Disease detection method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a disease detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring full-amount radar data in a target area, and extracting the full-amount radar data to obtain disease depth information of each acquisition position in the target area; calculating according to the radar data to obtain an initial reflection coefficient; for each piece of radar data, calculating a reflection correction factor according to the disease depth information of the acquisition position corresponding to the radar data, and correcting the initial reflection coefficient based on the reflection correction factor to obtain a target reflection coefficient; obtaining a target dielectric constant according to the target reflection coefficient, wherein the target dielectric constant is used for determining a detection result. By adopting the method, the accuracy of a detection result can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of disease detection, and in particular to a disease detection method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of heavy-load trains, heavy-load trains have large axle loads, concentrated loads and long action time, which makes it very easy for the ballast layer to sink into the roadbed layer, forming a "ballast trough" disease. Its special trough structure easily leads to moisture retention and forms a water-containing disease. Therefore, it is necessary to test the moisture content of the diseased area.

[0003] Traditionally, ground-penetrating radar (GPR) is used to inspect and process the roadbed and collect radar data. The terminal extracts this data and uses the maximum positive-phase fluctuation peak of the reflective interface as the defect center. The reflection coefficient is then calculated from the radar data at the defect center. The dielectric constant is then calculated from this reflection coefficient, which is then used to calculate the moisture content of the ballast sink.

[0004] However, in traditional technologies, the calculation of the reflection coefficient is affected by factors such as the surrounding environment of the defect, medium changes, and wave propagation path. As a result, there is often a certain error in the reflection coefficient, which leads to poor accuracy of the dielectric constant and, in turn, poor accuracy of the detection results. Summary of the Invention

[0005] Based on this, it is necessary to provide a disease detection method, device, computer equipment, computer-readable storage medium and computer program product to address the above technical problems.

[0006] In a first aspect, the present application provides a disease detection method, comprising:

[0007] Acquire a full amount of radar data in the target area, extract the full amount of radar data, and obtain disease depth information at each acquisition location in the target area;

[0008] Calculating according to the radar data to obtain an initial reflection coefficient;

[0009] For each radar data, a reflection correction factor is calculated according to the defect depth information at the acquisition position corresponding to the radar data, and the initial reflection coefficient is corrected based on the reflection correction factor to obtain a target reflection coefficient;

[0010] A target dielectric constant is obtained according to the target reflection coefficient, and the target dielectric constant is used to determine a detection result.

[0011] In one embodiment, obtaining the full amount of radar data in the target area includes:

[0012] Acquire calibration signal data and full initial radar data in the target area;

[0013] performing calibration processing on the initial radar data according to the calibration signal data to obtain calibrated radar data;

[0014] Gain processing and offset processing are performed on the calibrated radar data to obtain full radar data in the target area.

[0015] In one embodiment, the defect depth information includes the subsidence depth of each acquisition position; the calculation of the reflection correction factor for each radar data according to the defect depth information at the acquisition position corresponding to the radar data, and the correction of the initial reflection coefficient based on the reflection correction factor to obtain the target reflection coefficient includes:

[0016] Determining a maximum subsidence depth according to the subsidence depths of the respective acquisition locations;

[0017] For each piece of radar data, determining a subsidence degree of an area corresponding to each piece of radar data based on the subsidence depth of the acquisition location corresponding to the radar data and the maximum subsidence depth, and calculating a reflection correction factor corresponding to the radar data according to the subsidence degree;

[0018] The initial reflection coefficient is corrected according to the reflection correction factor to obtain a target reflection coefficient corresponding to the radar data.

[0019] In one embodiment, for each piece of radar data, determining the subsidence degree of the area corresponding to each piece of radar data based on the subsidence depth of the acquisition location corresponding to the radar data and the maximum subsidence depth, and calculating the reflection correction factor corresponding to the radar data according to the subsidence degree includes:

[0020] For each piece of radar data, determining a ratio of the subsidence depth to the maximum subsidence depth as a subsidence degree;

[0021] Determining an adjustment coefficient corresponding to each radar data based on a correspondence between the sinking degree and the candidate adjustment coefficient;

[0022] A reflection correction factor corresponding to the radar data is determined according to the sinking degree and the adjustment coefficient.

[0023] In one embodiment, obtaining a target dielectric constant according to the target reflection coefficient includes:

[0024] Calculating the initial dielectric constant corresponding to each of the acquisition positions according to the target reflection coefficient;

[0025] The initial reflection coefficients corresponding to the radar data are averaged to obtain the target dielectric constant of the target area.

[0026] In one embodiment, the calculating the mean of the initial reflection coefficients corresponding to the radar data to obtain the target dielectric constant of the target area includes:

[0027] determining a plurality of diseased areas in the target area according to peak distribution in the radar data in the target area;

[0028] A mean value calculation is performed based on the initial reflection coefficient corresponding to the radar data contained in each of the defective areas to obtain the target dielectric constant corresponding to each of the defective areas in the target area.

[0029] In a second aspect, the present application further provides a disease detection device, comprising:

[0030] An extraction module is used to obtain the full amount of radar data in the target area, extract the full amount of radar data, and obtain the disease depth information of each collection position in the target area;

[0031] A calculation module, configured to calculate based on the radar data to obtain an initial reflection coefficient;

[0032] a correction module, configured to calculate, for each radar data, a reflection correction factor according to the defect depth information at the acquisition position corresponding to the radar data, and correct the initial reflection coefficient based on the reflection correction factor to obtain a target reflection coefficient;

[0033] The determination module is used to obtain a target dielectric constant according to the target reflection coefficient, and the target dielectric constant is used to determine the detection result.

[0034] In one embodiment, the extraction module is specifically configured to obtain calibration signal data and a full amount of initial radar data in the target area;

[0035] performing calibration processing on the initial radar data according to the calibration signal data to obtain calibrated radar data;

[0036] Gain processing and offset processing are performed on the calibrated radar data to obtain full radar data in the target area.

