Emergency rescue method applied to slope engineering

Abstract

The invention relates to an emergency rescue method applied to slope engineering, and the method comprises the steps: collecting the multi-source data of a slope, and constructing a three-dimensional slope model; wherein the multi-source data comprises slope surface displacement data, internal stress data and environmental parameter data; based on the three-dimensional slope model, slope stability evaluation is carried out; based on the slope stability evaluation result, a corresponding emergency rescue scheme is obtained; performing optimal configuration on the emergency scheme by adopting a dynamic scheduling algorithm, and obtaining execution feedback data; and carrying out real-time tracking monitoring on the rescue process based on the execution feedback data. Through the multi-source sensor, three-dimensional modeling, finite element analysis, intelligent decision making and dynamic scheduling, real-time monitoring, accurate evaluation and efficient emergency rescue of slope disasters are achieved, a digital management platform is constructed, the emergency rescue efficiency and quality are improved, and digital transformation of a slope emergency rescue technical system is promoted.

Description

Technical Field

[0001] The invention relates to the technical field of slope engineering, and in particular to an emergency rescue method applied to slope engineering. Background Art

[0002] Slope engineering, as a crucial component of geological disaster prevention and infrastructure construction, is directly impacting the safety of people's lives and property, as well as national economic development. With the acceleration of urbanization and the frequent occurrence of extreme weather events, slope instability accidents are becoming more sudden and highly hazardous, placing higher demands on emergency response technologies. Traditional slope emergency response relies primarily on manual on-site surveys and empirical judgment, resulting in slow response, inaccurate risk assessments, and a lack of scientific evidence for emergency response plans. Existing monitoring methods, mostly based on single-point sensors, struggle to fully capture the overall state of the slope. Furthermore, the emergency response decision-making process lacks systematic analytical tools, often relying on engineers' individual experience to formulate plans, resulting in inefficient response and potential safety hazards. A key challenge facing slope emergency response is achieving comprehensive, real-time perception of slope conditions. Due to the complex and variable geological conditions of slopes, traditional monitoring methods are unable to quickly acquire complete three-dimensional spatial information, resulting in a lack of accurate understanding of slope stability. This limited perception further hinders the development of scientific emergency response plans. Without accurate current data for stability analysis and option comparison, emergency response decisions are often subject to significant subjectivity and uncertainty. More critically, the lack of a systematic digital management platform to organically integrate monitoring data, analysis results, decision-making processes, and execution feedback has led to a fragmented state in the entire rescue process, poor information transmission between various links, and serious impacts on rescue efficiency and quality. Therefore, how to build a slope emergency rescue technology system that integrates real-time monitoring, intelligent analysis, scientific decision-making, and digital execution to achieve a transition from passive response to active prevention and control has become a key issue that needs to be addressed in the current slope engineering field. Summary of the Invention

[0003] The purpose of the present invention is to provide an emergency rescue method applied to slope engineering to solve the problems existing in the above-mentioned prior art.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] An emergency rescue method applied to slope engineering, comprising:

[0006] Collecting multi-source data of the slope and constructing a three-dimensional slope model; wherein the multi-source data includes: slope surface displacement data, internal stress data and environmental parameter data;

[0007] performing slope stability assessment based on the three-dimensional slope model;

[0008] Obtain corresponding emergency rescue plans based on slope stability assessment results;

[0009] Using a dynamic scheduling algorithm to optimize the configuration of the emergency plan and obtain execution feedback data;

[0010] The emergency rescue process is tracked and monitored in real time based on the execution feedback data.

[0011] Optionally, collecting multi-source data of the slope and constructing a three-dimensional slope model includes:

[0012] Acquiring the multi-source data from the slope area through a multi-source sensor network deployment technology;

[0013] Preprocessing the multi-source data to construct a monitoring data set;

[0014] Based on the monitoring data set, the three-dimensional slope model is constructed.

[0015] Optionally, preprocessing the multi-source data includes:

[0016] Obtaining location coordinates and timestamp information of the multi-source data;

[0017] Data cleaning is performed through denoising and outlier removal;

[0018] The cleaned data is formatted and standardized to construct a monitoring data set.

