Railway roadbed collapse monitoring method and system

Abstract

The invention relates to the field of collapse monitoring, in particular to a railway roadbed collapse monitoring method and system, and the method comprises the steps: obtaining a reflected wave signal detected by a geological radar at each roadbed section each time; dielectric significance is obtained based on the outlier degree of the energy of the reflected wave signal of each roadbed section; obtaining a signal bending amount based on the frequency distribution convergence of the reflected wave signal in the frequency domain; obtaining a water content evaluation value of each roadbed section in each detection, and screening a to-be-confirmed road section; the change condition of the signal curvature of the reflected wave signal of each roadbed section to be confirmed in the continuous detection process is analyzed, and the static continuity of each roadbed section to be confirmed is obtained; and based on the static continuity and the water content evaluation value of each to-be-confirmed roadbed section in each detection, obtaining the collapse possibility of each to-be-confirmed roadbed section in each detection. The invention aims to improve the monitoring accuracy of roadbed collapse.

Description

Technical Field

[0001] The present application relates to the field of subsidence monitoring, and in particular to a method and system for monitoring subsidence of a railway subsidence. Background Art

[0002] In the monitoring of railway subsidence, commonly used technical means include surface deformation monitoring, geological radar detection, fiber optic sensor monitoring, and tilt sensors. Among them, in order to efficiently and accurately detect underground structures, geological radar (GPR) technology is widely used. Its basic principle is to use the reflection characteristics of electromagnetic waves when propagating in different media, and analyze the reflected signals of underground media (such as cavities, moisture changes, or soil density) to identify abnormal changes in underground structures. Geological radar can provide fast and real-time underground detection results, and is an effective means to monitor abnormal structures such as underground defects, cracks or cavities.

[0003] The moisture content of roadbed soil plays a vital role in the collapse judgment process. Real-time monitoring through geological radar detection technology can quickly evaluate the moisture content based on the characteristics of reflected waves. However, during the monitoring process, due to the uneven density of some soil materials, the dielectric constant will fluctuate. This fluctuation is similar to the characteristics of the moisture area, which may cause misjudgment of the water content, thereby affecting the accurate monitoring and evaluation of roadbed collapse. Summary of the invention

[0004] In view of the above, it is necessary to provide a railway subsidence monitoring method and system to solve the above problems.

[0005] The first aspect of the present application provides a railway subsidence monitoring method, the method comprising:

[0006] Obtain the reflected wave signal of each detection of the geological radar in each roadbed section;

[0007] Based on the outlier degree of the energy of the reflected wave signal of each roadbed section in each detection of all roadbed sections, the dielectric significance of each roadbed section in each detection is obtained;

[0008] The reflected wave signal of each roadbed section in each detection is transformed in the frequency domain, and the frequency is marked based on the amplitude change in the frequency domain; the signal bending amount of each roadbed section in each detection is obtained according to the distribution convergence and divergence of the marked frequency; based on the signal bending amount and dielectric significance, the water content evaluation value of each roadbed section in each detection is obtained, and the road section to be confirmed is screened;

[0009] The change in the signal curvature of the reflected wave signal of each roadbed section to be confirmed during the continuous detection process is analyzed to obtain the static continuity of each roadbed section to be confirmed; based on the static continuity and water content evaluation value of each roadbed section to be confirmed in each detection, the collapse possibility of each roadbed section to be confirmed in each detection is obtained.

[0010] The dielectric significance of each roadbed section in each test is obtained as follows:

[0011] The reflected wave signal energies of all roadbed sections in each detection are taken as samples to obtain the outlier degree of the reflected wave signal energy of each roadbed section; and the normalized value of the product of the reflected wave signal energy and the outlier degree is taken as the dielectric significance of each roadbed section in each detection.

[0012] The process of marking the frequency is as follows:

[0013] All frequency amplitudes of the reflected wave signals of each roadbed section in each detection are normalized, and the frequencies whose normalized values ​​of the frequency amplitudes are greater than a preset threshold are marked.

[0014] The step of obtaining the signal bending amount of each roadbed section in each detection is as follows:

[0015] According to the span and number of frequencies of the reflected wave signals of each roadbed section marked in each detection, the irregularity amount of the reflected wave signals of each roadbed section in each detection is obtained;

[0016] For the reflected wave signal of each roadbed section in each detection, the disorder degree of its marked frequency is obtained; and the fusion result of the disorder degree and the signal irregularity is used as the signal bending amount of each roadbed section in each detection.

[0017] The signal irregularity of the reflected wave signal of each roadbed section in each detection is obtained as follows:

[0018] The extreme value of the marked frequency is obtained; the number of marked frequencies is merged with the extreme value to obtain the signal irregularity of each roadbed section in each detection.

