A method, device, equipment and storage medium for determining the dirty state of a roadbed

Abstract

This article provides a method, device, equipment and storage medium for determining the dirty state of the roadbed, wherein the method includes: obtaining a radar echo signal corresponding to the roadbed of the target mileage; determining a characterization value sequence of the roadbed dirty state according to the radar echo signal; determining a selected characterization value corresponding to the target mileage according to the characterization value sequence, wherein the selected characterization value is used to represent the characterization value sequence of the target mileage; associating the actual dirtiness rate corresponding to the position point of the selected characterization value in the target mileage with the selected characterization value to obtain a roadbed dirty model; determining the roadbed dirty state corresponding to the roadbed of the target mileage according to the characterization value sequence of the roadbed dirty state and the roadbed dirty model. This article can determine the roadbed dirty state with high accuracy and improve the decision-making accuracy during roadbed maintenance.

Description

Technical Field

[0001] The present invention relates to the field of track detection, and in particular, to a method, device, equipment and storage medium for determining the dirty state of a track bed. Background Art

[0002] Gravel ballast is an important structural form of railway track. The state of gravel ballast affects the transportation speed, safety and comfort of railway lines. As the service time of gravel ballast increases, the ballast breaks and powders, the dirt on the ballast continues to accumulate, and the condition of the ballast continues to deteriorate. Due to the lack of fast and accurate means of detecting dirt on the ballast, according to the current "Rules for Repair of Conventional Railway Lines", the main basis for determining the overhaul cycle of the gravel ballast is the total weight of the line, and it is appropriately adjusted according to the evaluation results of whether the unclean rate is greater than 25% (sampled 100mm below the bottom edge of the pillow box).

[0003] Since the total weight of a line is the total mass of trains and goods passing through a line, this parameter has no direct correlation with the dirtiness of the track bed. However, when technology does not allow, the track research, management and engineering departments can only use the total weight to infer the dirtiness of the track bed. However, the dirtiness of the track bed is actually related to many factors such as the environment of the line (such as wind and sand, heavy rain, etc.), the material of the roadbed, the density of the roadbed, and the train load (the cumulative effect of the train load is the total weight). Therefore, the total weight alone cannot reflect the status of the track bed.

[0004] Making a decision on the overhaul of the roadbed based on the above-mentioned method for determining the dirty state of the roadbed is likely to result in under-repair or over-repair of the roadbed. Therefore, there is an urgent need for a method for determining the dirty state of the roadbed that can determine the dirty state of the roadbed with high accuracy and improve the accuracy of decision-making during roadbed maintenance. Summary of the invention

[0005] The purpose of the embodiments of this article is to provide a method, device, equipment and storage medium for determining the contamination state of the roadbed, which can determine the contamination state of the roadbed with high accuracy and improve the decision-making accuracy during roadbed maintenance.

[0006] To achieve the above objectives, on the one hand, an embodiment of the present invention provides a method for determining the dirty state of a roadbed, comprising:

[0007] Obtain the radar echo signal corresponding to the roadbed of the target mileage;

[0008] Determining a sequence of characterizing values ​​of a contamination state of a ballast bed according to the radar echo signal;

[0009] Determining, according to the characterization value sequence, a selected characterization value corresponding to the target mileage, wherein the selected characterization value is used to represent the characterization value sequence of the target mileage;

[0010] Associating the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage with the selected characterization value to obtain a roadbed contamination model;

[0011] The roadbed contamination state corresponding to the roadbed of the target mileage is determined according to the characterization value sequence of the roadbed contamination state and the roadbed contamination model.

[0012] Preferably, the step of obtaining a radar echo signal corresponding to the roadbed of the target mileage further includes:

[0013] The roadbed of the target mileage is sampled through the radar test system to obtain the radar echo signal corresponding to each position point in the target mileage;

[0014] Determining the characterization value sequence of the roadbed contamination state according to the radar echo signal further includes:

[0015] According to the radar echo signal corresponding to each position point in the target mileage, determining the signal time domain scanning area of ​​the radar echo signal at the set track bed depth at each position point;

[0016] The signal time domain scanning area of ​​the radar echo signal at the ballast depth at each position point is taken as the corresponding characterization value at the position point;

[0017] The characterization values ​​corresponding to all position points in the target mileage are integrated to obtain a characterization value sequence corresponding to the target mileage.

[0018] Preferably, the step of determining the signal time domain scanning area of ​​the radar echo signal at each position point for setting the ballast depth according to the radar echo signal corresponding to each position point in the target mileage further comprises:

[0019] According to the radar echo signal corresponding to each position point in the target mileage, determine a sampling point sequence of the radar echo signal for setting the ballast bed depth at each position point, and a time difference between two adjacent sampling points in the sampling point sequence;

[0020] Calculating the signal time domain scanning area of ​​each sampling point according to the radar echo signal amplitude corresponding to each sampling point in the sampling point sequence and the time difference;

[0021] The signal time domain scanning area of ​​each sampling point in the sampling point sequence is integrated to obtain the signal time domain scanning area of ​​the set track bed depth at the position point corresponding to the sampling point sequence.

[0022] Preferably, according to the characterization value sequence, a selected characterization value corresponding to the target mileage is determined, wherein the selected characterization value is used to represent the characterization value sequence of the target mileage further comprises:

[0023] Determine a multi-level selection interval according to the characterization value sequence, wherein the multi-level selection interval divides the characterization value sequence into multiple levels according to the characterization value from small to large;

[0024] A selected characterization value is selected from each level of the multi-level selection interval to obtain a selected characterization value corresponding to the target mileage.

[0025] Preferably, the step of determining the multi-level selection interval according to the characterization value sequence further comprises:

[0026] Determining the interval length according to the characterization value sequence and the number of levels of the multi-level selection interval;

[0027] The characterization values ​​in the characterization value sequence are divided into intervals of equal length from small to large to obtain multi-level selection intervals.

