceleration and other data are determined, and the train and the control center both hold the above data through communication transmission. On the one hand, real-time detection and modification of the train abnormal situation are realized, and on the other hand, the train state can reflect the line condition to perform train cooperative control.

[0152] According to the embodiments of the present disclosure, the above train control method can further include the following operations.

[0153] When the sliding deceleration value or the idling acceleration of the first train in the train cluster is obtained, a second train on the same line and located behind the first train is determined; the sliding deceleration value and the sliding occurrence position, or the idling acceleration and the idling occurrence position are sent to the second train, so that when the second train drives to the sliding occurrence position or the idling occurrence position, the train control is performed based on the sliding deceleration value or the idling acceleration, respectively.

[0154] According to an embodiment of the present disclosure, when the current train slips, the subsequent train can be informed in real time through the train-ground communication, and the control center cloud platform can directly issue an instruction, and the current train forms a train control strategy according to the positions and speeds of the front and rear trains and the working conditions, and issues a braking system and a traction system to realize active protection of train operation.

[0155] Figure 6 A flowchart of a train operation control method according to another embodiment of the present disclosure is schematically shown.

[0156] As shown in Figure 6 The method of operation control information generation and execution can include operations S601-S606.

[0157] In operation S601, the weather state perception of each section, the operation state perception of each train, and the track surface state perception of each section are obtained.

[0158] The weather state perception can be obtained based on the first weather condition included in the first environment sub-data, the second weather condition included in the second environment sub-data, and a preset weather prediction model.

[0159] The track surface state perception of each section can be obtained through the first section track surface condition included in the first environment sub-data and the second section track surface condition included in the second environment sub-data.

[0160] The operation state perception of each train can be obtained based on the train state data of each train.

[0161] In operation S602, the line operation state of the line is determined based on the weather state perception, the operation state perception of each train, and the track surface state perception of each section. In the case of a severe slip of the line operation state, operation S603 is performed; in the case of a light slip of the line operation state, operation S604 is performed; and in the case of no slip of the line operation state, operation S601 is performed.

[0162] The line operation state of the line can include the slip degree of the line, such as no slip, light slip, or severe slip.

[0163] The determination method of the line operation state is not limited, for example, by judging whether the weather is easy-to-slip weather, the number of vehicles or the total number of slips of the same section that occur in the slip or slip, and whether the track surface is an easy-to-slip track surface to determine the line operation state of each line. For example, when the weather is easy-to-slip weather, the number of vehicles or the total number of slips of the same section that occur in the slip or slip is greater than a preset value, and the track surface is an easy-to-slip track surface, it can be determined that the line operation state is severe slip.

[0164] In operation S603, the train is switched from the automatic driving mode to the manual driving mode.

[0165] In operation S604, the section sliding state of each section in the line is marked, and the original train operation plan of at least one target train of the line is adjusted to obtain operation control information.

[0166] In operation S605, the operation control information is sent to the at least one target train.

[0167] In operation S606, the target train implements operation control based on the operation control information.

[0168] For example, automatically adjusting acceleration and deceleration, automatically updating braking parameters, etc.

[0169] In operation S607, the operation control strategy is adjusted in the case where the target train determines that it has entered a next section with a different section operation state. For example, adjusting acceleration and deceleration, braking parameters, etc.

[0170] According to the embodiment of the present disclosure, by sliding detection and deceleration calculation, the threshold deceleration in the vehicle sliding state can be calculated and sent to the control center. The control center will issue a sliding state to the train group through comprehensive analysis of the sliding state of different areas and different trains. The train will automatically adjust the driving and braking force according to the sliding instruction, and can guarantee the automatic selection of the emergency braking rate. When a large-area sliding occurs on the whole line in a rain and snow disaster, the train can automatically adjust the operation plan, and mainly adjust the interval operation time and other parameters on the operation diagram level. In the case of serious sliding, the system is degraded, and the system enters the manual driving mode.

[0171] According to the embodiment of the present disclosure, through information sharing between individual trains and groups, the overall management of traction and braking force between different constituent units of the train is realized, the influence of different frames and shafts on the train operation control is reduced, the communication delay between the core functions of the train operation control system is shortened through deep fusion and interaction of the train core operation control system, the train response time and control accuracy are improved, the train braking distance is shortened, and the train is truly realized. Self-awareness, autonomous operation, and autonomous protection.

