A new method for detecting track geometry parameters

Abstract

The present invention belongs to the field of track detection technology. A new type of track geometry parameter detection method is provided, including: controlling a 2D laser profiler to scan the profile of the rail on which the train is traveling according to a set detection frequency to obtain laser image data; using high-speed image processing technology to extract the contour curve of the rail from the laser image data, calculating the track profile based on the contour curve, and calculating the track gauge based on the two track profiles; using an inertial reference measurement system arranged on the train body to detect the first inertial data of the train body, and calculating the displacement trajectory of the 2D laser profiler on both sides of the track inspection beam relative to the earth based on the first inertial data; calculating the track irregularity parameters based on the arrangement distance and displacement trajectory between the 2D laser profiler and the rail top. The present invention can quickly detect the track geometry parameters during the normal running of the train, and the detection efficiency is significantly higher than the method of manual detection beside the track.

Description

Technical Field

[0001] The present invention relates to the field of track detection technology, and in particular to a novel method for detecting track geometric parameters. Background Art

[0002] By testing the geometric parameters of train tracks, various track irregularities and defects caused by the power of trains can be detected in time, thereby improving the safety of train operation. The existing track geometric parameter detection method mainly relies on manual detection by detection personnel at the trackside. The detection efficiency is too low and it is difficult to meet the current demand for efficient and accurate detection of track geometric parameters. The solution of the present invention aims to improve this technical problem. Summary of the invention

[0003] In this regard, the present invention provides a new track geometry parameter detection method, system, electronic device, computer storage medium and computer program product to solve the above technical problems.

[0004] The present invention provides a novel method for detecting track geometric parameters, the method comprising the following steps:

[0005] Control the 2D laser profiler to scan the rail profile of the train according to the set detection frequency to obtain laser image data;

[0006] Using high-speed image processing technology to extract the contour curve of the rail from the laser image data, calculating the track profile based on the contour curve, and calculating the track gauge based on the two track profiles;

[0007] Using an inertial reference measurement system arranged on the train body to detect first inertial data of the train body, and calculating displacement tracks of 2D laser profilers on both sides of the track inspection beam relative to the ground according to the first inertial data;

[0008] The track irregularity parameter is calculated based on the layout distance between the 2D laser profiler and the rail top and the displacement trajectory.

[0009] Optionally, before controlling the 2D laser profiler to scan the rail profile of the train according to the set detection frequency, the method further includes:

[0010] Predict the buffer stability time corresponding to the train;

[0011] Determining whether the train has started according to the second inertial data of the train body detected by the inertial reference measurement system, and starting timing if it is determined that the train has started;

[0012] When the timing reaches the buffer stabilization time, a detection trigger signal is generated, and the detection trigger signal is used to trigger and control the 2D laser profiler to scan the rail profile of the train according to the set detection frequency, and to use the first inertial data of the train body detected by the inertial reference measurement system.

[0013] Optionally, the predicting of the buffer stability duration corresponding to the train includes:

[0014] The number of passengers carried and the number of first boarded passengers in the inspection carriage at the station are obtained from the train ticketing system; the inspection carriage refers to the carriage on the train equipped with a 2D laser profiler and an inertial reference measurement system;

[0015] The riding distance between the carriage entrance and the platform entrance is calculated according to the parking situation of the train at the station, a first adjustment number is calculated for the riding distance according to a positive correlation, and a second boarding number is calculated by multiplying the first adjustment number by the first boarding number; wherein the first adjustment number is greater than 1;

[0016] The number of passengers carried and the second number of passengers to be boarded are input into a stable duration prediction model, and the stable duration prediction model predicts the buffer stable duration.

[0017] Optionally, the stable duration prediction model is constructed based on a graph convolutional network and LSTM;

[0018] The stable duration prediction model first randomly assigns seats to each carried passenger and each passenger to be boarded according to the carried passenger quantity and the second number of passengers to be boarded, to obtain a seat distribution map;

[0019] The graph convolutional network layer in the stable duration prediction model extracts features from the seat distribution map to obtain seating features; the LSTM layer in the stable duration prediction model performs simulation analysis on the seating features based on time features to predict the buffer stable duration.