[0019] The water content evaluation value of each roadbed section in each detection is specifically a normalized value of the product of the signal curvature and the dielectric significance.

[0020] The process of screening the road section to be confirmed is specifically as follows: when the water content evaluation value is greater than or equal to a preset evaluation threshold, the corresponding roadbed section is marked as a road section to be confirmed.

[0021] The process of obtaining the static continuity of each roadbed section to be confirmed is specifically as follows:

[0022] Each detection and the preset number of detections before are taken as a detection interval, and the difference in signal curvature of adjacent reflected wave signals of each roadbed section to be confirmed in each detection interval is obtained. The negative correlation mapping results of all the differences in each detection interval of each roadbed section to be confirmed are averaged to obtain the static continuity of each roadbed section to be confirmed in each detection.

[0023] The method of obtaining the collapse possibility of each roadbed section to be confirmed in each detection is specifically as follows:

[0024] The difference between the value 1 and the static continuity is calculated, and the normalized value obtained by multiplying the difference by the water content assessment value is determined as the collapse possibility of the roadbed section to be confirmed in each detection.

[0025] In a second aspect, an embodiment of the present application further provides a railway subsidence monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned methods when executing the computer program.

[0026] This application has at least the following beneficial effects:

[0027] The embodiment of the present application analyzes the energy distribution of the reflected wave signal of each detection of all roadbed sections by the geological radar, and obtains the dielectric significance of each roadbed section in each detection, which effectively reduces the subsequent misjudgment caused by factors such as the difference in density of the roadbed material and the different soil types, and can more accurately distinguish the relationship between the changes caused by moisture and other physical characteristics, thereby improving the judgment accuracy of roadbed collapse; the frequency is marked based on the amplitude change in the frequency domain, and the signal bending amount of each roadbed section in each detection is obtained according to the distribution convergence and divergence of the marked frequency. By analyzing the convergence and divergence of the frequency distribution, the roadbed can be more accurately evaluated. The state of the roadbed is determined, the error caused by external environmental factors is reduced, and the accuracy of the detection results is improved; based on the signal curvature and dielectric significance, the water content evaluation value of each roadbed section in each detection is obtained, the road sections to be confirmed are screened, the subsequent calculation amount is reduced and the efficiency is improved; the change of the signal curvature of the reflected wave signal of each roadbed section to be confirmed during the continuous detection process is analyzed, and the static continuity of each roadbed section to be confirmed is obtained, and the reflected wave signals obtained for multiple consecutive times are analyzed as a whole. According to the water content change characteristics of the roadbed area, the interference of other materials is eliminated, the possibility of roadbed collapse is obtained, and accurate monitoring of roadbed collapse is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A flowchart of a method for monitoring railway subsidence provided in accordance with an embodiment of the present application;

[0029] Figure 2 A flowchart for obtaining collapse possibility is provided for one embodiment of the present application. DETAILED DESCRIPTION

[0030] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0032] It should also be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flow chart includes one or more steps for implementing the method. Without departing from the scope of protection of the present application, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0033] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0034] The specific scheme of a railway subsidence monitoring method and system provided by the present application is described in detail below with reference to the accompanying drawings.

[0035] See also Figure 1 , which shows a flow chart of the steps of a railway subsidence monitoring method provided by an embodiment of the present application, the method comprising the following steps:

[0036] The first step is to obtain the reflected wave signal detected by the geological radar at each roadbed section.

[0037] Geological radar equipment is deployed in different sections of the railway embankment, and each radar covers a certain monitoring range. In this embodiment, the resolution of the geological radar equipment used is: 0.1-0.5m, which is used to capture subtle changes; the detection depth range is 0.5-3m; the radar frequency range is: 250MHz-1GHz, and the implementer can select the appropriate frequency range according to the detection depth and resolution requirements; the signal acquisition frequency is 100Hz, and the reflected wave signal is collected every 30 minutes; the implementer can adjust it according to the actual situation.

[0038] The second step: based on the outlier degree of the energy of the reflected wave signal of each roadbed section in each detection of all roadbed sections, the dielectric significance of each roadbed section in each detection is obtained.

[0039] Each collected reflection wave signal comes from the electromagnetic wave propagating to different depths of the underground strata and reflecting when encountering different media. The waveform characteristics of the reflection wave signal can reflect the geological characteristics of the area, such as density and moisture content. In particular, the moisture content has a significant effect on the dielectric constant of the soil, because the high dielectric constant of water will greatly enhance the intensity of the reflection wave signal. In areas with high moisture content, the signal amplitude of the reflection wave increases significantly, and the energy value of the reflection wave signal is significantly higher than that of other areas. In addition, areas with high moisture content often cause the reflection waveform to become irregular, and even local bending or damage occurs.

