Intelligent real-time supply and control system and method for train

Abstract

The embodiment of the invention provides an intelligent real-time supply and control system for a train, and the system comprises a positioning unit which is used for obtaining the operation data of the train, and the operation data at least comprise the position information and the speed of the train; the calculation unit is used for generating a control instruction based on the operation data; and the variable-voltage variable-frequency unit is used for adjusting the speed of the train according to the control instruction.

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and in particular to a train intelligent real-time supply and control system and method. Background Art

[0002] Intelligent control and automatic driving (ATC) are the only way to replace manual driving. At present, the train positioning of Europe's Next Generation of Train Control System (NGTC) and the United States' PTC train control system completely relies on satellite navigation, and fails to integrate other technical means such as inertial navigation, speed measurement and distance measurement. The reliability and positioning accuracy are insufficient. The trackside equipment is greatly reduced compared with the previous system, but its overall design and concept are incompatible with the Chinese Train Control System (CTCS), and it is impossible to achieve interconnection between systems.

[0003] In addition, some domestic research institutions and rail transit equipment suppliers have proposed a train-centric, satellite navigation-based train control system, drawing on the concept of urban rail transit, reducing the configuration of trackside and ground equipment, and allowing on-board equipment to directly operate turnouts, signal machines and other equipment through target controllers to ensure the interlocking relationship between various safety equipment in the station. However, this type of technical solution does not fully consider the differences between national railways and urban rail transit in terms of operating scenarios and environments, train running speeds, and line complexity in stations. It cannot fully meet the needs of national railway network interconnection, diverse and complex operating environments, large speed spans, and complex station interlocking relationships. It lacks a backup mode, and the system availability and reliability are lacking.

[0004] Therefore, there is an urgent need to propose an intelligent real-time train control system and method to realize automatic train driving while ensuring safe train operation. Summary of the invention

[0005] One or more embodiments of the present specification provide an intelligent real-time supply and control system for a train, the system comprising: a positioning unit for acquiring operating data of a train, the operating data comprising at least position information and speed of the train; a computing unit for generating control instructions based on the operating data; and a voltage and frequency conversion unit for adjusting the speed of the train according to the control instructions.

[0006] In some embodiments, the computing unit is further used to: determine the inter-vehicle distance between the front train and the rear train based on the position information of the front train and the rear train; and generate a control instruction in response to the inter-vehicle distance not satisfying a preset condition.

[0007] In some embodiments, the control instruction includes at least one of the following: an instruction to control the front train to accelerate; an instruction to control the rear train to decelerate; and an instruction to control the brake device on the rear train to perform braking.

[0008] In some embodiments, the computing unit is further used to: predict the vehicle spacing at future times through a prediction model based on relevant data of train operation, and the prediction model is a machine learning model.

[0009] One of the embodiments of the present specification provides a method for intelligent real-time control of a train, which method includes: obtaining operation data of the train, the operation data at least including the position information and speed of the train; generating control instructions based on the operation data; and adjusting the speed of the train according to the control instructions.

[0010] In some embodiments, a control instruction is generated based on the operating data, including: determining the inter-vehicle distance between the front train and the rear train based on the position information of the front train and the rear train; and generating a control instruction in response to the inter-vehicle distance not satisfying a preset condition.

[0011] In some embodiments, the control instruction includes at least one of the following: an instruction to control the front train to accelerate; an instruction to control the rear train to decelerate; and an instruction to control the brake device on the rear train to perform braking.

[0012] In some embodiments, the method further includes: predicting the vehicle spacing at a future time through a prediction model based on relevant data of train operation, and the prediction model is a machine learning model.

[0013] One or more embodiments of the present specification provide a train intelligent real-time supply and control device, including a processor, wherein the processor is used to execute a train intelligent real-time supply and control method.

[0014] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for intelligent real-time supply and control of a train. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of an application scenario of a train intelligent real-time supply and control system according to some embodiments of this specification;

[0016] Figure 2 is an exemplary module diagram of a train intelligent real-time supply and control system according to some embodiments of this specification;

[0017] Figure 3 is an exemplary flow chart of a train intelligent real-time supply and control method according to some embodiments of this specification;

[0018] Figure 4is an exemplary schematic diagram of the distance between the front train and the rear train according to some embodiments of the present specification;

[0019] Figure 5 is an exemplary schematic diagram of a prediction model according to some embodiments of the present specification. DETAILED DESCRIPTION

[0020] The following is a brief introduction to the drawings required for describing the embodiments. The drawings do not represent all implementation methods.

