Early warning method based on fusion analysis of micro-fracture and internal stress change of rock mass in slope

Abstract

The invention belongs to the technical field of slope hazard early warning, and particularly relates to an early warning method based on fusion analysis of micro-fracture and internal stress change of rock mass in a slope, which comprises the following steps of: firstly, acquiring a slope field geophysical prospecting result from a slope field, analyzing, and determining a key monitoring area according to fracture zone distribution and slip zone distribution; monitoring lines and monitoring points are arranged in the key monitoring areas; then punching holes in the monitoring points in the key monitoring area of the side slope, and burying three-dimensional stress monitoring sensors; micro-fracture detectors are installed on the surface of the monitoring line in the slope key monitoring area and the monitoring point at intervals; continuously acquiring and processing the monitoring data through the monitoring platform, and comparing the monitoring data with a preset monitoring data threshold to generate monitoring data change data; and finally, generating developmental period early warning and outbreak period early warning of slope disaster early warning according to the monitoring data change data. The problem that advanced early warning cannot be effectively carried out in existing slope automatic monitoring and early warning can be solved.

Description

Technical Field

[0001] The invention belongs to the technical field of slope hazard early warning, and in particular relates to an early warning method based on fusion analysis of rock micro-fractures and internal stress changes in a slope. Background Art

[0002] The automatic slope monitoring and early warning system is a comprehensive technical system specially used for real-time monitoring and analysis of slope stability and timely alarm when potential dangerous situations occur. It integrates a variety of sensor technologies, data acquisition and transmission technologies, data processing and analysis technologies, etc. In the mining industry, it can continuously monitor the slopes of mines to ensure the safety of mining operations; in water conservancy projects, such as the slopes on both sides of reservoir dams, the system can ensure the stability of slopes and avoid damage to water conservancy facilities caused by disasters such as landslides; in the process of mountain construction, monitoring of slopes around buildings can protect the lives and property of residents; in the field of highway and railway construction, monitoring of slopes on both sides of the road can ensure the normal operation of transportation facilities. It obtains data related to the state of the slope by installing various sensors at different positions on the slope, such as displacement sensors, strain sensors, etc., and transmits these data to the processing center through the communication network. After a series of algorithm and model analysis, it determines whether the slope is dangerous according to the set conditions and issues early warning information when the danger comes.

[0003] At present, the automatic monitoring and early warning of slopes mainly revolve around the manifestation factors of geological disasters on slopes. This means that the system mainly focuses on monitoring the obvious external macro deformation parameters that are occurring on the slopes. For example, high-precision displacement sensors are used to accurately measure the displacement of different points on the slope surface, including horizontal and vertical displacements. When the displacement reaches a certain level, it is considered that there may be unstable factors in the slope. At the same time, the development of cracks on the slope surface is also monitored, and the changes in the crack width are monitored by sensors installed on both sides of the cracks. In addition, parameters such as the inclination of the slope surface are also measured in real time. The monitoring data of these macro deformation parameters will be transmitted to the monitoring center in real time, and then the technicians will set the corresponding thresholds based on the long-term accumulated design and application experience. When the monitoring data exceeds these thresholds, the system will issue a warning signal.

[0004] However, this method based on macroscopic phenomena monitoring has serious limitations. Because the occurrence of macroscopic phenomena often means that slope disasters are already in the process of occurring. For example, when the displacement exceeds the threshold or the crack width increases sharply, the damage inside the slope may be quite serious. Only then will an early warning be issued, and the time left for relevant departments to take disaster prevention and mitigation measures is extremely tight. Moreover, since the disaster has already begun, the operational spatial scope has also been greatly compressed. This makes it impossible to carry out effective advance warnings in the early stages of slope disasters, that is, before the disaster has developed on a large scale. This lag makes it very passive when dealing with slope disasters, which may cause serious casualties and economic losses, and cannot meet the actual needs of effective prevention and timely response to slope disasters. Summary of the invention

[0005] The technical problem solved by the present invention is to provide an early warning method based on the fusion analysis of rock micro-fractures and internal stress changes in the slope, so as to solve the problem that the existing automatic monitoring and early warning of the slope cannot effectively provide advance warning.