[0028] Preferably, the selecting a selected characterization value from each level of the multi-level selection interval to obtain the selected characterization value corresponding to the target mileage further includes:

[0029] Selecting a first selected characterization value from each level of the multi-level selection interval;

[0030] The characterization value corresponding to the position point adjacent to the first selected characterization value is determined as the second selected characterization value, and the first selected characterization value and the second selected characterization value are determined as the selected characterization values ​​corresponding to the level selection interval.

[0031] Preferably, the selecting a selected characterization value from each level of the multi-level selection interval to obtain the selected characterization value corresponding to the target mileage further includes:

[0032] A plurality of selected characterization values ​​are respectively selected from each level of the multi-level selection interval to obtain a selected characterization value corresponding to the target mileage.

[0033] Preferably, associating the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage with the selected characterization value to obtain the roadbed contamination model further includes:

[0034] Establishing a functional relationship between the actual dirtiness rate and the characterization value sequence;

[0035] Substitute the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage and the selected characterization value into the functional relationship to obtain the roadbed contamination model.

[0036] On the other hand, an embodiment of the present invention provides a device for determining the dirty state of a roadbed, the device comprising:

[0037] An acquisition module is used to acquire the radar echo signal corresponding to the roadbed of the target mileage;

[0038] A sequence determination module, used to determine a sequence of characterization values ​​of the contamination state of the ballast bed according to the radar echo signal;

[0039] a characterization value determination module, configured to determine a selected characterization value corresponding to the target mileage according to the characterization value sequence, wherein the selected characterization value is used to represent the characterization value sequence of the target mileage;

[0040] A model determination module, used for associating the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage with the selected characterization value to obtain a roadbed contamination model;

[0041] The contamination determination module is used to determine the contamination state of the roadbed corresponding to the roadbed of the target mileage according to the characterization value sequence of the contamination state of the roadbed and the roadbed contamination model.

[0042] On the other hand, the embodiments of the present invention further provide a computer device, including a memory, a processor, and a computer program stored in the memory, wherein when the computer program is executed by the processor, the instructions of any one of the above methods are executed.

[0043] On the other hand, the embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor of a computer device, the computer program executes instructions according to any one of the methods described above.

[0044] It can be seen from the technical solutions provided in the above embodiments of this invention that after determining the characterization value sequence of the roadbed contamination state, the embodiments of this invention select some representative selected characterization values ​​from the characterization value sequence, and determine the actual contamination rate of the selected characterization value at the position point in the target mileage. After associating the actual contamination rate with the selected characterization value, a roadbed contamination model can be obtained. Substituting the characterization value sequence into the roadbed contamination model can determine the roadbed contamination rate corresponding to the roadbed of the target mileage, and then the roadbed contamination state can be determined with high accuracy, thereby improving the decision-making accuracy during roadbed maintenance.

[0045] In order to make the above and other purposes, features and advantages of this article more obvious and easy to understand, the following specifically cites preferred embodiments and describes them in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of this article or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of this article. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 A schematic flow chart of a method for determining a dirty state of a ballast provided in an embodiment of the present invention is shown;

[0048] Figure 2 A schematic diagram for indicating the installation position of a radar antenna provided in an embodiment of this document is shown;

[0049] Figure 3 A schematic diagram of a flow chart of a sequence of characterization values ​​for determining a dirty state of a ballast provided in an embodiment of the present invention is shown;

[0050] Figure 4 A schematic diagram of a flow chart for determining a signal time domain scanning area of ​​a radar echo signal for setting a ballast bed depth at each position point provided in an embodiment of the present invention is shown;

[0051] Figure 5 A schematic diagram of a sampling point sequence for indicating a set ballast bed depth provided in an embodiment of the present invention is shown;

[0052] Figure 6 A schematic diagram of a process for calibrating a characterization value sequence provided in an embodiment of this invention is shown;

[0053] Figure 7 A schematic diagram of a process for determining a selected characterization value corresponding to a target mileage according to a characterization value sequence provided in an embodiment of the present invention is shown;

[0054] Figure 8 A schematic diagram of a process for determining a multi-level selection interval according to a characterization value sequence provided in an embodiment of this invention is shown;

[0055] Fig. 9 A schematic diagram of a process for obtaining a selected characterization value corresponding to a target mileage according to an embodiment of the present invention is shown;

[0056] Fig.10 A schematic diagram for representing a first selected characterization value of each level in a multi-level selection interval provided by an embodiment of the present invention is shown;

[0057] Fig.11 A schematic diagram of a process for selecting a first selected characterization value in each stage provided by an embodiment of the present invention is shown;

[0058] Fig.12 A schematic diagram of a process for obtaining a ballast bed contamination model provided in an embodiment of this invention is shown;

[0059] Fig.13 A schematic diagram of the enclosure equipment required at the sampling hole for determining the actual dirtiness rate provided in the embodiment of this invention is shown;

[0060] Fig.14A schematic diagram of the module structure of a device for determining the dirty state of a ballast provided in an embodiment of this invention is shown;

[0061] Fig.15 A schematic diagram showing the structure of a computer device provided in an embodiment of this invention is shown;

[0062] Fig.16 The overall structure schematic diagram of the first test device provided in the embodiment of this article is shown;

[0063] Fig.17 The overall structural schematic diagram of the second test device provided in the embodiment of this article is shown.

[0064] Description of the accompanying symbols:

[0065] 1. The first bracket;

[0066] 2. Metal plate;

[0067] 3. First connecting rod;

[0068] 4. The first antenna;

[0069] 5. A first connecting member;

[0070] 6. The second bracket;

[0071] 7. Standard ballast model box;

[0072] 8. Second connecting rod;

[0073] 9. Second antenna;

[0074] 10. A second connecting member;

[0075] 100. Get module;

[0076] 200. Sequence determination module;

[0077] 300, characterization value determination module;

[0078] 400. Model determination module;

[0079] 500, dirt determination module;

[0080] 1502. Computer equipment;

[0081] 1504. Processor;

[0082] 1506. Memory;

[0083] 1508, driving mechanism;

[0084] 1510, input / output module;

[0085] 1512. Input devices;

[0086] 1514. Output device;

[0087] 1516. Presentation equipment;

[0088] 1518. Graphical user interface;

[0089] 1520, network interface;

[0090] 1522. Communication link;

[0091] 1524. Communication bus. DETAILED DESCRIPTION

[0092] The following will be combined with the drawings in the embodiments of this article to clearly and completely describe the technical solutions in the embodiments of this article. Obviously, the described embodiments are only part of the embodiments of this article, not all of the embodiments. Based on the embodiments of this article, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this article.