[0172] According to the embodiment of the present disclosure, at the vehicle-road cooperation level, relying on the existing signal system communication network, the real-time perception and interaction of information such as speed, position, and track adhesion between vehicles in the train cluster are realized, the optimal scheduling, cooperative control, and safety protection of the train cluster are realized, and the train efficiency and safety are improved.

[0173] Figure 7 A schematic diagram of a train operation control system according to an embodiment of the present disclosure is schematically shown.

[0174] As shown in Figure 7 The train operation control system includes a control center, a trackside device, and an on-board device.

[0175] The trackside device is configured to collect first environment data through a trackside sensor and transmit the first environment data to the control center.

[0176] The on-board device is configured to collect second environment data through an on-board sensor, detect a running state of the train to obtain train state data, and transmit the second environment data and the train state data to the control center. The on-board device is further configured to receive running control information transmitted by the control center and perform train running control based on the running control information.

[0177] The control center is configured to perform the train running control method.

[0178] The control center can be implemented by a computing power network cloud platform. Hardware devices of the computing power network cloud platform can include computing devices, storage devices, and network devices. The computing devices can be servers.

[0179] The control center, the on-board device, and the trackside device can communicate through a 5G comprehensive bearer. The on-board device can transmit running states of the train, such as position, speed, idling, and coasting, to the control center. The trains can transmit the above information through the on-board device. Meanwhile, the trackside device can transmit road environment perception and section state to the control center.

[0180] The control center can implement functions such as automatic train supervision (ATS), vehicle-road cooperation, integrated perception, and AI assistance.

[0181] According to an embodiment of the present disclosure, the control center includes computing devices, storage devices, and network devices. The computing devices are configured to provide computing resources. The storage devices are configured to provide storage resources. The network devices are configured to provide network resources.

[0182] The computing devices are further configured to determine a priority of a to-be-processed task based on a type of the to-be-processed task, wherein the to-be-processed task includes a pre-prepared processing task for the first environment data, the second environment data, and the train state data. The computing devices are further configured to allocate computing resources, storage resources, and network resources to the to-be-processed task based on the priority. The servers are computing resources of the computing power network cloud platform, responsible for processing various system business data and running various application programs, and can meet the needs of large-scale data processing and high-concurrency access.

[0183] The storage devices include hard disk arrays, solid state drives (SSDs), network attached storage (NAS), etc., and are configured to store a large amount of data in the system, such as train running data, train monitoring data, and environment perception information, and can implement safe storage and fast access of data.

[0184] The network device can include a switch, a router, a firewall, etc., and can realize communication between various components in the control center and with external systems.

[0185] The control center can abstract various computing resources such as central processing units (CPUs), graphics processing units (GPUs), etc., storage resources such as hard disks, solid state disks, memories, etc., and network resources, encapsulate them into unified resource objects, and provide a unified interface for upper-layer scheduling management, thereby realizing integration and scheduling of resources.

[0186] Virtualization technology can be used to virtualize physical resources into multiple logical resources, and each virtual machine can independently run an operating system and an application. At the same time, storage virtualization technology is used to virtualize multiple physical storage devices into a unified storage pool, realizing centralized management and allocation of storage resources.

[0187] The computing device in the control center can dynamically allocate computing resources, storage resources, and network resources based on the processing type of the task, and distinguish priorities. For example, an application for processing train operation control tasks has a high priority and is preferentially allocated computing resources, storage resources, and network resources. The priority of an application for processing tasks such as vehicle state monitoring and environmental perception data processing is relatively low, so when priority allocation is performed, if there is a conflict with a high-priority task, processing can be temporarily suspended to prioritize resource requirements of the high-priority task.

[0188] In some embodiments, greedy algorithms, genetic algorithms, simulated annealing algorithms, etc. can be used to improve the efficiency and performance of resource scheduling.

[0189] When the resource status of the control center changes, the computing device can timely adjust the resource allocation scheme by rescheduling tasks, migrating virtual machines, adjusting network configurations, etc., to ensure normal operation of the tasks and stability of the system.

[0190] The control center business level mainly includes functions such as environmental fusion perception, intelligent train operation scheduling, train cluster collaborative control, and AI assistance.

[0191] According to embodiments of the present disclosure, since urban rail transit data has characteristics such as large data volume and multi-source heterogeneity, the control center can realize dynamic allocation of computing resources and storage resources and running of different application software on the same platform, realize AI-based train operation environment perception and train cluster state perception, and provide decision support for train cluster collaborative control.