[0006] The basic solution provided by the present invention is an early warning method based on the fusion analysis of rock micro-fractures and internal stress changes in the slope, including:

[0007] S1: Conduct field surveys on the slope site, obtain geophysical exploration results on the slope site, analyze them, determine key monitoring areas based on the distribution of broken zones and slip zones, and lay out monitoring lines and monitoring points in the key monitoring areas according to the preset layout method;

[0008] S2: Drill holes at monitoring points in the key monitoring area of ​​the slope and bury three-dimensional stress monitoring sensors; install micro-fracture geophones at intervals between the monitoring line surface and monitoring points in the key monitoring area of ​​the slope;

[0009] S3: Continuously acquire and process the monitoring data of the three-dimensional stress monitoring sensor and the microfracture geophone through the monitoring platform, compare it with the preset monitoring data threshold, and generate monitoring data change data;

[0010] S4: Generate development period warning and outbreak period warning of slope disaster according to the change data of monitoring data.

[0011] Further, the S1 includes:

[0012] S1-1: Select the corresponding geophysical exploration method according to the geological characteristics of the slope, conduct on-site investigation on the slope, and generate geophysical exploration results;

[0013] S1-2: Analyze different abnormal characteristics of geophysical exploration results according to different geophysical exploration methods, and output slope abnormal characteristics;

[0014] S1-3: Build a geological database and an AI slope geological empirical model, input the geological database into the AI ​​slope geological empirical model for training, then input the slope abnormal characteristics into the trained AI slope geological empirical model, and output the slope slip zone and fracture zone identification results;

[0015] S1-4: Call the data inversion technology to perform inversion processing on the slope slip zone identification results and the broken zone identification results, and output the position and shape of the slope slip zone, as well as the position and shape of the broken zone.

[0016] Furthermore, the S1 further includes:

[0017] S1-5: Generate multiple monitoring lines according to the position and shape of the slip zone and the broken zone, and call the optimized genetic algorithm to optimize and iterate the multiple monitoring lines to output the optimal monitoring line;

[0018] S1-6: Calculate the disaster degree of the position and shape of the slip zone and the broken zone according to the optimal monitoring line, and arrange key monitoring points and auxiliary monitoring points in the slip zone and broken zone where the disaster degree exceeds the preset disaster threshold.

[0019] Furthermore, in S1-5, the optimized genetic algorithm is called to iteratively optimize the multiple monitoring lines, and the optimal monitoring line is output as follows:

[0020] The generated multiple monitoring lines are used as the initial population, and the attribute parameters of each monitoring line in the initial population are extracted;

[0021] Construct a fitness function based on the attribute parameters and calculate the fitness value of each monitoring line on the fitness function;

[0022] Call the optimization algorithm to simulate and generate the optimization target value of each fitness function and construct the full attribute objective function;

[0023] The number of iterative optimization is preset, and the genetic algorithm is called to optimize and iterate each monitoring line in the initial population according to the full attribute objective function to obtain the full attribute objective function value, until the iterative optimization is completed, and the corresponding monitoring line and its layout method when the full attribute objective function value is the largest are obtained.

[0024] Further, the S1-6 is specifically:

[0025] Obtain the AI ​​slope geological empirical model trained by the geological database, and input the preset disaster level and the identification results of the target slope slip zone and fracture zone;

[0026] Obtain different disaster levels of the slip zone and fracture zone of the target slope output by the AI ​​slope geological empirical model;

[0027] Different monitoring point attributes are divided according to different disaster levels.