[0019] Optionally, constructing the three-dimensional slope model based on the monitoring data set includes:

[0020] Using a three-dimensional point cloud reconstruction algorithm, geometric reconstruction is performed on the monitoring data set to obtain a slope surface model;

[0021] According to the displacement vector information in the slope surface model, the displacement change of each monitoring point is calculated to obtain the displacement change distribution;

[0022] If the displacement change of any monitoring point in the displacement change distribution exceeds the preset threshold condition, the abnormal state mark is triggered and the abnormal area data set is generated;

[0023] Through interpolation calculation methods, the location information and abnormal area data sets are combined to fill the monitoring blind area data and obtain optimized 3D point cloud data;

[0024] A three-dimensional point cloud reconstruction algorithm is used to remodel the optimized three-dimensional point cloud data to obtain a final three-dimensional slope model.

[0025] Optionally, performing slope stability assessment based on the three-dimensional slope model includes:

[0026] Acquire spatial coordinate information of the abnormal state marked area from the three-dimensional slope model to determine the scope of the abnormal area;

[0027] For the abnormal area, the finite element analysis algorithm is used, combined with the soil strength parameters and boundary condition parameters in the geological parameter database, to calculate the stress distribution of each grid unit and obtain the stress distribution data;

[0028] Calculate the slope safety factor based on the stress distribution data. If the safety factor is lower than the preset threshold, mark the potential slip surface location and generate potential slip surface data.

[0029] By combining the potential slip surface data with the spatial coordinate information and adopting the interpolation calculation method, the slip surface geometry is generated to obtain the three-dimensional model of the slip surface;

[0030] Based on the three-dimensional model of the slip surface, the displacement change is obtained, and the machine learning regression algorithm is used to predict the displacement trend of the slip surface and obtain the displacement trend distribution;

[0031] If the displacement trend exceeds a preset threshold, a risk area mark is generated.

[0032] Optionally, based on the slope stability assessment results, obtaining a corresponding rescue plan includes:

[0033] Quantitatively assess the slope stability assessment results to obtain risk status at different levels;

[0034] According to different levels of risk status and corresponding risk area ranges, the corresponding rescue measures types and construction parameter configurations are matched through the emergency plan database. The support structure design parameters and construction process arrangements are calculated according to the slope geometry and geological conditions to obtain the corresponding rescue plan.

[0035] Optionally, obtaining a corresponding emergency plan includes:

[0036] Obtain the emergency response measures type and construction parameter configuration corresponding to the risk level identifier from the emergency plan database to obtain preliminary emergency response measures;

[0037] Through preliminary rescue measures, combined with the geometric dimensions of the slope and geological conditions, the finite element analysis method was used to calculate the design parameters of the support structure;

[0038] According to the support structure parameters, if the support structure parameters meet the geological condition constraints, the priority sorting method is used to sort the parameters based on the complexity of the construction process to obtain the construction process arrangement;

[0039] By arranging the construction process and combining the spatial distribution characteristics of the dangerous area, the spatial interpolation method is used to generate the spatial layout of the rescue measures and obtain the distribution of the rescue measures;

[0040] Based on the distribution of rescue measures, the logistic regression algorithm is used to predict the slope stability change trend after the implementation of rescue measures, and the stability change prediction is obtained;

[0041] According to the stability change prediction, if the prediction result shows that the stability is lower than the preset threshold, the alternative rescue measure type is re-obtained from the emergency plan database to generate an alternative rescue plan.

[0042] Optionally, optimizing the configuration of the emergency plan using a dynamic scheduling algorithm and obtaining execution feedback data include:

[0043] According to the construction process time nodes and resource allocation requirements in the rescue plan, a dynamic scheduling algorithm is used to optimize the configuration of rescue equipment and personnel, and construction instructions and safety warning information are pushed to on-site workers through mobile terminal devices to obtain execution feedback data.

[0044] Optionally, performing real-time tracking and monitoring of the emergency process based on the execution feedback data includes:

[0045] The execution feedback data is used to track and monitor the progress and quality status of the emergency construction in real time, and the effectiveness of the emergency measures is judged based on the trend of changes in the monitoring data during the construction process. If the slope displacement rate continues to decrease and the safety factor gradually increases, the effectiveness of the emergency plan is confirmed.

