Method and system for monitoring rock and soil layer structure changes based on sensor fusion

Through sensor fusion technology, real-time monitoring of changes in geotechnical layer structures has been solved, and the problems of inaccurate monitoring and high false alarm rates in the existing technology have been solved, and timely early warning and high-precision monitoring of landslide collapse have been achieved.

CN118654732BActive Publication Date: 2024-11-05BEIJING ZHIGAN TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411128285.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-05
Estimated Expiration
2044-08-16

AI Technical Summary

Technical Problem

The existing technology is difficult to monitor changes in the geotechnical layer structure in real time and accurately, resulting in a timely warning of landslide collapse accidents and a high false alarm rate.

Method used

Using a sensor fusion method, the monitoring parameters are obtained through geotechnical parameter sensors, sliding sensors, low-frequency vibration sensors and inclination sensors, and the multi-parameter fusion alarm conditions are compared. Combined with low threshold and high threshold alarm conditions, the geotechnical layer is realized. High-precision real-time monitoring of structural changes.

Benefits of technology

The false alarm rate is reduced, the accuracy and timeliness of monitoring changes in geotechnical layer structures are improved, and timely warnings for landslide collapse are ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118654732B_ABST
    Figure CN118654732B_ABST
Patent Text Reader

Abstract

The present application relates to the field of sensor monitoring technology, and discloses a method and system for monitoring changes in rock and soil layer structure based on sensor fusion, the method comprising: obtaining monitoring parameters output by a rock and soil parameter sensor, a rock and soil layer sliding sensor, a low-frequency vibration sensor, and an inclination sensor at the same monitoring point; performing a first comparison between the monitoring parameters and the multi-parameter fusion alarm conditions; wherein the multi-parameter fusion alarm conditions include the low threshold alarm conditions corresponding to each monitoring parameter; if the monitoring parameters all meet the corresponding low threshold alarm conditions, then an alarm message is output, otherwise the monitoring parameters are respectively compared with their respective corresponding high threshold alarm conditions for a second time, and whether to output an alarm message is determined based on the second comparison result; wherein the low threshold alarm condition corresponding to each monitoring parameter is lower than the corresponding high threshold alarm condition. The present application realizes high-precision real-time monitoring of changes in rock and soil layer structure by fusing multiple sensors, thereby reducing the false alarm rate.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of sensor monitoring technology, and in particular to a method and system for monitoring rock and soil layer structure changes based on sensor fusion. Background Art

[0002] Places with slopes and tunnels such as highways, railways, riverbanks, hydropower stations, mines, mine tunnels, rail transit tunnels, highway tunnels, municipal and scenic areas are all at risk of geological disasters such as landslides and collapses, which often lead to serious accidents. At present, areas with landslide and collapse risks are mainly monitored through Beidou high-precision receivers, inclinometers, rain gauges, deep displacement monitoring, video monitoring, etc., but only the surface conditions in dangerous areas are monitored, and most landslides and collapses start from the sliding of the soil layer inside the dangerous area. When external changes are detected, landslides and collapses may have already occurred. In addition, traditional monitoring methods are all about grasping the geographical environment and changes of the landslide body as a whole. These monitoring observations have a long observation period and a complex analysis and research process. They cannot make timely monitoring and early warnings and have a high false alarm rate. Summary of the invention

[0003] The embodiments of the present application provide a method and system for monitoring changes in rock and soil layer structures based on sensor fusion. By fusing monitoring data from multiple sensors, high-precision real-time monitoring of changes in rock and soil layer structures is achieved, thereby reducing the false alarm rate.

[0004] In a first aspect, an embodiment of the present application provides a method for monitoring rock and soil layer structure changes based on sensor fusion, comprising:

[0005] Acquire monitoring parameters output by a geotechnical parameter sensor, a geotechnical layer sliding sensor, a low-frequency vibration sensor, and an inclination sensor at the same monitoring point; wherein the monitoring parameters include the capacitance value and the impedance value of the surrounding geotechnical layer collected by the geotechnical parameter sensor, the relative cohesion and the relative internal friction angle of the geotechnical layer determined based on the capacitance value and the impedance value, the vibration change of the surrounding geotechnical layer output by the low-frequency vibration sensor, the inclination change of the surrounding geotechnical layer output by the inclination sensor, and the sliding condition of the surrounding geotechnical layer of the geotechnical layer sliding sensor;

[0006] Performing a first comparison between the monitoring parameter and the multi-parameter fusion alarm condition; wherein the multi-parameter fusion alarm condition includes a low threshold alarm condition corresponding to each monitoring parameter;

[0007] If all monitoring parameters involved in the first comparison meet the corresponding low threshold alarm conditions, an alarm message is output;

[0008] If at least one of the monitoring parameters participating in the first comparison does not meet the corresponding low threshold alarm condition, the monitoring parameters participating in the first comparison will be compared for a second time with their respective corresponding high threshold alarm conditions, and whether to output the alarm information is determined based on the second comparison results of all monitoring parameters participating in the first comparison; wherein the low threshold alarm condition corresponding to each monitoring parameter is lower than the corresponding high threshold alarm condition.

[0009] Optionally, before performing the first comparison, the method further comprises: performing data rationality verification on each monitoring parameter according to a change trend of each monitoring parameter to determine a parameter that passes the verification;

[0010] The first comparison of the monitoring parameters with the multi-parameter fusion alarm conditions specifically includes: first comparison of the parameters that pass the verification with the multi-parameter fusion alarm conditions.

[0011] Optionally, performing data rationality verification on each monitoring parameter according to the change trend of each monitoring parameter specifically includes:

[0012] Determine the number of items I1 with increased data and the number D1 with decreased data in the three items of the vibration change, the inclination angle change and the sliding condition, and determine the number D2 with decreased data and the number I2 with increased data in the relative cohesion and the relative internal friction angle;

[0013] If I1+D2 is not less than the preset value, it is determined that the item with increased data among the vibration change, the inclination angle change and the sliding condition and the item with decreased data among the relative cohesion and the relative internal friction angle have passed the verification; otherwise, it is determined that all monitoring data have failed the verification;

[0014] If D1+I2 is not less than the preset value, it is determined that the items with reduced data among the vibration change, the inclination angle change and the sliding condition and the items with increased data among the relative cohesion and the relative internal friction angle have passed the verification; otherwise, it is determined that all monitoring data have failed the verification.

[0015] Optionally, the method further comprises:

[0016] The corresponding multi-parameter fusion alarm condition is selected for the first comparison according to the number of parameters that pass the verification; wherein the number of parameters that pass the verification is inversely proportional to the threshold of the low threshold alarm condition in the corresponding multi-parameter fusion alarm condition.

[0017] Optionally, the method further comprises:

[0018] Determine the interval ranges to which the relative cohesion and the relative internal friction angle belong respectively, each interval range corresponding to a different data change rate threshold;

[0019] According to the data change rate thresholds corresponding to the interval ranges to which the relative cohesion and the relative internal friction angle belong respectively, the low threshold alarm condition and the high threshold alarm condition corresponding to the capacitance value, and the low threshold alarm condition and the high threshold alarm condition corresponding to the impedance value are determined.

[0020] Optionally, the relative cohesion and relative internal friction angle of the rock and soil layer are obtained by:

[0021] Finding a set of impedance values ​​and capacitance values ​​closest to the capacitance values ​​and impedance values ​​collected by the geotechnical parameter sensor in the pre-acquired cohesion relationship table, and determining the cohesion corresponding to the closest set of impedance values ​​and capacitance values ​​as the relative cohesion of the geotechnical layer; wherein the cohesion relationship table is used to indicate the corresponding relationship between the impedance and capacitance of the geotechnical layer and the cohesion;

[0022] In the pre-acquired internal friction angle relationship table, find a set of impedance values ​​and capacitance values ​​that are closest to the capacitance value and impedance value output by the geotechnical parameter sensor, and determine the internal friction angle corresponding to the closest set of impedance values ​​and capacitance values ​​as the relative internal friction angle of the geotechnical layer; wherein the internal friction angle relationship table is used to represent the correspondence between the impedance and capacitance of the geotechnical layer and the internal friction angle.