[0040] Based on the reflected wave signal amplitude of each roadbed section in each detection, the reflected wave signal energy is calculated, which is an existing well-known technology and will not be repeated in this application; based on the outlier degree of the reflected wave signal energy of each roadbed section in each detection of all roadbed sections, the dielectric significance of each roadbed section in each detection is obtained: the reflected wave signal energy of all roadbed sections in each detection is taken as a sample to obtain the outlier degree of the reflected wave signal energy of each roadbed section; the normalized value of the product of the reflected wave signal energy and the outlier degree is taken as the dielectric significance of each roadbed section in each detection.

[0041] In this embodiment, the degree of outlier is measured by Z score, which is a well-known technology and will not be described in detail in this application; in addition, the maximum and minimum method is used for normalization.

[0042] It should be understood that the larger the energy value of each roadbed section and the stronger the outlier, the higher the moisture content of the roadbed section, which leads to a greater possibility of dielectric constant change and a correspondingly higher dielectric significance.

[0043] The third step: use frequency domain transformation on the reflected wave signal of each roadbed section in each detection, and mark the frequency based on the amplitude change in the frequency domain; according to the distribution convergence and divergence of the marked frequency, obtain the signal bending amount of each roadbed section in each detection; based on the signal bending amount and dielectric significance, obtain the water content evaluation value of each roadbed section in each detection, and screen the road sections to be confirmed.

[0044] Due to the effect of water diffusion, the reflected wave signal usually exhibits irregular or curved characteristics. Therefore, in the frequency domain, the high-amplitude frequency region of the signal will show a more dispersed distribution.

[0045] Fourier transform is used for the reflected wave signal of each roadbed section in each detection, and the frequency is marked based on the amplitude change in the frequency domain. The signal irregularity is obtained according to the span and number of marked frequencies: all frequency amplitudes of the reflected wave signal of each roadbed section in each detection are normalized, and the frequencies whose normalized values ​​of the frequency amplitude are greater than a preset threshold are marked; the range values ​​of the marked frequencies are obtained; the number of marked frequencies is fused with the range value to obtain the signal irregularity of each roadbed section in each detection.

[0046] In this embodiment, the normalization adopts the sigmoid function, and the preset threshold value is 0.6, which can be adjusted by the implementer; multiple variables are fused by multiplication, that is, the signal irregularity is specifically the product of the number of marked frequencies and the extreme value.

[0047] It should be understood that if there are more marked frequency components and the distribution of these frequencies is more dispersed, it means that the bandwidth of the signal is wider, reflecting that the signal contains more components of different frequencies. This phenomenon usually indicates that the frequency range of the reflected wave signal is wider and its irregularity or complexity is higher. The increase in bandwidth means that the frequency components of the signal are richer, which is consistent with the characteristics of electromagnetic waves when they are reflected in areas with more moisture, because an environment with more moisture will lead to an expansion of the reflected wave frequency range and more complex signal characteristics.

[0048] Furthermore, based on the distribution of the frequency of the reflected wave signal of each roadbed section in each detection in the frequency domain, combined with the signal irregularity, the signal bending amount of each roadbed section in each detection is obtained: for the reflected wave signal of each roadbed section in each detection, the disorder degree of its marked frequency is obtained; the fusion result of the disorder degree and the signal irregularity is used as the signal bending amount of each roadbed section in each detection. In this embodiment, the entropy value is used to measure the disorder degree of the frequency; and the fusion of multiple variables is calculated by multiplication.

[0049] It should be understood that the frequency distribution will affect the irregularity of the signal. The more chaotic the frequency distribution is, the more likely it is that the intensity of some frequencies will suddenly increase or decrease in the frequency domain. This uneven frequency distribution will cause the signal to appear as complex and irregular fluctuations in the time domain, making the signal look irregular. If the frequency of the signal is distributed more evenly in the frequency domain, then the time domain performance of the signal may be relatively regular.

[0050] The normalized value of the product of the signal curvature and the dielectric significance is calculated to obtain the water content evaluation value of each roadbed section in each detection; when the water content evaluation value is greater than or equal to a preset evaluation threshold, the corresponding roadbed section is marked as a section to be confirmed. In this embodiment, the normalization method adopts the maximum and minimum value method, and the evaluation threshold is 0.8, which can be adjusted by the implementer.