[0093] The total weight of a line is the total mass of trains and goods passing through a line. This parameter has no direct correlation with the dirtiness of the track bed. However, when technology does not allow, the track research, management and engineering departments can only use the total weight to infer the dirtiness of the track bed. However, the dirtiness of the track bed is actually related to many factors, such as the environment of the line (such as wind and sand, heavy rain, etc.), the material of the roadbed, the density of the roadbed, and the train load (the cumulative effect of the train load is the total weight). Therefore, the total weight alone cannot reflect the status of the track bed.

[0094] In order to solve the above problems, the embodiments of this document provide a method for determining the dirty state of the track bed. Figure 1 This is a schematic diagram of the steps of a method for determining the dirty state of a roadbed provided in an embodiment of this invention. This specification provides the method operation steps described in the embodiment or flowchart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the system or device product is executed in practice, it can be executed in the order of the method shown in the embodiment or the drawings or in parallel.

[0095] Reference Figure 1 , a method for determining the contamination state of a ballast bed, comprising:

[0096] S101: Acquire a radar echo signal corresponding to the roadbed of the target mileage;

[0097] S102: determining a characterization value sequence of a contamination state of a ballast bed according to the radar echo signal;

[0098] S103: determining, according to the characterization value sequence, a selected characterization value corresponding to the target mileage, wherein the selected characterization value is used to represent the characterization value sequence of the target mileage;

[0099] S104: Associating the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage with the selected characterization value to obtain a roadbed contamination model;

[0100] S105: Determine the roadbed contamination state corresponding to the roadbed of the target mileage according to the characterization value sequence of the roadbed contamination state and the roadbed contamination model.

[0101] Railway mileage refers to the length of the railway mainline for passenger and freight transportation. The target mileage mentioned in this article refers to the part of the railway mileage that needs to be evaluated for the contamination status of the roadbed. The radar echo signal refers to the echo signal generated by the roadbed after the radar signal is transmitted to the roadbed by the radar test system. Since the radar echo signals generated by different contamination conditions are different, the radar echo signal can reflect the contamination status of the roadbed to a certain extent. According to the radar echo signal, the characterization value sequence of the roadbed contamination status can be determined, and then the contamination status of the roadbed can be characterized by the characterization value sequence.

[0102] It should be noted that the characterization value sequence here only characterizes the changes in the roadbed contamination state in the target mileage. For example, at points A and B in the target mileage, the radar echo signal at point A is stronger than that at point B, and the roadbed contamination rate at point A is also higher than that at point B. That is, the characterization value sequence obtained from the radar echo signal can only relatively reflect the roadbed contamination state in the target mileage, but cannot absolutely determine the roadbed contamination rate.

[0103] Therefore, we can further select some representative selected characterization values ​​from the characterization value sequence, and determine the actual contamination rate at the position point of the selected characterization value in the target mileage. After associating the actual contamination rate with the selected characterization value, we can get the roadbed contamination model. Substituting the characterization value sequence into the roadbed contamination model, we can determine the roadbed contamination rate corresponding to the roadbed of the target mileage. The contamination rate means the proportion of the mass of dirty particles to the total mass. The total mass is the sum of the mass of dirty particles and the mass of non-dirty particles. The higher the roadbed contamination rate, the more serious the contamination of the roadbed. Therefore, we can determine the roadbed contamination state with high accuracy, and improve the decision-making accuracy during roadbed maintenance.

[0104] In the embodiment of this article, the step of obtaining the radar echo signal corresponding to the roadbed of the target mileage further includes:

[0105] The roadbed of the target mileage is sampled through the radar test system to obtain the radar echo signal corresponding to each position point in the target mileage;

[0106] Specifically, the radar test system includes a main control unit, a distance encoder and a radar antenna; wherein the main control unit is connected to the radar antenna, the main control unit sends a transmission instruction to the radar antenna and receives a radar echo signal sent by the radar antenna, and the radar antenna transmits a radar signal after receiving the transmission instruction, receives a radar echo signal, and sends the radar echo signal to the main control unit. In the embodiment of this article, the radar test system is pushed forward along the target mileage during the process of sampling the target mileage, and the radar test system collects once every time the distance encoder rotates a certain distance, and the distance encoder rotates multiple times along the target mileage, and the radar test system collects radar echo signals at multiple positions on the target mileage.

[0107] Furthermore, in order to more accurately determine the contamination of the roadbed, it is necessary to ensure 1. Environmental conditions: To minimize the impact of water content on the sampling results, the last rainfall should be at least 10 days away from the sampling day. 2. Line conditions: To ensure the consistency of the source of roadbed contamination, the lines to be tested should have the same type of cargo and relatively similar environmental conditions (rainfall, wind and sand, subgrade, etc.); double-track railways should include up and down lines, and the overall target mileage should not be less than 10km; the target mileage should include line structures such as bridges, culverts, and tunnels.

[0108] Reference Figure 2 The radar test system is installed on a connecting fixture that can move along the target mileage, keeping the radar antenna at the end of the pillow outside the rail, such as Figure 2 You can choose any one of the two antenna positions shown in the figure, so that the distance between the bottom of the radar antenna and the top of the rail is the set distance, and ensure that the antenna is within the railway vehicle limit when the connecting tooling is moved. The set distance can be set according to the actual working conditions and can be 190mm. The railway vehicle limit refers to the outline dimension line that cannot be crossed between buildings, equipment and locomotives and vehicles on the line to ensure transportation safety.

[0109] Reference Figure 3 The step of determining the characterization value sequence of the roadbed contamination state according to the radar echo signal further includes:

[0110] S201: determining a signal time domain scanning area of ​​the radar echo signal at a set ballast depth at each position point according to the radar echo signal corresponding to each position point in the target mileage;

[0111] S202: taking the signal time domain scanning area of ​​the radar echo signal at the ballast depth at each position point as the corresponding characterization value at the position point;

[0112] S203: Integrate the representation values ​​corresponding to all position points in the target mileage to obtain a representation value sequence corresponding to the target mileage.