[0021] The "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. If other words can achieve the same purpose, the words can be replaced by other expressions.

[0022] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0023] When the operations performed in the embodiments of this specification are described in steps, unless otherwise specified, the order of the steps is interchangeable, steps may be omitted, and other steps may be included in the operation process.

[0024] Figure 1 It is a schematic diagram of an application scenario of a train intelligent real-time supply and control system according to some embodiments of this specification.

[0025] In some embodiments, the application scenario 100 of the train intelligent real-time supply and control system includes multiple tracks (e.g., track 110-1 and track 110-2) and multiple trains (e.g., train 120-1, train 120-2, train 120-3 and train 120-4).

[0026] In some embodiments, multiple trains may travel on the same track. For example, train 120-1 and train 120-2 may travel on track 110-1. There is a distance between the front and rear trains, and the speed of different trains is controlled by the train intelligent real-time supply and control system to keep a safe distance between the front and rear trains.

[0027] In some embodiments, the train can be powered by various methods. For example, a power shoe (not shown in the figure) is provided on the train, and a power supply rail (not shown in the figure) is provided on the track accordingly. The train obtains power for operation by connecting the power shoe to the power supply rail. The power shoe and the power supply rail can be connected in various feasible ways. For example, a three-phase power supply rail is provided on the track, and a power shoe is provided on the train. One power shoe can correspond to three power supply rails, or three power shoes are provided on the train, and the three power shoes correspond to three power supply rails respectively.

[0028] It should be noted that the application scenarios are provided for illustrative purposes only and are not intended to limit the scope of this specification. For those of ordinary skill in the art, various modifications or variations can be made based on the description of this specification. For example, the application scenarios may also include a station or a data processor. For another example, the application scenarios may implement similar or different functions on other devices. However, the changes and modifications will not deviate from the scope of this specification.

[0029] Figure 2 It is an exemplary module diagram of a train intelligent real-time supply and control system shown in some embodiments of this specification.

[0030] In some embodiments, the train intelligent real-time supply and control system 200 includes a positioning unit 210 , a computing unit 220 , and a voltage and frequency conversion unit 230 .

[0031] The positioning unit 210 is used to obtain the running data of the train, and the running data at least includes the position information and speed of the train.

[0032] For more information on operating data, train position information and speed, see Figure 3 and its related description.

[0033] In some embodiments, the positioning unit 210 may include a ground positioning unit, which may be composed of ground positioning and speed measuring devices such as positioning and speed measuring loop equipment, grating array, laser coding positioning and speed measuring equipment, etc.

[0034] In some embodiments, the ground positioning unit can obtain the position information and speed of the train in real time. In some embodiments, the ground positioning unit can simultaneously identify the train ID. For example, multiple ground positioning units are deployed on the ground, and the measurement areas corresponding to the multiple ground positioning units can cover the entire track line. When the train enters the measurement area of ​​the corresponding ground positioning unit, the position information and speed of the train are obtained in real time based on the ground positioning unit, and the train ID is identified at the same time.

[0035] In some embodiments, the ground positioning unit needs to achieve positioning accuracy higher than ±30mm, speed measurement accuracy higher than 2‰, measurement frequency no less than 30kHz, data transmission delay no more than 100μs, and meet the measurement requirements of the train speed of 1000km / h and various train operating postures.

[0036] In some embodiments, the positioning unit 210 may include a vehicle-mounted positioning unit, which may be composed of a vehicle-mounted positioning system (eg, GPS, Beidou, etc.) and a vehicle-mounted speed measuring device (eg, a speed sensor) and other vehicle-mounted positioning and speed measuring devices.

[0037] In some embodiments, the on-board positioning unit can obtain the position information and speed of the train in real time. In some embodiments, the on-board positioning unit can also identify the train ID. For example, each train is deployed with an on-board positioning unit, which is bound to the train ID. During the travel of the train, the on-board positioning unit can obtain the position information and speed of the train in real time.

[0038] In some embodiments, the on-board positioning unit can achieve positioning accuracy better than ±20cm, speed measurement accuracy better than 2%, data transmission delay no more than 100ms, and meet the measurement requirements of train speeds of 1000km / h and various train operating postures.

