A highway slope sudden instability risk prediction method, system, device and medium

Abstract

The application relates to a highway slope sudden instability risk prediction method, system, device and medium. The method comprises the following steps: obtaining wind speed and wind direction real-time data, combining slope rock-soil stress characteristics and wind load mechanism conversion to obtain smoothed internal pressure value and surface wind thrust value. The load parameters are input into the slope finite element numerical simulation model to obtain the slope stability safety factor and the comprehensive disturbance intensity; by presetting a critical threshold, comparing the two and determining the high risk state of slope instability, and synchronously recording the related parameters to form a high risk event record entry. Obtain the stress field and displacement field real-time data under the high risk state, fit the time series change trend, combine the high risk event record entry, predict the instability critical moment through trend extrapolation and critical feature matching, calculate the instability remaining time and generate real-time warning instructions. The method can improve the warning accuracy and reliability, improve the highway operation safety and reduce the disaster loss.

Description

Technical Field

[0001] This invention belongs to the field of disaster prevention and control technology, and in particular relates to a method, system, equipment and medium for predicting the risk of sudden instability of highway slopes. Background Technology

[0002] Highway slopes, as key geotechnical structures in highway network construction and operation, are particularly vulnerable to sudden instability and geological disasters, especially in mountainous areas, due to the coupled influence of topographical and geological conditions, wind dynamic loads, and other natural factors. This can lead not only to road damage and traffic disruptions but also to vehicle rollovers, injuries, and other safety accidents, seriously threatening highway operational safety and the safety of life and property along the route. Current methods for predicting highway slope instability risks often focus on analyzing single geomechanical parameters or local environmental factors, failing to adequately consider the coupling effects of internal pressure caused by wind loads, surface wind thrust, and the slope's soil and rock mass. Furthermore, existing risk assessment methods mostly rely on static threshold comparisons, lacking dynamic tracking of the slope instability evolution process. This makes it difficult to accurately predict the critical moment of instability and the remaining time before instability, resulting in a lack of quantitative basis for generating early warning commands. The real-time performance and accuracy of these warnings are ill-suited to the needs of preventing and controlling sudden highway slope instability. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, system, equipment, and medium for predicting the sudden instability risk of highway slopes that can effectively improve the safety of highway slope operation and reduce the losses caused by instability disasters, in response to the above-mentioned technical problems.

[0004] Firstly, this application provides a method for predicting the risk of sudden instability of highway slopes, including:

[0005] Real-time wind speed and direction data are acquired, and time-series filtering and instantaneous wind speed extraction are performed on the real-time wind speed and direction data to obtain smoothed internal pressure values ​​and surface wind thrust values.

[0006] Based on the internal pressure value and the surface wind thrust value, the slope stability safety factor and comprehensive disturbance intensity are obtained through finite element numerical simulation.

[0007] The overall disturbance intensity is correlated with the slope stability safety factor, and the current high-risk instability state of the slope is judged by threshold comparison, thus obtaining the record entries of high-risk slope instability events.

[0008] Based on the changing trends of stress and displacement fields under high-risk instability conditions, and combined with event record entries, the critical moment of slope instability is predicted, and the remaining time of slope instability is calculated to obtain real-time early warning instructions for slope instability.

[0009] In one embodiment, based on the internal pressure value and the surface wind thrust value, the slope stability safety factor and the comprehensive disturbance intensity are obtained through finite element numerical simulation, including:

[0010] A standardized multi-source input dataset is constructed based on internal pressure values ​​and surface wind thrust values.

[0011] The finite element numerical simulation method was used with a multi-source input dataset as the load input condition, internal pressure value as volume force and surface wind thrust value as surface load to perform numerical calculations on the slope, and obtain slope stress field distribution data and displacement field distribution data.

[0012] Data fusion technology is used to couple and integrate slope stress field distribution data and displacement field distribution data, extract the ratio of shear stress to shear strength at the potential sliding surface of the slope and the displacement increment of key points on the slope surface, and calculate and determine the slope stability safety factor.

[0013] Based on the combined effect of the slope stability safety factor and the internal pressure value and the surface wind thrust value, the comprehensive disturbance intensity is calculated through a preset coupled response model.

