A perception system for virtual coupled train motion state

Abstract

The application provides a virtual coupled train motion state sensing system, which comprises an integrated main machine and a functional module electrically connected to a current train, and an RFID tag installed on a front train; the functional module comprises a camera module, a radar module, an inertial measurement module and an RFID antenna. The system obtains motion parameters of the front train in the virtual coupled train in real time based on the radar module and the inertial measurement module, then tracks the front train with the assistance of the integrated main machine, and cooperatively controls the whole train formation when the front train establishes formation operation, so as to guarantee the safety of the virtual coupled train operation and improve the efficiency of the virtual coupled train operation.

Description

Technical Field

[0001] This invention relates to the field of virtual coupled trains, and more particularly to a sensing system for the motion status of virtual coupled trains. Background Technology

[0002] When a virtual coupled train is in operation, it is necessary to acquire real-time kinematic parameters of the preceding train, including its position, relative distance, and relative speed. Based on these kinematic parameters, coordinated control of the entire train convoy is crucial to ensure safety and efficiency during operation. Therefore, establishing a motion state sensing system for virtual coupled trains is of paramount importance. Summary of the Invention

[0003] This invention provides a method for real-time acquisition of motion parameters of preceding trains to track them, and for coordinated control of the entire train formation during the formation of preceding trains, thereby ensuring the safety of virtual coupled train operation.

[0004] This invention provides a virtual coupled train motion state sensing system, comprising: an integrated host and functional modules electrically connected to the current train, and RFID tags installed on the preceding train; the functional modules include: a camera module, a radar module, an inertial measurement module, and an RFID antenna;

[0005] The camera module is used to identify the preceding vehicle;

[0006] The radar module is used to measure the real-time speed of the current train; and to measure the relative distance when the train is coupled with the preceding train to form a trainset; and to measure the relative speed between the preceding train and the current train when the train is coupled with the preceding train to form a trainset.

[0007] The inertial measurement module is used to acquire the radial acceleration of the current train;

[0008] The integrated host is used to establish a train formation based on the real-time speed and radial acceleration of the current train and the preceding train; and to track the preceding train based on the relative distance between the train and the preceding train during the formation operation, and the relative speed between the preceding train and the current train, through the RFID antenna and the RFID tag installed on the preceding train.

[0009] Optionally, the camera module includes: a telephoto camera and a short-focus camera;

[0010] The telephoto camera is used to acquire targets of preceding trains that are beyond a preset distance from the train itself;

[0011] The short-focus camera is used to compensate for changes in field of view caused by railway curves when the train is coupled with the preceding train to form a marshalling group.

[0012] Optionally, the radar module includes: secondary radar, lidar, and millimeter-wave radar.

[0013] The lidar is used to determine the speed state of the current train, and when the speed state is low, to measure the real-time speed of the current train; and when the train is coupled with the preceding train to form a train formation, to continuously acquire the real-time distance between the preceding train and the current train at a frequency of 10Hz.

[0014] Millimeter-wave radar is used to measure the relative speed between the preceding vehicle and the vehicle itself, as well as the absolute speed of the vehicle itself.

[0015] The secondary radar is used to determine the target acquisition and ranging of a preceding vehicle on the same track at a preset distance, based on the RFID tag and the RFID antenna.

[0016] Optionally, the integrated host includes: a CPU processor, a GPU processor, and a communication interface board;

[0017] The CPU processor is used to use a preset algorithm to predict the motion state of the preceding vehicle based on the relative distance and the relative speed, obtain a prediction result, and track the preceding vehicle according to the prediction result;

[0018] The GPU processor is used to match the image information acquired by the camera module and the motion state data acquired by the radar module.

[0019] The communication interface board is used to provide a data interface for the functional unit.

[0020] Optionally, the lidar is specifically used to: determine whether the real-time speed of the current train is less than 10 km / h; if so, determine that the speed state of the current train is low speed.

[0021] Optionally, the lidar is further specifically used for:

[0022] The real-time speed of the current train is determined by acquiring the relative position change data of the current train in the low-speed state over a preset measurement period.

[0023] Optionally, the lidar is further specifically used to: continuously acquire distance information between the preceding train and the current train at a preset acquisition frequency when the train is coupled with the preceding train to form a train formation.

[0024] Optionally, the preset acquisition frequency is 10Hz.

[0025] Optionally, the CPU processor is specifically used to: track the preceding vehicles using a single-target tracking method based on the prediction results.