[0023] Optionally, the cohesion relationship table and the internal friction angle relationship table are improved in the following manner:

[0024] Collecting rock and soil at the monitoring point;

[0025] Based on the collected rock and soil, rock and soil samples with different water contents are obtained; wherein the water content ranges from 0 to saturation;

[0026] Using a preset impedance sensor and a preset capacitive sensor to monitor the impedance and capacitance of soil samples with different water contents;

[0027] Measure the cohesion and internal friction angle of soil samples with different water contents;

[0028] The impedance and capacitance of the soil samples with different water contents and the corresponding cohesion and internal friction angle are added to the cohesion relationship table and the internal friction angle relationship table.

[0029] Optionally, the method further comprises:

[0030] Acquire first calibration point data and second calibration point data collected by the geotechnical parameter sensor during installation of the geotechnical parameter sensor at the monitoring point; wherein the first calibration point data includes capacitance values ​​and impedance values ​​collected when the geotechnical parameter sensor is surrounded by water, and the second calibration point data includes capacitance values ​​and impedance values ​​collected when the geotechnical layer surrounding the geotechnical parameter sensor is in a water-saturated state;

[0031] If the capacitance value in the first calibration point data is smaller than the capacitance value of pure water, or the impedance value in the first calibration point data is larger than the impedance value of pure water, or the impedance value in the first calibration point data is larger than the impedance value in the second calibration point data, a prompt message indicating that the geotechnical parameter sensor is installed incorrectly is output.

[0032] In a second aspect, an embodiment of the present application provides a rock and soil layer structure change monitoring system based on sensor fusion, comprising: intelligent sensing terminals arranged at different monitoring points, at least one data analysis terminal and a big data early warning platform; each data analysis terminal is communicatively connected with at least one intelligent sensing terminal; the at least one data analysis terminal is communicatively connected with the big data early warning platform;

[0033] The intelligent sensing terminal includes a geotechnical parameter sensor, a geotechnical layer sliding sensor, a low-frequency vibration sensor and an inclination sensor. The geotechnical parameter sensor is used to monitor the capacitance value and impedance value of the surrounding geotechnical layer and the relative cohesion and relative internal friction angle of the geotechnical layer determined based on the capacitance value and the impedance value. The low-frequency vibration sensor is used to monitor the vibration change of the surrounding geotechnical layer. The inclination sensor is used to monitor the inclination change of the surrounding geotechnical layer. The geotechnical layer sliding sensor is used to monitor the sliding condition of the surrounding geotechnical layer.

[0034] The data analysis terminal comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of any one of the methods provided in the first aspect are implemented;

[0035] The big data early warning platform is used to receive and store data sent by the at least one data analysis terminal.

[0036] Optionally, the big data early warning platform is also used for:

[0037] According to the capacitance value and impedance value used to calculate the relative cohesion, a cohesion monitoring diagram is drawn with the horizontal axis representing impedance and the vertical axis representing capacitance, and the data in the cohesion relationship table obtained through the experiment are added as a background diagram to the cohesion monitoring diagram, wherein each coordinate point drawn in the cohesion monitoring diagram corresponds to the capacitance value and impedance value of the monitored relative cohesion, and the cohesion relationship table is used to represent the corresponding relationship between the impedance and capacitance of the rock and soil layer and the cohesion;

[0038] According to the capacitance value and impedance value used to calculate the relative internal friction angle, an internal friction angle monitoring diagram is drawn with the horizontal axis representing impedance and the vertical axis representing capacitance, and the data in the internal friction angle relationship table obtained through the experiment is added to the internal friction angle monitoring diagram as a background diagram, wherein each coordinate point drawn in the internal friction angle monitoring diagram corresponds to the capacitance value and impedance value of the monitored relative internal friction angle, and the internal friction angle relationship table is used to represent the correspondence between the impedance and capacitance of the rock and soil layer and the internal friction angle.

[0039] The sensor fusion-based rock and soil structure change monitoring method and system provided in the embodiments of the present application perform multi-parameter fusion judgment based on a low-threshold multi-parameter fusion alarm condition. If all the monitoring parameters participating in the first comparison meet the multi-parameter fusion alarm condition, it indicates that the rock and soil structure has undergone relatively serious changes, and an alarm can be issued immediately to avoid missed alarms. If not all the monitoring parameters participating in the first comparison meet the multi-parameter fusion alarm condition, it indicates that the changes in the rock and soil structure have not yet reached a very serious level. At this time, a single parameter can be judged based on the high-threshold alarm condition of each monitoring parameter, and then whether to output an alarm message can be determined based on the comparison results of each monitoring parameter to reduce the false alarm rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. Obviously, the drawings introduced below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A schematic diagram of the structure of a rock and soil layer structure change monitoring system based on sensor fusion provided in one embodiment of the present application;

[0042] Figure 2 A schematic diagram of the structure of an intelligent sensing terminal provided in one embodiment of the present application;

[0043] Figure 3 A schematic diagram of the structure of the internal electrodes of the impedance sensor provided in one embodiment of the present application;

[0044] Figure 4A A schematic diagram of the structure of an internal electrode of a capacitive sensor provided in an embodiment of the present application;

[0045] Figure 4B Another schematic diagram of the structure of the internal electrode of the capacitive sensor provided in one embodiment of the present application;

[0046] Figure 5A The signals of the X-axis, Y-axis and Z-axis output by the low-frequency vibration sensor provided in one embodiment of the present application;

[0047] Figure 5B The X-axis, Y-axis, and Z-axis signals output by traditional low-frequency vibration sensors;

[0048] Figure 6 A schematic diagram of a flow chart of a method for monitoring rock and soil layer structure changes based on sensor fusion provided in an embodiment of the present application;

[0049] Figure 7 An example of a visualization diagram of a cohesion relationship table and an internal friction angle relationship table provided in an embodiment of the present application;

[0050] Figure 8 A schematic diagram showing monitoring data of geotechnical parameter sensors provided in an embodiment of the present application;

[0051] Fig. 9 A schematic diagram of the position of calibration point data in the coordinate axis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0053] Any number of elements in the drawings is for illustration and not limitation, and any naming is for distinction only and does not have any limiting meaning.

[0054] This is described in detail below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of the present application provide method operation steps as shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided in the embodiments of the present application.

[0055] refer to Figure 1 , an embodiment of the present application provides a rock and soil layer structure change monitoring system based on sensor fusion, including: intelligent sensing terminals 10 set at different monitoring points, at least one data analysis terminal 20 and a big data early warning platform 30. Each data analysis terminal 20 is in communication connection with at least one intelligent sensing terminal 10, and at least one data analysis terminal 20 is in communication connection with the big data early warning platform 30. The intelligent sensing terminal 10 will send the data monitored by each internal sensor to the data analysis terminal 20 in real time, and the data analysis terminal 20 will further process the monitoring data and then upload it to the big data early warning platform 30. The big data early warning platform 30 is used to receive and store the data sent by the data analysis terminal 20, perform alarm processing based on these data, and display relevant data to users according to the user's query request.

[0056] In actual applications, the geographical location of the intelligent sensing terminal can be used to determine which data analysis terminal it is connected to. Data can be transmitted between the intelligent sensing terminal, the data analysis terminal and the big data early warning platform through wired or wireless communication methods.

[0057] refer to Figure 2 , the intelligent sensing terminal 10 at least includes: a geotechnical parameter sensor 101, a geotechnical layer sliding sensor 102, a low-frequency vibration sensor 103 and an inclination sensor 104. The geotechnical parameter sensor 101 is used to monitor the capacitance and impedance values ​​of the surrounding geotechnical layers and the relative cohesion and relative internal friction angle of the geotechnical layers determined based on the capacitance and impedance values, the geotechnical layer sliding sensor 102 is used to monitor the sliding conditions of the surrounding geotechnical layers, the low-frequency vibration sensor 103 is used to monitor the vibration changes of the surrounding geotechnical layers, and the inclination sensor 104 is used to monitor the inclination changes of the surrounding geotechnical layers. The geotechnical parameter sensor 101, the geotechnical layer sliding sensor 102, the low-frequency vibration sensor 103 and the inclination sensor 104 and some possible supporting circuits are all installed in the cylindrical housing 100. The possible supporting circuits are determined according to the requirements of the sensor and are not limited in this application. The number of various sensors contained in an intelligent sensing terminal 10 can be set according to actual needs. By setting geotechnical parameter sensors 101, geotechnical layer sliding sensors 102, low-frequency vibration sensors 103 and inclination sensors 104 at different heights, geotechnical layers at different depths can be monitored.