[0014] In one embodiment, the overall disturbance strength is calculated using the following formula:

[0015]

[0016] in, Indicates the overall disturbance intensity. This represents the coupling coefficient between internal pressure and surface wind thrust, with a value range of... According to the slope lithology, This represents the safety factor correction factor, with a range of values. Based on the engineering geological conditions of the slope, This represents the standardized internal pressure value of the slope. This represents the standardized wind thrust value on the slope surface. This represents the slope stability safety factor. , , It is in a critical state of instability. This represents the shear stress at the potential sliding surface of the slope. This represents the shear strength at the potential sliding surface of the slope. This represents a combined correction factor for internal pressure and wind load, with a range of values. According to the calibration of slope rock and soil mechanical parameters, This represents the displacement increment influence coefficient, with a value range of... Based on the characteristics of the potential sliding surface of the slope, This indicates the displacement increment of key points on the slope surface.

[0017] In one embodiment, the overall disturbance intensity is correlated with the slope stability safety factor, and a threshold comparison is used to determine the current high-risk instability state of the slope, resulting in a record of high-risk slope instability events, including:

[0018] A two-parameter coupled judgment model is constructed based on the slope stability safety factor and the comprehensive disturbance intensity.

[0019] Preset safety threshold Disturbance threshold Cooperative determination coefficient and collaborative threshold .

[0020] in, , Calibration was performed using slope engineering geological parameters and historical instability data. , Calibration is based on the mechanical properties of the slope rock and soil.

[0021] The safety factor was determined using a two-parameter coupled decision model. With safety critical threshold Comprehensive disturbance intensity With the critical threshold of disturbance Compare and judge to determine Is it less than or equal to? and Is it greater than or equal to? .

[0022] If the judgment result is and Then, the collaborative decision value is calculated through a two-parameter coupled decision model.

[0023] The formula for calculating the collaborative decision value is: Collaborative decision value D / K, This represents the preset collaborative decision coefficient.

[0024] The calculated collaboration determination value is compared with the preset collaboration threshold. Perform a comparison to determine whether the collaborative decision value is greater than or equal to .

[0025] If the collaborative determination value If the slope is in a high-risk instability state, a unique corresponding high-risk slope instability state identifier will be output.

[0026] Extract the spatial coordinates of the slope monitoring sensors and the monitoring timestamps corresponding to the high-risk status of slope instability.

[0027] Spatial location coordinates, monitoring timestamps, and collaborative judgment values ​​are linked, bound, and standardized to form structured high-risk slope instability event record entries.

[0028] Event log entries include a unique identifier, location information, time information, and risk quantification indicators.

[0029] In one embodiment, based on the stress field and displacement field variation trends under high-risk instability conditions, and combined with event record entries to predict the critical moment of slope instability, the remaining time for slope instability is calculated to obtain a real-time early warning command for slope instability, including:

[0030] To acquire real-time stress field and displacement field data under high-risk instability conditions.

[0031] The real-time stress field data was collected by stress sensors deployed on the slope; the displacement field data and the real-time stress field data were monitored simultaneously.

[0032] Based on real-time stress field data and displacement field data, time series analysis algorithms were used to fit the time series variation trends of stress field and displacement field, respectively.

[0033] Based on the established event record entries, a linear trend extrapolation algorithm is first used to extend the stress field time series change trend and the displacement field time series change trend to future time periods, thereby obtaining stress and displacement prediction sequences.

[0034] The real-time characteristic parameters in the stress and displacement prediction sequence are compared one by one with the critical thresholds for the transformation of historical high-risk conditions into instability in the event record entries. When the characteristic parameters at a certain moment simultaneously reach the critical threshold and the matching degree exceeds the preset matching threshold, the corresponding moment is determined as the critical moment of slope instability.

[0035] The time difference between the critical moment of slope instability and the current monitoring moment is compared with the preset instability warning time threshold. If the time difference exceeds the instability warning time threshold, the remaining time for slope instability is calculated.

[0036] Extract the remaining time of slope instability, the critical moment of slope instability, and the stress-displacement characteristic parameters corresponding to the critical moment of instability. After encapsulating the data in a preset structured data format and completing the integrity verification, generate a real-time early warning command for slope instability.

[0037] In one embodiment, the remaining time for slope instability is calculated using the following formula:

[0038]

[0039] in, Indicates the remaining time before slope instability. This indicates the critical moment of slope instability, which is when the characteristic parameters in the stress and displacement prediction sequences simultaneously reach the critical threshold and the actual matching degree is... Exceeding the preset matching threshold The corresponding timestamp, Indicates the current monitoring time of the slope. This represents the actual degree of matching between the characteristic parameters of the stress and displacement prediction sequence and the historical critical thresholds in the record entries of high-risk slope instability events. It is calculated by weighting the similarity after comparing each characteristic parameter. This indicates the preset matching threshold, with a range of values. It is calibrated based on the engineering geological conditions of the slope and historical high-risk event data.