[0026] Optionally, the preset algorithm is a Kalman filter algorithm.

[0027] As can be seen from the above technical solutions, the present invention has the following advantages:

[0028] This invention provides a virtual train coupling motion state sensing system, comprising: an integrated host and functional modules electrically connected to the current train, and an RFID tag installed on the preceding train; the functional modules include: a camera module, a radar module, an inertial measurement module, and an RFID antenna; the camera module is used to identify the preceding train; the radar module is used to measure the real-time speed of the current train; and to measure the relative distance when coupling with the preceding train to establish a train formation; and to measure the relative speed between the preceding train and the current train when coupling with the preceding train to establish a train formation; the inertial measurement module is used to acquire the radial acceleration of the current train; the integrated host is used to establish a train formation with the preceding train based on the real-time speed and radial acceleration of the current train; and to track the preceding train based on the relative distance when coupling with the preceding train to establish a train formation, and the relative speed between the preceding train and the current train, through the RFID antenna and the RFID tag installed on the preceding train.

[0029] Based on radar and inertial measurement modules, the motion parameters of the preceding cars in the virtual coupled train are acquired in real time. Then, with the assistance of the integrated host, the preceding cars are tracked, and the entire train formation is coordinated and controlled when the preceding cars are forming a train, thereby ensuring the safety of the virtual coupled train operation and improving the efficiency of the virtual coupled train operation. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is an overall architecture diagram of an embodiment of a virtual coupled train motion state sensing system according to the present invention;

[0032] Reference numerals: Integrated host 1, Functional module 2, CPU processor 11, GPU processor 12, Communication interface board 13, Camera module 21, Inertial measurement module 22, RFID antenna 23, Radar module 24, Long-focus camera 211, Short-focus camera 212, Secondary radar 241, LiDAR 242, Millimeter-wave radar 243. Detailed Implementation

[0033] This invention provides a sensing system for the motion status of a virtual coupled train, which is used to acquire the motion parameters of the preceding train in real time, thereby tracking the preceding train, and to perform coordinated control of the entire train formation when the preceding train is in formation, so as to ensure the safety of the virtual coupled train operation.

[0034] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0035] Please see Figure 1 , Figure 1 The present application provides an overall architecture diagram of a sensing system for the motion status of a virtual coupled train. The system includes: an integrated host 1 and a functional module 2 electrically connected to the current train, and an RFID tag installed on the preceding train. The functional module 2 includes: a camera module 21, a radar module 24, an inertial measurement module 22, and an RFID antenna 23.

[0036] The camera module 21 is used to identify the preceding vehicle;

[0037] The radar module 24 is used to measure the real-time speed of the current train; and to measure the relative distance when the train is coupled with the preceding train to form a trainset; and to measure the relative speed between the preceding train and the current train when the train is coupled with the preceding train to form a trainset.

[0038] The inertial measurement module 22 is used to acquire the radial acceleration of the current train;

[0039] The integrated host 1 is used to establish a train formation based on the real-time speed and radial acceleration of the current train and the preceding train; and to track the preceding train based on the relative distance between the train and the preceding train during the formation operation, and the relative speed between the preceding train and the current train, through the RFID antenna 23 and the RFID tag installed on the preceding train.

[0040] It should be noted that virtual coupling refers to two or more train formations that achieve close-range tracking and coordinated operation through wireless car-to-car communication, forming a virtual (without physical coupler connection) large train formation. Virtual coupling is a new technological form that improves the flexibility of rail transit and addresses tidal passenger flow and express train operations at major stations.

[0041] An inertial measurement unit (IMU) is a crucial device that measures and calculates the acceleration and angular velocity of an object in three different directions. Therefore, IMUs are widely used in various fields, including navigation, motion control, aerospace, and robotics. Specifically, an IMU calculates an object's position, velocity, and attitude information by measuring its acceleration and angular velocity. It typically consists of multiple sensors, such as accelerometers, gyroscopes, and magnetometers, which detect the object's motion state through minute vibrations and rotations. By calculating and analyzing these motion states, the IMU can determine the object's position, velocity, and attitude information, thereby enabling applications such as navigation and control.

[0042] The virtual coupled train motion state perception system of this invention can continuously and reliably autonomously perceive the kinematic parameters of the preceding train and the current train through the radar module 24 and the inertial measurement module 22 during the operation of the virtual coupled train, without relying on the current train's signal system and network control system. The perception results of the system can be used for the coordinated control of train formation and collision protection, supporting the virtual coupled train formation operation.