[0058] The geotechnical parameter sensor 101 includes: an impedance sensor, a capacitive sensor, a frequency generating circuit and a signal processing circuit. The impedance sensor is used to monitor the impedance of the geotechnical layer. The sensitive electrode of the impedance sensor extends out of the cylindrical shell 100 so as to contact the geotechnical layer outside the cylindrical shell. The internal circuit of the impedance sensor is connected to the external geotechnical layer through the extended sensitive electrode, thereby forming an RC or RLC oscillation circuit. Changes in the composition of the geotechnical layer will cause changes in the impedance of the geotechnical layer, thereby causing changes in the output of the impedance sensor. Figure 3 A schematic diagram of the structure of the electrode 302 inside the impedance sensor 301. The capacitive sensor is used to monitor the capacitance of the rock layer. The sensitive part of the capacitive sensor consists of two electrodes surrounding the cylindrical shell. The internal circuit of the capacitive sensor and the rock layer around the two electrodes form an LC oscillation circuit. Changes in the composition of the rock layer cause changes in the electrical parameters of the rock layer, which will cause changes in the output of the LC oscillation circuit. The capacitive sensor is a non-contact sensor, which is arranged inside the cylindrical shell to prevent the capacitive sensor from being corroded by the rock layer. Figure 4AIn one example shown, the electrodes inside the capacitive sensor are composed of two parallel annular electrodes 402 coaxial with the cylindrical housing 100, and the capacitor formed by the overall double rings monitors the soil layer around the depth where the capacitor is located. Figure 4B In an example shown, two parallel annular electrodes coaxially arranged with the cylindrical shell 100 are divided into four independent pairs of electrodes 402, which monitor four directions respectively, thereby improving the monitoring sensitivity in a single direction. The frequency generating circuit in the geotechnical parameter sensor is used to generate the resonant frequency required for the impedance sensor and the capacitive sensor to monitor. The signal processing circuit in the geotechnical parameter sensor is used to determine the relative cohesion and relative internal friction angle of the monitored geotechnical layer according to the impedance value output by the impedance sensor and the capacitance value output by the capacitive sensor and the predetermined cohesion relationship table and internal friction angle relationship table. The cohesion relationship table is used to indicate the corresponding relationship between the impedance and capacitance of the geotechnical layer and the cohesion, and the internal friction angle relationship table is used to indicate the corresponding relationship between the impedance and capacitance of the geotechnical layer and the internal friction angle. The output of the geotechnical parameter sensor includes the capacitance value and impedance value of the surrounding geotechnical layer and the relative cohesion and relative internal friction angle of the geotechnical layer determined based on the capacitance value and impedance value. The specific structure, function and working principle of the geotechnical parameter sensor can be referred to the patent document with the publication number of CN118362710A, which will not be repeated here.

[0059] The soil layer sliding sensor 102 includes: a soil monitoring sensor, a frequency generating circuit and a signal processing circuit. The soil monitoring sensor includes a plurality of pairs of sensitive electrodes evenly distributed around a cylindrical shell, each pair of sensitive electrodes is used to monitor the soil in a corresponding direction, and the output of the soil monitoring sensor includes monitoring data related to soil density in each monitoring direction. The soil monitoring sensor includes an impedance sensor and / or a capacitive sensor. The monitoring data output by the impedance sensor is impedance, and the monitoring data output by the capacitive sensor is capacitance. When the soil monitoring sensor is an impedance sensor, the distribution of the sensitive electrodes inside it can refer to Figure 3 When the geotechnical monitoring sensor is a capacitive sensor, the distribution of its internal sensitive electrodes can refer to Figure 4BThe layout of the middle electrode. The frequency generating circuit inside the rock and soil layer sliding sensor is used to generate the resonant frequency required for the operation of the rock and soil monitoring sensor. The working principle of the impedance sensor and the capacitive sensor inside the rock and soil layer sliding sensor can refer to the working principle of the impedance sensor and the capacitive sensor inside the rock and soil parameter sensor 101, and will not be repeated here. The signal processing circuit inside the rock and soil layer sliding sensor 102 is used to: determine the sliding judgment parameters in each monitoring direction at the depth where the rock and soil monitoring sensor is located according to the monitoring data of the rock and soil monitoring sensor in each monitoring direction, and the sliding judgment parameters include: the monitoring data change rate, and, and the ratio of the monitoring data in other monitoring directions; according to the sliding judgment parameters in each monitoring direction at the depth where the rock and soil monitoring sensor is located, determine the sliding situation of the rock and soil layer at the depth where the rock and soil monitoring sensor is located. Among them, the sliding situation may include: whether sliding occurs, the sliding direction and the sliding size, or whether there is a sliding trend, a potential sliding direction and the sliding trend size. When the geotechnical monitoring sensor includes an impedance sensor and a capacitive sensor, the sliding condition of the geotechnical layer at the depth where the geotechnical monitoring sensor is located is determined according to the sliding judgment parameters in each monitoring direction at the depth where the geotechnical monitoring sensor is located, specifically including: if the impedance in at least one monitoring direction decreases and the change amplitude exceeds the first impedance threshold, and / or the capacitance in at least one monitoring direction increases and the change amplitude exceeds the first capacitance threshold, then it is determined that the geotechnical layer at the depth where the geotechnical monitoring sensor is located has a sliding trend; if at least N of the three conditions are met, it is determined that the geotechnical layer at the depth where the geotechnical monitoring sensor is located has slipped; wherein the value of N is 1 or 2 or 3, and the three conditions include: the impedance in at least one monitoring direction increases and the change amplitude exceeds the second impedance threshold, the capacitance in at least one monitoring direction decreases and the change amplitude exceeds the second capacitance threshold, and at least one monitoring data ratio is greater than the ratio threshold. The signal processing circuit in the geotechnical layer sliding sensor 102 is also used for: if it is determined that the geotechnical layer at the depth where the geotechnical monitoring sensor is located has a sliding trend, then the potential sliding direction is determined according to the monitoring direction corresponding to the maximum monitoring data change rate; if it is determined that the geotechnical layer at the depth where the geotechnical monitoring sensor is located has sliding, then the sliding direction is determined according to the monitoring direction corresponding to the maximum monitoring data change rate, or the sliding direction is determined according to the monitoring direction corresponding to the maximum impedance or the monitoring direction corresponding to the minimum capacitance. The signal processing circuit in the geotechnical layer sliding sensor 102 is also used for: if it is determined that the geotechnical layer at the depth where the geotechnical monitoring sensor is located has sliding, then the sliding size is determined according to the ratio of the maximum monitoring data and the minimum monitoring data obtained from each monitoring direction; wherein, the larger the ratio of the maximum monitoring data to the minimum monitoring data, the larger the sliding generated, and the determination relationship between the ratio and the sliding size can be determined in advance through experimental data.The signal processing circuit is also used for: if it is determined that the rock and soil layer at the depth where the rock and soil monitoring sensor is located has a sliding trend, then the magnitude of the sliding trend generated is determined according to the change amplitude and change speed of the monitoring data; wherein, the larger the change amplitude of the monitoring data and the faster the change speed, the greater the stress on the rock and soil, that is, the greater the sliding trend generated. The specific structure, function and working principle of the rock and soil sliding sensor 102 can be referred to the patent document with publication number CN118408601A, which will not be repeated here.

[0060] The low-frequency vibration sensor 103 includes: a packaging component and a three-axis sensor that is sensitive to a magnetic field, an acoustic field or a pressure field; the three-axis sensor is shielded and packaged by the packaging component so that the three-axis sensor is not sensitive to the magnetic field, the acoustic field or the pressure field generated by the vehicle in the monitored environment, but is only affected by vibration; the low-frequency vibration sensor outputs a signal related to the vibration of the environment.