[0020] Optionally, after calculating the track irregularity parameter, the method further includes:

[0021] A second adjustment number is calculated according to the track irregularity parameter, and a target detection frequency is calculated according to the second adjustment number and the detection frequency; wherein the second adjustment number is greater than 1;

[0022] If the target detection frequency is higher than the detection frequency, the rail profile on which the train is traveling is scanned according to the target detection frequency; if the target detection frequency is lower than the detection frequency, the rail profile on which the train is traveling is scanned according to the detection frequency.

[0023] Optionally, the train is provided with a plurality of detection carriages, and the track irregularity parameter is obtained by fusion calculation based on the displacement trajectories corresponding to each of the detection carriages.

[0024] The present invention also provides a novel track geometry parameter detection system, the system comprising a processor and a memory, the processor calling the program code in the memory to implement the following steps:

[0025] Control the 2D laser profiler to scan the rail profile of the train according to the set detection frequency to obtain laser image data;

[0026] Using high-speed image processing technology to extract the contour curve of the rail from the laser image data, calculating the track profile based on the contour curve, and calculating the track gauge based on the two track profiles;

[0027] Using an inertial reference measurement system arranged on the train body to detect first inertial data of the train body, and calculating displacement tracks of 2D laser profilers on both sides of the track inspection beam relative to the ground according to the first inertial data;

[0028] The track irregularity parameter is calculated based on the layout distance between the 2D laser profiler and the rail top and the displacement trajectory.

[0029] The present invention also provides an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement any of the methods described above.

[0030] The present invention also provides a computer storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0031] The present invention also provides a computer program product, which implements any of the above methods when the computer program product is executed by a processor.

[0032] The solution of the present invention sets the track geometry parameter detection equipment on the train body, so that the track geometry parameters can be quickly detected during the normal running of the train. Compared with the method of manual detection beside the track, the detection efficiency is significantly higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0034] Figure 1 It is a flow chart of a novel method for detecting track geometric parameters disclosed in an embodiment of the present invention;

[0035] Figure 2 It is a schematic diagram of the structure of the stable duration prediction model disclosed in the embodiment of the present invention;

[0036] Figure 3 It is a structural schematic diagram of a novel track geometry parameter detection device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0038] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0039] like Figure 1 As shown, the embodiment of the present invention discloses a novel method for detecting track geometric parameters, the method comprising the following steps:

[0040] Control the 2D laser profiler to scan the rail profile of the train according to the set detection frequency to obtain laser image data;

[0041] Using high-speed image processing technology to extract the contour curve of the rail from the laser image data, calculating the track profile based on the contour curve, and calculating the track gauge based on the two track profiles;

[0042] Using an inertial reference measurement system arranged on the train body to detect first inertial data of the train body, and calculating displacement tracks of 2D laser profilers on both sides of the track inspection beam relative to the ground according to the first inertial data;

[0043] The track irregularity parameter is calculated based on the layout distance between the 2D laser profiler and the rail top and the displacement trajectory.

[0044] The present invention arranges two detection systems on the train body, namely, an inertial reference measurement system and two 2D laser profilers, wherein the two 2D laser profilers are respectively arranged at the two side ends of the track inspection beam to detect the left and right rails. The inertial reference measurement system can measure the inertial data (including the posture data of the track inspection beam and the acceleration data of the track inspection beam) generated when the train passes through the corresponding track, and the 2D laser profiler can scan and obtain the profile of the rail on which the train is currently traveling, and use high-speed image processing technology to extract the contour curve of the rail from the laser image data, calculate the track profile based on the contour curve, and calculate the track gauge based on the left and right track profiles. At the same time, the displacement trajectory of the profilers on both sides of the track inspection beam relative to the earth can be calculated based on the first inertial data. When the track is very smooth, the measured displacement trajectory should be an approximately smooth straight line. If there are protrusions or pits on the track, it will cause the train to vibrate, resulting in a fluctuating area on the displacement trajectory. Furthermore, since the distance between the 2D laser profiler and the rail top is known, the track irregularity parameter can be calculated based on the distance and the displacement trajectory obtained above. When the track gauge is not within the normal track gauge range and / or the track irregularity parameter is too high, an alarm message can be output, and the alarm message includes the track position.