[0113] Reference Figure 4 Specifically, in the embodiment of this article, the step of determining the signal time domain scanning area of ​​the radar echo signal at each position point to set the ballast depth at each position point according to the radar echo signal corresponding to each position point in the target mileage further includes:

[0114] S301: determining, according to the radar echo signal corresponding to each position point in the target mileage, a sampling point sequence for setting the ballast depth of the radar echo signal at each position point, and a time difference between two adjacent sampling points in the sampling point sequence;

[0115] S302: Calculating a signal time domain scanning area of ​​each sampling point according to the radar echo signal amplitude corresponding to each sampling point in the sampling point sequence and the time difference;

[0116] S303: Integrate the signal time domain scanning area of ​​each sampling point in the sampling point sequence to obtain the signal time domain scanning area of ​​the set track bed depth at the position point corresponding to the sampling point sequence.

[0117] Reference Figure 5 After collecting the radar echo signals corresponding to each position point in the target mileage, these radar echo signals form a matrix of n rows and m columns, where n is the number of sampling points of the radar test system, and the value of n is generally 512 or 1024, such as Figure 5 The value of n is shown as 512; m is the number of acquisition tracks, the distance between adjacent acquisition tracks is Δd, generally speaking, the value range of Δd is 5 to 20 cm, and mΔd is the target mileage. It can be understood that: for the target mileage, a radar signal is emitted once at each position point and the radar echo signal of the position point is collected. By rotating the distance encoder, a radar signal is emitted once at the next position point and the radar echo signal of the position point is collected, where the distance between two adjacent position points is Δd, and each position point corresponds to a collection track. There are m collection tracks in the entire target mileage. For a certain position point, a radar signal is emitted at the position point through a radar antenna. The radar signal goes through: air-sleeper-inside the ballast bed, and the radar echo signal is generated after being reflected by the gravel inside the ballast bed. The radar echo signal goes through: inside the ballast bed-sleeper-air, and then is received by the radar antenna. The radar echo signal received in the time window is divided according to the number of sampling points to obtain the radar echo signal along the depth direction of the roadbed at the position point, where a certain sampling point represents a certain depth at the position point. The time window is generally 15 to 25ns. After the radar signal is transmitted, the radar echo signal is received, and a total of 15 to 25ns of radar echo signals are received.

[0118] According to the actual working conditions, it is only necessary to determine the radar echo signal corresponding to the set track bed depth in the track bed depth. For example, it is only necessary to collect the echo signal segment within 30 cm below the bottom surface of the sleeper. It is necessary to determine the echo signal segment of the set track bed depth in the received radar echo signal, that is, the sampling point data within 30 cm.

[0119] The specific method is: comprehensively consider the distance between the radar antenna and the sleeper (the signal propagates in the air) a , sleeper thickness l s 、Propagation distance in the track bed l b = 30 cm, as well as the radar transmission frequency and the propagation speed v in the air, sleepers and ballast bed a 、v s 、v b . Reference Figure 5 As shown in the figure, the radar sampling point sequence corresponding to the set track bed depth is s t ~s b :

[0120]

[0121]

[0122] Δt is the time difference between two adjacent sampling points, Δt = T / [2×(n-1)], where n is the number of sampling points. n sampling points divide the radar echo signal into n-1 segments, and T is the time window. Since the time window T corresponds to the time from transmitting the radar signal to receiving the radar echo signal, it is the round-trip time of the signal. T needs to be divided by 2 to obtain the propagation time of the radar echo signal, and then a sampling point sequence consisting of a series of sampling points corresponding to the set roadbed depth is obtained.

[0123] The signal time domain scanning area of ​​a certain sampling point in the sampling point sequence is the area enclosed by the radar echo signal of the sampling point and the time axis. Specifically, the time can be used as the horizontal coordinate and the signal amplitude as the vertical coordinate. The radar echo signal amplitude of the sampling point is multiplied by the time difference to obtain the signal time domain scanning area of ​​the sampling point. The signal time domain scanning area of ​​each sampling point in the sampling point sequence is integrated to obtain the signal time domain scanning area of ​​the set track bed depth at the corresponding position point. This paper integrates the signal time domain scanning areas of multiple sampling points, and uses the sum of the areas enclosed by the radar echo signals of all sampling points in the sampling point sequence at each position point and the time axis to approximate the signal time domain scanning area of ​​the set track bed depth at the position point, so that the calculation accuracy is higher. The signal time domain scanning area at a certain position point is used as the corresponding characterization value at the position point, and the corresponding characterization values ​​of all position points in the target mileage are integrated to obtain the characterization value sequence corresponding to the target mileage.

[0124] Reference Figure 6After obtaining the characterization value sequence corresponding to the target mileage, the characterization value sequence can also be calibrated. Specifically:

[0125] S401: Acquire the detection value of the standard antenna and the detection value of the antenna to be calibrated in the same environment;

[0126] S402: Obtaining a calibration coefficient according to the detection value of the standard antenna and the detection value of the antenna to be calibrated;

[0127] S403: Calibrate the characterization value sequence of the antenna to be calibrated using the calibration coefficient.

[0128] Among them, the standard antenna is an antenna whose performance and indicators all meet the standards. Specifically, the standard antenna can be selected according to the selection standard of "Highway Section Flaw Detection and Structural Layer Thickness Ground Penetrating Radar" JJG (Traffic) 124-2015.

[0129] The detection value of the standard antenna is: the peak-to-valley difference of the echo signal or the time-domain scanning area of ​​the echo signal obtained after the standard antenna transmits the radar signal;

[0130] The detection value of the antenna to be calibrated is: the peak-to-valley difference of the echo signal or the time-domain scanning area of ​​the echo signal obtained after the antenna to be calibrated transmits the radar signal.