[0061] Figure 5A The three figures in FIG. 1 are the signals of the X-axis, Y-axis and Z-axis output by the low-frequency vibration sensor 103 provided in the embodiment of the present application. The horizontal axis represents time and the vertical axis represents the amplitude of vibration. Figure 5B The three graphs in the figure are the X-axis, Y-axis, and Z-axis signals output by traditional vibration sensors. The horizontal axis represents time, and the vertical axis represents the amplitude of vibration. Figure 5B It can be seen that the output signal of the traditional vibration sensor has a large amount of noise. Figure 5A It can be seen that the low-frequency vibration sensor 103 has extremely high sensitivity to the low-frequency vibration required for rock and soil structure monitoring, and its output signal can well reflect the vibration amplitude, vibration frequency and other parameters of the rock and soil layer. It has the advantages of low noise, high sensitivity and high resolution. It is especially suitable for vibration monitoring of non-rigid materials such as rock and soil layers, and can well adapt to application scenarios such as roads and rail transit with large electromagnetic and acoustic field interference.

[0062] The inclination sensor 104 includes: a packaging component, a three-axis sensor sensitive to a magnetic field, an acoustic field or a pressure field, and a processor; the three-axis sensor is shielded and packaged by the packaging component so that the three-axis sensor is not sensitive to the magnetic field, acoustic field or pressure field generated by the vehicle in the monitored environment, but is only affected by vibration; the processor is used to: determine the inclination change caused by vibration based on the signal output by the three-axis sensor and a predetermined mapping relationship; wherein the mapping relationship represents the corresponding relationship between the signal output by the three-axis sensor and the angle change of the three-axis sensor.

[0063] The total amplitude of the output signal of the triaxial sensor at time t is:

[0064] (1);

[0065] in, TX,t It represents the amplitude of the X-axis signal output by the triaxial sensor at time t. T Y,t It represents the amplitude of the Y-axis signal output by the triaxial sensor at time t. T Z,t Indicates the amplitude of the Z-axis signal output by the triaxial sensor at time t.

[0066] The mapping relationship can be determined in advance through experiments. The specific experimental process includes: applying different external forces to the three-axis sensor so that the three-axis sensor generates vibrations at different preset angles, and recording the output signals of the three-axis sensor at different preset angles; calculating the total amplitude when the angle changes at different preset angles based on formula (1), thereby obtaining the corresponding relationship between the total amplitude and the angle change, which is the mapping relationship. The mapping relationship is loaded into the processor inside the tilt sensor.

[0067] When used, the processor inside the inclination sensor is specifically used to: obtain the real-time output signal of the three-axis sensor; determine the total amplitude at the current moment according to formula (1); and determine the angle change corresponding to the total amplitude at the current moment according to the total amplitude at the current moment and the mapping relationship. The angle change is the inclination change caused by the vibration.

[0068] The inclination sensor 104 provided in the embodiment of the present application also has the advantages of low noise, high sensitivity and high resolution. It has extremely high sensitivity to the low-frequency vibration required for rock and soil structure monitoring. It is suitable for inclination monitoring of non-rigid materials such as rock and soil layers. It can also be used in application scenarios with large electromagnetic and acoustic field interference such as roads and rail transit.

[0069] The three-axis sensors used in the low-frequency vibration sensor 103 and the tilt sensor 104 include, but are not limited to: a three-axis flexible cantilever sensor (i.e., a three-axis Cantilever sensor), a three-axis stress sensor, a three-axis torque sensor, a three-axis magnetic field sensor, a three-axis acoustic sensor (including a three-axis surface acoustic wave sensor or a three-axis body wave acoustic sensor), and a three-axis pressure sensor, etc. The above three-axis sensors are generally not used as vibration sensors and tilt sensors.

[0070] The specific structure, function and working principle of the low-frequency vibration sensor 103 and the tilt sensor 104 can be found in the patent document with publication number CN118425316A, which will not be described in detail.

[0071] When installing the equipment, bury the intelligent sensing terminal 10 in the pit dug at the monitoring point. The gap between the intelligent sensing terminal 10 and the pit should be backfilled with some of the excavated rock and soil. Appropriate pressure should be given to the backfilled rock and soil, and backfilled layer by layer. After backfilling, water the backfill soil to the ground level. If the backfill soil sinks, continue to fill it up. This is done to prevent artificial air gaps from being created when digging a pit to bury the device, which affects the monitoring effect. As the watering continues to spread after backfilling, the rock and soil layer around the intelligent sensing terminal 10 will return to the stable state before the installation of the device, and then monitoring can begin.

[0072] The data analysis terminal 20 includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it can achieve: obtaining the structural changes of the rock and soil layers around the monitoring point based on the various monitoring data uploaded by the intelligent sensing terminal, and then making a decision on whether to alarm. Among them, the data analysis terminal 20 can select a corresponding data analysis method according to the type of monitoring data uploaded by the intelligent sensing terminal 10, which is not limited in the embodiment of the present application.

[0073] In order to better integrate the monitoring data of various sensors uploaded by the intelligent sensing terminal, thereby improving the accuracy of monitoring results and reducing the false alarm rate, the data analysis terminal will perform a series of processing on the monitoring data before making an alarm decision, for example: based on the relationship between various monitoring parameters, the data rationality of each monitoring parameter is checked to eliminate obviously abnormal monitoring parameters; multi-parameter fusion alarm conditions are set to achieve dynamic adjustment of alarm thresholds, so as to detect changes in rock and soil structure earlier and extend the warning time; etc. For specific implementation methods, please refer to the rock and soil structure change monitoring method based on sensor fusion provided in the embodiment of this application.

[0074] refer to Figure 6 The present application embodiment provides a method for monitoring rock and soil layer structure changes based on sensor fusion, comprising the following steps:

[0075] S601, obtaining monitoring parameters output by a geotechnical parameter sensor, a geotechnical layer sliding sensor, a low-frequency vibration sensor and an inclination sensor at the same monitoring point.

[0076] Among them, the monitoring parameters include but are not limited to: the capacitance and impedance values ​​of the surrounding rock and soil layers collected by the geotechnical parameter sensors and the relative cohesion and relative internal friction angle of the rock and soil layers determined based on the capacitance and impedance values, the vibration changes of the surrounding rock and soil layers output by the low-frequency vibration sensors, the inclination changes of the surrounding rock and soil layers output by the inclination sensors, and the sliding conditions of the surrounding rock and soil layers output by the rock and soil layer sliding sensors.

[0077] S602: Perform a first comparison between the monitoring parameters and the multi-parameter fusion alarm conditions, wherein the multi-parameter fusion alarm conditions include the low threshold alarm conditions corresponding to each monitoring parameter.

[0078] S603: If all monitoring parameters involved in the first comparison meet the corresponding low threshold alarm conditions, an alarm message is output.

[0079] S604. If at least one of the monitoring parameters participating in the first comparison does not meet the corresponding low threshold alarm condition, the monitoring parameters participating in the first comparison will be compared for the second time with their respective corresponding high threshold alarm conditions, and whether to output the alarm information is determined based on the second comparison results of all monitoring parameters participating in the first comparison, wherein the low threshold alarm condition corresponding to each monitoring parameter is lower than the corresponding high threshold alarm condition.

[0080] It should be noted that whether to output an alarm message based on the second comparison result can be set according to actual application requirements and is not limited in the embodiments of the present application. For example, as long as one of the monitoring parameters participating in the second comparison meets its corresponding high threshold alarm condition, an alarm message is output; or, when more than a preset number of monitoring parameters meet their respective corresponding high threshold alarm conditions, an alarm message is output.

[0081] It should be noted that, compared with the high threshold alarm condition, the low threshold alarm condition is easier to be satisfied, that is, it is easier to trigger an alarm. The low threshold alarm condition and the high threshold alarm condition corresponding to each monitoring parameter can be determined according to the alarm judgment method adopted by each monitoring parameter, and the embodiments of the present application are not specifically limited.

[0082] For example, the alarm judgment method for relative cohesion is: if the magnitude of the decrease in relative cohesion within a preset time interval exceeds the mutation threshold, an alarm is issued. At this time, the low threshold alarm condition of relative cohesion can be "if the magnitude of the decrease in relative cohesion within a preset time interval exceeds the first mutation threshold, an alarm is issued", and the high threshold alarm condition of relative cohesion can be "if the magnitude of the decrease in relative cohesion within a preset time interval exceeds the second mutation threshold, an alarm is issued", and the first mutation threshold is less than the second mutation threshold.

[0083] For example, the alarm determination method for the sliding size is: if the sliding size exceeds the sliding threshold, an alarm is issued. At this time, the low threshold alarm condition of the sliding size can be "if the sliding size exceeds the first sliding threshold, an alarm is issued", and the high threshold alarm condition of the sliding size can be "if the sliding size exceeds the second sliding threshold, an alarm is issued", and the first sliding threshold is less than the second sliding threshold.