[0192] According to an embodiment of the present disclosure, based on the control center, a fusion perception system is constructed to form a standardized and unified service access. The system includes a device access module, a fusion perception module, a basic resource module, and a data output module, and realizes fusion processing of raw data of a camera, a laser radar, and a millimeter wave radar, and outputs real-time environment perception data for train cluster cooperative control.

[0193] According to an embodiment of the present disclosure, data fusion perception of the control center mainly includes four stages of data acquisition, data access, fusion analysis, and fusion processing. The data after fusion can be further used for event-level scene analysis for train cluster cooperative control input and AI large model training based on environment data.

[0194] According to an embodiment of the present disclosure, based on the control center, a train cluster working diagram based on real-time passenger flow and track section congestion data of passengers can be constructed, and scheduling optimization can be performed, such as adjusting a train operation plan, so as to realize the best matching of dynamic passenger flow changes, train dynamic running interval changes, and transport capacity.

[0195] According to an embodiment of the present disclosure, based on the control center, a train cluster cooperative control function is constructed according to train cluster running state information and train-road cooperative perception information, train cluster cooperative control is realized, information sharing such as train running speed, position, idling, and coasting is provided, control input is provided for train cluster cooperative control speed curve planning and tracking, and train running safety and efficiency are improved.

[0196] Figure 8 An architecture diagram of a vehicle-mounted device according to an embodiment of the present disclosure is schematically shown.

[0197] As shown in Figure 8 , the vehicle-mounted device mainly includes a perception device, a vehicle-mounted pre-processing module, a vehicle-mounted monitoring and perception platform, a train operation control platform, a vehicle-mounted display device, a vehicle-mounted network device, and a vehicle-ground wireless communication device.

[0198] The data perceived by the perception device can be pre-processed by the vehicle-mounted pre-processing module, such as data of Beidou positioning, a camera, a radar, and a running part sensor.

[0199] The brake sensor can be used for brake local control or for executing control instructions from the train operation control platform. Similarly, the traction force sensor can be used for traction force local control or for executing control instructions from the train operation control platform.

[0200] The train operation control platform can be responsible for train-level control functions, can integrate train control and operation management functions of an automatic train operation (ATO), traction / brake force management of a traction system, brake force management of a brake control unit (BCU), and other functions, realize function reconstruction and optimization to realize direct output of control instructions, and improve the overall vehicle control performance.

[0201] The train operation control platform can include a train traction force management module, a train brake force management module, a train control and management system (TCMS), an automatic train protection (ATP), a traction control unit (TCU), and a train automatic driving control module.

[0202] The train automatic driving module is composed of train speed curve control, precise parking, door and platform door management, and other functions, and realizes train start-up acceleration, interval operation such as cruise, coasting, train braking parking, door opening and closing, and other operations.

[0203] The train operation control platform can support an integrated application running environment shared by multiple subsystems, support simultaneous running of applications with different safety integrity levels (SIL) and different system requirements, support virtualization technology to realize simultaneous running of applications of different systems, support scheduling and communication of all hardware and software resources in the chassis, and support standard-compliant Ethernet communication functions.

[0204] The vehicle front-end processor can integrate network input / output (I / O) units, traction I / O units, brake I / O units, and signal system I / O unit functions, and can realize diversified driving, acquisition, and local logic centralized control with high safety level.

[0205] The vehicle front-end processor supports different SIL levels, supports simultaneous running of application functions, has vehicle mixed safety level input / output signal control and acquisition functions, supports IO board card management functions, supports standard-compliant Ethernet communication functions, and supports standard-compliant Time-Sensitive Networking (TSN) communication functions.

[0206] The vehicle-mounted Ethernet supports integrated and efficient transmission of multiple types of data, and can realize real-time and determinism of data flow end-to-end under shared media transmission of control data, media data, monitoring data, and operation and maintenance data.

[0207] The vehicle-mounted monitoring and sensing platform is composed of a main control board, a storage board, a power supply board, a switching board and an IO board. The main control board is responsible for internal board management, comprehensive diagnosis and TSN communication of the whole machine, the storage board is responsible for storage of original data, log files and fault information of the whole machine, the power supply board is responsible for power supply, the switching board is responsible for building internal dual-hundred-megabit Ethernet and providing maintenance interface, and the IO board is responsible for IO function of the whole machine and provides fault / alarm hard-wire output of each monitoring board.