[0131] The detection value refers to the peak-to-valley difference of the echo signal or the time-domain scanning area of ​​the echo signal obtained after the radar antenna transmits the radar signal. The specific time-domain scanning area of ​​the echo signal can be calculated and solved by referring to the signal time-domain scanning area of ​​the sampling point mentioned above. The peak-to-valley difference of the echo signal is the difference between the peak and the trough of the echo signal.

[0132] Under the same environment, the peak-to-valley difference of the echo signal of a certain metal plate is detected by the standard antenna and the antenna to be calibrated respectively, and the detection value of the standard antenna and the detection value of the antenna to be calibrated are obtained. Alternatively, under the same environment, the time domain scanning area of ​​the echo signal of a certain standard ballast model is detected by the standard antenna and the antenna to be calibrated respectively, and the detection value of the standard antenna and the detection value of the antenna to be calibrated are obtained.

[0133] The obtaining of the detection value of the standard antenna and the detection value of the antenna to be calibrated under the same environment further includes:

[0134] Under the same environment, the standard antenna and the antenna to be calibrated are respectively tested by a first test device to obtain a peak-to-valley difference value of an echo signal of the standard antenna and a peak-to-valley difference value of an echo signal of the antenna to be calibrated;

[0135] Alternatively, the standard antenna and the antenna to be calibrated are tested respectively by a second test device under the same environment to obtain the time domain scanning area of ​​the echo signal of the standard antenna and the time domain scanning area of ​​the echo signal of the antenna to be calibrated.

[0136] Reference Fig.16 Specifically, the first test equipment includes two first brackets 1, a metal plate 2, a first connecting rod 3, a first antenna 4, a first connecting member 5, a first distance encoder (not shown in the figure) and a first main control unit (not shown in the figure).

[0137] The metal plate 2 is placed between the two first brackets 1 and laid flat on the hard and flat ground. The two ends of the first connecting rod 3 are respectively connected to the two first brackets 1. The first antenna 4 is set on the first connecting rod 3 through the first connecting member 5, so that the center of the first antenna 4 and the center of the metal plate 2 are kept horizontally without deviation, and a first set distance is maintained between the first antenna 4 and the metal plate 2; wherein the first connecting member 5 can be a connecting rod, a connecting block or other structures with a connecting function. The first set distance is set according to the actual working conditions. In this article, the first set distance can be 300mm.

[0138] The first antenna 4 is used to receive the instruction of the first main control unit to transmit the radar signal, and after receiving the echo signal, send the echo signal to the first main control unit.

[0139] The first antenna 4 is a standard antenna or an antenna to be calibrated. The environment for testing the standard antenna or the antenna to be calibrated is the same, including the same connection method of the cable between the first antenna 4 and the first main control unit. The cable is kept flat and must not be knotted or coiled.

[0140] When conducting the test, the following settings need to be set: sampling point 512, time window 15ns, channel spacing 5cm, pulse frequency 800k, distance trigger, no gain, and the test system is preheated for 5min. Turn the first distance encoder to continuously receive multiple echo signals.

[0141] Specifically, after the transmitting end of the first antenna 4 transmits a radar signal, the receiving end receives the echo signal within 15ns reflected by the metal plate 2, divides the echo signal, and obtains the echo signal values ​​corresponding to the 512 sampling points. Then the first distance encoder can be rotated 5cm. It should be noted that in the embodiment of this article, the first distance encoder is rotated but the actual first antenna 4 does not move and remains in the initial position. Then the radar signal is transmitted again, and the above steps are repeated multiple times to obtain multiple echo signals.

[0142] Reference Fig.17The second test equipment includes two second brackets 6, a standard ballast model box 7, a second connecting rod 8, a second antenna 9, a second connecting member 10, a second distance encoder (not shown in the figure) and a second main control unit (not shown in the figure).

[0143] The standard ballast model box 7 is placed between the two second brackets 6. The length and width of the standard ballast model box 7 are not less than twice the corresponding size of the second antenna 9. The ballast thickness is not less than 100 cm. The box body shall not be made of metal material. The ballast model box should be kept in a dry and vibration-free environment for a long time. The two ends of the second connecting rod 8 are respectively connected to the two second brackets 6. The second antenna 9 is set on the second connecting rod 8 through the second connecting member 10 to keep the center of the second antenna 9 and the center of the metal plate 2 horizontally without deviation. The second antenna 9 and the standard ballast model box 7 are maintained at a second set distance; wherein the second connecting member 10 can be a connecting rod, a connecting block or other structures with a connecting function. The second set distance is set according to the actual working conditions. In this article, the second set distance can be 300 mm.

[0144] The second antenna 9 is used to receive the instruction of the second main control unit to transmit the radar signal, and receive the echo signal and send it to the second main control unit.

[0145] The second antenna 9 is a standard antenna or an antenna to be calibrated. The environment for testing the standard antenna or the antenna to be calibrated is the same, including the same connection method of the cable between the second antenna 9 and the second main control unit. The cable is kept flat and must not be knotted or coiled.

[0146] When conducting the test, the following settings need to be set: sampling point 512, time window 15ns, channel spacing 5cm, pulse frequency 800k, distance trigger, no gain, and the test system is preheated for 5min. Turn the second distance encoder to continuously receive multiple echo signals.

[0147] The obtaining of the calibration coefficient according to the detection value of the standard antenna and the detection value of the antenna to be calibrated further comprises:

[0148] Obtaining a first calibration coefficient according to a correlation between a peak-to-valley difference value of an echo signal of the standard antenna and a peak-to-valley difference value of an echo signal of the antenna to be calibrated;

[0149] Or, the second calibration coefficient is obtained according to the correlation between the time-domain scanning area of ​​the echo signal of the standard antenna and the time-domain scanning area of ​​the echo signal of the antenna to be calibrated.

[0150] The first calibration coefficient is calculated by the following formula:

[0151]

[0152] in, is the first calibration coefficient, V R0 is the peak-to-valley difference of the echo signal of the standard antenna, V R is the peak-to-valley difference of the echo signal of the antenna to be calibrated.