[0084] For example, the alarm judgment method for vibration changes is: filter out the first signal segment when the vehicle passes through the monitoring area from the signal representing the vibration change output in real time by the low-frequency vibration sensor; identify the pulse signal appearing in the first signal segment, and determine the pulse amplitude, pulse half-width and pulse frequency of each pulse signal, and count the total number of pulses of the pulse signal appearing in the first signal segment, the pulse frequency represents the inverse of the duration of the pulse signal; when at least N of the four conditions are met, an alarm is issued; wherein the value of N is 1 or 2 or 3 or 4, and the above four conditions include: the pulse amplitude of at least m pulse signals exceeds the amplitude threshold, the pulse half-width of at least p pulse signals exceeds the pulse width threshold, the total number of pulses exceeds the pulse number threshold, and at least q pulse frequencies do not belong to the pulse frequencies monitored historically, and m, p, and q are all integers not less than 1. At this time, in the low threshold alarm condition for vibration changes, N is 3, the amplitude threshold is A1, the pulse width threshold is B1, the pulse number threshold is C1, and q is 6; in the high threshold alarm condition for vibration changes, N is 4, the amplitude threshold is A2, the pulse width threshold is B2, the pulse number threshold is C3, and q is 10; among them, A1 is less than A2, B1 is less than B2, and C1 is less than C2.

[0085] Monitoring parameters such as relative cohesion, relative internal friction angle, vibration change, inclination change and sliding of the rock and soil layer all reflect the changes in the rock and soil structure, and there is an implicit correlation between the various monitoring parameters. For example, the larger the micro-vibration amplitude detected by the vibration sensor and the larger the amplitude of the micro-shake of the inclination sensor, the smaller the density and the lower the water content of the rock and soil layer, and the density and water content are closely related to the relative cohesion and relative internal friction angle. Therefore, the more monitoring parameters that meet the alarm conditions, the more serious the situation of the monitoring point. When the changes in the rock and soil structure are not obvious, it may only cause a small number of changes in the monitoring parameters. At this time, in order to reduce the false alarm rate, the alarm conditions need to be raised; when the rock and soil structure undergoes serious changes, various bad factors accumulate with each other, which will cause a large number of monitoring parameters to change, but this change may not be able to reach the high threshold alarm condition. At this time, the alarm conditions need to be lowered to avoid missed alarms.

[0086] Therefore, in the method provided in the embodiment of the present application, a multi-parameter fusion judgment is performed based on a low-threshold multi-parameter fusion alarm condition. If the monitoring parameters participating in the first comparison all meet the multi-parameter fusion alarm condition, it indicates that the geotechnical structure has undergone relatively serious changes, and an alarm can be issued immediately to avoid missed alarms. If the monitoring parameters participating in the first comparison do not all meet the multi-parameter fusion alarm condition, it indicates that the changes in the geotechnical structure have not yet reached a very serious level. At this time, a single parameter can be judged based on the high-threshold alarm condition of each monitoring parameter, and then whether to output an alarm message can be determined based on the comparison results of each monitoring parameter to reduce the false alarm rate.

[0087] Furthermore, the corresponding multi-parameter fusion alarm condition can be pre-set according to the number of monitoring parameters involved in the comparison. Specifically, the number of parameters involved in the comparison is inversely proportional to the threshold of the low threshold alarm condition in the corresponding multi-parameter fusion alarm condition, that is, the more parameters involved in the comparison, the lower the threshold of the low threshold alarm condition in the multi-parameter fusion alarm condition. For example, when there are four parameters involved in the first comparison, the multi-parameter fusion alarm condition F1 is adopted, and when there are three parameters involved in the first comparison, the multi-parameter fusion alarm condition F2 is adopted. The low threshold alarm condition adopted in the multi-parameter fusion alarm condition F1 is lower than the low threshold alarm condition adopted in the multi-parameter fusion alarm condition F2.

[0088] In a possible implementation, before executing step S602, the method implemented in the present application further includes the following steps: performing data rationality verification on each monitoring parameter according to the change trend of each monitoring parameter to determine the parameters that pass the verification. To this end, step S602 specifically includes: performing a first comparison between the parameters that pass the verification and the multi-parameter fusion alarm conditions. That is, the parameters that fail the verification do not participate in the subsequent comparison, so that obviously abnormal monitoring parameters can be eliminated and the accuracy of the monitoring results can be improved.

[0089] Changes in the density and water content of the rock and soil around the geotechnical parameter sensor will cause changes in the relative cohesion and relative internal friction angle measured by the geotechnical parameter sensor. Changes in these factors will also cause changes in the output values ​​of the geotechnical layer sliding sensor, low-frequency vibration sensor and inclination sensor. In practical applications, it is found that when the relative cohesion and relative internal friction angle increase, the micro-perturbations of vibration and angle monitored by the low-frequency vibration sensor and inclination sensor will become smaller; conversely, when the relative cohesion and relative internal friction angle decrease, the micro-perturbations of vibration and angle monitored by the low-frequency vibration sensor and inclination sensor will become larger. Based on the working principle of the geotechnical layer sliding sensor, it can be known that the ratio of the maximum monitoring data and the minimum monitoring data obtained in multiple monitoring directions at the same depth can be used to determine the size of the sliding or the size of the sliding trend. If the sliding or sliding trend changes, especially if this change is caused by a change in water content, it means that the relative cohesion and relative internal friction angle are also changing. In actual applications, it is found that when the sliding or sliding tendency decreases, the relative cohesion and relative internal friction angle will increase; conversely, when the sliding or sliding tendency increases, the relative cohesion and relative internal friction angle will decrease. To this end, data rationality verification can be performed based on the relationship between the trend changes of the above monitoring parameters, that is, the monitoring parameters whose change trends do not meet the above relationship are abnormal parameters and need to be eliminated.

[0090] Further, the data rationality of each monitoring parameter is verified according to the change trend of each monitoring parameter, specifically including: determining the number of items I1 with increased data and the number D1 with decreased data in the three items of vibration change, inclination change and sliding condition, determining the number D2 with decreased data and the number I2 with increased data in relative cohesion and relative internal friction angle; if I1+D2 is not less than the preset value, then it is determined that the items with increased data in the three items of vibration change, inclination change and sliding condition and the items with decreased data in relative cohesion and relative internal friction angle have passed the verification, otherwise, it is determined that all monitoring data have not passed the verification; if D1+I2 is not less than the preset value, then it is determined that the items with decreased data in the three items of vibration change, inclination change and sliding condition and the items with increased data in relative cohesion and relative internal friction angle have passed the verification, otherwise, it is determined that all monitoring data have not passed the verification. Among them, the preset value can be set according to the actual situation, and the preset value is generally at least greater than half of the total number of monitoring parameters.

[0091] Furthermore, the method of the embodiment of the present application also includes: selecting corresponding multi-parameter fusion alarm conditions for a first comparison based on the number of parameters that have passed the verification; wherein the number of parameters that have passed the verification is inversely proportional to the threshold of the low threshold alarm condition in the corresponding multi-parameter fusion alarm condition.

[0092] In specific implementation, the more parameters that pass the verification, that is, the more parameters that participate in the first comparison, the lower the low threshold alarm conditions corresponding to the various monitoring parameters involved in the multi-parameter fusion alarm conditions. For example, when three parameters pass the verification, an alarm is triggered when the change rate of relative cohesion exceeds 10%; when four parameters pass the verification, an alarm is triggered when the change rate of relative cohesion exceeds 9%; when five parameters pass the verification, an alarm is triggered when the change rate of relative cohesion exceeds 8%.

[0093] In a possible implementation, the relative cohesion and relative internal friction angle of the rock and soil layer can be obtained in the following manner: find a set of impedance values ​​and capacitance values ​​that are closest to the capacitance values ​​and impedance values ​​collected by the rock and soil parameter sensor in a pre-acquired cohesion relationship table, and determine the cohesion corresponding to the closest set of impedance values ​​and capacitance values ​​as the relative cohesion of the rock and soil layer; wherein the cohesion relationship table is used to represent the correspondence between the impedance and capacitance of the rock and soil layer and the cohesion; find a set of impedance values ​​and capacitance values ​​that are closest to the capacitance values ​​and impedance values ​​output by the rock and soil parameter sensor in a pre-acquired internal friction angle relationship table, and determine the internal friction angle corresponding to the closest set of impedance values ​​and capacitance values ​​as the relative internal friction angle of the rock and soil layer; wherein the internal friction angle relationship table is used to represent the correspondence between the impedance and capacitance of the rock and soil layer and the internal friction angle.