[0208] Figure 9 A structural block diagram in which a train operation control system according to an embodiment of the present disclosure implements train-road-cloud cooperation is schematically shown.

[0209] As shown in Figure 9 The sensing device is composed of a camera, a laser radar, a millimeter wave radar, a combined inertial navigation system, a speed sensor and a running part sensor.

[0210] The vehicle-mounted camera is installed at the top central position in front of the train head and tail, ensuring clear vision in front of and behind the train, and is used for visual image data collection of the train operation environment, monitoring of obstacles, track conditions and signal marks in the train running direction and the like.

[0211] The image data collected by the vehicle-mounted camera is transmitted to the vehicle-mounted front-end processing module through a Gigabit Multimedia Serial Link (GMSL) interface. The vehicle-mounted front-end processing module can cache the image data of the vehicle-mounted camera and perform preprocessing such as contrast adjustment and sharpening, highlighting key features in the image.

[0212] The image processing algorithm running in the vehicle-mounted monitoring and sensing platform detects obstacles in the image. A deep learning-based method such as a convolutional neural network is used to identify obstacles in the image, such as pedestrians, vehicles and foreign objects on the track.

[0213] The laser radar can be embedded in front of the train head and tail, ensuring a large enough scanning range, and is used for three-dimensional space point cloud data collection and all-around monitoring of the environment around the train. The vehicle-mounted laser radar can emit laser beams and receive reflected signals, quickly constructing a three-dimensional model of the environment around the vehicle and providing accurate environmental sensing information for the train automatic driving system.

[0214] The vehicle-mounted laser radar can continuously scan the surrounding environment and construct and update the map. At the same time, combined with satellite navigation and an inertial measurement unit, the vehicle-mounted laser radar can provide accurate position information of the vehicle in three-dimensional space, with an accuracy of centimeters, providing position information for precise control and safety protection of the train.

[0215] By monitoring the objects around the vehicle in real time, the vehicle-mounted laser radar can issue an early warning in the event of a possible collision, display on the vehicle display screen, and issue an audible and visual alarm. If the mobile authority allows, the driver can take timely measures to avoid a collision. In the automatic driving mode, the system can automatically brake or quickly drive away to ensure the safety of the vehicle.

[0216] In an emergency situation, such as a sudden obstacle in front of the vehicle or a vehicle breakdown, the vehicle-mounted laser radar can quickly detect the danger and send an emergency braking command to the train operation protection module to trigger the emergency braking system to avoid a collision.

[0217] The point cloud data collected by the vehicle-mounted laser radar is transmitted to the vehicle-mounted front-end processing module through the Ethernet interface. The vehicle-mounted front-end processing module can filter and smooth the collected data to improve data quality. The vehicle-mounted front-end processing module can compress the data to reduce the data volume and improve the efficiency of data transmission and storage.

[0218] Target detection and recognition are performed in the vehicle-mounted monitoring and perception platform. The point cloud data collected by the vehicle-mounted laser radar is segmented by clustering algorithms and region growing algorithms to separate different target objects from the background. The vehicle-mounted monitoring and perception platform runs support vector machines and convolutional neural network algorithms for target recognition.

[0219] The vehicle-mounted monitoring and perception platform runs Kalman filtering and extended Kalman filtering algorithms for data fusion to improve the accuracy and reliability of environmental perception.

[0220] The millimeter wave radar is embedded in the front and rear of the vehicle and is used for obstacle detection data collection in front of and behind the train. The millimeter wave radar can work in bad weather conditions such as rain, snow, and fog, providing important protection for the safe operation of the train.

[0221] The vehicle-mounted millimeter wave radar can be connected to the vehicle-mounted front-end processing module through the Controller Area Network (CAN) interface or the Ethernet interface to realize data transmission and communication. The vehicle-mounted front-end processing module can filter, amplify, and analog-to-digital convert the collected data.

[0222] Based on the data collected by the millimeter wave radar and the processing results, the vehicle-mounted front-end processing module can provide decision support for the vehicle's automatic driving system or the driver. For example, when an obstacle is detected in front of the vehicle, an alarm is issued or automatic braking measures are taken.

[0223] The vehicle-mounted front-end processing module can also communicate with other control systems of the vehicle to control the traction, braking, and other parameters of the vehicle.

[0224] The vehicle-mounted monitoring and perception platform can realize multi-source data fusion processing of different sensors, and millimeter wave radar can realize SLAM technology mapping based on Beidou, vision, inertial navigation, radar and other multi-source information fusion to map the adhesion state of different lines and different sections, realize accurate positioning of the track adhesion, and realize fine perception and prediction of the adhesion state of different sections of the wheel and rail.