[0051] It should be understood that if the water content assessment value of a roadbed section in this test is greater than or equal to the assessment threshold, the possibility of collapse of the roadbed section is greater and further confirmation is needed; if the water content assessment values ​​of all roadbed sections in this test are less than the assessment threshold, it means that there is no collapse of the roadbed section and it is necessary to wait for the next test.

[0052] The fourth step: Analyze the changes in the signal curvature of the reflected wave signal of each roadbed section to be confirmed during the continuous detection process to obtain the static continuity of each roadbed section to be confirmed; based on the static continuity and water content evaluation value of each roadbed section to be confirmed in each detection, obtain the collapse possibility of each roadbed section to be confirmed in each detection.

[0053] Different types of roadbed materials, such as soil, gravel, clay, etc., have their own natural dielectric constants. When these materials are mixed or unevenly distributed, it may cause changes in signal reflection, similar to the phenomenon caused by increased moisture content. In addition, changes in the looseness or compaction state of the roadbed will also affect the reflection intensity of the medium to the radar wave, resulting in an enhancement of the radar signal or more signal disturbances. Therefore, the water content assessment value is only one of the necessary conditions for identification. In order to distinguish more accurately, it is also necessary to analyze and process in combination with the dynamic changes in areas with higher water content.

[0054] Dynamic variability means that during multiple detections, radar signals in water-saturated areas usually show a characteristic of gradual enhancement and expansion, that is, as water accumulates or diffuses, the reflection intensity of the signal will gradually increase, and this change shows a continuous trend. Compared with other areas, the reflection parameters of water-saturated areas are relatively stable at different time points. Therefore, in order to accurately distinguish these areas, it is necessary to monitor multiple continuous reflection wave signals and analyze their dynamic change characteristics.

[0055] Analyze the change of the signal curvature of the reflected wave signal of each roadbed section to be confirmed during the continuous detection process to obtain the static continuity of each roadbed section to be confirmed: take each detection and the preset number of detections before as a detection interval, obtain the difference in the signal curvature of adjacent reflected wave signals of each roadbed section to be confirmed in each detection interval, average the negative correlation mapping results of all the differences in each detection interval for each roadbed section to be confirmed, and obtain the static continuity of each roadbed section to be confirmed in each detection. In this embodiment, the preset number is 23, and the implementer can adjust it according to the actual situation; the difference between the variables is measured by the absolute value of the difference; the negative correlation mapping result of the difference is specifically the inverse value of the difference. It should be noted that in order to avoid the denominator being 0, a constant greater than zero needs to be added to the denominator, and the value is 1.

[0056] It should be understood that the smaller the difference in signal curvature of the reflected wave signal between two adjacent detections, the closer the negative correlation mapping result is to 1, indicating that due to the fixed nature of the roadbed section, the characteristics of the reflected wave signal under different detections remain consistent; and in areas with high moisture content, it usually shows a trend of gradual enhancement and diffusion, that is, the greater the difference in signal curvature of the reflected wave signal between two adjacent detections, the less the difference in the negative correlation mapping result is than 1, which means that the dynamic characteristics of the signal are more obvious and can better reflect the changing law of the moisture content area.

[0057] Furthermore, based on the static continuity and water content evaluation value of each roadbed section to be confirmed in each detection, the collapse possibility of each roadbed section to be confirmed in each detection is obtained: the difference between 1 and the static continuity is calculated, and the normalized value after multiplying the difference with the water content evaluation value is obtained to obtain the collapse possibility of the roadbed section to be confirmed in each detection.

[0058] Among them, the flowchart for obtaining the possibility of collapse is as follows Figure 2 shown.

[0059] Based on the same inventive concept as the above method, an embodiment of the present application also provides a railway subsidence monitoring system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above-mentioned railway subsidence monitoring methods are implemented.

[0060] In summary, the present application obtains the dielectric significance of each roadbed section in each detection by analyzing the energy distribution of the reflected wave signal of the geological radar in each detection of all roadbed sections, effectively reducing the subsequent misjudgment caused by factors such as differences in the density of roadbed materials and different soil types, and can more accurately distinguish the relationship between changes caused by moisture and other physical characteristics, thereby improving the accuracy of judgment on roadbed collapse; the frequency is marked based on the amplitude change in the frequency domain, and the signal bending amount of each roadbed section in each detection is obtained according to the distribution convergence and divergence of the marked frequency. By analyzing the convergence and divergence of the frequency distribution, it is possible to more accurately evaluate The state of the roadbed is determined, the error caused by external environmental factors is reduced, and the accuracy of the detection results is improved; based on the signal curvature and dielectric significance, the water content evaluation value of each roadbed section in each detection is obtained, the road sections to be confirmed are screened, the subsequent calculation amount is reduced and the efficiency is improved; the change of the signal curvature of the reflected wave signal of each roadbed section to be confirmed during the continuous detection process is analyzed, and the static continuity of each roadbed section to be confirmed is obtained, and the reflected wave signals obtained for multiple consecutive times are analyzed as a whole. According to the water content change characteristics of the roadbed area, the interference of other materials is eliminated, the possibility of roadbed collapse is obtained, and accurate monitoring of roadbed collapse is realized.