[0094] By monitoring the impedance-capacitance of rock and soil, the relative internal friction angle and relative cohesion of rock and soil can be obtained. The reason why the absolute internal friction angle and cohesion cannot be obtained is that it is difficult to encounter rock and soil sand samples under the same conditions as those in the experiment during the actual measurement process.

[0095] Tables 1 and 2 record various rocks and soils with different cohesion and internal friction angles. The capacitance and impedance of various rocks and soils in Tables 1 and 2 can be measured by geotechnical parameter sensors to obtain the following: Figure 7 An example of a visualization of the cohesion relationship table and the internal friction angle relationship table shown in Figure 1. Figure 7 Only part of the data in Table 1 and Table 2 is plotted. Figure 7 The data displayed by the visualization diagram include Table 1, Table 2 and other experimental rock and soil layer related data. In practical applications, since the components of the monitored rock and soil layer cannot be completely consistent with the experimental rock and soil layer, the cohesion relationship table and the internal friction angle relationship table cannot completely cover all situations, and the sensor will also be disturbed by environmental factors. Therefore, it is inevitable that the corresponding values ​​of the monitoring data output by the sensor cannot be found in the cohesion relationship table and the internal friction angle relationship table. At this time, a set of impedance values ​​and capacitance values ​​closest to the monitoring data can be found in the cohesion relationship table and the internal friction angle relationship table. The internal friction angle and cohesion corresponding to this set of values ​​are used as the relative internal friction angle and relative cohesion of the monitored rock and soil layer.

[0096] Table 1

[0097]

[0098] Table 2

[0099]

[0100] In the early stage of sensor application, it is impossible to obtain the information of cohesion and internal friction angle of all or even most types of rock, soil and sand, that is, the cohesion relationship table and the internal friction angle relationship table cannot completely cover all situations. To this end, the cohesion relationship table and the internal friction angle relationship table can be improved in the following ways: collect rock and soil at the monitoring point; based on the collected rock and soil, use laboratory equipment to obtain rock and soil samples with different water contents by weighing, drying, adding water, etc., where the water content ranges from 0 to saturation; use preset impedance sensors and preset capacitive sensors to monitor the impedance and capacitance of rock and soil samples with different water contents; measure the cohesion and internal friction angle of rock and soil samples with different water contents; add the impedance and capacitance of rock and soil samples with different water contents and the corresponding cohesion and internal friction angle to the cohesion relationship table and the internal friction angle relationship table.

[0101] In the actual measurement process, the relative cohesion and relative internal friction angle are obtained. The relationship between these relative values ​​and absolute values ​​(cohesion and internal friction angle in Table 1 and Table 2) may be parallel curves or straight lines with different slopes. For this reason, when displaying monitoring data, the big data early warning platform draws a cohesion monitoring graph with impedance on the horizontal axis and capacitance on the vertical axis based on the capacitance and impedance values ​​used to calculate the relative cohesion, and adds the data in the cohesion relationship table obtained through experiments as a background graph to the cohesion monitoring graph; draws an internal friction angle monitoring graph with impedance on the horizontal axis and capacitance on the vertical axis based on the capacitance and impedance values ​​used to calculate the relative internal friction angle, and adds the data in the internal friction angle relationship table obtained through experiments as a background graph to the internal friction angle monitoring graph. Among them, each coordinate point drawn in the cohesion monitoring diagram corresponds to the monitored capacitance value and impedance value of the relative cohesion, and the cohesion relationship table is used to represent the corresponding relationship between the impedance and capacitance of the experimental rock and soil layer and the absolute cohesion of the experimental rock and soil layer; each coordinate point drawn in the internal friction angle monitoring diagram corresponds to the monitored capacitance value and impedance value of the relative internal friction angle, and the internal friction angle relationship table is used to represent the corresponding relationship between the impedance and capacitance of the experimental rock and soil layer and the absolute internal friction angle of the experimental rock and soil layer.

[0102] For example, when displaying the capacitance and impedance values ​​collected by the geotechnical parameter sensors at the monitoring point, Figure 7 As a background image, the capacitance and impedance values ​​collected by the geotechnical parameter sensors are plotted on the basis of the background image. The capacitance and impedance values ​​monitored in real time and the absolute values ​​used as standards can be displayed at the same time. Therefore, users can clearly know the relationship between the relative values ​​monitored in real time and the absolute values ​​used as standards. Figure 8 , which will Figure 7 As a background image, the data in the background image can be set to be semi-transparent or use a different color from the real-time monitoring data, while the real-time monitoring data uses a more prominent display method, such as Figure 8 A five-pointed star is used to mark the position of the monitoring data in the coordinate axis, and the corresponding relative cohesion and relative friction angle are indicated.

[0103] Since the data in the cohesion relationship table and the internal friction angle relationship table are segmented and incomplete, only the relative cohesion and relative internal friction angle can be obtained. Therefore, when judging whether an alarm is needed based on the monitoring data output by the geotechnical parameter sensor, it is more necessary to pay attention to the percentage change and value mutation of the capacitance value and impedance value. The larger the relative cohesion and relative internal friction angle, the less likely the geotechnical collapse and sliding will occur. The alarm threshold should be set higher to reduce the false alarm rate; on the contrary, for the geotechnical collapse and relative internal friction angle, the smaller the relative cohesion and relative internal friction angle, the alarm threshold should be lowered so that early warning can be given before collapse and sliding occur.

[0104] To this end, the values ​​of relative cohesion and relative internal friction angle are divided into multiple interval ranges, and each interval range uses different thresholds to check the capacitance value and the impedance value. Specifically, the method of the embodiment of the present application also includes the following steps: determining the interval ranges to which the relative cohesion and the relative internal friction angle belong respectively, and each interval range corresponds to a different data change rate threshold; according to the data change rate thresholds corresponding to the interval ranges to which the relative cohesion and the relative internal friction angle belong respectively, determining the low threshold alarm condition and the high threshold alarm condition corresponding to the capacitance value, and the low threshold alarm condition and the high threshold alarm condition corresponding to the impedance value.

[0105] The division method of the interval range and the data change rate threshold corresponding to each interval range can be determined according to experimental data and application requirements, and the embodiments of the present application are not limited thereto.

[0106] For each interval range divided for relative cohesion, the data change rate threshold corresponding to capacitance and the data change rate threshold corresponding to impedance can be set respectively. For example, for the interval range where the relative cohesion is less than 10KPA, the data change rate threshold corresponding to capacitance is 10%, and the data change rate threshold corresponding to impedance is 15%.

[0107] For example, when the relative cohesion is less than 10KPA, the data change rate threshold corresponding to the capacitance is 10%. At this time, the low threshold alarm condition corresponding to the capacitance value may be: "If the data change rate threshold corresponding to the capacitance value is greater than 8%, an alarm is issued", and the high threshold alarm condition corresponding to the capacitance value may be: "If the data change rate threshold corresponding to the capacitance value is greater than 10%, an alarm is issued". When the relative cohesion is not less than 10KPA and less than 30KPA, the data change rate threshold corresponding to the capacitance is 20%. At this time, the low threshold alarm condition may be: "If the data change rate threshold corresponding to the capacitance value is greater than 18%, an alarm is issued", and the high threshold alarm condition may be: "If the data change rate threshold corresponding to the capacitance value is greater than 20%, an alarm is issued". When the relative cohesion is not less than 30KPA, the corresponding data change rate threshold is 30%. At this time, the low threshold alarm condition may be: "If the data change rate threshold corresponding to the capacitance value is greater than 25%, an alarm is issued", and the high threshold alarm condition may be: "If the data change rate threshold corresponding to the capacitance value is greater than 30%, an alarm is issued".