[0040] Secondly, this application also provides a system for predicting the risk of sudden instability of highway slopes, the system comprising:

[0041] The wind field data processing module is used to acquire real-time wind speed and direction data, perform time series filtering on the real-time wind speed and direction data and extract instantaneous wind speed to obtain smoothed internal pressure values ​​and surface wind thrust values.

[0042] The finite element simulation module is used to obtain the slope stability safety factor and comprehensive disturbance intensity through finite element numerical simulation based on internal pressure values ​​and surface wind thrust values.

[0043] The instability risk assessment module is used to correlate and map the comprehensive disturbance intensity with the slope stability safety factor, and to determine the current high-risk instability state of the slope by threshold comparison, thereby obtaining high-risk instability event record entries for the slope.

[0044] The instability early warning generation module is used to predict the critical moment of slope instability based on the stress field and displacement field change trends under high-risk instability conditions, combined with event record entries, and calculate the remaining time of slope instability to obtain real-time early warning instructions for slope instability.

[0045] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0046] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned method.

[0047] The aforementioned method, system, computer equipment, and storage medium for predicting the sudden instability risk of highway slopes acquire real-time wind speed and direction data through wind field sensors deployed at pre-set monitoring points on the slope. To eliminate noise interference and ensure data accuracy, the real-time wind speed and direction data undergoes time-series filtering, and instantaneous wind speed parameters are extracted. Combined with the stress characteristics of the slope's soil and rock mass and the wind load mechanism, smoothed internal pressure and surface wind thrust values ​​are obtained through mechanical calculations, serving as core load input parameters for subsequent slope risk analysis. Based on the obtained internal pressure and surface wind thrust values, these are input as external load parameters into a pre-set finite element numerical simulation model of the slope. Combining the slope's soil and rock mechanical parameters, topographic and geological conditions, and other basic data, the slope stability safety factor and comprehensive disturbance intensity are obtained through finite element numerical simulation. The slope stability safety factor characterizes the slope's soil and rock mass's resistance to instability, while the comprehensive disturbance intensity characterizes the degree of disturbance of the slope under wind load. Subsequently, a safety threshold for the slope stability safety factor and a disturbance threshold for the comprehensive disturbance intensity are preset. The simulated comprehensive disturbance intensity is correlated with the slope stability safety factor. By comparing each with its corresponding critical threshold, it is determined whether the current slope is in a high-risk instability state. If it is determined to be in a high-risk instability state, the current slope load parameters, stability safety factor, comprehensive disturbance intensity, and determination time are recorded simultaneously, forming a standardized high-risk slope instability event record. Finally, real-time stress field data and displacement field data collected by slope monitoring sensors under the high-risk instability state are acquired. The time series change trend of the two is obtained by using a time series analysis algorithm. Combined with the aforementioned high-risk slope instability event record, the critical moment of slope instability is predicted by trend extrapolation and critical feature matching. The remaining time of slope instability is calculated using a preset calculation formula, thereby generating a real-time early warning command for slope instability carrying the remaining time of instability, the critical moment of instability, and corresponding characteristic parameters. This method for predicting the sudden instability risk of highway slopes realizes full-process quantitative analysis from load input to early warning output. It effectively solves the problems of insufficient consideration of the coupling effect between wind load and slope soil and rock mass, lack of dynamic risk assessment, and lack of quantitative basis for early warning in existing methods. By accurately processing wind speed and direction data to obtain load parameters, it uses finite element numerical simulation to ensure the accuracy of the calculation of stability safety factor and comprehensive disturbance intensity, and combines high-risk event record entries to improve the reliability of instability critical moment prediction. Finally, it generates accurate early warning instructions by quantifying the remaining time of instability, providing scientific and efficient technical support for the prevention and control of sudden instability of highway slopes. It can effectively improve the safety of highway slope operation and reduce the losses caused by instability disasters. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart illustrating a method for predicting the risk of sudden instability of highway slopes provided in an embodiment of the present invention;

[0050] Figure 2 The present invention provides a structural block diagram of a highway slope sudden instability risk prediction system. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0052] In one embodiment, such as Figure 1 As shown, this application provides a method for predicting the risk of sudden instability of highway slopes, which may include the following steps:

[0053] Step S101: Obtain real-time wind speed and direction data, perform time series filtering and instantaneous wind speed extraction on the real-time wind speed and direction data, and obtain smoothed internal pressure value and surface wind thrust value.