[0037] In one embodiment, the disease depth information includes the subsidence depth of each sampling location; the correction module is specifically configured to determine the maximum subsidence depth based on the subsidence depth of each sampling location;

[0038] For each piece of radar data, determining a subsidence degree of an area corresponding to each piece of radar data based on the subsidence depth of the acquisition location corresponding to the radar data and the maximum subsidence depth, and calculating a reflection correction factor corresponding to the radar data according to the subsidence degree;

[0039] The initial reflection coefficient is corrected according to the reflection correction factor to obtain a target reflection coefficient corresponding to the radar data.

[0040] In one embodiment, the correction module is specifically configured to determine, for each radar data, a ratio of the subsidence depth to the maximum subsidence depth as the subsidence degree;

[0041] Determining an adjustment coefficient corresponding to each radar data based on a correspondence between the sinking degree and the candidate adjustment coefficient;

[0042] A reflection correction factor corresponding to the radar data is determined according to the sinking degree and the adjustment coefficient.

[0043] In one embodiment, the determination module is specifically configured to calculate the initial dielectric constant corresponding to each of the acquisition positions according to the target reflection coefficient;

[0044] The initial reflection coefficients corresponding to the radar data are averaged to obtain the target dielectric constant of the target area.

[0045] In one embodiment, the determining module is specifically configured to determine a plurality of diseased areas in the target area based on peak distribution in the radar data in the target area;

[0046] A mean value calculation is performed based on the initial reflection coefficient corresponding to the radar data contained in each of the defective areas to obtain the target dielectric constant corresponding to each of the defective areas in the target area.

[0047] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0048] Acquire a full amount of radar data in the target area, extract the full amount of radar data, and obtain disease depth information at each acquisition location in the target area;

[0049] Calculating according to the radar data to obtain an initial reflection coefficient;

[0050] For each radar data, a reflection correction factor is calculated according to the defect depth information at the acquisition position corresponding to the radar data, and the initial reflection coefficient is corrected based on the reflection correction factor to obtain a target reflection coefficient;

[0051] A target dielectric constant is obtained according to the target reflection coefficient, and the target dielectric constant is used to determine a detection result.

[0052] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0053] Acquire a full amount of radar data in the target area, extract the full amount of radar data, and obtain disease depth information at each acquisition location in the target area;

[0054] Calculating according to the radar data to obtain an initial reflection coefficient;

[0055] For each radar data, a reflection correction factor is calculated according to the defect depth information at the acquisition position corresponding to the radar data, and the initial reflection coefficient is corrected based on the reflection correction factor to obtain a target reflection coefficient;

[0056] A target dielectric constant is obtained according to the target reflection coefficient, and the target dielectric constant is used to determine a detection result.

[0057] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0058] Acquire a full amount of radar data in the target area, extract the full amount of radar data, and obtain disease depth information at each acquisition location in the target area;

[0059] Calculating according to the radar data to obtain an initial reflection coefficient;

[0060] For each radar data, a reflection correction factor is calculated according to the defect depth information at the acquisition position corresponding to the radar data, and the initial reflection coefficient is corrected based on the reflection correction factor to obtain a target reflection coefficient;

[0061] A target dielectric constant is obtained according to the target reflection coefficient, and the target dielectric constant is used to determine a detection result.

[0062] The above-mentioned defect detection method, apparatus, computer device, computer-readable storage medium, and computer program product obtain all radar data in the target area, extract the full amount of radar data, and obtain defect depth information at each acquisition location in the target area; perform calculations based on the radar data to obtain an initial reflection coefficient; calculate a reflection correction factor for each radar data segment based on the defect depth information at the acquisition location corresponding to the radar data, and correct the initial reflection coefficient based on the reflection correction factor to obtain a target reflection coefficient; and obtain a target dielectric constant based on the target reflection coefficient, which is used to determine the detection result. Using this method, the initial reflection coefficient is corrected using the defect depth information in the target area to obtain the target reflection coefficient. This method can reduce the influence of factors such as the surrounding environment of the defect, medium changes, and wave propagation path, more accurately reflect the reflection characteristics under actual defect conditions, make the target reflection coefficient more consistent with actual conditions, reduce the error in the reflection coefficient, improve the accuracy of the dielectric constant, and thus improve the accuracy of the detection results. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0064] Figure 1 1 is a flow chart of a disease detection method according to an embodiment;

[0065] Figure 2 Schematic diagram of a water-damaged model of heavy-load railway ballast sinks in one embodiment;

[0066] Figure 3 A schematic diagram of a two-dimensional image of disease center data and total reflection data in one embodiment;

[0067] Figure 4 1 is a schematic diagram of a process for preprocessing initial radar data in one embodiment;

[0068] Figure 5 A schematic diagram of comparing two-dimensional radar images after initial radar data and pre-processed radar data are respectively visualized in one embodiment;

[0069] Figure 6 1. A schematic diagram of a process for correcting an initial reflection coefficient in one embodiment;

[0070] Figure 7 FIG1 is a schematic diagram of a process for determining a reflection correction factor in one embodiment;

[0071] Figure 8 FIG1 is a schematic diagram of a process for determining a target dielectric constant in one embodiment;

[0072] Figure 9 A schematic diagram of a process for dividing a defective area and determining a target dielectric constant in one embodiment;

[0073] Figure 10 A schematic diagram of a diseased area present in a target area in one embodiment;

[0074] Figure 11 is a schematic diagram of a corrected target reflection coefficient in one embodiment;

[0075] Figure 12 is a schematic diagram of the dielectric constant of a diseased area in one embodiment;

[0076] Figure 13 is a structural block diagram of a disease detection device in one embodiment;

[0077] Figure 14 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0078] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0079] In one embodiment, Figure 1 As shown, a disease detection method is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, or to a system including a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0080] Step 102: Acquire all radar data in the target area, extract the full amount of radar data, and obtain the damage depth information of each acquisition position in the target area.