[0045] Therefore, the solution of the present invention sets the track geometry parameter detection equipment on the train body, so that the track geometry parameters can be quickly detected during the normal operation of the train. Compared with the method of manual detection beside the track, the detection efficiency is significantly higher.

[0046] Optionally, before controlling the 2D laser profiler to scan the rail profile of the train according to the set detection frequency, the method further includes:

[0047] Predict the buffer stability time corresponding to the train;

[0048] Determining whether the train has started according to the second inertial data of the train body detected by the inertial reference measurement system, and starting timing if it is determined that the train has started;

[0049] When the timing reaches the buffer stabilization time, a detection trigger signal is generated, and the detection trigger signal is used to trigger and control the 2D laser profiler to scan the rail profile of the train according to the set detection frequency, and to use the first inertial data of the train body detected by the inertial reference measurement system.

[0050] In this embodiment, the track geometry parameter detection system of the present invention can be set on a train in normal operation, so there is no need for a special detection vehicle and the normal operation of the train is not affected. However, the back and forth movement of passengers on a normally operating train will cause the train itself to vibrate to a certain extent, and this self-vibration is particularly obvious when there are many moving passengers, which will cause the inertial reference measurement system to measure larger inertial data, and correspondingly, the displacement trajectory obtained later will also be distorted.

[0051] In view of the above technical problems, the present invention first obtains the buffer stability time corresponding to the train, controls the inertial reference measurement system to detect the second inertial data of the train body when the train stops, and judges whether the train has started. If it is determined that the train has started, the timing is started, and when the timing reaches the buffer stability time obtained above, a detection trigger signal is generated. The detection trigger signal is used to trigger the formal implementation of the above technical solution of the present invention, that is, to trigger the control of the 2D laser profiler to scan the rail profile of the train according to the set detection frequency, and to use the first inertial data of the train body detected by the inertial reference measurement system.

[0052] It should be noted that the stopped state of the train corresponds to the stage of getting on and off passengers. During this stage, the deadweight of the train car undergoes a significant change, and the inertial data of the train body detected by the inertial reference measurement system cannot be used to analyze whether there are bumps, pits, etc. on the track, otherwise it is easy to cause misjudgment. At the same time, in the early stage of the train start, since the passengers have not yet completed their seats, many passengers are still moving frequently at this time, resulting in the inertial data of the train body detected by the inertial reference measurement system still being unsuitable for the inertial data of the train body detected by the inertial reference measurement system. Therefore, the present invention is arranged that when the train is in the start state and the start time reaches the buffer stability time, it is determined that most of the passengers at this time have been seated, and the interference from the passengers is basically eliminated. At this time, the geometric parameters of the track are detected based on the above-mentioned scheme of the present invention.

[0053] Optionally, the predicting of the buffer stability duration corresponding to the train includes:

[0054] The number of passengers carried and the number of first boarded passengers in the inspection carriage at the station are obtained from the train ticketing system; the inspection carriage refers to the carriage on the train equipped with a 2D laser profiler and an inertial reference measurement system;

[0055] The riding distance between the carriage entrance and the platform entrance is calculated according to the parking situation of the train at the station, a first adjustment number is calculated for the riding distance according to a positive correlation, and a second boarding number is calculated by multiplying the first adjustment number by the first boarding number; wherein the first adjustment number is greater than 1;

[0056] The number of passengers carried and the second number of passengers to be boarded are input into a stable duration prediction model, and the stable duration prediction model predicts the buffer stable duration.