[0061] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two continuous operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0062] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive; the technical solutions recorded in the above embodiments are modified, or some of the technical features are replaced by equivalents, which does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A railway subsidence monitoring method, characterized in that: The method comprises the following steps: Obtain the reflected wave signal of each detection of the geological radar in each roadbed section; Based on the outlier degree of the energy of the reflected wave signal of each roadbed section in each detection of all roadbed sections, the dielectric significance of each roadbed section in each detection is obtained; The reflected wave signal of each roadbed section in each detection is transformed in the frequency domain, and the frequency is marked based on the amplitude change in the frequency domain; the signal bending amount of each roadbed section in each detection is obtained according to the distribution convergence and divergence of the marked frequency; based on the signal bending amount and dielectric significance, the water content evaluation value of each roadbed section in each detection is obtained, and the road section to be confirmed is screened; The change in the signal curvature of the reflected wave signal of each roadbed section to be confirmed during the continuous detection process is analyzed to obtain the static continuity of each roadbed section to be confirmed; based on the static continuity and water content evaluation value of each roadbed section to be confirmed in each detection, the collapse possibility of each roadbed section to be confirmed in each detection is obtained.

2. A railway subsidence monitoring method as claimed in claim 1, characterized in that: The dielectric significance of each roadbed section in each test is obtained as follows: The reflected wave signal energies of all roadbed sections in each detection are taken as samples to obtain the outlier degree of the reflected wave signal energy of each roadbed section; and the normalized value of the product of the reflected wave signal energy and the outlier degree is taken as the dielectric significance of each roadbed section in each detection.

3. A railway subsidence monitoring method as claimed in claim 1, characterized in that: The process of marking the frequency is as follows: All frequency amplitudes of the reflected wave signals of each roadbed section in each detection are normalized, and the frequencies whose normalized values ​​of the frequency amplitudes are greater than a preset threshold are marked.

4. A railway subsidence monitoring method as claimed in claim 1, characterized in that: The steps of obtaining the signal bending amount of each roadbed section in each detection are as follows: According to the span and number of frequencies of the reflected wave signals of each roadbed section marked in each detection, the irregularity amount of the reflected wave signals of each roadbed section in each detection is obtained; For each reflected wave signal of each roadbed section in each detection, obtain the disorder degree of its marked frequency; The fusion result of the chaos degree and the signal irregularity is used as the signal bending amount of each roadbed section in each detection.

5. A railway subsidence monitoring method as claimed in claim 4, characterized in that: The signal irregularity of the reflected wave signal of each roadbed section in each detection is obtained as follows: The extreme value of the marked frequency is obtained; the number of marked frequencies is merged with the extreme value to obtain the signal irregularity of each roadbed section in each detection.

6. A railway subsidence monitoring method as claimed in claim 1, characterized in that: The water content evaluation value of each roadbed section in each detection is specifically a normalized value of the product of the signal tortuosity and the dielectric significance.

7. A railway subsidence monitoring method as claimed in claim 1, characterized in that: The process of screening the road section to be confirmed is specifically as follows: when the water content evaluation value is greater than or equal to a preset evaluation threshold, the corresponding roadbed section is marked as a road section to be confirmed.

8. A railway subsidence monitoring method as claimed in claim 1, characterized in that: The process of obtaining the static continuity of each roadbed section to be confirmed is specifically as follows: Each detection and the preset number of detections before are taken as a detection interval, and the difference in signal curvature of adjacent reflected wave signals of each roadbed section to be confirmed in each detection interval is obtained. The negative correlation mapping results of all the differences in each detection interval of each roadbed section to be confirmed are averaged to obtain the static continuity of each roadbed section to be confirmed in each detection.

9. A railway subsidence monitoring method as claimed in claim 1, characterized in that: The method of obtaining the collapse possibility of each roadbed section to be confirmed in each detection is specifically as follows: The difference between the value 1 and the static continuity is calculated, and the normalized value obtained by multiplying the difference by the water content assessment value is determined as the collapse possibility of the roadbed section to be confirmed in each detection.

10. A railway subsidence monitoring system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images