[0225] The vehicle-mounted monitoring and perception platform can run multi-sensor fusion algorithms such as fusion perception algorithms and fusion positioning algorithms, and can be used for fusion processing of externally collected data to provide control input for the train operation control device.

[0226] The vehicle-mounted monitoring and perception platform can obtain continuous real-time relative position information of the train through inertial navigation, and obtain absolute position information of the train through images, and realize continuous real-time positioning of the train through data fusion.

[0227] The train operation control platform can formulate train operation control decisions based on the results of target detection and recognition and multi-sensor fusion data.

[0228] The vehicle-mounted computing power network platform can realize dynamic resource management, support the registration and access of heterogeneous computing power such as central processing units (CPUs) and graphics processing units (GPUs), and provide fine-grained resource management and isolation.

[0229] The vehicle-mounted computing power network platform can realize resource scheduling and arrangement, support flexible mobilization of heterogeneous computing power nodes, realize flexible arrangement of tasks and node resources, and provide resource capabilities for upper function modules based on customized development of Kubemetes.

[0230] The vehicle-mounted computing power network platform can realize heterogeneous computing power adaptation, support the adaptation of heterogeneous computing power from the bottom layer to the application layer framework, and ensure the elastic migration and scheduling of applications on different computing power nodes.

[0231] The vehicle-mounted computing power network platform can realize the platform capabilities of intelligent computing, support data processing, AI training and inference framework, model services and other functions based on bottom-layer heterogeneous computing power.

[0232] The vehicle-mounted automatic driving module can realize automatic driving based on the analysis results of the data of the perception device of the vehicle-mounted monitoring and perception platform, and send traction instructions and levels to the train traction force management module, and send brake instructions and levels to the train brake force management module.

[0233] The vehicle-mounted monitoring and sensing platform can send the analysis result of the data sent by the sensing device to the vehicle-mounted safety protection module for brake analysis, so that the module sends an emergency brake instruction to the train brake force management module based on the analysis result.

[0234] When the train is in an automatic driving mode, the vehicle-mounted safety protection module can authorize the movement of the vehicle-mounted automatic driving module and send a brake parameter list, such as a GEBR list, to the vehicle-mounted automatic driving module. At the same time, the control center can also send environmental sensing, train running state, detection, and other information to the vehicle-mounted automatic driving module to realize comprehensive and accurate external environment sensing and train state sensing information for individual and group trains.

[0235] The trackside device can include a track inspection sensing module, a track inspection sensing processing module, a track inspection communication module, and the like. The track inspection sensing module can send track surface environment information to the trackside sensing processing module. The track inspection sensing processing module can aggregate and process the track surface environment information to obtain trackside sensing information, i.e., first environment data, and then send the information to the control center through the track inspection communication module. The control center can be a ground device.

[0236] Based on vehicle-mounted autonomous sensing, vehicle-road cooperative sensing information, and control center AI model assisted weather prediction, comprehensive and accurate external environment sensing and train state sensing information can be provided for individual and group trains, and collaborative driving and safety protection of individual and group trains can be realized.

[0237] According to embodiments of the present disclosure, through the architecture of "sensing-planning-decision control-execution" and "vehicle-road-cloud" collaborative control centering on trains, through data information sharing of individual, group, and control center levels, the external environment sensing capability of individual and group trains on track adhesion state is improved, the train operation control process is optimized, adaptive control of train traction and braking is realized, the purpose of active protection during train operation and group train collaborative control is met, the train operation control performance is improved, the train operation risk is reduced, and the train operation safety and efficiency are improved. At the same time, to meet the demand of high computing power for intelligent algorithms such as image recognition and multi-sensor fusion, a vehicle-mounted system architecture is constructed with the train operation control platform and the vehicle-mounted monitoring and sensing platform as the core, dynamic scheduling and management of local storage and operation resources of the train are realized, fusion of train operation control functions is realized, utilization rate and operation capacity of vehicle-mounted hardware resources are improved, the types and quantities of hardware devices are reduced, and the system life cycle cost is reduced.