[0153] The second calibration coefficient is calculated by the following formula:

[0154] μ = StAb0 / StAb;

[0155] Wherein, μ is the second calibration coefficient, StAb0 is the time domain scanning area of ​​the echo signal of the standard antenna, and StAb is the time domain scanning area of ​​the echo signal of the antenna to be calibrated.

[0156] The calibrating the characterization value sequence of the antenna to be calibrated by using the calibration coefficient further includes:

[0157] The calibration coefficient is multiplied by the characterization value sequence of the antenna to be calibrated to obtain a calibrated characterization value sequence.

[0158] The calibration coefficient is obtained by dividing the detection value of the standard antenna by the detection value of the calibration antenna. The calibrated characterization value sequence can be obtained by multiplying the characterization value sequence by the calibration coefficient. The calibrated characterization value sequence has higher accuracy.

[0159] Reference Figure 7 In the embodiment of this invention, the selected characterization value corresponding to the target mileage is determined according to the characterization value sequence, wherein the selected characterization value is used to represent the characterization value sequence of the target mileage further includes:

[0160] S501: determining a multi-level selection interval according to the characterization value sequence, wherein the multi-level selection interval divides the characterization value sequence into multiple levels according to the characterization value from small to large;

[0161] S502: Select a selected characterization value from each level of the multi-level selection interval to obtain a selected characterization value corresponding to the target mileage.

[0162] Specifically, to ensure that the selected characterization value is representative, the multi-level selection interval is at least a three-level selection interval.

[0163] Reference Figure 8 In addition to the above multi-level division method, in the embodiment of this article, the determination of the multi-level selection interval according to the characterization value sequence further includes:

[0164] S601: Determine the interval length according to the characterization value sequence and the number of levels of the multi-level selection interval;

[0165] S602: Divide the characterization values ​​in the characterization value sequence into intervals of equal length from small to large to obtain multi-level selection intervals.

[0166] Specifically, if it is a three-level selection interval, its level is three, and if it is a five-level selection interval, its level is five. The total number of representation values ​​in the representation value sequence is divided by the level, and the quotient obtained is the interval length. The meaning of the interval length is the number of representation values ​​included in any one-level selection interval. After sorting the representation values ​​in the representation value sequence from small to large, multiple-level selection intervals are taken from small to large, and the number of representation values ​​in any one-level selection interval is the interval length. Of course, it should be noted that since the total number of representation values ​​may not be divided evenly when divided by the level, and this article only uses the quotient as the interval length, it is very likely that there is a part of the representation values ​​that are ranked later and the number is less than the interval length and cannot form one of the first-level selection intervals. For the above situation, this article can use the size of the number of the representation values ​​to determine whether to determine the part of the representation values ​​as one of the first-level selection intervals. If the number of the representation values ​​of this part is greater than the set length, the representation values ​​of this part are determined as one of the first-level selection intervals, and vice versa. The set length here can be determined according to the actual situation, for example, it can be half of the interval length.

[0167] Reference Fig. 9 In the embodiment of this article, the step of selecting a selected characterization value from each level of the multi-level selection interval to obtain the selected characterization value corresponding to the target mileage further includes:

[0168] S701: Selecting a first selected characterization value from each level of the multi-level selection interval;

[0169] S702: Determine the characterization value corresponding to the position point adjacent to the first selected characterization value as the second selected characterization value, and determine the first selected characterization value and the second selected characterization value as the selected characterization values ​​corresponding to the level selection interval.

[0170] Reference Fig.10 Specifically, each characterization value in the characterization value sequence of the target mileage has its corresponding level, and a first selected characterization value is randomly selected from each level. Taking the three-level selection interval as an example, Fig.10 The circled position points shown are the first selected characterization values ​​corresponding to the first level, the second level and the third level respectively; then the characterization value corresponding to the position point adjacent to the first characterization value is determined as the second selected characterization value. It should be noted that the above-mentioned adjacent position points do not only refer to the adjacent ones. The position points within a set number before and after the first selected characterization value can be centered on the first selected characterization value as the adjacent position points of the first selected characterization value. For example, the 20 position points before and after the first selected characterization value are all adjacent position points of the first selected characterization value, and the second selected characterization value is selected from these 40 position points before and after.

[0171] The specific second selected characterization value may be one or more. In order to improve the accuracy of the calculation and ensure the efficiency of the calculation, two second selected characterization values ​​may be selected. The two second selected characterization values ​​may be selected one before and one after the first selected characterization value, which is more representative. Each level has one first selected characterization value and two second selected characterization values, and there are three levels and nine selected characterization values ​​in total.

[0172] On this basis, in order to avoid the abnormal situation of sudden increase or decrease of the characterization value, when randomly selecting a first selected characterization value in each level, the sudden increase or decrease value happens to be selected, resulting in inaccurate final calculation results, refer to Fig.11 , a first selected characterization value can be selected in each level by the following method:

[0173] S801: Selecting a continuous segment of a representation value in a certain level selection interval in the representation value sequence;

[0174] S802: Randomly select a first selected characterization value from the characterization value segment.

[0175] Taking the first-level selection interval as an example, in the characterization value sequence, being continuously in the first-level selection interval means that multiple consecutive characterization values ​​in the characterization value sequence belong to the first level. The specific number of consecutive characterization values ​​can be determined according to the actual working conditions. If multiple consecutive characterization values ​​belong to the first level, it means that the characterization value segment does not contain a sudden increase or decrease value, and a first selected characterization value can be randomly selected from the characterization value segment. If there are multiple characterization value segments in the first-level selection interval, any one of the characterization value segments can be randomly selected, so that the final calculation result can be guaranteed to be more accurate.

[0176] In the embodiment of this article, the step of selecting a selected characterization value from each level of the multi-level selection interval to obtain the selected characterization value corresponding to the target mileage further includes:

[0177] A plurality of selected characterization values ​​are respectively selected from each level of the multi-level selection interval to obtain a selected characterization value corresponding to the target mileage.

[0178] Taking the three-level selection interval as an example, multiple selected characterization values ​​are selected from each level. In order to ensure calculation efficiency while taking into account calculation accuracy, three selected characterization values ​​can be selected at each level, and a total of nine selected characterization values ​​are selected in three levels.