[0081] In an embodiment of the present application, to detect the actual presence of water-retained ballast troughs on heavy-haul railways, inspectors use ground-penetrating radar (GPR) to survey the ballast and roadbed, obtaining radar data corresponding to the heavy-haul railway. GPR transmits electromagnetic waves through the ballast and reflects the internal structure and condition of the ballast based on information such as the characteristics of the reflected waves. The terminal then analyzes the reflected wave characteristics of the radar data to identify target areas where ballast troughs are present. In the radar data, a normal ballast surface produces a distinct reflected wave with high intensity and a relatively regular shape. By analyzing the amplitude and phase characteristics of the radar image, combined with known geological information and ballast structural characteristics, the terminal can identify the location of the reflected wave from the normal ballast surface. Furthermore, changes in the ballast medium caused by water retention in the ballast troughs result in reflected waves that differ significantly from those from the normal ballast surface in terms of intensity, phase, and waveform. Furthermore, the terminal can determine the depth information of the damage at each collection location in the target area by comparing the difference between the intensity, phase, waveform, etc. of the reflected wave and the preset threshold.

[0082] During the simulation experiment, the terminal can simulate water-infested ballast sinks in heavy-haul railways using gprMax software (an open-source, 3D, full-waveform simulator for ground-penetrating radar) based on FDTD (Finite-Difference Time-Domain), construct a ballast sink damage model, and obtain damage data. This embodiment does not limit the simulation software or tools used for the simulation.

[0083] In a specific embodiment, the construction of a ballast sink water hazard model is illustrated using the gprMax software as an example. The terminal can use the ballast commonly used in heavy-haul railways as the primary component of the roadbed in the ballast sink water hazard model. The ballast sink water hazard model can be constructed sequentially from top to bottom, consisting of an air layer, a ballast layer, and a base layer. For example, the air layer thickness is set to 40 cm, with a relative dielectric constant of 1 to ensure consistency with the physical properties of actual air; the ballast layer thickness is also set to 40 cm, with a relative dielectric constant of 5, reflecting the electrical properties of the ballast itself; the base layer thickness is set to 80 cm, with a relative dielectric constant of 20. The electrical conductivity of the air layer, ballast layer, and base layer are all set to 0, and the relative magnetic permeability is all set to 1.

[0084] In view of the fact that the actual ballast pit water-containing disease is not in a flat state and there will be settlements of different depths, the disease model can be set in detail. The width of the upper top surface of the ballast pit disease is set to 60cm, the width of the lower bottom surface is 30cm, and the thickness is 40cm. Since the water-containing dirt is mainly concentrated in the ballast pit, the relative dielectric constant of this area is 50, the conductivity is 0.01, and the relative magnetic permeability is 1. In addition, the ballast pit water-containing disease model can also set a full reflection interface model of the ballast pit surface, that is, a metal plate with a negligible thickness and a length of 60cm is set on the top surface of the ballast pit to simulate the full reflection state of the ground penetrating radar signal. The heavy-duty railway ballast pit water-containing disease model obtained by simulation based on the above parameters is as follows Figure 2 As shown, Figure 2 This is a model for water-infused sump damage in heavy-haul railway ballast. Finally, the terminal acquires radar data using forward modeling of a ground-penetrating radar (GPR). The forward modeling radar uses a 1500MHz center frequency, 161 channels, a 0.025m interval, and 6361 sampling points to extract GPR forward modeling data.

[0085] Step 104: Calculate based on the radar data to obtain an initial reflection coefficient.

[0086] In the embodiment of the present application, the radar data includes the disease center data and the total reflection data, such as Figure 3 As shown in FIG, the disease center data can be extracted based on the intensity, phase, waveform and other characteristics of the reflected wave of each radar data. For example, Figure 3 The maximum positive phase fluctuation peak value of the reflection interface of the water-containing disease in the disease center data is 120.776V / m, and the maximum positive phase fluctuation peak value of the total reflection data at the total reflection is 353.000V / m. Then, the terminal calculates the disease center data and the total reflection data according to the following formula (1) to obtain the water-containing interface reflection coefficient of the heavy-duty railway ballast sink water disease and use it as the initial reflection coefficient, where:

[0087] (1)

[0088] in, is the initial reflection coefficient of the water-containing interface of the heavy-haul railway ballast sink hole water-containing disease, is the damage center data, i.e. the radar reflection intensity of the water-bearing damage interface, is the total reflection data, that is, the radar reflection intensity of the metal plate interface.

[0089] Step 106 : For each radar data, a reflection correction factor is calculated according to the defect depth information at the acquisition position corresponding to the radar data, and the initial reflection coefficient is corrected based on the reflection correction factor to obtain the target reflection coefficient.

[0090] In the embodiments of this application, when detecting heavy-duty railway ballast groove defects, the extent of sinking varies across different areas of the ballast groove defect, resulting in uneven surfaces that are not completely planar. Calculating the reflection coefficient of the ballast groove defect's water-containing interface using only the defect center data will result in significant errors due to the failure to account for the actual complexity of the defect area. This error will further affect the accuracy of subsequent calculations of the dielectric constant of the water-containing defect area and the moisture content test results.

[0091] Therefore, for each GPR data point, the terminal first identifies the corresponding acquisition location. This means that different acquisition locations have different defect depth information, which significantly affects radar wave reflection. Then, based on the defect depth information at that acquisition location, the terminal uses the Reflection Coefficient Correction Model for Water-Contained Ballast Sinks in Heavy Haul Railways (hereinafter referred to as the Correction Model) to calculate the reflection correction factor. This correction model fully considers the defect depth and the actual characteristics of water-contained ballast sinks, more accurately reflecting the impact of the defect on radar wave reflection.