[0238] The AI model running in the control center can realize historical data analysis under complex environments such as different seasons, different weather conditions, and different external environments, combined with comprehensive judgment of train individual and group idling and coasting states, to realize accurate perception and prediction of track adhesion state capability. When the track adhesion state changes significantly, the system can automatically adjust the GEBR value according to the numerical list to ensure the emergency braking rate, automatically adjust the safety protection distance, and push the dispatching center for early warning, recommend increasing temporary speed limit and degraded operation, and reduce the safety risk caused by uncertain train braking distance in adverse environmental conditions, thereby improving train operation safety and efficiency.

[0239] According to embodiments of the present disclosure, the present disclosure is based on new perception technology, train automatic driving technology, train autonomous safety protection technology and computing power network technology, and constructs an intelligent train active protection control method and system taking vehicles as the core, characterized by "perception-planning-decision control-execution". The method and system comprehensively improve the train autonomous perception, autonomous adjustment, autonomous operation and autonomous protection capabilities, can realize the operation control of individual trains and the collaborative control of multiple train groups, improve the intelligent level of rail transit equipment, and improve the safety and efficiency of rail transit transportation.

[0240] Figure 10 A block diagram of an electronic device suitable for implementing the train operation control method and information execution method according to embodiments of the present disclosure is schematically shown.

[0241] As shown in Figure 10 The electronic device 1000 according to embodiments of the present disclosure includes a processor 1001, which can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1002 or loaded from a storage portion 1008 into a random access memory (RAM) 1003. The processor 1001 can include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a special-purpose microprocessor (such as an application-specific integrated circuit (ASIC)), and the like. The processor 1001 can also include an on-board memory for cache use. The processor 1001 can include a single processing unit or multiple processing units for performing different actions of the method processes according to embodiments of the present disclosure.

[0242] In the RAM 1003, various programs and data required for the operation of the electronic device 1000 are stored. The processor 1001, the ROM 1002, and the RAM 1003 are connected to each other via the bus 1004. The processor 1001 performs various operations of the method flow according to the embodiments of the present disclosure by executing the programs in the ROM 1002 and / or the RAM 1003. It should be noted that the programs can also be stored in one or more memories other than the ROM 1002 and the RAM 1003. The processor 1001 can also perform various operations of the method flow according to the embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0243] According to an embodiment of the present disclosure, the electronic device 1000 can further include an input / output (I / O) interface 1005, which is also connected to the bus 1004. The electronic device 1000 can further include one or more of the following components connected to the I / O interface 1005: an input part 1006 including a keyboard, a mouse, etc.; an output part 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage part 1008 including a hard disk, etc.; and a communication part 1009 including a network interface card such as a LAN card, a modem, etc. The communication part 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as necessary. A removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 1010 as necessary, so that a computer program read out therefrom is installed in the storage part 1008 as necessary.

[0244] The present disclosure also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments; or can exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, when the one or more programs are executed, the method according to the embodiments of the present disclosure is implemented.

[0245] According to an embodiment of the present disclosure, the computer readable storage medium can be a nonvolatile computer readable storage medium, for example, can include, but is not limited to, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination thereof. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, the computer readable storage medium can include one or more memories such as the ROM 1002 and / or the RAM 1003 described above and / or one or more memory chips other than the ROM 1002 and the RAM 1003.

[0246] Embodiments of the present disclosure also include a computer program product including a computer program containing program codes for executing the methods shown in the flowcharts. When the computer program product is run in a computer system, the program codes are used to make the computer system implement the item recommendation method provided by the embodiments of the present disclosure.

[0247] The above-described functions defined in the system / device of the embodiments of the present disclosure are performed when the computer program is executed by the processor 1001. According to an embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by computer program modules.

[0248] In one embodiment, the computer program can rely on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program can also be transmitted, distributed, and downloaded in the form of a signal on a network medium and installed and downloaded through the communication part 1009 and / or installed from the detachable medium 1011. The program codes contained in the computer program can be transmitted by any appropriate network medium, including but not limited to wireless, wired, etc., or any appropriate combination thereof.

[0249] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009 and / or installed from the detachable medium 1011. When the computer program is executed by the processor 1001, the above-described functions defined in the system of the embodiments of the present disclosure are performed. According to an embodiment of the present disclosure, the system, device, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0250] According to embodiments of the present disclosure, program code of the computer program for performing the methods provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages, and can be implemented in a computer program product. Specifically, the computer program can be implemented in a high-level procedural and / or object-oriented programming language, and / or in assembly / machine language. The programming language includes, but is not limited to, Java, C++, python, “C” language, or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, and partly on a remote computing device, or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider (ISP).