[0179] Reference Fig.12 In the embodiment of this article, associating the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage with the selected characterization value to obtain the roadbed contamination model further includes:

[0180] S901: Establishing a functional relationship between the actual dirtiness rate and the characterization value sequence;

[0181] S902: Substitute the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage and the selected characterization value into the functional relationship to obtain a roadbed contamination model.

[0182] Taking the three-level selection interval as an example, after establishing the functional relationship between the actual dirtiness rate and the characterization value sequence, it is necessary to further determine the actual dirtiness rate corresponding to the position point of the selected characterization value in the target mileage. Specifically, there are three levels and nine selected characterization values. According to the position point of each selected characterization value in the target mileage, the position point is sampled: refer to Fig.13 First, a sampling hole is dug at the location point. The depth of the sampling hole is the set ballast depth, for example, 30 cm. When digging the sampling hole, a temporary steel chisel should be used to protect it to prevent the ballast from collapsing. Then, the wet weight of the n samples dug is weighed, and then the dry weight M of the samples is weighed after drying. t . Finally, screening is performed to obtain the mass M of dirty particles below the specified particle size distribution in each sample, where the specified particle size distribution is the apparent diameter of the sample particles, which can be 25mm, 16mm, 10mm, 5mm, or 0.075mm according to the working conditions. In the ballast gravel, particles below the specified particle size distribution are identified as dirty particles, so the above-mentioned sampling and screening work is required. Calculate the actual dirtiness rate FI(i) of the i-th excavation test point (for n excavation test points, 1≤i≤n).

[0183]

[0184] The functional relationship between the actual dirtiness rate and the characterization value sequence is established as follows:

[0185] FI = k × StAb2 + b;

[0186] Where FI is the actual dirtiness rate, StAb2 is the characterization value sequence, b is the constant term of the function; k is the function coefficient, which is also the slope of the function.

[0187] Both k and b are calculated using the least squares method. For data with n samples, the calculation formula is as follows:

[0188]

[0189]

[0190] Among them, FI(i) is the actual dirtiness rate of the i-th position point, StAb2(i) is the selected characterization value of the i-th position point, and n is the number of position points.

[0191] After calculating the values ​​of k and b, substituting the values ​​of k and b into the above functional relationship, the functional relationship between the actual fouling rate and the characterization value sequence, that is, the ballast bed fouling model, can be obtained.

[0192] For the track bed contamination model, each characterization value in the characterization value sequence StAb2 has a corresponding actual contamination rate, that is, there is a corresponding actual contamination rate at each position point in the target mileage, so the actual contamination rate of the track bed of the target mileage can be obtained with high accuracy, which helps to improve the decision-making accuracy during track bed maintenance.

[0193] Based on the above-mentioned method for determining the dirty state of the roadbed, the embodiments of this article also provide a device for determining the dirty state of the roadbed. The device may include a system (including a distributed system), software (application), module, component, server, client, etc. using the method described in the embodiments of this article and a device combined with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiments of this article is as described in the following embodiments. Since the implementation scheme and method of the device to solve the problem are similar, the implementation of the specific device in the embodiments of this article can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0194] Specifically, Fig.14 is a schematic diagram of a module structure of an embodiment of a device for determining the dirty state of a roadbed provided in an embodiment of this invention, with reference to Fig.14 As shown, a device for determining the contamination state of a roadbed provided in an embodiment of the present invention includes: an acquisition module 100, a sequence determination module 200, a characterization value determination module 300, a model determination module 400, and a contamination determination module 500.

[0195] The device comprises:

[0196] An acquisition module 100 is used to acquire a radar echo signal corresponding to the roadbed of a target mileage;

[0197] A sequence determination module 200, for determining a sequence of characterization values ​​of a contamination state of a ballast according to the radar echo signal;

[0198] A characterization value determination module 300, configured to determine a selected characterization value corresponding to the target mileage according to the characterization value sequence, wherein the selected characterization value is used to represent the characterization value sequence of the target mileage;

[0199] A model determination module 400 is used to associate the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage with the selected characterization value to obtain a roadbed contamination model;

[0200] The contamination determination module 500 is used to determine the contamination state of the roadbed corresponding to the roadbed of the target mileage according to the characterization value sequence of the contamination state of the roadbed and the roadbed contamination model.

[0201] Reference Fig.15 As shown, based on the above-mentioned method for determining the dirty state of the roadbed, a computer device 1502 is also provided in one embodiment of the present invention, wherein the above-mentioned method is run on the computer device 1502. The computer device 1502 may include one or more processors 1504, such as one or more central processing units (CPUs) or graphics processing units (GPUs), and each processing unit may implement one or more hardware threads. The computer device 1502 may also include any memory 1506, which is used to store any kind of information such as code, settings, data, etc. In a specific embodiment, the computer program on the memory 1506 and can be run on the processor 1504, when the computer program is run by the processor 1504, the instructions according to the above-mentioned method can be executed. Non-limitingly, for example, the memory 1506 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of the computer device 1502. In one embodiment, when the processor 1504 executes the associated instructions stored in any memory or combination of memories, the computer device 1502 can perform any operation of the associated instructions. The computer device 1502 also includes one or more drive mechanisms 1508 for interacting with any memory, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0202] The computer device 1502 may also include an input / output module 1510 (I / O) for receiving various inputs (via input devices 1512) and for providing various outputs (via output devices 1514). A specific output mechanism may include a presentation device 1516 and an associated graphical user interface 1518 (GUI). In other embodiments, the input / output module 1510 (I / O), input device 1512, and output device 1514 may not be included, and the computer device 1502 may be used as a computer device in a network. The computer device 1502 may also include one or more network interfaces 1520 for exchanging data with other devices via one or more communication links 1522. One or more communication buses 1524 couple the components described above together.

[0203] The communication link 1522 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 1522 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

[0204] Corresponds to Figure 1 , Figure 3-Figure 4 , Figure 6-Figure 9 , Figure 11-Figure 12 The method in this article also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are executed.