[0039] The positioning unit 210 may also include other data information collection devices.

[0040] In some embodiments, the positioning unit 210 may transmit the acquired operation data to the computing unit 220 and the voltage and frequency conversion unit 230 through a wired or wireless transmission method. For example, the ground positioning unit may transmit the acquired operation data to the computing unit 220 and the voltage and frequency conversion unit 230 through a wired network. For another example, the vehicle-mounted positioning unit may transmit the acquired operation data to the computing unit 220 through a wireless network.

[0041] In some embodiments of the present specification, by respectively limiting the accuracy of the ground positioning unit and the on-board positioning unit and the data transmission speed, not only the accuracy of the acquired operating data can be guaranteed, but also the computing unit can acquire and process the operating data in a timely manner, so as to generate control instructions in time for emergency situations and ensure the safe operation of the train.

[0042] The calculation unit 220 is used to generate a control instruction based on the operation data.

[0043] For more information about control instructions and how to generate them, see Figure 3-Figure 5 and its related description.

[0044] In some embodiments, computing unit 220 may include a processor and a storage device.

[0045] In some embodiments, the processor may be used to process data and / or information from at least one component of the train intelligent real-time supply and control system 200 or an external data source. For example, the operation data of the train received from the positioning unit 210. In some embodiments, the processor may include one or more sub-processing devices (e.g., a single-core processing device or a multi-core multi-core processing device).

[0046] In some embodiments, the storage device can be used to store data and / or instructions. Data refers to a digital representation of information and can include various types, such as binary data, text data, image data, video data, etc. In some embodiments, the data may include train operation data, track line data, speed-distance curves of lines and trains calculated by calculation, time-distance curves, train current-distance curves, and other data. Instructions refer to programs that can control a device or device to perform a specific function. For example, control instructions. In some embodiments, the storage device can store one or more machine learning models.

[0047] In some embodiments, the storage device may be a part of the processor. In some embodiments, the processor may be connected to the storage device via a network or directly to access and / or receive data and information.

[0048] In some embodiments, the computing unit 220 may be disposed on the ground.

[0049] In some embodiments, the computing unit 220 may receive data information from the positioning unit 210 and the voltage and frequency conversion unit 230 in a wired or wireless manner. In some embodiments, the computing unit 220 may send control instructions to the voltage and frequency conversion unit 230 in a wired or wireless manner.

[0050] In some embodiments, the computing unit 220 can transmit data information to the train in a wired or wireless manner. For example, the computing unit 220 can directly transmit the control instruction to the on-board braking device through a wireless network to control the braking device on the train to perform braking. For another example, the computing unit 220 can load the control signal at the output end of the converter in the form of a power line carrier, transmit it to the train through the power shoe, and demodulate it through the demodulator on the train, thereby controlling the speed of the train.

[0051] The voltage and frequency conversion unit 230 is used to adjust the speed of the train according to the control instructions.

[0052] In some embodiments, there are multiple voltage-frequency conversion units 230, each of which corresponds to a sub-track, and the train track is composed of multiple sub-tracks. Each voltage-frequency conversion unit 230 adjusts the speed of the train on its corresponding sub-track according to the control instruction.

[0053] For more information about sub-tracks and how to adjust the speed of the train according to control instructions, see Figure 3-Figure 5 and its related description.

[0054] In some embodiments, the voltage and frequency conversion unit 230 may be disposed on the ground.

[0055] In some embodiments of the present specification, by arranging the computing unit 220 and the voltage and frequency conversion unit 230 on the ground, it is possible to reduce the weight of the on-board electrical equipment, reduce the axle weight, achieve lightweight trains, improve the train's load-bearing efficiency and power density, and adapt to higher speed operation; and it is possible to achieve automatic control and unmanned driving of the train operation through ground control.

[0056] It should be noted that the above description of the system and its modules is only for convenience of description and does not limit the present specification to the scope of the embodiments. It is understandable that, after understanding the principle of the system, those skilled in the art may arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from the principle.

[0057] Figure 3 is an exemplary flow chart of a train intelligent real-time supply and control method according to some embodiments of this specification. Figure 3 As shown, process 300 includes the following steps:

[0058] Step 310 , obtaining the running data of the train. In some embodiments, step 310 may be performed by the positioning unit 210 .