[0092] Finally, the terminal corrects the initial reflection coefficient based on the calculated reflection correction factor. Because the initial reflection coefficient is obtained without considering the complexity of the disease, it does not accurately reflect the actual reflection conditions. By adjusting the reflection correction factor, the terminal can obtain a target reflection coefficient that better reflects the actual situation. This provides a reliable data foundation for the subsequent accurate calculation of the dielectric constant and moisture content detection, thereby improving the accuracy and reliability of the entire disease detection process.

[0093] Step 108: Obtain a target dielectric constant according to the target reflection coefficient.

[0094] The target dielectric constant is used to determine the test result.

[0095] In the embodiment of the present application, after the initial reflection coefficient is corrected according to the reflection correction factor to obtain the target reflection coefficient, the terminal calculates the target dielectric constant according to the target reflection coefficient. Specifically, the terminal further calculates the moisture content of the water-containing disease of the heavy-duty railway ballast groove by combining the target dielectric constant with the empirical formula, namely, the Top p formula, and uses the moisture content as the detection result. The Top p formula is shown in the following formula (2):

[0096] (2)

[0097] in, is the target dielectric constant of the target area, is the moisture content of the target area.

[0098] In the above-mentioned disease detection method, the initial reflection coefficient is corrected by the disease depth information of the target area to obtain the target reflection coefficient, which can reduce the influence of factors such as the surrounding environment of the disease, medium changes, and wave propagation path, and can more accurately reflect the reflection characteristics under the actual disease condition, making the target reflection coefficient more in line with the actual situation, reducing the error of the reflection coefficient, and improving the accuracy of the dielectric constant, thereby improving the accuracy of the detection results.

[0099] In an exemplary embodiment, in order to improve the accuracy of radar data, the radar data needs to be preprocessed, such as Figure 4 As shown, step 102 includes steps 402 to 406. Among them:

[0100] Step 402: Acquire calibration signal data and all initial radar data in the target area.

[0101] In the embodiment of the present application, during the acquisition of the ground penetrating radar system, due to the antenna coupling between the transmitting and receiving antennas, echoes, system zero drift and invalid reflections in the air, there are a lot of background interferences introduced by the system in the original signal. These interferences are mostly manifested as initial waveforms with fixed patterns, which will be repeated in each channel of original radar data, seriously affecting the judgment of the real stratum reflection characteristics. Therefore, after the terminal acquires the full amount of initial radar data in the target area, it performs air calibration on the initial radar data. Among them, air calibration refers to the terminal acquiring the echo response data of the ground penetrating radar system itself as calibration signal data without contacting the measured medium, which is recorded as , and detect the heavy-load railway ballast sinkhole to obtain the full amount of initial radar data in the target area (ballast sinkhole water-damaged area), which is recorded as .

[0102] Step 404 : calibrate the initial radar data according to the calibration signal data to obtain calibrated radar data.

[0103] In the embodiment of the present application, the terminal passes the calibration signal data Initial radar data collected from actual Subtract point by point from the , and get the calibrated signal as the calibration radar data. The calibration process is shown in the following formula (3):

[0104] (3)

[0105] Where n represents the time sampling point index, It is the calibration radar data after air calibration.

[0106] Step 406 : Perform gain processing and offset processing on the calibrated radar data to obtain the full amount of radar data in the target area.

[0107] In the embodiments of this application, because ground-penetrating radar signals are affected by various mechanisms such as dielectric loss, conductivity, and scattering when propagating through a medium, the signal energy decays exponentially with depth. This attenuation causes deep reflection information to be submerged in background noise, which is particularly noticeable in multi-layer interfaces or aquifers. Therefore, the terminal uses exponential gain to perform gain and offset processing on the calibration radar data.

[0108] First, the gain processing of the calibrated radar data is defined as:

[0109] (4)

[0110] in, is the calibration radar data after air calibration processing, is the data after ground penetrating radar gain, is the gain function.

[0111] In order to restore the deep reflection characteristics, an exponential gain function is introduced to compensate the signal amplitude in the depth direction.

[0112] (5)

[0113] in, is the exponential gain coefficient.

[0114] Regarding the offset processing of calibration radar data, when a ground-penetrating radar scans a water-bearing area, the raw data profiles collected by the radar do not truly reflect the geometric structure of the detection area due to the radar's recording method, the complexity of the detection area structure, and the diffraction of electromagnetic waves in the target area. This causes the target signal to be offset. To return the target signal to its true location, the calibration radar data must be offset. Therefore, the FK offset algorithm is used to achieve this target signal homed, facilitating the calculation of the water interface reflection coefficient.

[0115] Assume that the calibration radar data received by the ground penetrating radar is , which satisfies the homogeneous Helmholtz equation:

[0116] (6)

[0117] Where x represents the antenna scanning direction, z represents the antenna detection direction, t represents the propagation time of the electromagnetic wave, and v represents the wave velocity in the background. The expression is:

[0118] (7)

[0119] in, Represents the relative dielectric constant of the background. Since the transmission from the antenna to the receiver is a two-way travel time, the wave speed here is taken as 1 / 2 of the actual background wave speed.

[0120] Performing a two-dimensional Fourier transform on formula (6) with respect to x and t yields:

[0121] (8)

[0122] in, is the angular frequency, is the component of the wave number vector in the x-axis direction.

[0123] Assume that when the antenna collects data, it is located at , then the calibration radar data is recorded as , the corresponding frequency domain and wave number domain data are recorded as , which is the initial condition of the electric field, and assuming that the source is , combined with the two-dimensional inverse Fourier transform, according to equation (8) we can get:

[0124] (9)

[0125] The final result , which is the radar data after the required offset, that is, the full amount of radar data in the target area is obtained. Figure 5 As shown, Figure 5 The two-dimensional radar image comparison diagram is after the initial radar data and the preprocessed radar data are visualized.