[0108] For example, when the relative internal friction angle is less than 10 degrees, the data change rate threshold corresponding to the capacitance is 10%. At this time, the low threshold alarm condition corresponding to the capacitance value may be: "If the data change rate threshold corresponding to the capacitance value is greater than 7%, an alarm is issued", and the high threshold alarm condition corresponding to the capacitance value may be: "If the data change rate threshold corresponding to the capacitance value is greater than 10%, an alarm is issued". When the relative internal friction angle is greater than 10 degrees and less than 30 degrees, the data change rate threshold corresponding to the capacitance is 20%. At this time, the low threshold alarm condition corresponding to the capacitance value may be: "If the data change rate threshold corresponding to the capacitance value is greater than 16%, an alarm is issued", and the high threshold alarm condition corresponding to the capacitance value may be: "If the data change rate threshold corresponding to the capacitance value is greater than 20%, an alarm is issued". When the relative internal friction angle is greater than 30 degrees, the data change rate threshold corresponding to the capacitance is 30%. At this time, the low threshold alarm condition corresponding to the capacitance value may be: "If the data change rate threshold corresponding to the capacitance value is greater than 24%, an alarm is issued", and the high threshold alarm condition corresponding to the capacitance value may be: "If the data change rate threshold corresponding to the capacitance value is greater than 30%, an alarm is issued".

[0109] The method for determining the low threshold alarm condition and the high threshold alarm condition corresponding to the impedance value is similar and will not be described in detail.

[0110] If the data change rate threshold T1 corresponding to the interval range to which the relative cohesion belongs is consistent with the data change rate threshold T2 corresponding to the interval range to which the relative internal friction angle belongs, the low threshold alarm condition and the high threshold alarm condition corresponding to the capacitance value, and the low threshold alarm condition and the high threshold alarm condition corresponding to the impedance value are determined according to T1 or T2. If the data change rate threshold T1 corresponding to the interval range to which the relative cohesion belongs is inconsistent with the data change rate threshold T2 corresponding to the interval range to which the relative internal friction angle belongs, the low threshold alarm condition and the high threshold alarm condition corresponding to the capacitance value, and the low threshold alarm condition and the high threshold alarm condition corresponding to the impedance value are determined according to the smaller value of T1 and T2.

[0111] For example, the relative cohesion of rock and soil is measured to be less than 10KPA, and the data change rate threshold of capacitance corresponding to this interval is 10%; the relative internal friction angle of rock and soil is measured to be greater than 10 degrees and less than 30 degrees, and the data change rate threshold of capacitance corresponding to this interval is 20%; at this time, the data change rate threshold of capacitance takes a smaller value (i.e. 10%), and accordingly, the low threshold alarm condition corresponding to the capacitance value can be: "If the data change rate threshold corresponding to the capacitance value is greater than 7%, an alarm is issued", and the high threshold alarm condition corresponding to the capacitance value can be: "If the data change rate threshold corresponding to the capacitance value is greater than 10%, an alarm is issued".

[0112] In a possible implementation, during the installation of the intelligent sensing terminal, it can be determined whether there is a problem in the installation process based on data collected by the sensor.

[0113] The installation process of the intelligent sensing terminal includes: digging a pit at the monitoring point, placing the intelligent sensing terminal into the pit, pouring water into the pit until the first layer of geotechnical parameter sensors are covered, obtaining the capacitance value and impedance value collected by the first layer of geotechnical parameter sensors at this time, as the first calibration point data of the first layer of geotechnical parameter sensors, and then using the soil dug out of the pit to backfill the pit. The height of the backfill soil is between the height of the first layer of geotechnical parameter sensors and the height of the second layer of geotechnical parameter sensors, and appropriately giving a certain pressure to the backfill soil in the water to make it similar to the shape of the soil soaked in water around the pit, and then pouring water to below the height of the second layer of geotechnical parameter sensors. At this time, the rock and soil around the first layer of geotechnical parameter sensors are in a water-saturated state, and the capacitance value and impedance value collected by the first layer of geotechnical parameter sensors at this time are obtained as the second calibration point data of the first layer of geotechnical parameter sensors. Repeat the above process, continue to water the second layer of geotechnical parameter sensors, obtain the capacitance value and impedance value collected by the second layer of geotechnical parameter sensors at this time, as the first calibration point data of the second layer of geotechnical parameter sensors, and then use the soil from the pit to backfill the pit. The height of the backfill soil is between the second layer of geotechnical parameter sensors and the third layer of geotechnical parameter sensors, and appropriately give a certain pressure to the backfill soil in the water, so that it is similar to the shape of the soil soaked around the pit, and then water it below the height of the third layer of geotechnical parameter sensors. At this time, the rock and soil around the second layer of geotechnical parameter sensors are in a water-saturated state, and the capacitance value and impedance value collected by the second layer of geotechnical parameter sensors at this time are obtained as the second calibration point data of the second layer of geotechnical parameter sensors. Similarly, water is injected layer by layer to obtain the first calibration point data and the second calibration point data of each layer of geotechnical parameter sensors. Finally, according to the first calibration point data and the second calibration point data of each layer of geotechnical parameter sensors, it is judged whether there is a problem in the installation process of the geotechnical parameter sensors of this layer.

[0114] To this end, the method provided in the embodiment of the present application also includes the following steps: obtaining first calibration point data and second calibration point data collected by the geotechnical parameter sensor during the installation of the geotechnical parameter sensor (or intelligent sensing terminal) at the monitoring point; wherein the first calibration point data includes capacitance values ​​and impedance values ​​collected when the geotechnical parameter sensor is surrounded by water, and the second calibration point data includes capacitance values ​​and impedance values ​​collected when the geotechnical layer around the geotechnical parameter sensor is in a water-saturated state; if the capacitance value in the first calibration point data is less than the capacitance value of pure water, or the impedance value in the first calibration point data is greater than the impedance value of pure water, or the impedance value in the first calibration point data is greater than the impedance value in the second calibration point data, then a prompt message indicating that the geotechnical parameter sensor (or intelligent sensing terminal) is incorrectly installed is output.

[0115] It should be noted that since pure water Fig. 9 The corresponding resistance value is a range. Therefore, when the impedance value in the first calibration point data is greater than the maximum impedance value corresponding to pure water, it is considered that the impedance value in the first calibration point data is greater than the impedance value of pure water.

[0116] refer to Fig. 9 , the positions of the first calibration point data (represented by solid circles) and the second calibration point data (represented by solid triangles) obtained at three different monitoring points in the coordinate axis are given. The first calibration point data and the second calibration point data of the same monitoring point are connected by a dotted line, and the rock and soil salinity of the three monitoring points gradually increases in the direction of the arrows. During the watering process, the salt in the rock and soil will dissolve in the water, causing the capacitance of the water to increase and the impedance to decrease. The higher the salt content, the greater the capacitance and the smaller the impedance. Therefore, the first calibration point data obtained at each monitoring point should be located in the upper left corner of the pure water. It can be seen that when the capacitance value in the first calibration point data is smaller than the capacitance value of pure water or the impedance value in the first calibration point data is greater than the impedance value of pure water, it indicates that there is a problem with the installation process or the sensor. According to Fig. 9 From the large amount of data shown, it can be seen that the impedance-capacitance value corresponding to water (excluding rock, soil and sand) should be on the left side of the impedance-capacitance value of various rocks and soils. Therefore, when the first calibration point data is located on the right side of the second calibration point data, it indicates that there is a problem with the installation process or the sensor. It can be seen that when the impedance value in the first calibration point data is greater than the impedance value in the second calibration point data, it indicates that there is a problem with the installation process or the sensor.

[0117] The above embodiments are only used to introduce the technical solutions of the present application in detail, but the description of the above embodiments is only used to help understand the methods of the embodiments of the present application and should not be understood as limiting the embodiments of the present application. Any changes or substitutions that can be easily thought of by technicians in this technical field should be included in the protection scope of the embodiments of the present application.