[0059] Operation data refers to various data information generated during the operation of the train, such as the time it takes for the train to pass through each station, the train's electrical system parameters (such as voltage / current), and the train's energy consumption data.

[0060] In some embodiments, the operation data includes at least the location information and speed of the train. The location information of the train refers to information related to the real-time location of the train, such as the longitude and latitude of the train, the track information of the train, the distance between the train and the station or other landmarks, etc.

[0061] For more information about how to obtain operation data, see Figure 2 and its related description.

[0062] Step 320 , generating a control instruction based on the operation data. In some embodiments, step 320 may be performed by the computing unit 220 .

[0063] Control instructions refer to programs that can control equipment or devices on the train to perform specific functions, such as instructions to control the speed of the train.

[0064] In some embodiments, the control instruction includes at least one of the following: an instruction to control the front train to accelerate, an instruction to control the rear train to decelerate, and an instruction to control a brake device on the rear train to perform braking.

[0065] In some embodiments, different control instructions may be applicable to different situations. For example, in a non-emergency situation (e.g., the distance between vehicles is greater than a threshold), if controlling the front train to accelerate takes the shortest time and consumes the least energy, then the instruction to control the front train to accelerate is applicable in this situation; if controlling the rear train to decelerate takes the shortest time and consumes the least energy, then the instruction to control the rear train to decelerate is applicable in this situation. For another example, in an emergency situation (e.g., the distance between vehicles is less than a threshold), it is difficult to get the train out of danger by controlling the train to accelerate or decelerate, and emergency mechanical braking is required. In this case, the instruction to control the brake device on the rear train to perform braking is applicable.

[0066] The brake device is a mechanical brake device provided on the train. In some embodiments, the computing unit 220 can directly transmit the instruction for controlling the brake device on the train to perform braking to the on-board braking device via a wireless network, thereby controlling the brake device on the train to perform braking. In some embodiments, the brake device can be manually controlled to achieve braking.

[0067] In some embodiments of this specification, control instructions suitable for different situations are generated based on operation data, which can not only meet the automatic driving of trains in different situations, but also fully ensure the operation safety of trains. In addition, by setting a braking device on the train, the train can be braked in time in an emergency to avoid accidents caused by failure to control the acceleration or deceleration of the train, or failure in data information transmission.

[0068] In some embodiments, the computing unit 220 may process the operating data and generate control instructions through modeling or various data analysis methods.

[0069] In some embodiments, the storage device of the calculation unit 220 pre-stores the speed-time curve and the position-time curve after the train departs. Based on the real-time position information and speed of the train, by comparing with the speed-time curve and the position-time curve, it is determined whether the train speed needs to be adjusted, and a corresponding control instruction is generated. For example, if the speed of the train at the current moment is greater than the speed corresponding to the moment in the speed-time curve, an instruction to control the train to decelerate is generated. For another example, if the train has not reached the position corresponding to the moment in the position-time curve at the current moment, an instruction to control the train to accelerate is generated.

[0070] In some embodiments, the calculation unit 220 may determine the inter-vehicle distance between the front train and the rear train based on the position information of the front train and the rear train, and generate a control instruction in response to the inter-vehicle distance not satisfying a preset condition.

[0071] Figure 4 is an exemplary schematic diagram of the distance between the front train and the rear train according to some embodiments of the present specification.

[0072] The front train and the rear train are determined relatively. The front train refers to the train in front of the rear train, and the rear train refers to the train in the rear of the front train. Figure 4 As shown, in the direction of travel of the train, train A is the front train relative to train B, and train B is the rear train relative to train A. If the train travels in the opposite direction, train A is the rear train relative to train B, and train B is the front train relative to train A.

[0073] The distance between cars refers to the distance between the rear of the front train and the front of the rear train. Figure 4 As shown, in the travel direction of the train, the distance S between the rear end of the front train A and the front end of the rear train B is the distance between the two trains.

[0074] In some embodiments, the calculation unit 220 can directly determine the inter-vehicle distance between the front train and the rear train based on the position information of the front train and the rear train. For example, the positioning unit 210 directly obtains the specific position of the rear of the front train and the specific position of the front of the rear train, and the calculation unit 220 directly calculates the inter-vehicle distance between the front train and the rear train based on the specific position of the rear of the front train and the specific position of the front of the rear train.