[0205] The embodiment of the present invention also provides a computer readable instruction, wherein when the processor executes the instruction, the program therein causes the processor to execute the following Figure 1 , Figure 3-Figure 4 , Figure 6-Figure 9 , Figure 11-Figure 12 The method shown.

[0206] It should be understood that in the various embodiments of this document, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this document.

[0207] It should also be understood that in the embodiments of this article, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0208] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this article.

[0209] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0210] In the several embodiments provided herein, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0211] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of this article.

[0212] In addition, each functional unit in each embodiment of this invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional unit.

[0213] If the integrated unit is implemented in the form of 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 article is essentially 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, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of this article. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0214] Specific embodiments are used in this article to illustrate the principles and implementation methods of this article. The description of the above embodiments is only used to help understand the methods and core ideas of this article. At the same time, for general technicians in this field, according to the ideas of this article, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on this article.

Claims

1. A method for determining the contamination state of a roadbed, characterized in that: include: Obtain the radar echo signal corresponding to the roadbed of the target mileage; Determining a sequence of characterizing values ​​of a contamination state of a ballast bed according to the radar echo signal; Determining, according to the characterization value sequence, a selected characterization value corresponding to the target mileage, wherein the selected characterization value is used to represent the characterization value sequence of the target mileage; Associating the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage with the selected characterization value to obtain a roadbed contamination model; Determining the roadbed contamination state corresponding to the roadbed of the target mileage according to the characterization value sequence of the roadbed contamination state and the roadbed contamination model; The step of determining the selected characterization value corresponding to the target mileage according to the characterization value sequence, wherein the selected characterization value is used to represent the characterization value sequence of the target mileage, comprises: Determining the interval length according to the characterization value sequence and the number of levels of the multi-level selection interval; Divide the characterization values ​​in the characterization value sequence into equal intervals from small to large to obtain multi-level selection intervals, wherein the multi-level selection intervals divide the characterization value sequence into multiple levels according to the characterization values ​​from small to large; A first selected characterization value is selected from each level of the multi-level selection interval; a characterization value corresponding to a position point adjacent to the first selected characterization value is determined as a second selected characterization value, and the first selected characterization value and the second selected characterization value are determined as selected characterization values ​​corresponding to the level of selection interval; Alternatively, a plurality of selected characterization values ​​are respectively selected from each level of the multi-level selection interval to obtain the selected characterization value corresponding to the target mileage.

2. The method for determining the contamination state of the track bed according to claim 1, characterized in that: The step of obtaining the radar echo signal corresponding to the roadbed of the target mileage further includes: The roadbed of the target mileage is sampled through the radar test system to obtain the radar echo signal corresponding to each position point in the target mileage; Determining the characterization value sequence of the roadbed contamination state according to the radar echo signal further includes: According to the radar echo signal corresponding to each position point in the target mileage, determining the signal time domain scanning area of ​​the radar echo signal at the set track bed depth at each position point; The signal time domain scanning area of ​​the radar echo signal at the ballast depth at each position point is taken as the corresponding characterization value at the position point; The characterization values ​​corresponding to all position points in the target mileage are integrated to obtain a characterization value sequence corresponding to the target mileage.

3. The method for determining the contamination state of the roadbed according to claim 2, characterized in that: The step of determining the signal time domain scanning area of ​​the radar echo signal at each position point to set the ballast depth according to the radar echo signal corresponding to each position point in the target mileage further comprises: According to the radar echo signal corresponding to each position point in the target mileage, determine a sampling point sequence of the radar echo signal for setting the ballast bed depth at each position point, and a time difference between two adjacent sampling points in the sampling point sequence; Calculating the signal time domain scanning area of ​​each sampling point according to the radar echo signal amplitude corresponding to each sampling point in the sampling point sequence and the time difference; The signal time domain scanning area of ​​each sampling point in the sampling point sequence is integrated to obtain the signal time domain scanning area of ​​the set track bed depth at the position point corresponding to the sampling point sequence.

4. The method for determining the contamination state of the roadbed according to claim 1, characterized in that: The step of associating the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage with the selected characterization value to obtain the roadbed contamination model further includes: Establishing a functional relationship between the actual dirtiness rate and the characterization value sequence; Substitute the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage and the selected characterization value into the functional relationship to obtain the roadbed contamination model.

5. A device for determining the dirty state of a roadbed, characterized in that: The device comprises: An acquisition module is used to acquire the radar echo signal corresponding to the roadbed of the target mileage; A sequence determination module, used to determine a sequence of characterization values ​​of the contamination state of the ballast bed according to the radar echo signal; a characterization value determination module, configured to determine a selected characterization value corresponding to the target mileage according to the characterization value sequence, wherein the selected characterization value is used to represent the characterization value sequence of the target mileage; A model determination module, used for associating the actual contamination rate corresponding to the position point of the selected characterization value in the target mileage with the selected characterization value to obtain a roadbed contamination model; A contamination determination module, configured to determine the contamination state of the roadbed corresponding to the roadbed of the target mileage according to the characterization value sequence of the contamination state of the roadbed and the roadbed contamination model; The step of determining the selected characterization value corresponding to the target mileage according to the characterization value sequence, wherein the selected characterization value is used to represent the characterization value sequence of the target mileage, comprises: Determining the interval length according to the characterization value sequence and the number of levels of the multi-level selection interval; Divide the characterization values ​​in the characterization value sequence into equal intervals from small to large to obtain multi-level selection intervals, wherein the multi-level selection intervals divide the characterization value sequence into multiple levels according to the characterization values ​​from small to large; A first selected characterization value is selected from each level of the multi-level selection interval; a characterization value corresponding to a position point adjacent to the first selected characterization value is determined as a second selected characterization value, and the first selected characterization value and the second selected characterization value are determined as selected characterization values ​​corresponding to the level of selection interval; Alternatively, a plurality of selected characterization values ​​are respectively selected from each level of the multi-level selection interval to obtain the selected characterization value corresponding to the target mileage.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the computer program is executed by the processor, the computer program executes the instructions of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor of a computer device, the computer program executes the instructions of the method according to any one of claims 1 to 4.

Images