[0028] Further, the S2 includes:

[0029] S2-1: Retrieve the monitoring points arranged on the slope and drill holes for key monitoring points and auxiliary monitoring points;

[0030] S2-2: burying three-dimensional stress monitoring sensors in the key monitoring point holes and the auxiliary monitoring point holes, wherein the horizontal main force Y direction of the three-dimensional stress monitoring sensors is consistent with the landslide direction of the slope;

[0031] S2-3: profile the monitoring line, and install micro-fracture geophones between the profile surface of the monitoring line and the internal three-dimensional stress monitoring sensor, wherein the number of the micro-fracture geophones is at least 4.

[0032] Further, the S3 includes:

[0033] S3-1: wirelessly communicate with the three-dimensional stress monitoring sensor and the micro-fracture geophone through the monitoring platform, and receive monitoring data from the three-dimensional stress monitoring sensor and the micro-fracture geophone;

[0034] S3-2: Construct a target slope geological model in the monitoring platform, and perform numbering, position coordinate marking and communication parameter setting in the target slope geological model according to the optimal monitoring line and monitoring point settings;

[0035] S3-3: Based on the attributes of the monitoring points, the monitoring areas of different disaster levels are delineated on the monitoring line profile of the monitoring platform;

[0036] S3-4: Preset stress prediction threshold, stress change rate prediction threshold, and micro-fracture prediction threshold according to the monitoring areas of different disaster levels;

[0037] S3-5: The monitoring platform receives the stress monitoring data and microfracture data generated by the three-dimensional stress monitoring sensor and the microfracture geophone in real time, and processes and generates stress value change, stress change rate and microfracture frequency;

[0038] S3-6: Compare the stress value change with the preset stress prediction threshold, compare the stress change rate with the stress change rate prediction threshold, compare the micro-fracture frequency with the micro-fracture prediction threshold, and output the comparison result.

[0039] Further, the S4 includes:

[0040] S4-1: If the stress value change in the judgment result is lower than the preset stress prediction threshold, the stress change rate is lower than the stress change rate prediction threshold and there is no sudden change, and the micro-fracture frequency in the monitoring area is lower than the preset micro-fracture prediction threshold, then the development period warning of the monitoring area is delineated;

[0041] S4-2: If the stress value change in the judgment result is higher than the preset stress prediction threshold, the stress change rate is higher than the stress change rate prediction threshold, and the micro-fracture frequency in the monitoring area is higher than the preset micro-fracture prediction threshold, the monitoring area is designated as an outbreak warning.

[0042] The principle and advantage of the present invention are as follows: in the present application, the key areas and monitoring profiles where disasters occur in the slope are first detected by geophysical methods. For the determination of the occurrence of slope disasters, the present application adopts the determination of slip zones and broken zones to obtain the target factors of disasters occurring in the slope. Subsequently, according to the positions and shapes of slip zones and broken zones, on the one hand, the optimal monitoring line is arranged according to the actual target values ​​of the attribute parameters. On the other hand, different types of monitoring points are arranged according to the different disaster levels of the monitoring areas on the monitoring lines, including key monitoring points and auxiliary monitoring points. A key monitoring point is set for each monitoring area on the monitoring line. A plurality of auxiliary monitoring points are arranged near the key monitoring points according to the disaster level. The auxiliary monitoring points serve as auxiliary monitoring points to assist the key monitoring points, so as to avoid the inability to obtain the monitoring data of the current monitoring area when the key monitoring points are damaged or fail. The key monitoring points and the auxiliary monitoring points are associated with each other through a correlation algorithm.

[0043] On this basis, three-dimensional stress monitoring sensors are deployed at the monitoring points, the monitoring lines are profiled to generate monitoring profile lines, micro-fracture detectors are deployed on the monitoring profile lines, and the three-dimensional stress monitoring sensors and micro-fracture detectors are wirelessly communicated with the monitoring platform. A slope model is built in the monitoring platform, so that the monitoring platform can obtain and display the changes in the monitoring area and monitoring data of the target slope in real time.

[0044] In the monitoring platform, the real-time monitoring data is compared with the preset thresholds of each monitoring data to obtain the judgment results of the target slope in the development period and the outbreak period, which is convenient for users to carry out subsequent slope disaster prevention and treatment.