[0251] The computer program product of the present disclosure can be a computer program product, which is a machine-readable medium (or computer readable medium) having stored therein a sequence of instructions readable, by one or more processors of a computer system, the instructions being executable by the one or more processors to cause the computer system to execute the method of the present disclosure. The instructions can be software instructions stored in memory (e.g., memory 120 of the computer system) and implemented as software programs to perform the method of the present disclosure. The computer program product can be propagated to and executed by one or more computer systems and / or apparatuses by way of one or more computer readable media.

[0252] Those skilled in the art will understand that features of the various embodiments and / or claims of the present disclosure can be combined or / and integrated with one another, even though such combinations or integrations are not expressly disclosed in the present disclosure. In particular, the features of the various embodiments and / or claims of the present disclosure can be combined and / or integrated with one another in any manner, without departing from the spirit and scope of the present disclosure. All such combinations and / or integrations are within the scope of the present disclosure.

[0253] The above describes embodiments of the present disclosure. However, these embodiments are merely for illustrative purposes, and are not intended to limit the scope of the present disclosure. Although each embodiment is described above separately, this does not mean that the measures in each embodiment cannot be used advantageously in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Those skilled in the art can make various substitutions and modifications without departing from the scope of the present disclosure, and these substitutions and modifications should all fall within the scope of the present disclosure.

Claims

1. A train operation control method characterized by comprising: The method comprises: receiving first environment data transmitted by trackside equipment and train state data and second environment data transmitted by on-board equipment of each train in a train cluster in a running state; processing the first environment data and the second environment data and the train state data of each train based on the line on which each train and the trackside equipment are located, to obtain a line running state of each of a plurality of lines; determining an abnormal line from the plurality of lines based on the line running state of each of the plurality of lines; determining running control information of at least one target train in the train cluster that is running on or is to run on the abnormal line based on the line running state of the abnormal line, and transmitting the running control information to at least one of the target trains to facilitate coordinated control of the at least one target train.

2. The method of claim 1, wherein, The trackside equipment is a plurality of trackside equipment; the first environment data is obtained by a plurality of trackside equipment; the processing of the first environment data and the second environment data and the train state data of each train based on the line on which each train and the trackside equipment are located to obtain a line running state of each of a plurality of lines comprises: dividing the first environment data and the second environment data and the train state data of each train into first environment sub-data sets, second environment sub-data sets and state sub-data sets matched with a plurality of lines based on the line on which each train is running and the line on which the plurality of trackside equipment is located; for each line, performing data analysis on the first environment sub-data set, the second environment sub-data set and the state sub-data set matched with the line based on a plurality of sections included in the line to determine a section running state of each of the plurality of sections; performing status marking of each section on a preset line map based on the section running state of each of the plurality of sections of each line to obtain a running state of each of the plurality of lines; wherein the first environment sub-data set comprises first environment sub-data of each of a plurality of sections of the line, the second environment sub-data set comprises second environment sub-data of each of the plurality of sections of the line, and the state sub-data set comprises train state sub-data of each of the plurality of sections of the line.

3. The method of claim 2, wherein, The first environment sub-data comprises a first weather condition and a first section track condition; the second environment sub-data comprises a second weather condition and a second section track condition; and the train state sub-data represents the running condition of a train in the section. wherein the data analysis on the first environment sub-data set, the second environment sub-data set and the state sub-data set matched with the line based on a plurality of sections included in the line to determine a section running state of each of the plurality of sections comprises: for each section, determining a target weather condition based on the first weather condition and the second weather condition; determining a target section track condition based on the first section track condition and the second section track condition; determining a section running state of the section based on the target weather condition, the target section track condition and the train state sub-data.

4. The method according to any one of claims 1 to 3, characterized in that, The line operation state of the abnormal line comprises track adhesion states of each section and operation states of target trains running on the abnormal line; The operation control information of at least one target train running on or to be running on the abnormal line in the train cluster is determined based on the line operation state of the abnormal line, comprising: Determine the abnormal degree of the abnormal line based on a preset weather prediction model, track adhesion states of each section, and operation states of target trains running on the abnormal line; In the case of the first abnormal degree, generate a train operation plan for at least one target train; Generate the operation control information based on the train operation plan and the track adhesion state of each section.