[0046] The beneficial effects of the present invention are:

[0047] The present invention discloses an emergency rescue method applied to slope engineering. The method obtains slope surface displacement, internal stress and environmental parameter data through a multi-source sensor network, establishes a slope model using a three-dimensional point cloud reconstruction algorithm, and uses finite element analysis to calculate the slope safety factor and potential slip surface. The slope risk level is quantitatively assessed based on the safety factor. For high-risk areas, the present invention matches rescue measures from the emergency plan database, calculates support structure design parameters and construction procedures, and optimizes the allocation of rescue resources through a dynamic scheduling algorithm. The present invention also monitors the progress and quality of rescue construction in real time, evaluates the rescue effect based on the trend of changes in monitoring data, and ultimately forms a stable state assessment report. The method achieves accurate identification, rapid response and effective disposal of slope risks, and improves the ability to prevent and control slope disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 The figure is a flow chart of an emergency rescue method applied to slope engineering according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0051] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0052] like Figure 1 As shown, this embodiment proposes an emergency rescue method applied to slope engineering, including:

[0053] Collect multi-source data of the slope and construct a three-dimensional slope model; the multi-source data includes: slope surface displacement data, internal stress data and environmental parameter data;

[0054] Conduct slope stability assessment based on three-dimensional slope models;

[0055] Obtain corresponding emergency rescue plans based on slope stability assessment results;

[0056] Use dynamic scheduling algorithms to optimize the configuration of emergency plans and obtain execution feedback data;

[0057] Real-time tracking and monitoring of the rescue process is carried out based on execution feedback data.

[0058] Furthermore, collecting multi-source data of the slope and constructing a 3D slope model include:

[0059] Through the deployment of multi-source sensor networks, multi-source data is obtained from the slope area;

[0060] Preprocess multi-source data and construct monitoring data sets;

[0061] A three-dimensional slope model is constructed based on the monitoring dataset.

[0062] Furthermore, preprocessing of multi-source data includes:

[0063] Obtain location coordinates and timestamp information of multi-source data;

[0064] Data cleaning is performed through denoising and outlier removal;

[0065] The cleaned data is formatted and standardized to construct a monitoring data set.

[0066] Furthermore, based on the monitoring data set, a three-dimensional slope model is constructed, including:

[0067] Using the 3D point cloud reconstruction algorithm, the monitoring data set is geometrically reconstructed to obtain the slope surface model;

[0068] According to the displacement vector information in the slope surface model, the displacement change of each monitoring point is calculated to obtain the displacement change distribution;

[0069] If the displacement change of any monitoring point in the displacement change distribution exceeds the preset threshold condition, the abnormal state mark is triggered and the abnormal area data set is generated;

[0070] Through interpolation calculation methods, the location information and abnormal area data sets are combined to fill the monitoring blind area data and obtain optimized 3D point cloud data;

[0071] The 3D point cloud reconstruction algorithm is used to re-model the optimized 3D point cloud data to obtain the final 3D slope model.

[0072] Specifically, in this embodiment, the implementation process of collecting multi-source data of the slope and constructing a three-dimensional slope model is as follows:

[0073] A multi-source sensor network deployment technique is used to acquire slope surface displacement data, internal stress data, and environmental parameter data. Specifically, laser displacement sensors (0.1 mm accuracy) are deployed every 10 meters on the slope surface to monitor surface displacement. Data is collected once per second, generating a displacement time series (e.g., [0.2, 0.3, 0.25] mm). Stress sensors (range 0-10 MPa, accuracy 0.01 MPa) are embedded every 5 meters within the slope to record geotechnical stress data (e.g., [2.15, 2.18, 2.20] MPa). Environmental parameters are collected using temperature and humidity sensors (0.1°C accuracy, 1% humidity accuracy), such as 25.3°C and 60% humidity. Data is transmitted in real time to a data processing center in JSON format via a LoRa wireless transmission module (915 MHz frequency, 2 km transmission range), with a transmission rate of once per second. Data packets are approximately 200 bytes in size and contain the sensor ID, data value, and timestamp. After receiving the data, the data processing center preprocesses the raw data using a Python script to remove outliers (such as displacement data > 5 mm or stress data > 10 MPa). A median filter (window size 5) is then used to smooth the data noise, generating a smoothed dataset such as displacement [0.25, 0.26, 0.24] mm. The data is then aligned using timestamps and sensor coordinates and stored as a standardized monitoring dataset in a standardized format (e.g., CSV, containing the following fields: time, sensor ID, X, Y, Z coordinates, displacement, stress, temperature, and humidity).