[0045] Therefore, the advantage of the present invention is that by judging the current period of the slope, it is possible to effectively achieve advance warning of slope disasters, allowing users to take preventive measures against slope disasters in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flowchart of an embodiment of the present invention;

[0047] Figure 2 A schematic diagram of a geophysical exploration device according to an embodiment of the present invention;

[0048] Figure 3 A schematic diagram of the layout of monitoring lines and monitoring points according to an embodiment of the present invention;

[0049] Figure 4This is a logic diagram for judging monitoring data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following is further described in detail through specific implementation methods:

[0051] In the current automatic slope monitoring and early warning system, early warning is mainly achieved by monitoring the displacement, inclination, cracks, rainfall, moisture content and internal displacement of the slope surface related to environmental factors. This method uses a relatively macroscopic surface parameter of the slope for monitoring and analysis, but has defects in the early warning of impending landslide before the occurrence of slope disasters. In this regard, the embodiments of the present application are basically as shown in the attached Figure 1 As shown: The early warning method based on the fusion analysis of rock micro-fractures and internal stress changes in the slope includes:

[0052] S1: Conduct a field survey on the slope site, obtain the geophysical exploration results of the slope site and analyze them, determine the key monitoring area according to the distribution of the broken zone and the slip zone, and deploy monitoring lines and monitoring points in the key monitoring area according to the preset deployment method; in this application, for the early warning of slope disasters, the influencing factors used are judged as broken zones and slip zones. First, the corresponding geophysical exploration method is selected according to the geological characteristics of the slope. In this embodiment, the geophysical exploration method includes seismic method, electrical method, magnetic method and gravity method, etc., among which:

[0053] The seismic method is based on the propagation characteristics of elastic waves in different media. First, at the slope site, an explosive source (under appropriate safety conditions) or a non-explosive source (such as a heavy hammer, air gun, etc.) is used, and detectors are arranged on the slope surface in a certain grid or linear manner to ensure that the area to be surveyed can be covered. The collected seismic wave data is transmitted to the data acquisition system via a cable, and then analyzed using special seismic data processing software to obtain an image of the underground geological structure; the magnetic method is based on the different magnetic properties of different geological bodies, and the magnetic field strength and magnetic field gradient of the surface are measured to infer the magnetic distribution of underground geological bodies; the gravity method uses the changes in the gravity field caused by the density differences of different geological bodies for exploration.

[0054] In this embodiment, the electrical method is mainly used for exploration, specifically: the electrical method is to use different geological bodies with different electrical parameters to detect the geological characteristics of the slope. First, the structural data of the target slope is obtained, the working face is arranged and the drilling is carried out, and the survey line is arranged in the working face slot and the drill hole, and the survey lines of the drill hole and the working face slot are connected by a large line to form a three-dimensional long survey line. In this application, Figure 2As shown, the cable connecting the electrodes in series is called a large line, and each large line is evenly distributed with 10 distributed switches, which are numbered 1-10 from the beginning to the end. The distributed switch is connected to the plug-in card of the electrode, which means that each large line can connect 10 electrodes. The large lines are connected in series through cascade electrode converters. Therefore, the three-dimensional long survey line in this application may include multiple large lines to form an upward large line and a downward large line, and the upward large line and the downward large line are respectively connected to the host through transition cables; then the target slope is run to obtain geological body data, that is, the geophysical exploration results of the target slope.

[0055] Then, the broken zone and slip zone are screened from the geophysical exploration results. Specifically, the abnormal characteristics of the obtained geophysical exploration results are analyzed. For example, the abnormal characteristics in the seismic method include a significant decrease in the seismic wave velocity in a certain area and complex reflection and scattering phenomena of the waves; the abnormal characteristics in the electrical method include a low resistivity in a certain area; thus, the abnormal characteristics of the slope are output;

[0056] Then, a geological database is constructed, and an AI slope geological empirical model is constructed. In this embodiment, the geological database includes historical slope data stored in enterprise and company databases and geological data documents publicly available on the Internet. The geological database generated in this way is input into the AI ​​slope geological empirical model generated by the big data AI model for training, so that the AI ​​slope geological empirical model can judge the abnormal characteristics of the slope and then output the slip zone identification results and the broken zone identification results.