[0126] In this embodiment, by calibrating, gaining, and offsetting the original collected initial radar data, the impact of interference can be reduced, and gain and offset processing can be performed to reduce the interference of background noise, so that the radar data can reflect the actual geometric structure of the detection area, thereby improving the accuracy of the radar data.

[0127] In an exemplary embodiment, the damage depth information includes the subsidence depth of each acquisition location, the maximum lower limit depth is obtained through subsidence depth analysis, and the subsidence depth and the maximum subsidence depth are used as the basis for correcting the initial reflection coefficient, such as Figure 6 As shown, step 106 includes steps 602 to 606. Among them:

[0128] Step 602: Determine the maximum subsidence depth based on the subsidence depths of the acquisition positions.

[0129] In the embodiment of the present application, when detecting and analyzing heavy-load railway ballast grooving defects, the terminal obtains the corresponding sink depth of each sampling location. The sampling locations are distributed in different parts of the ballast grooving defect area, that is, the defect depth at each location may be different. The terminal then determines the maximum sink depth among the sink depths corresponding to each sampling location and uses it as the maximum sink depth.

[0130] This maximum sink depth is a key indicator, representing the most severe damage within the ballast sink area. This maximum sink depth allows for a more comprehensive analysis of the overall water-related damage, serving as a foundation for subsequent radar data processing and analysis based on the damage depth.

[0131] Step 604 : For each radar data, determine the subsidence degree of the area corresponding to each radar data based on the subsidence depth and the maximum subsidence depth of the acquisition location corresponding to the radar data, and calculate the reflection correction factor corresponding to the radar data according to the subsidence degree.

[0132] In the embodiment of the present application, each radar data point corresponds to a specific acquisition location. The subsidence depth corresponding to this acquisition location is used for comparison and calculation with the maximum subsidence depth, allowing the terminal to determine the degree of subsidence in the area corresponding to the radar data point. For example, the terminal can quantify the degree of subsidence by calculating the ratio of the subsidence depth corresponding to each radar data point to the maximum subsidence depth. The higher the subsidence depth, the more severe the damage in the area. Furthermore, for each radar data point, the terminal determines the degree of subsidence in the area corresponding to each radar data point based on the subsidence depth and the maximum subsidence depth, and calculates the reflection correction factor corresponding to the radar data point based on the subsidence depth.

[0133] The radar wave's reflection at the acquisition location varies with the degree of subsidence. When the subsidence is large, the radar wave's propagation path and energy loss within the affected area differ significantly from those with less severe subsidence, affecting the intensity and characteristics of the reflected wave. Based on the degree of subsidence, the terminal combines the physical characteristics of water-containing troughs in heavy-duty railway ballast with the principles of radar wave propagation to calculate a reflection correction factor for the radar data. This factor is used to correct the radar wave reflection coefficient to more accurately reflect the actual reflection situation.

[0134] Step 606: Correct the initial reflection coefficient according to the reflection correction factor to obtain the target reflection coefficient corresponding to the radar data.

[0135] In the embodiment of the present application, as shown in formula (1), the initial reflection coefficient is calculated based on the damage center data and the total reflection data. Due to the different sinking degrees of water-containing damage, the accumulation state, porosity and water content distribution of the ballast will also change, thereby affecting the propagation path, speed and attenuation of the radar wave in the ballast sinking grooves with different lower limit degrees, resulting in the initial reflection coefficient being unable to accurately reflect the actual radar wave reflection situation.

[0136] The reflection correction factor fully considers the impact of the degree of subsidence of water-containing defects on the reflection of radar waves. Therefore, the terminal applies the reflection correction factor to the initial reflection coefficient and corrects the initial reflection coefficient through the reflection correction factor. The target reflection coefficient obtained after correction can more accurately reflect the reflection of radar waves in the actual defect area, providing a more reliable data basis for subsequent accurate calculation of dielectric constant and detection of water content and other operations.

[0137] In this embodiment, by determining the maximum subsidence depth within the damage depth information at each acquisition location, a comprehensive understanding of the maximum severity of damage within the damaged area can be achieved. Furthermore, for each radar data point, the degree of subsidence is determined based on the damage depth information and the maximum subsidence depth, and a reflection correction factor is calculated. This fully accounts for the impact of varying subsidence levels on radar wave reflection, allowing the correction factor to more accurately reflect the actual effect of the damage area on reflection. Finally, the initial reflection coefficient is corrected using the reflection correction factor. The resulting target reflection coefficient more accurately reflects the reflection of radar waves in the actual damage area, providing a reliable data foundation for the subsequent accurate calculation of the target dielectric constant and the detection of moisture content. This improves the accuracy of the target dielectric constant, and therefore the accuracy of the moisture content, and thus the accuracy of the test results.

[0138] In an exemplary embodiment, Figure 7 As shown, step 604 includes steps 702 to 706. Among them:

[0139] Step 702: For each radar data, the ratio of the subsidence depth to the maximum subsidence depth is determined as the subsidence degree.

[0140] In this embodiment of the present application, in a heavy-haul railway ballast grooving defect detection scenario, a ground-penetrating radar collects a series of radar data, each corresponding to a specific acquisition location. Because the extent of ballast grooving varies across different areas, the terminal quantifies the extent of grooving at each acquisition location using the quantified extent.

[0141] For each radar data, the terminal obtains the maximum subsidence depth by statistically analyzing the subsidence depth of each collection location in the entire diseased area, and compares the subsidence depth of each radar data collection location with the maximum subsidence depth. The obtained ratio is used as the subsidence degree of the collection location corresponding to the radar data.