[0057] In this embodiment, the buffer stability time is roughly the time from the last passenger in the detected car to the time when most passengers are seated. During this time, passengers look for seats and place luggage in the car, resulting in many passengers still in motion. At this time, it is not appropriate to detect the track geometry parameters. The above time is mainly determined by the number of passengers already on board and the number of passengers boarding in the car. Generally speaking, the more passengers on board and the more passengers boarding in the car, the more time it takes for the newly boarded passengers to complete the above boarding and seating process. The fewer passengers on board and the fewer passengers boarding in the car, the less time it takes for the newly boarded passengers to complete the above boarding and seating process. Based on this, the present invention constructs a stable time prediction model, which conducts an in-depth analysis of the number of passengers on board and the number of passengers to be boarded, so as to predict the corresponding buffer stability time of the passengers at the station.

[0058] In addition, the number of passengers already carried and the number of first boarded passengers in the detection carriage at this station can be directly obtained from the train ticketing system, and the number of passengers detected in the carriage from other carriages must also be considered. Specifically, the passengers in the carriage detected from other carriages are mainly those who choose to enter the train first due to tight travel time and then go to the destination carriage from the carriage. The number of passengers who implement this type of travel behavior is positively correlated with the travel distance between the carriage entrance and the platform entrance. That is, the greater the distance between the detection carriage and the platform entrance, the more passengers will implement the above-mentioned travel behavior due to tight travel time, and vice versa, there will be fewer passengers who implement the above-mentioned travel behavior due to tight travel time. Based on this, the present invention is arranged to first calculate the riding distance between the entrance of the carriage and the entrance of the platform (from which passengers formally enter the platform area) according to the parking situation of the train at this station (from which the approximate parking position of each carriage of the train can be determined), and then convert the riding distance according to the positive correlation to obtain the first adjustment number, and multiply the first adjustment number by the first passenger boarding number obtained above to calculate the second passenger boarding number. The second passenger boarding number can be used to represent the actual "non-seated" passenger volume of the detection carriage within the above-mentioned time period. However, the present invention does not limit the specific formula form of the above-mentioned positive correlation.

[0059] Optionally, the stable duration prediction model is constructed based on a graph convolutional network and LSTM;

[0060] The stable duration prediction model first randomly assigns seats to each carried passenger and each passenger to be boarded according to the carried passenger quantity and the second number of passengers to be boarded, to obtain a seat distribution map;

[0061] The graph convolutional network layer in the stable duration prediction model extracts features from the seat distribution map to obtain seating features; the LSTM layer in the stable duration prediction model performs simulation analysis on the seating features based on time features to predict the buffer stable duration.

[0062] In this embodiment, the present invention constructs the above-mentioned stable duration prediction model based on graph convolutional network and LSTM, such as Figure 2 As shown in the figure, the stable duration prediction model includes an input layer, a graph convolutional network layer, an LSTM layer and an output layer.

[0063] The prediction process of the stable duration prediction model is as follows: the stable duration prediction model first randomly assigns seats to the passengers already on board and the passengers waiting to board based on the seat distribution model diagram of the detection carriage to obtain a seat distribution diagram, which is the virtual final seating diagram obtained by simulation. The graph convolutional network layer then extracts features from the seat distribution diagram to obtain seating features. Finally, the LSTM layer performs time-based simulation analysis on the seating features to predict the buffer stable duration.

[0064] It should be noted that LSTM is particularly suitable for capturing the temporal dependency of corresponding data from time series data. The present invention uses the LSTM layer to perform simulation analysis based on time characteristics on the seating features extracted by the graph convolutional network layer, that is, to determine the seating time trajectories of various passengers through simulation, and to average the total time consumption corresponding to all time trajectories, and use the average as the overall seating time of this group of passengers, that is, to determine the buffer stability time. Of course, compared with the overall seating time, the buffer stability time can also add a certain buffer coefficient (greater than 1) to ensure that the buffer stability time is credible.

[0065] Optionally, after calculating the track irregularity parameter, the method further includes:

[0066] A second adjustment number is calculated according to the track irregularity parameter, and a target detection frequency is calculated according to the second adjustment number and the detection frequency; wherein the second adjustment number is greater than 1;

[0067] If the target detection frequency is higher than the detection frequency, the rail profile on which the train is traveling is scanned according to the target detection frequency; if the target detection frequency is lower than the detection frequency, the rail profile on which the train is traveling is scanned according to the detection frequency.