5. The method of claim 1, wherein, The train state sub-data includes train coasting detection results; The train coasting detection results include coasting state values, coasting occurrence time periods, coasting occurrence positions, and coasting accelerations; The coasting acceleration is one of the parameters for reflecting the track adhesion state; The train coasting detection results are obtained by detecting the train as follows: In the case where the speed of the train is in a first speed range, the acceleration or speed difference of the wheel shaft driven by the traction motor in the train is detected to obtain a first detection result, and the speed difference is the speed difference between the wheel shaft and any wheel shaft in the train; In the case where the first acceleration of the target wheel shaft is greater than a preset acceleration threshold or the first speed difference is greater than a preset speed difference threshold, it is determined that the train is coasting, and the actual output traction force is changed from a first traction force to a second traction force, the first traction force is greater than the second traction force; In the case where the second acceleration of the target wheel shaft is less than or equal to the preset acceleration threshold or the second speed difference is less than or equal to the preset speed difference threshold, the second traction force is updated by a preset gradient until the updated second traction force is consistent with the target traction force; The difference between the first acceleration and the preset acceleration threshold is taken as the coasting acceleration.

6. The method according to claim 1 or 5, characterized in that, The train state sub-data includes train coasting detection results; The train coasting detection results include coasting state values, coasting occurrence time periods, coasting occurrence positions, and coasting accelerations; The coasting acceleration is one of the parameters for reflecting the track adhesion state; The train coasting detection results are obtained by detecting the train as follows: In the case where the speed of the train is in a second speed range, the rotational shaft speed deviation of a plurality of wheels in the same braking unit of the train is detected to obtain a second detection result, and the rotational speed deviation detection is to subtract the rotational shaft speed of a plurality of wheels from a rotational speed threshold and compare a plurality of rotational speed differences with a preset rotational speed difference threshold, the rotational speed threshold is determined from a plurality of rotational shaft speeds of the wheels: determining that the brake unit has a target wheel in a sliding state, and switching a brake force output mode from a unit control to a wheel control, so as to switch a first brake force output to the target wheel to a second brake force, the first brake force being greater than the second brake force, when it is determined that the second detection result represents that there is a rotational speed difference greater than a preset rotational speed difference threshold value; turning off an electric brake function for the target wheel and releasing pressure in an air brake cylinder for the target wheel when it is determined that the target wheel in which the second brake force is switched is still in a sliding state and a sliding duration is greater than a preset duration; inflating the air brake cylinder for the target wheel when it is determined that a rotational shaft speed of the target wheel is in an ascending state; determining a sliding deceleration value based on a current rotational shaft speed of the target wheel, a rotational shaft speed at a sliding start time, and a sliding duration, when it is determined that the target wheel is in a normal state.

7. The method of claim 4, wherein, The method further comprises: determining a second train on the same line and behind the first train in position when the sliding deceleration value or the idling acceleration of the first train in the train cluster is obtained; sending the sliding deceleration value and a sliding occurrence position, or the idling acceleration and an idling occurrence position to the second train, so that the second train travels to the sliding occurrence position or the idling occurrence position and performs train control based on the sliding deceleration value or the idling acceleration, respectively.

8. An information execution method characterized by comprising: Applied to a train, comprising: determining a departure time point and a travel speed curve based on a train operation plan included in operation control information in response to the train receiving the operation control information, wherein the operation control information is obtained by using the train operation control method according to any one of claims 1-7; determining brake parameters matched with track adhesion states of each section based on the track adhesion states of each section included in the operation control information; performing operation control on the train based on the departure time point, the travel speed curve, and the brake parameters.

9. A train operation control system characterized by comprising: Comprising: a control center, a trackside device, and an on-board device; the trackside device is configured to collect first environment data through a trackside sensor and send the first environment data to the control center; the on-board device is configured to collect second environment data through an on-board sensor, perform operation state detection on the train to obtain train state data, and send the second environment data and the train state data to the control center, wherein the on-board device is further configured to receive operation control information sent by the control center and perform train operation control based on the operation control information; the control center is configured to perform the train operation control method according to any one of claims 1-7.

10. The system of claim 1, wherein, The control center comprises a computing device, a storage device, and a network device; the computing device is configured to provide computing resources; the storage device is configured to provide storage resources; the network device is configured to provide network resources; and the computing device is further configured to: determine a priority of the to-be-processed task based on a type of the to-be-processed task, wherein the to-be-processed task comprises a pre-prepared processing task of the first environment data, the second environment data, and the train state data; allocate the computing resource, the storage resource, and the network resource for the to-be-processed task based on the priority.

Images