[0142] Step 704: Determine the adjustment coefficient corresponding to each radar data based on the correspondence between the sag degree and the candidate adjustment coefficient.

[0143] In the embodiments of this application, different degrees of subsidence have varying degrees of impact on the radar wave reflection coefficient. To accurately correct the reflection coefficient, an adjustment coefficient is introduced to further adjust the reflection correction factor. The terminal pre-sets a correspondence between subsidence degrees and candidate adjustment coefficients. This correspondence is derived based on the actual situation of water-containing sag in heavy-haul railway ballast and a large amount of experimental data.

[0144] For each radar data point, a pre-set correspondence is searched based on the degree of subsidence to determine the corresponding adjustment coefficient. For example, α is the adjustment coefficient, which represents the maximum impact of the subsidence depth on the reflection coefficient at each data point. Regarding the value of the adjustment coefficient α, if the subsidence is slight, α is α≤0.015; if the subsidence is moderate, α is 0.015≤α≤0.040; if the subsidence is severe, α is α≥0.040.

[0145] Step 706: Determine a reflection correction factor corresponding to the radar data according to the sinking degree and the adjustment coefficient.

[0146] In the embodiment of the present application, after obtaining the degree of sag and the adjustment coefficient, the terminal determines the reflection correction factor corresponding to the radar data according to the degree of sag and the adjustment coefficient, and further corrects the initial reflection coefficient according to the reflection correction factor and the following formula (10) to obtain the target reflection coefficient. Formula (10) is as follows:

[0147] (10)

[0148] in, is the target reflection coefficient, i.e. the modified reflection coefficient of the water-containing interface of the heavy-duty railway ballast sink hole water-containing disease, is the radar reflection intensity of the water-bearing disease interface, is the radar reflection intensity of the metal plate interface, d is the sink depth of the data, H is the maximum sink depth of the ballast groove disease, and α is the adjustment coefficient, which indicates the maximum influence of the sink depth on the reflection coefficient at each data point.

[0149] In this embodiment, by determining the ratio of the damage depth information to the maximum subsidence depth as the subsidence degree, the subsidence situation at each acquisition location can be quantified, providing basic data for subsequent analysis. Determining the adjustment coefficient corresponding to each radar data point based on the correspondence between the subsidence degree and the candidate adjustment coefficient can more accurately reflect the impact of different subsidence degrees on the radar wave reflection coefficient. Finally, a reflection correction factor is determined based on the subsidence degree and the adjustment coefficient, and the initial reflection coefficient is corrected to obtain the target reflection coefficient. This fully considers the complex situation of the damage area, allowing the corrected reflection coefficient to more accurately reflect the actual radar wave reflection situation, thereby improving the accuracy of the target dielectric constant, that is, improving the accuracy of the water content, and thus improving the accuracy of the detection results.

[0150] In an exemplary embodiment, Figure 8 As shown, step 108 includes steps 802 to 804. Among them:

[0151] Step 802: Calculate the initial dielectric constant corresponding to each acquisition position according to the target reflection coefficient.

[0152] In the embodiment of the present application, the terminal calculates the target reflection coefficient of the water-containing interface in the water-containing disease area of ​​the ballast groove according to the first positive phase peak of the radar data in the target area, and calculates the initial dielectric constant according to the following formula (11) for the radar data of each collection position:

[0153] (11)

[0154] in, To introduce the initial dielectric constant of each radar data in the water disease area after the modified model is introduced, is the dielectric constant of heavy-duty railway ballast layer, is the target reflection coefficient .

[0155] Step 804 : Calculate the mean of the initial reflection coefficients corresponding to each radar data to obtain the target dielectric constant of the target area.

[0156] In the embodiment of the present application, the terminal calculates the mean of the initial reflection coefficients corresponding to each radar data according to the following formula (12) to obtain the target dielectric constant of the target area: :

[0157] (12)

[0158] in, The initial dielectric constant of each radar data in the water-bearing disease area introduced into the modified model is: , is the target dielectric constant of the target area (water-damaged area) introduced into the modified model, and N is the total number of channels occupied by the water-damaged area.

[0159] In this embodiment, the first positive phase amplitude extreme value point of all reflection interfaces of the defect after preprocessing is extracted, and the reflection coefficients of all reflection interfaces are calculated to obtain the average of the initial dielectric constants of each collection position. This average is used as the target reflection coefficient to calculate the moisture content of the ballast groove water-containing defect, which helps to reduce errors caused by local instability or noise, improve the precision of the defect moisture content detection, and improve the accuracy of the detection results.

[0160] In an exemplary embodiment, Figure 9 As shown, step 804 includes steps 902 to 904. Among them:

[0161] Step 902: Determine multiple diseased areas in the target area based on peak distribution in radar data in the target area.

[0162] In an embodiment of the present application, the terminal first performs a characteristic analysis on the radar data of the target area, determines the peak distribution in the radar data, and then further divides the target area into multiple more detailed diseased areas according to the peak distribution, so as to obtain multiple more detailed diseased areas. For example, the terminal can select the area to be extracted according to Matlab's drawrectangle function, or the terminal can automatically calibrate the diseased area using a pre-set peak-related threshold (for example, a peak intensity threshold, an adjacent peak spacing threshold) based on the differences in the reflection characteristics of radar waves when encountering different media and the differences reflected in the peak characteristics of the radar data. Specifically, the terminal reads the ground-penetrating radar data, and then compares the peak characteristics of each point or segment with the threshold when traversing the data, preliminarily determines the suspected diseased area, and then combines factors such as the continuous length of the area and the peak distribution law to screen and eliminate interference, determine the final diseased area, and finally calculate the mean initial reflection coefficient of the radar data of each diseased area and the target dielectric constant to complete the automatic calibration of the diseased area. Figure 10 As shown, Figure 10 The target area is divided into diseased areas based on the peak distribution of radar data in the target area.