[0057] Finally, through the inversion technology, the three-dimensional distribution model of the slope is obtained, such as the resistivity inversion model in the electrical method. If the low-resistance area shows a certain continuity and directionality, it will be judged as a broken zone or slip zone, thereby obtaining the broken zone identification results and slip zone identification results.

[0058] After the identification results of the broken zone and slip zone of the target slope are generated, multiple monitoring lines are generated according to their positions and shapes, and the optimized genetic algorithm is called to optimize and iterate the multiple monitoring lines to output the optimal monitoring line, which is as follows:

[0059] The generated multiple monitoring lines are used as the initial population, and the attribute parameters of each monitoring line in the initial population are extracted; in this embodiment, the target slope is connected to form monitoring lines according to the positions of the fracture zone and the slip zone, and there are multiple connection methods, and there are multiple monitoring lines. When sensors or detectors are to be arranged on each monitoring line, different attributes will be mapped, such as monitoring line length attribute, equipment cost attribute, and transportation cost attribute;

[0060] A fitness function is constructed according to the attribute parameters, and the fitness value of each monitoring line on the fitness function is calculated; in this embodiment, the constructed fitness function includes a length fitness function, an equipment cost fitness function, a transportation cost fitness function, etc.;

[0061] The optimization algorithm is called to simulate and generate the optimization target value of each fitness function, and a full attribute objective function is constructed. In this embodiment, the called optimization algorithm is to calculate the shortest distance in length, the minimum equipment cost and the minimum transportation cost of each monitoring line, and assign different weights to each fitness according to the actual situation of different slopes. For example, for slopes with convenient transportation, the weight proportion of transportation cost is lower, and vice versa. In this way, a full attribute objective function is generated as the optimal result for evaluating the three fitnesses of each monitoring line in this scheme.

[0062] The number of iterative optimization searches is preset, and the genetic algorithm is called to iteratively optimize each monitoring line in the initial population according to the full-attribute objective function to obtain the full-attribute objective function value, until the iterative optimization is completed, and the corresponding monitoring line and its layout method when the full-attribute objective function value is maximum are obtained; in this embodiment, the number of iterative optimization searches is preset, and then the layout of the monitoring lines is randomly adjusted and cross-mutated by the genetic algorithm, and the monitoring line with the maximum full-attribute objective function value is finally obtained, and its layout method is the monitoring line finally selected in this scheme.

[0063] Monitoring points need to be deployed at each broken zone and slip zone location on the monitoring line. The monitoring points are deployed in the following way: the disaster degree is calculated according to the location and shape of the slip zone and broken zone in the monitoring area on the optimal monitoring line, and key monitoring points and auxiliary monitoring points are deployed at the slip zone and broken zone where the disaster degree exceeds the preset disaster threshold. Specifically, the disaster degree is calculated by calculating the severity of the slip zone and broken zone. The calculation method can call the AI ​​slope geological experience model trained by the geological database, and then input the sample data and judgment level used to determine the severity of the slip zone and broken zone to train the AI ​​slope geological experience model again. In this way, the retrained AI slope geological experience model can output different disaster levels in the monitoring area of ​​the target slope, for example In this application, the disaster level is divided into A, B, and C, where A indicates that the disaster level of the broken zone and the slip zone in the monitoring area is high, B indicates that the disaster level of the broken zone and the slip zone in the monitoring area is average, and C indicates that the disaster level of the broken zone and the slip zone in the monitoring area is low; and the disaster level of the monitoring area cannot usually be represented by one level, but usually has several disaster levels. In this application, through the range map, the center of the broken zone or the slip zone is used as the radius, and the A-level disaster range is generated; similarly, outside the A-level disaster range, the B-level disaster radiation range is used as the radius to generate the B-level disaster range. In this way, the monitoring area is divided into areas representing multiple different disaster levels;

[0064] In this way, key monitoring points are deployed within the monitoring range with the highest disaster severity, and auxiliary monitoring points are deployed in the outer range. At the same time, the key monitoring points and the auxiliary monitoring points are associated through an association algorithm, so that even if the equipment at the key monitoring points is damaged, the auxiliary monitoring points can receive data in real time and calculate the monitoring data range value of the key monitoring points.