[0074] Using the stereoscopic algorithm in the point cloud library, the spatial coordinates and displacement vectors of the monitoring dataset were converted into 3D point cloud data. The point cloud density was set to 1,000 points per cubic meter to generate an initial point cloud dataset. For example, a point cloud file containing 10,000 points would be approximately 5MB in size. Next, a normal vector estimation algorithm (based on the covariance matrix and a neighborhood radius of 0.5 meters) was applied to calculate the surface normal vector for each point, resulting in a set of normal vectors, such as [0.1, 0.2, 0.98]. Subsequently, a continuous 3D slope surface model was generated using a Poisson reconstruction algorithm (depth parameter 8, grid resolution 0.1 meters).

[0075] For displacement change detection, a threshold of 0.5 mm is set. If the displacement vector modulus of a monitoring point (for example, sqrt(0.15^2 + 0.10^2 + 0.05^2) = 0.19 mm) does not exceed the threshold, it is marked as normal. If the displacement modulus of another monitoring point is 0.60 mm, an abnormal state is triggered and stored as a JSON-formatted log file containing a timestamp, for example, the timestamp, point coordinates, and displacement value. To fill in the monitoring blind spot data, the Kriging interpolation algorithm (variogram range 1 meter, interpolation grid resolution 0.2 meter) is used to calculate estimated displacement values ​​for unmonitored areas, generating interpolation results such as 0.12 mm, which are integrated to form a complete three-dimensional slope model.

[0076] Furthermore, based on the three-dimensional slope model, slope stability assessment includes:

[0077] Obtain spatial coordinate information of the abnormal state marked area from the three-dimensional slope model to determine the scope of the abnormal area;

[0078] For the abnormal area, the finite element analysis algorithm is used, combined with the soil strength parameters and boundary condition parameters in the geological parameter database, to calculate the stress distribution of each grid unit and obtain the stress distribution data;

[0079] Calculate the slope safety factor based on the stress distribution data. If the safety factor is lower than the preset threshold, mark the potential slip surface location and generate potential slip surface data.

[0080] By combining the potential slip surface data with the spatial coordinate information and adopting the interpolation calculation method, the slip surface geometry is generated to obtain the three-dimensional model of the slip surface;

[0081] Based on the three-dimensional model of the slip surface, the displacement change is obtained, and the machine learning regression algorithm is used to predict the displacement trend of the slip surface and obtain the displacement trend distribution;

[0082] If the displacement trend exceeds a preset threshold, a risk area mark is generated.

[0083] Specifically, in this embodiment, based on the areas marked as abnormal in the three-dimensional slope model, soil strength parameters, such as cohesion of 20 kPa and internal friction angle of 30 degrees, as well as boundary condition parameters, such as a groundwater level of 25 meters and a slope inclination of 45 degrees, are first extracted from the geological parameter database. Using a finite element stability analysis algorithm, the three-dimensional slope model is imported into the finite element mesh, and the mesh cell size is set. Next, based on the Mohr-Coulomb criterion and combined with soil parameters, the stress distribution is calculated, and the strain is calculated using an iterative solver to obtain the maximum shear strain. Furthermore, the slope safety factor is analyzed using the strength reduction method. Initially assuming a safety factor of 1.0, the cohesion and internal friction angle are gradually reduced until the slope reaches a critical failure state. For example, when the reduction factor is 1.25, the safety factor is calculated to be 1.15, indicating that the slope is stable but nearing a critical state. For the location of the potential slip surface, based on the stress concentration area, the minimum potential energy principle is used to calculate the center coordinates of the slip surface, the slip surface area, and the inclination angle. The analysis results are stored in JSON format, including timestamps, safety factors, slip surface coordinates, and stress values. To ensure analysis continuity, the results are linked to the geological database, automatically updating boundary conditions. For example, if rainfall increases by 10 mm, the calculation will be recalculated to generate a new safety factor of 1.10. The results are then linked to the 3D model to provide data support for subsequent slope reinforcement design.