[0075] In some embodiments, the calculation unit 220 can predict the inter-vehicle distance at a future time based on the relevant data of train operation and the prediction model. For more information about the relevant data of train operation, the inter-vehicle distance at a future time, the prediction model, and how to predict the inter-vehicle distance, please refer to Figure 5 and its related description.

[0076] The preset condition refers to a condition that can ensure the safe operation of the front and rear trains based on the inter-vehicle distance and can ensure that only one train runs on each section of sub-track. In some embodiments, the preset condition includes that the inter-vehicle distance satisfies a distance threshold. For example, the inter-vehicle distance is greater than the distance threshold.

[0077] In some embodiments, the distance threshold includes a safety threshold and a limit threshold. The safety threshold refers to the maximum distance between vehicles that can ensure the safe operation of the front and rear trains by controlling the normal acceleration or deceleration of the train. The limit threshold refers to the maximum distance between vehicles that requires emergency braking measures to ensure the safe operation of the front and rear trains. In some embodiments, the safety threshold is greater than the limit threshold.

[0078] In some embodiments, the distance threshold may be determined based on prior experience. In some embodiments, the distance threshold is related to relevant data of train operation.

[0079] The data related to train operation refers to data related to or affecting the operation of the train. In some embodiments, the data related to train operation includes historical operation data, equipment data of the train, and weather data. In some embodiments, the data related to train operation also includes line data.

[0080] Historical operation data refers to various data information generated during the historical operation of the train. For example, the time when the train passes through each station, the electrical system parameters (such as voltage / current) of the historical operation of the train, the energy consumption data of the historical operation of the train, etc. In some embodiments, the operation data generated by each operation of the train can be stored in a storage device, and the historical operation data can be directly obtained from the storage device.

[0081] The equipment data of the train refers to data related to the status of each device or component on the train. For example, the performance indicators, fault diagnosis data, service life, etc. of each device or component of the train (such as traction system, braking system, bogie, door, air conditioning system, etc.). In some embodiments, the equipment data of the train can be stored in a storage device and updated regularly.

[0082] Weather data refers to data related to weather conditions when the train is running, such as temperature, humidity, rainfall time, etc. In some embodiments, weather data can be directly obtained based on various meteorological data networks.

[0083] Line data refers to data related to the train running line, such as turnout data of the line, maintenance status of the track, etc. In some embodiments, the line data can be stored in a storage device and updated regularly.

[0084] In some embodiments, the calculation unit 220 may determine the historical operation stability of the train based on the historical operation data. The historical operation stability reflects the stability of the historical operation of the train. In some embodiments, the historical operation stability may be represented by specific levels (such as levels I to V), and the lower the level (such as, level I is the lowest, level V is the highest), the weaker the historical operation stability. For example, if the historical operation data reflects that the number of times the train was not on time through each station accounts for a large proportion, or the number of times the electrical system parameters did not reach the standard value accounts for a large proportion, then the historical operation stability of the train is weak and the level is low.

[0085] In some embodiments, the calculation unit 220 may determine the equipment performance of the train based on the equipment data of the train. The equipment performance reflects the quality of the equipment or components on the train. In some embodiments, the equipment performance can be represented by specific levels (such as levels I to V), and the lower the level (such as level I is the lowest and level V is the highest), the worse the equipment performance. For example, if the number of failures of various equipment or components of the train accounts for a large proportion and the service life is long, the equipment performance of the train is poor and the level is low.

[0086] In some embodiments, the computing unit 220 may determine the operating environment of the train based on weather data. The operating environment reflects the external environment that affects the operation of the train. In some embodiments, the operating environment may be represented by specific levels (such as levels I to V), and the lower the level (such as level I is the lowest and level V is the highest), the worse the operating environment. For example, if the train is running in extreme weather such as heavy rain or hail, the operating environment of the train is relatively bad and has a lower level.

[0087] In some embodiments, the calculation unit 220 may determine the line condition of a train running on a certain line based on the line data. The line condition reflects the influence of the line on the train running therein. In some embodiments, the line condition may be represented by specific levels (such as levels I to V), and the lower the level (such as level I is the lowest and level V is the highest), the worse the line condition. For example, if the maintenance condition of the line on which the train runs reflects that it is severely aged, then the line condition of the train running on the line is poor and the level is low.