[0068] In this embodiment, the roughness parameter of the track can be calculated based on the layout distance and displacement trajectory between the 2D laser profiler and the rail top. When the roughness parameter is higher than a certain threshold, it is determined that there are bumps or pits on the track, and the corresponding roughness parameter is larger. At the same time, the presence of bumps or pits will cause the laser image data detected by the 2D laser profiler to be distorted (the vibration generated by the train during high-speed driving may cause the relative position between the laser transmitter and the receiver to change, thereby affecting the accuracy of the measurement), and the larger the roughness parameter, the greater the corresponding distortion probability.

[0069] In response to this technical problem, the present invention is configured to adaptively adjust the detection frequency of the 2D laser profiler. The second adjustment number is determined based on the track unevenness parameter obtained by the above detection and the corresponding conversion method (such as a reference table). The second adjustment number in the reference table is positively correlated with the track unevenness parameter. The target detection frequency can be calculated by multiplying the above preset detection frequency by the second adjustment number. In addition, the detection frequency of the 2D laser profiler should not be lower than the above preset detection frequency. Therefore, when the target detection frequency is higher than the detection frequency, the target detection frequency is executed, otherwise the preset detection frequency continues to be executed. With such a setting, it is possible to appropriately increase the detection frequency of the 2D laser profiler when encountering bumps or pits, so as to reduce the distortion of the laser image data caused by subsequent bumps or pits.

[0070] In addition, after the track irregularity parameter is lower than the parameter threshold for a set period of time (for example, 1 minute), the target detection frequency can be adjusted back to the preset detection frequency.

[0071] Optionally, the train is provided with a plurality of detection carriages, and the track irregularity parameter is obtained by fusion calculation based on the displacement trajectories corresponding to each of the detection carriages.

[0072] In this embodiment, the present invention can also deploy 2D laser profilers and inertial reference measurement systems on multiple carriages of the train, and calculate a displacement trajectory based on the detection data of the 2D laser profilers and inertial reference measurement systems deployed on each carriage. Since the deployment distances between the 2D laser profilers on each detection carriage and the rail top are the same, all of these displacement trajectories can be fused and calculated (for example, the average value can be calculated) to obtain a track irregularity parameter with higher credibility. Through this processing method, the probability of excessive deviation of the track irregularity parameter caused by looseness or detection errors of the 2D laser profiler and inertial reference measurement system on the detection carriage can be reduced.

[0073] Among them, when performing fusion calculation, it is necessary to first align the positions of multiple displacement trajectories according to the train speed and the installation distance between the 2D laser profilers on adjacent carriages, so that each displacement trajectory used for fusion calculation corresponds to the same track position.

[0074] like Figure 3 As shown, an embodiment of the present invention further discloses a novel track geometry parameter detection system, the system comprising a processor and a memory, the processor calling the program code in the memory to implement the following steps:

[0075] Control the 2D laser profiler to scan the rail profile of the train according to the set detection frequency to obtain laser image data;

[0076] Using high-speed image processing technology to extract the contour curve of the rail from the laser image data, calculating the track profile based on the contour curve, and calculating the track gauge based on the two track profiles;

[0077] Using an inertial reference measurement system arranged on the train body to detect first inertial data of the train body, and calculating displacement tracks of 2D laser profilers on both sides of the track inspection beam relative to the ground according to the first inertial data;

[0078] The track irregularity parameter is calculated based on the layout distance between the 2D laser profiler and the rail top and the displacement trajectory.

[0079] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in the above embodiment.

[0080] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method described in the above embodiment.

[0081] The embodiment of the present invention further discloses a computer program product. When the computer program product is executed by a processor, the method described in the above embodiment is implemented.

[0082] Various embodiments of the devices and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0083] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0084] In the context of the present disclosure, a computer storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A computer storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a computer storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0085] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be performed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document is not limited here.