[0065] S2: Drill holes at monitoring points in the key monitoring area of ​​the slope and bury three-dimensional stress monitoring sensors; install micro-fracture detectors at intervals between the monitoring line surface and monitoring points in the key monitoring area of ​​the slope; specifically: Figure 3 As shown, firstly, the monitoring points arranged on the slope are retrieved, and holes are drilled at the key monitoring points and auxiliary monitoring points;

[0066] Then, three-dimensional stress monitoring sensors are buried in the key monitoring point holes and the auxiliary monitoring point holes. In this application, the three-dimensional stress monitoring sensors can monitor the forces in three mutually perpendicular directions of X, Y, and Z. In this embodiment, the horizontal main force Y direction of the three-dimensional stress monitoring sensor is consistent with the landslide direction of the slope; thereby improving the sensitivity of stress monitoring;

[0067] The monitoring line is profiled, and micro-fracture geophones are installed between the profile surface of the monitoring line and the internal three-dimensional stress monitoring sensor. The number of the micro-fracture geophones is at least 4 to ensure positioning accuracy.

[0068] S3: The monitoring data of the three-dimensional stress monitoring sensor and the micro-fracture detector are continuously acquired and processed through the monitoring platform, and compared with the preset monitoring data threshold to generate monitoring data change data; Figure 4 As shown, specifically:

[0069] S3-1: wirelessly communicate with the three-dimensional stress monitoring sensor and the micro-fracture geophone through the monitoring platform, and receive monitoring data from the three-dimensional stress monitoring sensor and the micro-fracture geophone;

[0070] S3-2: Construct a target slope geological model in the monitoring platform, and perform numbering, position coordinate marking and communication parameter setting in the target slope geological model according to the optimal monitoring line and monitoring point settings;

[0071] S3-3: Based on the attributes of the monitoring points, the monitoring areas of different disaster levels are delineated on the monitoring line profile of the monitoring platform;

[0072] S3-4: Preset stress prediction threshold, stress change rate prediction threshold, and micro-fracture prediction threshold according to the monitoring areas of different disaster levels;

[0073] S3-5: The monitoring platform receives the stress monitoring data and microfracture data generated by the three-dimensional stress monitoring sensor and the microfracture geophone in real time, and processes and generates stress value change, stress change rate and microfracture frequency;

[0074] S3-6: Compare the stress value change with the preset stress prediction threshold, compare the stress change rate with the stress change rate prediction threshold, compare the micro-fracture frequency with the micro-fracture prediction threshold, and output the comparison result.

[0075] S4: Generate developmental warning and outbreak warning of slope disaster warning according to the monitoring data change data; specifically, for the judgment result, if the stress value change in the judgment result is lower than the preset stress prediction threshold, the stress change rate is lower than the stress change rate prediction threshold and there is no sudden change, and the micro-fracture frequency in the monitoring area is lower than the preset micro-fracture prediction threshold, then the developmental warning of the monitoring area is delineated;

[0076] If the stress value change in the judgment result is higher than the preset stress prediction threshold, the stress change rate is higher than the stress change rate prediction threshold, and the micro-fracture frequency in the monitoring area is higher than the preset micro-fracture prediction threshold, the monitoring area will be designated as an outbreak period warning.