[0043] Furthermore, the camera module 21 includes: a telephoto camera 211 and a short-focus camera 212;

[0044] The telephoto camera 211 is used to acquire targets of preceding trains that are beyond a preset distance from the train.

[0045] The short-focus camera 212 is used to compensate for changes in field of view caused by railway curves when the train is coupled with the preceding train to form a marshalling group.

[0046] In this embodiment of the invention, a camera module 21 is composed of a combination of a long-focus camera 211 and a short-focus camera 212. The long-focus camera 211 acquires the target of the preceding train beyond a preset distance, thereby achieving target acquisition of the preceding train at a greater distance. The short-focus camera 212 compensates for changes in field of view caused by railway curves when the train is coupled with the preceding train to form a marshalling train, i.e., blind spot filling, thereby improving curve adaptability. Combining the characteristics of different sensors in the system, a distance-level and multi-segment progressive fusion method is adopted to achieve target matching and stable tracking and locking of the preceding train.

[0047] Furthermore, the radar module 24 includes: a secondary radar 241, a lidar 242, and a millimeter-wave radar 243.

[0048] The lidar 242 is used to determine the speed state of the current train, and when the speed state is low, to measure the real-time speed of the current train; and when the train is coupled with the preceding train to form a train formation, to continuously acquire the real-time distance between the preceding train and the current train at a frequency of 10Hz.

[0049] Millimeter-wave radar 243 is used to measure the relative speed between the preceding vehicle and the vehicle itself, and to measure the absolute speed of the vehicle itself.

[0050] The secondary radar 241 is used to determine the target acquisition and ranging of a preceding vehicle on the same track at a preset distance based on the RFID tag and the RFID antenna 23.

[0051] It should be noted that the LiDAR 242 is a device that measures distance and detects targets based on laser technology. It calculates the distance between the object and the radar by emitting a pulsed laser beam and measuring the time it takes for the laser beam to bounce back. The LiDAR 242 offers advantages such as high accuracy, high-density data, high-speed imaging capabilities, and adaptability to various environments.

[0052] Millimeter-wave radar 243 is a radar technology based on millimeter-wave high-frequency electromagnetic waves. It utilizes radio frequencies outside the microwave band to transmit and detect radar signals with high bandwidth and high resolution. Compared to traditional radar technologies, millimeter-wave radar 243 has a higher frequency and shorter wavelength, resulting in higher resolution and better penetration, enabling more accurate detection of information such as the position, speed, and direction of moving targets.

[0053] Secondary radar 241 refers to radar technology based on radio or electromagnetic wave signals such as millimeter waves or infrared rays. Unlike traditional radar, secondary radar 241 does not directly transmit radar signals, but uses other transmission media as a source of detection signals to measure and analyze their interactions with other objects or obstacles, thereby achieving functions such as ranging, image reconstruction, and environmental perception.

[0054] The virtual coupled train motion state sensing system of this invention includes the following steps when measuring the motion state of the preceding trains:

[0055] (1) Target recognition. The camera module 21, consisting of a long-focus camera 211 and a short-focus camera 212, performs target detection and recognition on the preceding train that is about to be virtually coupled. The detection includes the detection of the preceding train, the distance (long-focus and short-focus binocular visual depth estimation value), and whether it is on the current track; and the recognition of the type of the preceding train and the number of the train in front of the train.

[0056] (2) Target Matching. As the virtual coupled train gradually approaches, various types of sensors sequentially detect the preceding train target. After the long- and short-focus binocular camera module 21 stably detects and identifies the preceding train, it first performs result-level fusion target matching with the secondary radar 241, based on the target distance and running on the same track. After the lidar 242 detects the preceding train, it performs pixel-level fusion target matching with the long- and short-focus binocular camera module 21 in space to obtain accurate target distance and position information. After the millimeter-wave radar 243 detects the preceding train, it performs result-level target matching with the fused target obtained by the camera and lidar 242 in space to obtain the relative speed of the target. Finally, all sensors detect the target train and achieve fusion.

[0057] (3) Target tracking and locking. The perception system continuously detects the target train, with the detection results updated every 100ms. Single target tracking (STT) is used to record the trajectory of the preceding train. At the same time, the Kalman filter (KF) algorithm is used to predict the motion state of the preceding train. The lidar 242 provides precise distance input, the millimeter-wave radar 243 provides relative speed input, and the IMU provides the acceleration correction input for the train itself.

[0058] The LiDAR 242 is used to perform high-precision distance measurement and accurate speed measurement at low speeds during train coupling and formation operation.