[0088] In some embodiments, the calculation unit 220 may determine the distance threshold based on at least one of historical operation stability, device performance, operating environment, and line conditions. For example, the weaker the historical operation stability, the worse the device performance, the worse the operating environment, and the worse the line conditions, the greater the distance threshold.

[0089] In some embodiments of the present specification, by distinguishing the distance threshold into a safety threshold and a limit threshold, more applicable preset conditions exist in both emergency and non-emergency situations, and resources can be saved to the maximum extent on the basis of ensuring the safe operation of the train. In addition, since the conditions involved in train operation are changeable (e.g., the conditions of different trains are different, the conditions of different lines are different, and the weather conditions of operation at different times are also different), the distance threshold is determined based on the relevant data of the train operation, and multiple factors can be fully considered, so that the distance threshold finally determined is more in line with actual needs and more scientific and reasonable.

[0090] Step 330 , adjusting the speed of the train according to the control instruction. In some embodiments, step 330 may be performed by the voltage and frequency conversion unit 230 .

[0091] In some embodiments, the train track is composed of a plurality of sub-tracks, and a power supply rail is connected between corresponding sub-tracks through the voltage and frequency conversion unit 230 to adjust the speed of the train located on the sub-track.

[0092] Sub-track refers to a section of a complete train track. Figure 4 As shown, sub-track 1 and sub-track 2 are two sections of sub-tracks in a complete train track.

[0093] In some embodiments, the lengths of different sub-tracks may be the same or different. Figure 4 As shown, the lengths of sub-track 1 and sub-track 2 may be the same or different.

[0094] In some embodiments, only one train is allowed to travel on each section of track. Figure 4 As shown, train A runs on sub-track 1, and train B runs on sub-track 2. Trains A and B cannot run on sub-track 1 or 2 at the same time.

[0095] In some embodiments, the number and length of the sub-tracks are determined based on at least one of the line station length, the line terrain conditions, and the power supply distance.

[0096] The length of a track station refers to the distance between one station and the next station on the track. A complete track line contains multiple stations.

[0097] Line terrain conditions refer to the terrain conditions of the area through which the track passes, such as altitude, slope, undulations, geological data, etc.

[0098] The power supply distance refers to the distance from the voltage and frequency conversion unit 230 to the farthest point where it can effectively supply power.

[0099] In some embodiments, the voltage and frequency conversion unit 230 is connected to the power supply rail at the middle position of the corresponding sub-rail, and the power supply distance is half the length of the sub-rail.

[0100] In some embodiments, the calculation unit 220 can determine the number and length of the sub-tracks directly based on at least one of the line station length, the line terrain condition, and the power supply distance by basic mathematical calculation methods. For example, the length of the sub-track can be directly calculated based on the power supply distance, and the number of sub-tracks can be directly calculated based on the line station length and the length of the sub-track.

[0101] In some embodiments, the calculation unit 220 may determine the number and length of the sub-tracks based on at least one of the line station length, the line terrain conditions, and the power supply distance by constructing a model. For example, the calculation unit 220 may construct a track line simulation model based on the line station length, the line terrain conditions, and the power supply distance, and determine the number and length of the sub-tracks corresponding to the situation with higher power supply efficiency and lower cost by adjusting the number and length of the sub-tracks.

[0102] The calculation unit 220 may also determine the number and length of the sub-tracks based on at least one of the line station length, the line terrain condition, and the power supply distance in other feasible ways.

[0103] In some embodiments of the present specification, the number and length of sub-tracks are determined based on the line station length, line terrain conditions, and power supply distance, which can fully take into account the actual environmental conditions and voltage drops corresponding to different sub-track areas, while ensuring power supply efficiency and reducing construction costs and operation and maintenance costs as much as possible.

[0104] In some embodiments, the voltage and frequency conversion unit 230 can determine the power supply parameters of the corresponding sub-track according to the control instruction, and the power supply parameters are configured to adjust the speed of the train located on the sub-track.

[0105] Power supply parameters refer to various power data when the train intelligent real-time power supply control system drives the train to run, such as voltage, current, frequency, power, etc.

[0106] In some embodiments, the voltage-frequency conversion unit 230 can directly determine the power supply parameters of the corresponding sub-track according to the control instruction. For example, if the control instruction is an instruction to control the acceleration of the front train, the voltage-frequency conversion unit 230 will increase the output torque of the corresponding sub-track accordingly.