[0084] Furthermore, based on the slope stability assessment results, the corresponding rescue plan is obtained, including:

[0085] Quantitatively evaluate the slope stability assessment results to obtain different levels of risk status;

[0086] According to different levels of risk status and corresponding risk area ranges, the corresponding rescue measures types and construction parameter configurations are matched through the emergency plan database. The support structure design parameters and construction process arrangements are calculated according to the slope geometry and geological conditions to obtain the corresponding rescue plan.

[0087] Furthermore, obtaining the corresponding emergency plan includes:

[0088] Obtain the emergency response measures type and construction parameter configuration corresponding to the risk level identifier from the emergency plan database to obtain preliminary emergency response measures;

[0089] Through preliminary rescue measures, combined with the geometric dimensions of the slope and geological conditions, the finite element analysis method was used to calculate the design parameters of the support structure;

[0090] According to the support structure parameters, if the support structure parameters meet the geological condition constraints, the priority sorting method is used to sort the parameters based on the complexity of the construction process to obtain the construction process arrangement;

[0091] By arranging the construction process and combining the spatial distribution characteristics of the dangerous area, the spatial interpolation method is used to generate the spatial layout of the rescue measures and obtain the distribution of the rescue measures;

[0092] Based on the distribution of rescue measures, the logistic regression algorithm is used to predict the slope stability change trend after the implementation of rescue measures, and the stability change prediction is obtained;

[0093] According to the stability change prediction, if the prediction result shows that the stability is lower than the preset threshold, the alternative rescue measure type is re-obtained from the emergency plan database to generate an alternative rescue plan.

[0094] Specifically, for example, based on the danger zone range corresponding to the third-level response, the emergency plan database extracts the appropriate rescue measures, including anchor support and drainage system combinations, for high-risk slopes. The database query algorithm first selects appropriate measures based on the slope's geometric dimensions (e.g., 50 meters in height, 120 meters in length, and 80 meters in width), combined with geological constraints (e.g., rock shear strength of 2.5 MPa and cohesion of 0.3 MPa). The system then calculates anchor parameters using the support structure design algorithm using the formula F = rock shear strength × slope width × safety margin, where the safety margin is set to 1.3. The calculated total anchor force is F = 2.5 × 80 × 1.3 = 260 MPa. Based on this, the anchor diameter is determined to be 32 mm, the length is 6 meters, and the spacing is 2.5 meters. The number of anchors is (slope length ÷ spacing) × (slope width ÷ spacing) = 120 ÷ 2.5 × 80 ÷ 2.5 = 1536. The drainage system design is based on slope seepage rates and surface runoff data. For example, if the seepage rate is 10 liters / square meter / hour and the total slope area is 50 × 120 = 6,000 square meters, the total seepage volume is 6,000 × 10 = 60,000 liters / hour. Using a flow balance algorithm, the formula Q = seepage volume × attenuation coefficient, where the attenuation coefficient is set to 0.7 based on the soil permeability, the total flow rate through the drainage pipe is calculated as Q = 60,000 × 0.7 = 42,000 liters / hour. This determines a 200 mm diameter drainage pipe and a grid layout with 5-meter spacing. Construction schedules are optimized using a scheduling algorithm, incorporating equipment availability data. For example, if there are three excavators and the daily operating time is 8 hours, the total construction time is calculated as (number of anchor bolts / number of anchor bolts installed per hour per excavator) / number of equipment = (1,536 / 20) / 3, which is approximately 26 hours. The system also links terrain data with construction parameters to generate a three-dimensional construction model to confirm that the support and drainage system covers the danger zone, for example, 95% of the area is covered.

[0095] Furthermore, a dynamic scheduling algorithm is used to optimize the configuration of the emergency plan and obtain execution feedback data, including:

[0096] Based on the construction process time nodes and resource allocation requirements in the rescue plan, a dynamic scheduling algorithm is used to optimize the configuration of rescue equipment and personnel, and construction instructions and safety warning information are pushed to on-site workers through mobile terminal devices to obtain execution feedback data.