[0059] (4) The relative speed between the preceding vehicle and the vehicle itself, as well as the absolute speed of the vehicle itself, are measured by the millimeter-wave radar 243.

[0060] (5) Target acquisition and ranging of vehicles following the same track at long distances is achieved through secondary radar 241 and RFID. 12

[0061] Furthermore, the integrated host 1 includes: a CPU processor 11, a GPU processor 12, and a communication interface board 13;

[0062] The CPU processor 11 is used to use a preset algorithm to predict the motion state of the preceding vehicle based on the relative distance and the relative speed, obtain a prediction result, and track the preceding vehicle according to the prediction result.

[0063] The GPU processor 12 is used to match the image information acquired by the camera module 21 and the motion state data acquired by the radar module 24;

[0064] The communication interface board 13 is used to provide a data interface for the functional unit.

[0065] In this embodiment of the invention, the integrated embedded platform host integrates main functional units such as CPU processor 11, GPU processor 12, and communication interface board 13. The CPU processor 11 is used to process point cloud clustering and ranging of lidar 242, velocity measurement of millimeter-wave radar 243, communication ranging of secondary radar 241, pose and acceleration measurement of IMU, and tag information of RFID. The GPU processor 12 performs machine vision image recognition and sensor information fusion. The communication interface board 13 provides data interfaces for each functional unit and sensor, and finally converts the data information into data information transmitted via Ethernet.

[0066] Furthermore, the lidar 242 is specifically used to: determine whether the real-time speed of the current train is less than 10 km / h; if so, determine that the speed state of the current train is low speed.

[0067] Furthermore, the lidar 242 is specifically used for:

[0068] The real-time speed of the current train is determined by acquiring the relative position change data of the current train in the low-speed state over a preset measurement period.

[0069] In an optional embodiment, the lidar 242 is further specifically used to: continuously acquire distance information between the preceding train and the current train at a preset acquisition frequency when the train is coupled with the preceding train to form a train formation.

[0070] Specifically, considering the characteristics of different radars, the virtual coupled train motion state sensing system of the present invention achieves relative distance measurement, absolute position positioning, absolute speed measurement, and relative speed measurement through the following methods:

[0071] (1) Relative Distance Measurement: After the target identification, track alignment, and locking of the preceding vehicle are completed, relative distance measurement is continuously performed. Different distance values ​​with varying accuracies can be obtained using secondary radar 241, camera module 21, lidar 242, and millimeter-wave radar 243. The distance measurement result from the secondary radar 241, which has the highest reliability, is then used as a reference benchmark. The high-precision distance measurement value from lidar 242 is used as the basis for correction. After correction, the validity of the correction result is determined using the distance values ​​measured by camera module 21 and millimeter-wave radar 243. This results in a relative distance measurement with an accuracy of no more than 0.1m relative to the preceding vehicle.

[0072] (2) Absolute Positioning: A sparse point cloud map of the entire line is constructed using LiDAR 242. The 100-meter markers along the track are identified by camera module 21, and the position is corrected by combining the current train's RFID tag to quickly determine the map search range. Then, the point cloud data collected in real time by LiDAR 242 is processed by inertial measurement module 22 to correct the current train's movement and vibration data. After correction, it is quickly matched with the pre-collected sparse map to determine the precise position of the current train on the entire line. Thus, an absolute position positioning accuracy of no more than 0.5m is obtained.

[0073] (3) Absolute speed measurement: In high-speed scenarios (generally 10 km / h and above), taking advantage of the fact that most targets within the emission angle range of the millimeter-wave radar 243 are stationary, the multiplicity of the speed measurement results for each target is taken to determine the relative speed between the current train and stationary objects on the ground, thereby indirectly measuring the absolute speed of the current train itself; in low-speed scenarios, the relative position change of the sleepers is measured by the lidar 242 with a stable period of 100 ms to obtain high-precision speed information. By combining the millimeter-wave radar 243 and the lidar 242, high-precision measurement of the absolute speed of the current train in both high-speed and low-speed ranges is achieved, with a measurement accuracy of up to 0.1 m / s.