[0163] Step 904 , performing mean calculation based on the initial reflection coefficient corresponding to the radar data contained in each defective area, to obtain the target dielectric constant corresponding to each defective area in the target area.

[0164] In the embodiment of the present application, the terminal calculates the target dielectric constant corresponding to each defect area according to the same principle as step 804. The calculation process of the target dielectric constant is not described in detail in this embodiment. Finally, a more detailed analysis of the water-containing defects in the target area is achieved. Then, the corrected target reflection coefficient is as follows: Figure 11 As shown in the figure, and the dielectric constant of the diseased area is shown in the figure Figure 12 shown.

[0165] In an exemplary embodiment, analysis results of a simulation experiment are provided, wherein:

[0166] The dielectric constant of the water-damaged area of ​​heavy-haul railway ballast sink without the introduction of the modified model is calculated as shown in the following formula (13):

[0167] (13)

[0168] in, is the dielectric constant of heavy-duty railway ballast layer, is the radar reflection intensity of the water-bearing disease interface, is the radar reflection intensity of the metal plate interface.

[0169] like Figure 3 As shown in the figure, the maximum positive phase fluctuation peak value of the reflection interface at the extracted water-damaged center data is 120.776 V / m, and the maximum positive phase fluctuation peak value at the total reflection is 353.000 V / m. This means that the reflection coefficient of the water-damaged interface in this damaged area calculated based on the damage center data is 0.367637. Based on the introduced correction model for the reflection coefficient of heavy-haul railway ballast sinks, with an adjustment coefficient α of 0.01, the recalculated target reflection coefficient of the water-damaged interface for heavy-haul railway ballast sinks is 0.368786.

[0170] From the mean results, it can be seen that the mean dielectric constant of the water-containing area without the introduction of the correction model is 47.513218, with an error of 4.97%; the mean dielectric constant of the water-containing area with the introduction of the correction model is 48.861284, with an error of 2.97%. The mean dielectric constant of the water-containing area using the defect center data without the introduction of the correction model is 23.387229, with an error of 53.23%. The mean dielectric constant of the water-containing area using the defect center data and the introduction of the correction model is 24.560000, with an error of 51.68%. From the final calculation results, it can be seen that the reflection interface mean method is more suitable for calculating the moisture content of the uneven interface of heavy-duty railway ballast sink water defects, and has higher accuracy. At the same time, the dielectric constant calculation results of the water-containing area using the reflection coefficient correction model for heavy-duty railway ballast sink water defects are approximately 2.00% more accurate than those without the introduction.

[0171] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0172] Based on the same inventive concept, the present application also provides a disease detection device for implementing the aforementioned disease detection method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more disease detection device embodiments provided below can be found in the above-mentioned limitations of the disease detection method and will not be further elaborated here.

[0173] In an exemplary embodiment, Figure 13 As shown, a disease detection device 1300 is provided, comprising: an extraction module 1301, a calculation module 1302, a correction module 1303 and a determination module 1304, wherein:

[0174] Extraction module 1301 is used to obtain the full amount of radar data in the target area, extract the full amount of radar data, and obtain the disease depth information of each collection position in the target area;

[0175] A calculation module 1302 is used to calculate based on radar data to obtain an initial reflection coefficient;

[0176] Correction module 1303 is used to calculate the reflection correction factor for each radar data according to the damage depth information at the acquisition location corresponding to the radar data, and correct the initial reflection coefficient based on the reflection correction factor to obtain the target reflection coefficient;

[0177] The determination module 1304 is configured to obtain a target dielectric constant according to the target reflection coefficient, and the target dielectric constant is used to determine the detection result.

[0178] In one embodiment, the extraction module 1301 is specifically configured to obtain calibration signal data and a full amount of initial radar data in the target area;

[0179] Performing calibration processing on the initial radar data according to the calibration signal data to obtain calibrated radar data;

[0180] Perform gain and offset processing on the calibrated radar data to obtain the full amount of radar data in the target area.

[0181] In one embodiment, the correction module 1303 is specifically configured to determine the maximum subsidence depth based on the damage depth information at each acquisition location;

[0182] For each radar data, determine the subsidence degree of the area corresponding to each radar data based on the damage depth information and the maximum subsidence depth, and calculate the reflection correction factor corresponding to the radar data according to the subsidence degree;

[0183] The initial reflection coefficient is corrected according to the reflection correction factor to obtain the target reflection coefficient corresponding to the radar data.

[0184] In one embodiment, the correction module 1303 is specifically configured to determine the ratio of the disease depth information to the maximum subsidence depth as the subsidence degree for each radar data;

[0185] Based on the corresponding relationship between the degree of sag and the candidate adjustment coefficients, the adjustment coefficient corresponding to each radar data is determined;

[0186] The reflection correction factor corresponding to the radar data is determined according to the degree of depression and the adjustment coefficient.

[0187] In one embodiment, the determination module 1304 is specifically configured to calculate the initial dielectric constant corresponding to each acquisition position according to the target reflection coefficient;

[0188] The initial reflection coefficients corresponding to each radar data are averaged to obtain the target dielectric constant of the target area.

[0189] In one embodiment, the determination module 1304 is specifically configured to determine a plurality of diseased areas in the target area based on peak distribution in radar data in the target area;

[0190] The target dielectric constant corresponding to each defect area in the target area is obtained by calculating the average value of the initial reflection coefficient corresponding to the radar data contained in each defect area.