Claims

1. A method for monitoring rock and soil layer structure changes based on sensor fusion, characterized in that: include: Acquire monitoring parameters output by a geotechnical parameter sensor, a geotechnical layer sliding sensor, a low-frequency vibration sensor, and an inclination sensor at the same monitoring point; wherein the monitoring parameters include the capacitance value and the impedance value of the surrounding geotechnical layer collected by the geotechnical parameter sensor, the relative cohesion and the relative internal friction angle of the geotechnical layer determined based on the capacitance value and the impedance value, the vibration change of the surrounding geotechnical layer output by the low-frequency vibration sensor, the inclination change of the surrounding geotechnical layer output by the inclination sensor, and the sliding condition of the surrounding geotechnical layer of the geotechnical layer sliding sensor; Performing a first comparison between the monitoring parameter and the multi-parameter fusion alarm condition; wherein the multi-parameter fusion alarm condition includes a low threshold alarm condition corresponding to each monitoring parameter; If all monitoring parameters involved in the first comparison meet the corresponding low threshold alarm conditions, an alarm message is output; If at least one of the monitoring parameters participating in the first comparison does not meet the corresponding low threshold alarm condition, the monitoring parameters participating in the first comparison are respectively compared with their respective corresponding high threshold alarm conditions for a second time, and whether to output an alarm message is determined based on the second comparison results of all monitoring parameters participating in the first comparison; wherein the low threshold alarm condition corresponding to each monitoring parameter is lower than the corresponding high threshold alarm condition; compared with the high threshold alarm condition, the low threshold alarm condition is easier to be met and easier to trigger an alarm; The low threshold alarm condition corresponding to the relative cohesion is "if the magnitude of the decrease in the relative cohesion within a preset time interval exceeds a first mutation threshold, an alarm is issued", and the high threshold alarm condition corresponding to the relative cohesion is "if the magnitude of the decrease in the relative cohesion within a preset time interval exceeds a second mutation threshold, an alarm is issued", and the first mutation threshold is smaller than the second mutation threshold; The low threshold alarm condition corresponding to the sliding size is "if the sliding size exceeds the first sliding threshold, an alarm is issued", and the high threshold alarm condition corresponding to the sliding size is "if the sliding size exceeds the second sliding threshold, an alarm is issued", and the first sliding threshold is smaller than the second sliding threshold.

2. The method according to claim 1, characterized in that Before performing the first comparison, the method further includes: performing data rationality verification on each monitoring parameter according to the change trend of each monitoring parameter to determine the parameters that pass the verification; The first comparison of the monitoring parameters with the multi-parameter fusion alarm conditions specifically includes: first comparison of the parameters that pass the verification with the multi-parameter fusion alarm conditions.

3. The method according to claim 2, characterized in that The data rationality verification of each monitoring parameter according to the change trend of each monitoring parameter specifically includes: Determine the number of items I1 with increased data and the number D1 with decreased data in the three items of the vibration change, the inclination angle change and the sliding condition, and determine the number D2 with decreased data and the number I2 with increased data in the relative cohesion and the relative internal friction angle; If I1+D2 is not less than the preset value, it is determined that the item with increased data among the vibration change, the inclination angle change and the sliding condition and the item with decreased data among the relative cohesion and the relative internal friction angle have passed the verification; otherwise, it is determined that all monitoring data have failed the verification; If D1+I2 is not less than the preset value, it is determined that the items with reduced data among the vibration change, the inclination angle change and the sliding condition and the items with increased data among the relative cohesion and the relative internal friction angle have passed the verification; otherwise, it is determined that all monitoring data have failed the verification.

4. The method according to claim 2, characterized in that: The method further comprises: The corresponding multi-parameter fusion alarm condition is selected for the first comparison according to the number of parameters that pass the verification; wherein the number of parameters that pass the verification is inversely proportional to the threshold of the low threshold alarm condition in the corresponding multi-parameter fusion alarm condition.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Determine the interval ranges to which the relative cohesion and the relative internal friction angle belong respectively, each interval range corresponding to a different data change rate threshold; According to the data change rate thresholds corresponding to the interval ranges to which the relative cohesion and the relative internal friction angle belong respectively, the low threshold alarm condition and the high threshold alarm condition corresponding to the capacitance value, and the low threshold alarm condition and the high threshold alarm condition corresponding to the impedance value are determined.

6. The method according to any one of claims 1 to 4, characterized in that: The relative cohesion and relative internal friction angle of the rock and soil layer are obtained as follows: Finding a set of impedance values ​​and capacitance values ​​closest to the capacitance values ​​and impedance values ​​collected by the geotechnical parameter sensor in the pre-acquired cohesion relationship table, and determining the cohesion corresponding to the closest set of impedance values ​​and capacitance values ​​as the relative cohesion of the geotechnical layer; wherein the cohesion relationship table is used to indicate the corresponding relationship between the impedance and capacitance of the geotechnical layer and the cohesion; In the pre-acquired internal friction angle relationship table, find a set of impedance values ​​and capacitance values ​​that are closest to the capacitance value and impedance value output by the geotechnical parameter sensor, and determine the internal friction angle corresponding to the closest set of impedance values ​​and capacitance values ​​as the relative internal friction angle of the geotechnical layer; wherein the internal friction angle relationship table is used to represent the correspondence between the impedance and capacitance of the geotechnical layer and the internal friction angle.

7. The method according to claim 6, characterized in that The cohesion relationship table and the internal friction angle relationship table are improved by the following method: Collecting rock and soil at the monitoring point; Based on the collected rock and soil, rock and soil samples with different water contents are obtained; wherein the water content ranges from 0 to saturation; Using a preset impedance sensor and a preset capacitive sensor to monitor the impedance and capacitance of soil samples with different water contents; Measure the cohesion and internal friction angle of soil samples with different water contents; The impedance and capacitance of the soil samples with different water contents and the corresponding cohesion and internal friction angle are added to the cohesion relationship table and the internal friction angle relationship table.

8. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Acquire first calibration point data and second calibration point data collected by the geotechnical parameter sensor during installation of the geotechnical parameter sensor at the monitoring point; wherein the first calibration point data includes capacitance values ​​and impedance values ​​collected when the geotechnical parameter sensor is surrounded by water, and the second calibration point data includes capacitance values ​​and impedance values ​​collected when the geotechnical layer surrounding the geotechnical parameter sensor is in a water-saturated state; If the capacitance value in the first calibration point data is smaller than the capacitance value of pure water, or the impedance value in the first calibration point data is larger than the impedance value of pure water, or the impedance value in the first calibration point data is larger than the impedance value in the second calibration point data, a prompt message indicating that the geotechnical parameter sensor is installed incorrectly is output.

9. A rock and soil layer structure change monitoring system based on sensor fusion, characterized in that: include: Intelligent sensing terminals set up at different monitoring points, at least one data analysis terminal and a big data early warning platform; Each data analysis terminal is communicatively connected to at least one intelligent sensing terminal; the at least one data analysis terminal is communicatively connected to the big data early warning platform; The intelligent sensing terminal includes a geotechnical parameter sensor, a geotechnical layer sliding sensor, a low-frequency vibration sensor and an inclination sensor. The geotechnical parameter sensor is used to monitor the capacitance value and impedance value of the surrounding geotechnical layer and the relative cohesion and relative internal friction angle of the geotechnical layer determined based on the capacitance value and the impedance value. The low-frequency vibration sensor is used to monitor the vibration change of the surrounding geotechnical layer. The inclination sensor is used to monitor the inclination change of the surrounding geotechnical layer. The geotechnical layer sliding sensor is used to monitor the sliding condition of the surrounding geotechnical layer. The data analysis terminal comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 8 when executing the computer program; The big data early warning platform is used to receive and store data sent by the at least one data analysis terminal.

10. The system according to claim 9, characterized in that The big data early warning platform is also used for: According to the capacitance value and impedance value used to calculate the relative cohesion, a cohesion monitoring diagram is drawn with the horizontal axis representing impedance and the vertical axis representing capacitance, and the data in the cohesion relationship table obtained through the experiment are added as a background diagram to the cohesion monitoring diagram, wherein each coordinate point drawn in the cohesion monitoring diagram corresponds to the capacitance value and impedance value of the monitored relative cohesion, and the cohesion relationship table is used to represent the corresponding relationship between the impedance and capacitance of the rock and soil layer and the cohesion; According to the capacitance value and impedance value used to calculate the relative internal friction angle, an internal friction angle monitoring diagram is drawn with the horizontal axis representing impedance and the vertical axis representing capacitance, and the data in the internal friction angle relationship table obtained through the experiment is added to the internal friction angle monitoring diagram as a background diagram, wherein each coordinate point drawn in the internal friction angle monitoring diagram corresponds to the capacitance value and impedance value of the monitored relative internal friction angle, and the internal friction angle relationship table is used to represent the correspondence between the impedance and capacitance of the rock and soil layer and the internal friction angle.