[0074] (4) Relative Speed ​​Measurement: After the target in the preceding train is identified, and the same track is determined and locked, the relative speed of the preceding train can be continuously measured. During the measurement process, the millimeter-wave radar 243 directly measures the relative speed of the preceding train. The reference speed is obtained by using the ranging information of the stable cycle of the secondary radar 241 and the lidar 242. When the difference between the relative speed measured by the millimeter-wave radar and the target is less than 1%, the speed measurement by the millimeter-wave radar 243 is considered valid. When the relative speed with the preceding train is very small, that is, when the train is running stably in coupling, the speed measurement accuracy of the millimeter-wave radar 243 will drop significantly. At this time, the lidar 242 is used to continuously output high-precision ranging information according to the pre-set acquisition frequency to calculate the relative speed between the current train and the preceding train. Thus, even when the relative speed between the current train and the preceding train is small, a speed measurement accuracy of 0.1 m / s can still be achieved.

[0075] Furthermore, the preset acquisition frequency is 10Hz.

[0076] Furthermore, the CPU processor 11 is specifically used to: track the preceding vehicles using a single-target tracking method based on the prediction results.

[0077] It's important to note that single-object tracking refers to tracking a single target within a video or image sequence. Its purpose is to determine the target's position within consecutive frames and, where possible, estimate its velocity and orientation. Common single-object tracking methods include color-based tracking, shape-based tracking, motion-based tracking, feature-based tracking, and deep learning-based tracking.

[0078] Furthermore, the preset algorithm is the Kalman filter algorithm.

[0079] It should be noted that the Kalman filter algorithm is an algorithm for estimating the state of a system, based on a linear dynamic system model and the Gaussian noise assumption. It iteratively updates the estimated system state using measurement data and the system model, and estimates the uncertainty of the system state. It is widely used in control systems, navigation, robotics, signal processing, and other fields.

[0080] In this embodiment of the invention, by combining the Kalman filtering algorithm with the single-target tracking method, the operating status of the preceding train can be better determined, thereby improving the accuracy and stability of the current train when tracking the preceding train.

[0081] The system designed in this invention mainly operates in the following four scenarios, and the corresponding strategies for each scenario are as follows:

[0082] (1) In the independent operation state, the current train itself is the first train in the virtual coupling formation, or there is no preceding train in the sequence. At this time, the current train does not have the need to establish a virtual coupling operation with the preceding train. The system designed in this embodiment of the invention is in obstacle detection mode, that is, it only detects obstacles that pose a collision risk in the limit in front of the train and is used as an active collision avoidance system. Each sensor detects the target in front indiscriminately.

[0083] (2) When the train receives the command to establish a coupling, the system designed in this embodiment of the invention switches to coupling mode and begins to use the secondary radar 241 based on highly reliable vehicle-to-vehicle communication to confirm whether the distance and running track of the preceding train meet the requirements for establishing a virtual coupling (the distance between the two trains is less than 500m and they are running on the same track). If the requirements are met, the current train is allowed to approach the preceding train further and sequentially use the long-focus camera 211, short-focus camera 212, lidar 242, and millimeter-wave radar 243 to detect and match the target of the preceding train. After all the sensors have captured the target of the preceding train, the system enters the target locking state and notifies the train to complete the coupling establishment.

[0084] (3) During the virtual coupling and merging operation of the current train, the motion state perception system of the virtual coupling train in this embodiment of the invention continuously measures the kinematic parameters of the locked preceding train target. The measurement content includes, but is not limited to, the relative distance and relative speed between the preceding train and the current train, the absolute position and absolute speed of the current train on the track, etc., and multicasts them to the train network control system and signal system via the Ethernet TRDP protocol for collaborative control during the operation of the virtual coupling and merging train; when the target is lost, the virtual coupling train is notified to end the coupling operation and brake to guide safety.

[0085] (4) During normal coupling and decoupling, the current train sends a signal to notify the virtual coupling train motion status perception system of this embodiment of the invention, and then enters the coupling and decoupling state. As the distance between the current train and the preceding train increases, the millimeter-wave radar 243, lidar 242, short-focus camera 212 and long-focus camera 211 will successively exceed the target detection range. In the process of gradually moving away from the preceding train, the secondary radar 241 is used to monitor the train spacing, so that each sensor switches smoothly within the pre-set detection range boundary interval, avoiding the loss of the target during decoupling and causing emergency braking for guidance safety.