[0107] In some embodiments, the control instructions and the corresponding power supply parameters may be stored in the form of a data table, and the voltage and frequency conversion unit 230 may determine the corresponding power supply parameters through the data table according to the control instructions.

[0108] The voltage and frequency conversion unit 230 may also determine the power supply parameters of the corresponding sub-track according to the control instruction in other ways.

[0109] In some embodiments, the voltage and frequency conversion unit 230 can control the motor based on the power supply parameters, thereby achieving control of the train speed.

[0110] In some embodiments of the present specification, the voltage-frequency conversion unit 230 and the sub-track are matched one by one, and the speed of the train running on the corresponding sub-track is controlled by the voltage-frequency conversion unit 230, thereby realizing automatic train control and fixed block of the train set while ensuring the punctuality of the train operation.

[0111] In some embodiments, the calculation unit 220 may also modify the power supply parameters using a preset algorithm.

[0112] Since the equivalent impedance of the sub-track cannot be ignored, the power supply parameters converted to the motor need to be corrected at different positions of each sub-track. For example, in order to ensure the normal operation of the train, when the train is at position a of the sub-track, the motor needs to provide x A current, but due to the equivalent impedance at position a of the sub-track, the x A current provided by the motor will be weakened at position a, so the motor actually needs to provide (x+z) A current.

[0113] The preset algorithm refers to a pre-set algorithm for correcting power supply parameters, for example, a machine learning model (such as a neural network, a support vector machine, a decision tree, etc.), data fitting, etc.

[0114] In some embodiments, the calculation unit 220 may divide each sub-track into several small sections, determine the power supply parameter correction value of each small section through a preset algorithm, and store the correction value in the voltage and frequency conversion unit 230 of the corresponding small section. When the train arrives at each small section, the corresponding voltage and frequency conversion unit 230 determines the corrected power supply parameter according to the control instruction and the correction value.

[0115] In some embodiments, for each small segment, the calculation unit 220 may obtain data by combining simulation and experiment, and determine the power supply parameter correction value by data fitting.

[0116] In some embodiments, the calculation unit 220 may determine the power supply parameter correction value based on the power supply parameter and the line data by correcting the model.

[0117] The correction model refers to a model used to correct the power supply parameters. In some embodiments, the correction model can be a machine learning model, such as a convolutional neural network (CNN), a deep neural network (DNN), etc. or a combination thereof.

[0118] The correction model can be obtained by training based on the first training sample and the first label. The first training sample includes sample power supply parameters and sample line data, and the first sample can be obtained based on historical data. The first label is the power supply parameter when the train runs at a specified speed, and the first label can be determined by manual labeling or automatic labeling. During training, the first training sample is input into the initial correction model, and a loss function is constructed based on the output of the initial correction model and the first label. The parameters of the initial correction model are updated through the loss function until the trained initial correction model meets the first preset condition, and the trained correction model is obtained. Among them, the first preset condition can be that the loss function is less than a threshold, converges, or the training cycle reaches a threshold, etc. The above description is only an example and not a limitation. For example, the first label can be obtained in various ways.

[0119] In some embodiments of the present specification, by correcting the power supply parameters, the non-negligible equivalent impedance in each sub-track is fully considered, so that the power supply parameters received by the motor are more accurate, thereby achieving precise control of the train speed.

[0120] The embodiments in this specification are only for illustration and description, and do not limit the scope of application of this specification. For those skilled in the art, various modifications and changes that can be made under the guidance of this specification are still within the scope of this specification.

[0121] Figure 5 is an exemplary schematic diagram of a prediction model according to some embodiments of the present specification.

[0122] In some embodiments, the computing unit 220 may predict the vehicle spacing at a future time through a prediction model based on relevant data of train operation, and the prediction model is a machine learning model.

[0123] The prediction model refers to a model for predicting the inter-vehicle distance at a future time. In some embodiments, the prediction model 520 can process the relevant data 510 of train operation to obtain the inter-vehicle distance 530 at a future time.

[0124] In some embodiments, the prediction model 520 may be various feasible neural network models, such as convolutional neural networks (CNN), deep neural networks (DNN), etc., or a combination thereof.

[0125] like Figure 5 As shown, the input of the prediction model 520 may include historical operation data 511 , train equipment data 512 , and weather data 513 .