[0191] Each module in the disease detection device described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0192] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 14As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means, and the wireless means can be implemented via Wi-Fi, mobile cellular networks, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a disease detection method. The display unit of the computer device is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0193] Those skilled in the art will understand that Figure 14 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0194] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0195] Obtain all radar data in the target area, extract the data, and obtain the depth information of the damage at each sampling location in the target area;

[0196] Calculate based on radar data to obtain the initial reflection coefficient;

[0197] For each radar data, the reflection correction factor is calculated according to the damage depth information at the acquisition location corresponding to the radar data, and the initial reflection coefficient is corrected based on the reflection correction factor to obtain the target reflection coefficient;

[0198] The target dielectric constant is obtained according to the target reflection coefficient, and the target dielectric constant is used to determine the detection result.

[0199] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0200] Acquire calibration signal data and full initial radar data in the target area;

[0201] Performing calibration processing on the initial radar data according to the calibration signal data to obtain calibrated radar data;

[0202] Perform gain and offset processing on the calibrated radar data to obtain the full amount of radar data in the target area.

[0203] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0204] Determine the maximum subsidence depth based on the subsidence depth of each sampling location;

[0205] For each radar data, based on the subsidence depth and maximum subsidence depth of the acquisition location corresponding to the radar data, the subsidence degree of the area corresponding to each radar data is determined, and the reflection correction factor corresponding to the radar data is calculated according to the subsidence degree;

[0206] The initial reflection coefficient is corrected according to the reflection correction factor to obtain the target reflection coefficient corresponding to the radar data.

[0207] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0208] For each radar data, the ratio of the subsidence depth to the maximum subsidence depth is determined as the subsidence degree;

[0209] Based on the corresponding relationship between the degree of sag and the candidate adjustment coefficients, the adjustment coefficient corresponding to each radar data is determined;

[0210] The reflection correction factor corresponding to the radar data is determined according to the degree of depression and the adjustment coefficient.

[0211] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0212] Calculate the initial dielectric constant corresponding to each acquisition position according to the target reflection coefficient;

[0213] The initial reflection coefficients corresponding to each radar data are averaged to obtain the target dielectric constant of the target area.

[0214] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0215] Determine multiple diseased areas in the target area based on peak distribution in radar data in the target area;

[0216] The target dielectric constant corresponding to each defect area in the target area is obtained by calculating the average value of the initial reflection coefficient corresponding to the radar data contained in each defect area.

[0217] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0218] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0219] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0220] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0221] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0222] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A disease detection method, characterized in that: The method comprises: Acquire a full amount of radar data in the target area, extract the full amount of radar data, and obtain disease depth information at each acquisition location in the target area; Calculating according to the radar data to obtain an initial reflection coefficient; For each radar data, a reflection correction factor is calculated according to the defect depth information at the acquisition position corresponding to the radar data, and the initial reflection coefficient is corrected based on the reflection correction factor to obtain a target reflection coefficient; A target dielectric constant is obtained according to the target reflection coefficient, and the target dielectric constant is used to determine a detection result.

2. The method according to claim 1, characterized in that The acquisition of the full amount of radar data in the target area includes: Acquire calibration signal data and full initial radar data in the target area; performing calibration processing on the initial radar data according to the calibration signal data to obtain calibrated radar data; Gain processing and offset processing are performed on the calibrated radar data to obtain full radar data in the target area.

3. The method according to claim 1, characterized in that The defect depth information includes the subsidence depth of each acquisition position; for each radar data, calculating a reflection correction factor according to the defect depth information of the acquisition position corresponding to the radar data, and correcting the initial reflection coefficient based on the reflection correction factor to obtain a target reflection coefficient, including: Determining a maximum subsidence depth according to the subsidence depths of the respective acquisition locations; For each piece of radar data, determining a subsidence degree of an area corresponding to each piece of radar data based on the subsidence depth of the acquisition location corresponding to the radar data and the maximum subsidence depth, and calculating a reflection correction factor corresponding to the radar data according to the subsidence degree; The initial reflection coefficient is corrected according to the reflection correction factor to obtain a target reflection coefficient corresponding to the radar data.

4. The method according to claim 3, characterized in that The step of determining, for each piece of radar data, a subsidence degree of an area corresponding to each piece of radar data based on the subsidence depth of the acquisition position corresponding to the radar data and the maximum subsidence depth, and calculating a reflection correction factor corresponding to the radar data according to the subsidence degree, includes: For each piece of radar data, determining a ratio of the subsidence depth to the maximum subsidence depth as a subsidence degree; Determining an adjustment coefficient corresponding to each radar data based on a correspondence between the sinking degree and the candidate adjustment coefficient; A reflection correction factor corresponding to the radar data is determined according to the sinking degree and the adjustment coefficient.

5. The method according to claim 1, characterized in that Obtaining a target dielectric constant according to the target reflection coefficient includes: Calculating the initial dielectric constant corresponding to each of the acquisition positions according to the target reflection coefficient; The initial reflection coefficients corresponding to the radar data are averaged to obtain the target dielectric constant of the target area.

6. The method according to claim 5, characterized in that The calculating the mean of the initial reflection coefficients corresponding to the radar data to obtain the target dielectric constant of the target area includes: determining a plurality of diseased areas in the target area according to peak distribution in the radar data in the target area; A mean value calculation is performed based on the initial reflection coefficient corresponding to the radar data contained in each of the defective areas to obtain the target dielectric constant corresponding to each of the defective areas in the target area.

7. A disease detection device, characterized in that: The device comprises: An extraction module is used to obtain the full amount of radar data in the target area, extract the full amount of radar data, and obtain the disease depth information of each collection position in the target area; The calculation module is used to calculate according to the radar data to obtain an initial reflection coefficient; a correction module, configured to calculate, for each radar data, a reflection correction factor according to the defect depth information at the acquisition position corresponding to the radar data, and correct the initial reflection coefficient based on the reflection correction factor to obtain a target reflection coefficient; The determination module is used to obtain a target dielectric constant according to the target reflection coefficient, and the target dielectric constant is used to determine the detection result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images