[0097] Specifically, the construction process and time nodes are obtained from the emergency plan, and a dynamic scheduling algorithm is used to calculate the optimal configuration of equipment and personnel to obtain the resource allocation results. Based on the resource allocation results, construction instructions are pushed to on-site workers via mobile terminals, and the instruction issuance record is obtained. The worker's reception status is extracted from the instruction issuance record. If the status is not received, the construction instruction is re-sent via the mobile terminal to obtain instruction confirmation data. Based on the instruction confirmation data, safety warning information corresponding to the construction process is pushed to obtain warning receipt feedback. The worker confirmation information is extracted from the warning receipt feedback, and a machine learning classification algorithm is used to determine the integrity of the execution feedback data to obtain the feedback data evaluation results. Based on the feedback data evaluation results, the input parameters of the dynamic scheduling algorithm are updated, and the equipment and personnel configuration plan is recalculated to obtain the optimized resource allocation results. The configuration change trend is extracted from the optimized resource allocation results, and a time series analysis algorithm is used to predict the resource requirements of subsequent construction processes to obtain a predicted resource allocation plan.

[0098] Furthermore, real-time tracking and monitoring of the emergency process based on execution feedback data includes:

[0099] Execution feedback data is used to track and monitor the progress and quality status of emergency construction in real time. The effectiveness of emergency measures is judged based on the changing trend of monitoring data during the construction process. If the slope displacement rate continues to decrease and the safety factor gradually increases, the effectiveness of the emergency plan is confirmed.

[0100] Specifically, monitoring data is acquired through sensors and processed using a time series analysis method to obtain real-time trends in construction progress and quality status. Based on the real-time trends, the slope displacement rate is calculated using a sliding window technique to obtain time series data of the displacement rate. If the displacement rate time series data shows a continuous downward trend, the data is fitted using a regression analysis model to obtain a predicted value of the displacement rate. Based on the predicted displacement rate, the safety factor is calculated using a finite element analysis method to obtain dynamic data on the safety factor. If the dynamic data on the safety factor gradually increases and is higher than a preset threshold, the data is classified using a cluster analysis method to determine the effectiveness of the emergency measures. Based on the effectiveness, a weighted average algorithm is used to fuse the displacement rate and safety factor data to obtain a comprehensive stability index. By comparing the comprehensive stability index with the preset stability threshold, it is determined whether the emergency plan has reached the final stable state and an evaluation result is obtained.

[0101] This embodiment utilizes a multi-source sensor network to acquire real-time data on slope surface displacement, internal stress, and environmental parameters. A complete slope model is constructed using a 3D point cloud reconstruction algorithm. Finite element analysis is then used to accurately calculate the slope's safety factor and potential slip surface location, enabling quantitative assessment of slope stability and risk classification. For high-risk areas, the system matches optimal emergency response measures from an emergency plan database, intelligently calculates support structure parameters, and dynamically dispatches resources to ensure a scientific and efficient emergency response plan. Furthermore, by monitoring key indicators during construction in real time, the system dynamically assesses emergency response effectiveness and provides timely feedback and adjustments to ensure construction quality and safety. This solution transcends the limitations of traditional slope emergency response, which relies on manual experience and single-point monitoring. Instead, it establishes a digital platform that integrates real-time monitoring, intelligent analysis, scientific decision-making, and efficient execution. This significantly improves the accuracy, timeliness, and coordination of slope disaster prevention and control, providing an innovative and systematic technical solution for the slope engineering field. This effectively protects the safety of people and property, and the stable operation of infrastructure, promoting the intelligent and digital transformation of slope emergency response technology.

[0102] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. An emergency rescue method applied to slope engineering, characterized in that: include: Collecting multi-source data of the slope and constructing a three-dimensional slope model; wherein the multi-source data includes: slope surface displacement data, internal stress data and environmental parameter data; performing slope stability assessment based on the three-dimensional slope model; Obtain corresponding emergency rescue plans based on slope stability assessment results; Using a dynamic scheduling algorithm to optimize the configuration of the emergency plan and obtain execution feedback data; The emergency rescue process is tracked and monitored in real time based on the execution feedback data.

2. The emergency rescue method for slope engineering according to claim 1, characterized in that: Collecting multi-source slope data and building a 3D slope model includes: Acquiring the multi-source data from the slope area through a multi-source sensor network deployment technology; Preprocessing the multi-source data to construct a monitoring data set; Based on the monitoring data set, the three-dimensional slope model is constructed.

3. The emergency rescue method for slope engineering according to claim 2, characterized in that: Preprocessing the multi-source data includes: Obtaining location coordinates and timestamp information of the multi-source data; Data cleaning is performed through denoising and outlier removal; The cleaned data is formatted and standardized to construct a monitoring data set.