[0077] In this regard, in the present application, firstly, the key areas and monitoring profiles where slope disasters occur are detected by geophysical methods. For the determination of slope disasters, the present application adopts the judgment of slip zones and broken zones to obtain the target factors of disasters in the slope. Subsequently, based on the position and shape of slip zones and broken zones, on the one hand, the optimal monitoring line is laid out according to the actual attribute parameter target value, and on the other hand, different types of monitoring points are set according to the different disaster levels of the monitoring areas on the monitoring line, including key monitoring points and auxiliary monitoring points. A key monitoring point is set for each monitoring area on the monitoring line, and multiple auxiliary monitoring points are set near the key monitoring points according to the disaster level. They serve as auxiliary monitoring points to assist the key monitoring points to avoid the inability to obtain monitoring data of the current monitoring area when the key monitoring points are damaged or fail. The key monitoring points and the auxiliary monitoring points are associated with each other through a correlation algorithm.

[0078] On this basis, three-dimensional stress monitoring sensors are deployed at the monitoring points, the monitoring lines are profiled to generate monitoring profile lines, micro-fracture detectors are deployed on the monitoring profile lines, and the three-dimensional stress monitoring sensors and micro-fracture detectors are wirelessly communicated with the monitoring platform. A slope model is built in the monitoring platform, so that the monitoring platform can obtain and display the changes in the monitoring area and monitoring data of the target slope in real time.

[0079] In the monitoring platform, the real-time monitoring data is compared with the preset thresholds of each monitoring data to obtain the judgment results of the target slope in the development period and the outbreak period, which is convenient for users to carry out subsequent slope disaster prevention and treatment.

[0080] The above are only embodiments of the present invention. Common knowledge such as the known specific structures and characteristics in the scheme is not described in detail here. Ordinary technicians in the relevant field know all the common technical knowledge in the technical field to which the invention belongs before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply conventional experimental means before that date. Ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. An early warning method based on the fusion analysis of rock micro-fractures and internal stress changes in the slope, characterized by: include: S1: Conduct field surveys on the slope site, obtain geophysical exploration results on the slope site, analyze them, determine key monitoring areas based on the distribution of broken zones and slip zones, and lay out monitoring lines and monitoring points in the key monitoring areas according to the preset layout method; S2: Drill holes at monitoring points in the key monitoring area of ​​the slope and bury three-dimensional stress monitoring sensors; install micro-fracture geophones at intervals between the monitoring line surface and monitoring points in the key monitoring area of ​​the slope; S3: Continuously acquire and process the monitoring data of the three-dimensional stress monitoring sensor and the microfracture geophone through the monitoring platform, compare it with the preset monitoring data threshold, and generate monitoring data change data; S4: Generate development period warning and outbreak period warning of slope disaster according to the change data of monitoring data.

2. The early warning method based on the fusion analysis of rock micro-fractures and internal stress changes in the slope according to claim 1 is characterized by: The S1 includes: S1-1: Select the corresponding geophysical exploration method according to the geological characteristics of the slope, conduct on-site investigation on the slope, and generate geophysical exploration results; S1-2: Analyze different abnormal characteristics of geophysical exploration results according to different geophysical exploration methods, and output slope abnormal characteristics; S1-3: Build a geological database and an AI slope geological empirical model, input the geological database into the AI ​​slope geological empirical model for training, then input the slope abnormal characteristics into the trained AI slope geological empirical model, and output the slope slip zone and fracture zone identification results; S1-4: Call the data inversion technology to perform inversion processing on the slope slip zone identification results and the broken zone identification results, and output the position and shape of the slope slip zone, as well as the position and shape of the broken zone.

3. The early warning method based on the fusion analysis of rock micro-fractures and internal stress changes in the slope according to claim 2 is characterized by: The S1 further comprises: S1-5: Generate multiple monitoring lines according to the position and shape of the slip zone and the broken zone, and call the optimized genetic algorithm to optimize and iterate the multiple monitoring lines to output the optimal monitoring line; S1-6: Calculate the disaster degree of the position and shape of the slip zone and the broken zone according to the optimal monitoring line, and arrange key monitoring points and auxiliary monitoring points in the slip zone and broken zone where the disaster degree exceeds the preset disaster threshold.