[0086] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present disclosure is not limited by these embodiments or examples, but is only limited by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples may be omitted or replaced by their equivalent elements. In addition, each step may be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples may be combined in various ways. It is important that with the evolution of technology, many of the elements described herein may be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A new method for detecting track geometric parameters, characterized in that: include: Predict the buffer stability time corresponding to the train: obtain the number of passengers already carried and the first number of passengers to be boarded in the inspection car at this station from the train ticketing system; the inspection car is a car on the train equipped with a 2D laser profiler and an inertial reference measurement system; the riding distance between the car entrance and the platform entrance is calculated based on the parking situation of the train at this station, and the first adjustment number is calculated based on the positive correlation of the riding distance, and the second number of passengers to be boarded is calculated by multiplying the first adjustment number by the first number of passengers to be boarded; the first adjustment number is greater than 1; the number of passengers already carried and the second number of passengers to be boarded are input into the stable time prediction model, and the stable time prediction model predicts the buffer stability time; Judging whether the train has started according to the second inertial data of the train body detected by the inertial reference measurement system, and starting timing if it is determined that the train has started; When the timing reaches the buffer stability time, a detection trigger signal is generated, and the detection trigger signal is used to trigger and control the 2D laser profiler to scan the rail profile of the train according to the set detection frequency, and to use the first inertial data of the train body detected by the inertial reference measurement system; Control the 2D laser profiler to scan the rail profile of the train according to the set detection frequency to obtain laser image data; Use high-speed image processing technology to extract the rail contour curve from the laser image data, calculate the track profile based on the contour curve, and calculate the track gauge based on the two track profiles; An inertial reference measurement system arranged on the train body is used to detect first inertial data of the train body, and displacement tracks of 2D laser profilers on both sides of the track inspection beam relative to the ground are calculated based on the first inertial data; The track irregularity parameters are calculated based on the layout distance and displacement trajectory between the 2D laser profiler and the rail top.

2. A novel track geometry parameter detection method according to claim 1, characterized in that: The stable duration prediction model is constructed based on graph convolutional network and LSTM; The stable duration prediction model first randomly assigns seats to each carried passenger and each passenger to be boarded according to the carried passenger quantity and the second number of passengers to be boarded, to obtain a seat distribution map; The graph convolutional network layer in the stable duration prediction model extracts features from the seat distribution map to obtain seating features; the LSTM layer in the stable duration prediction model performs simulation analysis on the seating features based on time features to predict the buffer stable duration.

3. A novel track geometry parameter detection method according to claim 2, characterized in that: After calculating the track irregularity parameter, the method further includes: A second adjustment number is calculated according to the track irregularity parameter, and a target detection frequency is calculated according to the second adjustment number and the detection frequency; wherein the second adjustment number is greater than 1; If the target detection frequency is higher than the detection frequency, the rail profile on which the train is traveling is scanned according to the target detection frequency; if the target detection frequency is lower than the detection frequency, the rail profile on which the train is traveling is scanned according to the detection frequency.

4. A novel track geometry parameter detection method according to claim 3, characterized in that: The train is provided with a plurality of detection carriages, and the track irregularity parameter is obtained by fusion calculation based on the displacement trajectories corresponding to the detection carriages.

5. A novel track geometry parameter detection system, the system is based on the method according to any one of claims 1 to 4, the system comprises a processor and a memory, and is characterized in that: The processor calls the program code in the memory to implement the following steps: Control the 2D laser profiler to scan the rail profile of the train according to the set detection frequency to obtain laser image data; Using high-speed image processing technology to extract the contour curve of the rail from the laser image data, calculating the track profile based on the contour curve, and calculating the track gauge based on the two track profiles; Using an inertial reference measurement system arranged on the train body to detect first inertial data of the train body, and calculating displacement tracks of 2D laser profilers on both sides of the track inspection beam relative to the ground according to the first inertial data; The track irregularity parameter is calculated based on the layout distance between the 2D laser profiler and the rail top and the displacement trajectory.

6. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 4.

7. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 4.

8. A computer program product, characterized in that: When the computer program product is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images