[0086] This application provides a virtual coupled train motion state sensing system, comprising: an integrated host 1 and a functional module 2 electrically connected to the current train, and an RFID tag installed on the preceding train; the functional module 2 includes: a camera module 21, a radar module 24, an inertial measurement module 22, and an RFID antenna 23; the camera module 21 is used to identify the preceding train; the radar module 24 is used to measure the real-time speed of the current train; and to measure the relative distance when coupled with the preceding train to establish a train formation; and to measure the distance when coupled with the preceding train. During train formation operation, the relative speed between the preceding train and the current train is measured; the inertial measurement module 22 is used to acquire the radial acceleration of the current train; the integrated host 1 is used to establish train formation operation by coupling with the preceding train based on the real-time speed and radial acceleration of the current train; and based on the relative distance between the train and the preceding train during train formation operation, and the relative speed between the preceding train and the current train, the preceding train is tracked via the RFID antenna 23 and the RFID tag installed on the preceding train.

[0087] Based on radar module 24 and inertial measurement module 22, the motion parameters of the preceding cars in the virtual coupled train are acquired in real time. Then, with the assistance of integrated host 1, the preceding cars are tracked, and the entire train formation is coordinated and controlled when the preceding cars are forming a formation, thereby ensuring the safety of the virtual coupled train operation and improving the efficiency of the virtual coupled train operation.

[0088] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0089] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0091] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods described in the various embodiments of this application through a computer device (which may be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0092] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A sensing system for the motion state of a virtual coupled train, characterized in that, include: The current train's electrical connections include integrated mainframes and functional modules, as well as RFID tags installed on the preceding trains; The functional modules include: a camera module, a radar module, an inertial measurement module, and an RFID antenna; The camera module is used to identify the preceding vehicle; The radar module is used to measure the real-time speed of the current train; and to measure the relative distance when the train is coupled with the preceding train to form a trainset; and to measure the relative speed between the preceding train and the current train when the train is coupled with the preceding train to form a trainset. The inertial measurement module is used to acquire the radial acceleration of the current train; The integrated host is used to establish a train formation based on the real-time speed and radial acceleration of the current train and the preceding train; and to track the preceding train based on the relative distance between the train and the preceding train during the formation operation, and the relative speed between the preceding train and the current train, through the RFID antenna and the RFID tag installed on the preceding train. The radar module includes: secondary radar, lidar, and millimeter-wave radar. The lidar is used to determine the speed state of the current train, and when the speed state is low, to measure the real-time speed of the current train; and when the train is coupled with the preceding train to form a train formation, to continuously acquire the real-time distance between the preceding train and the current train at a frequency of 10Hz. Millimeter-wave radar is used to measure the relative speed between the preceding vehicle and the vehicle itself, as well as the absolute speed of the vehicle itself. The secondary radar is used to determine the target acquisition and ranging of a preceding vehicle on the same track at a preset distance, based on the RFID tag and the RFID antenna.

2. The virtual coupled train motion state sensing system according to claim 1, characterized in that, The camera module includes: a long-focus camera and a short-focus camera; The telephoto camera is used to acquire targets of preceding trains that are beyond a preset distance from the train itself; The short-focus camera is used to compensate for changes in field of view caused by railway curves when the train is coupled with the preceding train to form a marshalling group.

3. The virtual coupled train motion state sensing system according to claim 1, characterized in that, The integrated host includes: a CPU processor, a GPU processor, and a communication interface board; The CPU processor is used to use a preset algorithm to predict the motion state of the preceding vehicle based on the relative distance and the relative speed, obtain a prediction result, and track the preceding vehicle according to the prediction result; The GPU processor is used to match the image information acquired by the camera module and the motion state data acquired by the radar module. The communication interface board is used to provide a data interface for the functional modules.

4. The virtual coupled train motion state sensing system according to claim 1, characterized in that, The lidar is specifically used to: determine whether the real-time speed of the current train is less than 10 km / h; if so, determine that the current train's speed state is low speed.

5. The virtual coupled train motion state sensing system according to claim 4, characterized in that, The lidar is also specifically used for: The real-time speed of the current train is determined by acquiring the relative position change data of the current train in the low-speed state over a preset measurement period.

6. The virtual coupled train motion state sensing system according to claim 5, characterized in that, The lidar is also specifically used for: when the train is coupled with the preceding train to form a train formation, continuously acquiring distance information between the preceding train and the current train according to a pre-set acquisition frequency.

7. The virtual coupled train motion state sensing system according to claim 6, characterized in that, The preset acquisition frequency is 10Hz.

8. The virtual coupled train motion state sensing system according to claim 3, characterized in that, The CPU processor is specifically used to: track the preceding vehicles using a single-target tracking method based on the prediction results.

9. The virtual coupled train motion state sensing system according to claim 8, characterized in that, The preset algorithm is the Kalman filter algorithm.

Images