4. The early warning method based on the fusion analysis of rock micro-fractures and internal stress changes in the slope according to claim 3 is characterized by: In S1-5, the optimized genetic algorithm is called to iteratively optimize multiple monitoring lines, and the optimal monitoring line is output as follows: The generated multiple monitoring lines are used as the initial population, and the attribute parameters of each monitoring line in the initial population are extracted; Construct a fitness function based on the attribute parameters and calculate the fitness value of each monitoring line on the fitness function; Call the optimization algorithm to simulate and generate the optimization target value of each fitness function and construct the full attribute objective function; The number of iterative optimization is preset, and the genetic algorithm is called to optimize and iterate each monitoring line in the initial population according to the full attribute objective function to obtain the full attribute objective function value, until the iterative optimization is completed, and the corresponding monitoring line and its layout method when the full attribute objective function value is the largest are obtained.

5. The early warning method based on the fusion analysis of rock micro-fractures and internal stress changes in the slope according to claim 4 is characterized by: The S1-6 is specifically: Obtain the AI ​​slope geological empirical model trained by the geological database, and input the preset disaster level and the identification results of the target slope slip zone and fracture zone; Obtain different disaster levels of the slip zone and fracture zone of the target slope output by the AI ​​slope geological empirical model; Different monitoring point attributes are divided according to different disaster levels.

6. The early warning method based on the fusion analysis of rock micro-fractures and internal stress changes in the slope according to claim 5 is characterized by: The S2 includes: S2-1: Retrieve the monitoring points arranged on the slope and drill holes for key monitoring points and auxiliary monitoring points; S2-2: burying three-dimensional stress monitoring sensors in the key monitoring point holes and the auxiliary monitoring point holes, wherein the horizontal main force Y direction of the three-dimensional stress monitoring sensors is consistent with the landslide direction of the slope; S2-3: profile the monitoring line, and install micro-fracture geophones between the profile surface of the monitoring line and the internal three-dimensional stress monitoring sensor, wherein the number of the micro-fracture geophones is at least 4.

7. The early warning method based on fusion analysis of rock micro-fractures and internal stress changes in the slope according to claim 6 is characterized by: The S3 includes: S3-1: wirelessly communicate with the three-dimensional stress monitoring sensor and the micro-fracture geophone through the monitoring platform to receive monitoring data from the three-dimensional stress monitoring sensor and the micro-fracture geophone; S3-2: Construct a target slope geological model in the monitoring platform, and perform numbering, position coordinate marking and communication parameter setting in the target slope geological model according to the optimal monitoring line and monitoring point settings; S3-3: Based on the attributes of the monitoring points, the monitoring areas of different disaster levels are delineated on the monitoring line profile of the monitoring platform; S3-4: Preset stress prediction threshold, stress change rate prediction threshold, and micro-fracture prediction threshold according to the monitoring areas of different disaster levels; S3-5: The monitoring platform receives the stress monitoring data and microfracture data generated by the three-dimensional stress monitoring sensor and the microfracture detector in real time, and processes and generates stress value change, stress change rate and microfracture frequency; S3-6: Compare the stress value change with the preset stress prediction threshold, compare the stress change rate with the stress change rate prediction threshold, compare the micro-fracture frequency with the micro-fracture prediction threshold, and output the comparison result.

8. The early warning method based on the fusion analysis of rock micro-fractures and internal stress changes in the slope according to claim 7 is characterized by: The S4 includes: S4-1: If the stress value change in the judgment result is lower than the preset stress prediction threshold, the stress change rate is lower than the stress change rate prediction threshold and there is no sudden change, and the micro-fracture frequency in the monitoring area is lower than the preset micro-fracture prediction threshold, then the development period warning of the monitoring area is delineated; S4-2: If the stress value change in the judgment result is higher than the preset stress prediction threshold, the stress change rate is higher than the stress change rate prediction threshold, and the micro-fracture frequency in the monitoring area is higher than the preset micro-fracture prediction threshold, the monitoring area is designated as an outbreak warning.

Images