4. The emergency rescue method for slope engineering according to claim 2, characterized in that: Constructing the three-dimensional slope model based on the monitoring data set includes: Using a three-dimensional point cloud reconstruction algorithm, geometric reconstruction is performed on the monitoring data set to obtain a slope surface model; According to the displacement vector information in the slope surface model, the displacement change of each monitoring point is calculated to obtain the displacement change distribution; If the displacement change of any monitoring point in the displacement change distribution exceeds the preset threshold condition, the abnormal state mark is triggered and the abnormal area data set is generated; Through interpolation calculation methods, the location information and abnormal area data sets are combined to fill the monitoring blind area data and obtain optimized 3D point cloud data; A three-dimensional point cloud reconstruction algorithm is used to remodel the optimized three-dimensional point cloud data to obtain a final three-dimensional slope model.

5. The emergency rescue method for slope engineering according to claim 1, characterized in that: Based on the three-dimensional slope model, slope stability assessment includes: Acquire spatial coordinate information of the abnormal state marked area from the three-dimensional slope model to determine the scope of the abnormal area; For the abnormal area, the finite element analysis algorithm is used, combined with the soil strength parameters and boundary condition parameters in the geological parameter database, to calculate the stress distribution of each grid unit and obtain the stress distribution data; Calculate the slope safety factor based on the stress distribution data. If the safety factor is lower than the preset threshold, mark the potential slip surface location and generate potential slip surface data. By combining the potential slip surface data with the spatial coordinate information and adopting the interpolation calculation method, the slip surface geometry is generated to obtain the three-dimensional model of the slip surface; Based on the three-dimensional model of the slip surface, the displacement change is obtained, and the machine learning regression algorithm is used to predict the displacement trend of the slip surface and obtain the displacement trend distribution; If the displacement trend exceeds a preset threshold, a risk area mark is generated.

6. The emergency rescue method for slope engineering according to claim 1, characterized in that: Based on the slope stability assessment results, the corresponding rescue plan includes: Quantitatively assess the slope stability assessment results to obtain risk status at different levels; According to different levels of risk status and corresponding risk area ranges, the corresponding rescue measures types and construction parameter configurations are matched through the emergency plan database. The support structure design parameters and construction process arrangements are calculated according to the slope geometry and geological conditions to obtain the corresponding rescue plan.

7. The emergency rescue method for slope engineering according to claim 6, characterized in that: Obtaining the corresponding emergency plan includes: Obtain the emergency response measures type and construction parameter configuration corresponding to the risk level identifier from the emergency plan database to obtain preliminary emergency response measures; Through preliminary rescue measures, combined with the geometric dimensions of the slope and geological conditions, the finite element analysis method was used to calculate the design parameters of the support structure; According to the support structure parameters, if the support structure parameters meet the geological condition constraints, the priority sorting method is used to sort the parameters based on the complexity of the construction process to obtain the construction process arrangement; By arranging the construction process and combining the spatial distribution characteristics of the dangerous area, the spatial interpolation method is used to generate the spatial layout of the rescue measures and obtain the distribution of the rescue measures; Based on the distribution of rescue measures, the logistic regression algorithm is used to predict the slope stability change trend after the implementation of rescue measures, and the stability change prediction is obtained; According to the stability change prediction, if the prediction result shows that the stability is lower than the preset threshold, the alternative rescue measure type is re-obtained from the emergency plan database to generate an alternative rescue plan.

8. The emergency rescue method for slope engineering according to claim 1, characterized in that: The dynamic scheduling algorithm is used to optimize the configuration of the emergency plan and obtain execution feedback data including: According to the construction process time nodes and resource allocation requirements in the rescue plan, a dynamic scheduling algorithm is used to optimize the configuration of rescue equipment and personnel, and construction instructions and safety warning information are pushed to on-site workers through mobile terminal devices to obtain execution feedback data.

9. The emergency rescue method for slope engineering according to claim 1, characterized in that: Real-time tracking and monitoring of the emergency process based on the execution feedback data includes: The execution feedback data is used to track and monitor the progress and quality status of the emergency construction in real time, and the effectiveness of the emergency measures is judged based on the trend of changes in the monitoring data during the construction process. If the slope displacement rate continues to decrease and the safety factor gradually increases, the effectiveness of the emergency plan is confirmed.

Images