[0126] In some embodiments, the input of the prediction model 520 may also include route data (not shown).

[0127] For more information on historical operating data, train equipment data, weather data, and line data, see Figure 3 and its related description.

[0128] The output of the prediction model 520 may include the inter-vehicle distance 530 at a future time, for example, the inter-vehicle distance 1 hour in the future.

[0129] In some embodiments, the prediction model 520 can be trained based on historical data alone. In some embodiments, the prediction model 520 can be trained based on the second training sample and the second label.

[0130] In some embodiments, the second training sample includes sample historical operation data, sample train equipment data, sample weather data, and sample line data, and the second training sample can be obtained based on historical data. The second label is the vehicle spacing at different times, and the second label can be determined by manual labeling or automatic labeling.

[0131] During training, the second training sample is input into the initial prediction model, a loss function is constructed based on the output of the initial prediction model and the second label, and the parameters of the initial prediction model are updated by the loss function until the trained initial prediction model meets the second preset condition, and the trained prediction model 520 is obtained, wherein the second preset condition may be that the loss function is less than a threshold, converges, or the training cycle reaches a threshold, etc. The above description is only an example and not a limitation, for example, the second label can be obtained in various ways.

[0132] In some embodiments, after the calculation unit 220 obtains the inter-vehicle distance at a future time, if the inter-vehicle distance at the future time does not meet a preset condition, a control instruction is generated before the future time and the speed of the train is adjusted.

[0133] In some embodiments of this specification, by predicting the distance between the front and rear trains at a future time in advance through the prediction model, the danger that may occur to the train at a future time can be known in advance, and relevant measures can be taken in advance, thereby reducing the probability of an emergency. In addition, the prediction model predicts the distance between trains based on historical operation data, train equipment data, weather data and line data. The training model can take into account multiple influencing factors at the same time to ensure the accuracy of the model's prediction of the distance between trains.

[0134] Furthermore, certain features, structures or characteristics in one or more embodiments of this specification may be appropriately combined.

[0135] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0136] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the materials cited in this specification and the contents described in this specification, the descriptions, definitions, and / or usage of terms in this specification shall prevail.

Claims

1. A train intelligent real-time supply and control system, characterized in that: The system comprises: A positioning unit, used to obtain running data of a train, wherein the running data at least includes the position information and speed of the train; A computing unit, configured to generate a control instruction based on the operating data; and The voltage and frequency conversion unit is used to adjust the speed of the train according to the control instruction.

2. The system according to claim 1, characterized in that The computing unit is further configured to: Determining the inter-vehicle distance between the front train and the rear train based on the position information of the front train and the rear train; In response to the inter-vehicle distance not satisfying a preset condition, generating the control instruction.

3. The system according to claim 2, characterized in that The control instruction includes at least one of the following: an instruction to control the acceleration of the preceding train; an instruction to control the following train to decelerate; and The brake device on the rear train is controlled to execute a braking instruction.

4. The system according to claim 2, characterized in that The computing unit is further configured to: Based on the relevant data of the train operation, the vehicle spacing at a future time is predicted through a prediction model, and the prediction model is a machine learning model.

5. A train intelligent real-time supply and control method, characterized in that: The method comprises: Acquiring running data of a train, wherein the running data at least includes position information and speed of the train; generating control instructions based on the operating data; and According to the control instruction, the speed of the train is adjusted.

6. The method according to claim 5, characterized in that The generating of control instructions based on the operation data includes: Determining the inter-vehicle distance between the front train and the rear train based on the position information of the front train and the rear train; In response to the inter-vehicle distance not satisfying a preset condition, generating the control instruction.

7. The method according to claim 6, characterized in that The control instruction includes at least one of the following: an instruction to control the acceleration of the preceding train; an instruction to control the following train to decelerate; and The brake device on the rear train is controlled to execute a braking instruction.

8. The method according to claim 6, characterized in that The method further comprises: Based on the relevant data of the train operation, the vehicle spacing at a future time is predicted through a prediction model, and the prediction model is a machine learning model.

9. An intelligent real-time supply and control device for a train, comprising a processor, wherein the processor is used to execute the intelligent real-time supply and control method for a train according to any one of claims 5 to 8.

10. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the intelligent real-time supply and control method for trains as described in any one of claims 5 to 8.

Images