[0054] Specifically, real-time wind speed and direction data are acquired, and time-series filtering and instantaneous wind speed extraction are performed on the real-time wind speed and direction data to obtain smoothed internal pressure and surface wind thrust values. Wind field sensors deployed at pre-set monitoring points on the slope collect real-time wind speed and direction data for the area where the slope is located. Time-series filtering is used to remove random noise and abnormal fluctuations in the data to ensure data stability. Instantaneous wind speed extraction is used to capture the dynamic changes in wind speed. Combined with the slope's soil and rock mass stress model and wind load mechanism, the processed wind speed and direction data are converted into smoothed internal pressure and surface wind thrust values ​​of the slope through mechanical calculations.

[0055] Step S102: Based on the internal pressure value and the surface wind thrust value, the slope stability safety factor and comprehensive disturbance intensity are obtained through finite element numerical simulation.

[0056] Based on internal pressure and surface wind thrust values, the slope stability safety factor and comprehensive disturbance intensity are obtained through finite element numerical simulation. The obtained internal pressure and surface wind thrust values ​​are used as external load parameters and input into a pre-defined slope finite element numerical simulation model. This model, combined with basic data such as slope soil and rock mechanical parameters, topographic and geological conditions, and soil and rock structural characteristics, calculates the slope stability safety factor and comprehensive disturbance intensity through finite element numerical calculations. The slope stability safety factor characterizes the ability of the slope soil and rock mass to resist instability and failure, while the comprehensive disturbance intensity characterizes the degree of disturbance of the slope soil and rock mass under wind load. Both serve as core quantitative indicators for assessing slope instability risk.

[0057] Step S103: The comprehensive disturbance intensity is correlated and mapped with the slope stability safety factor. The current slope instability high-risk state is determined by threshold comparison, and the slope instability high-risk event record is obtained.

[0058] The overall disturbance intensity is correlated with the slope stability safety factor. Threshold comparisons are used to determine the current high-risk instability state of the slope, resulting in high-risk slope instability event records. Using the obtained overall disturbance intensity and slope stability safety factor as inputs, a correlation mapping relationship is established between the two. Preset safety thresholds for the slope stability safety factor and disturbance thresholds for the overall disturbance intensity. The two core quantitative indicators are compared with their corresponding thresholds. When the overall disturbance intensity reaches or exceeds the disturbance threshold, and the slope stability safety factor reaches or falls below the safety threshold, the current slope is determined to be in a high-risk instability state. Simultaneously, the internal pressure value, surface wind thrust value, slope stability safety factor, overall disturbance intensity, and the time of risk determination of the current slope are recorded, forming standardized high-risk slope instability event records.

[0059] Step S104: Based on the stress field and displacement field change trends under the high-risk instability state, and combined with the event record entries, predict the critical moment of slope instability, calculate the remaining time of slope instability, and obtain the real-time early warning command for slope instability.

[0060] Based on the stress and displacement field trends under high-risk instability conditions, and combined with event record entries, the critical moment of slope instability is predicted, and the remaining time for slope instability is calculated to obtain a real-time early warning command for slope instability. When a slope is determined to be in a high-risk instability state, real-time stress and displacement field data collected by slope monitoring sensors under this state are acquired, and time series analysis algorithms are used to fit the time series trends of both. Combined with the obtained high-risk slope instability event record entries, the trend is extended to future time periods using a linear trend extrapolation algorithm. Simultaneously, the extended stress and displacement prediction sequences are matched and compared with historical critical characteristic parameters in the event record entries to predict the critical moment of slope instability. Using a preset calculation formula, the time difference between the critical moment of slope instability and the current monitoring time is calculated to obtain the remaining time for slope instability. Based on this remaining time, a real-time early warning command for slope instability is generated, carrying the remaining time, the critical moment of instability, and the corresponding stress and displacement characteristic parameters, thus completing the real-time early warning of sudden slope instability risk.

[0061] The aforementioned method for predicting the risk of sudden instability of highway slopes acquires real-time wind speed and direction data from wind field sensors at pre-set monitoring points on the slope. After time-series filtering to remove noise and extracting instantaneous wind speed parameters, and combining this with the stress characteristics of the slope's soil and rock mass and wind load mechanisms, smoothed internal pressure and surface wind thrust values ​​are obtained. These load parameters are input into a finite element numerical simulation model of the slope. Combined with basic data such as slope soil and rock mechanical parameters and topographic and geological conditions, the slope stability safety factor and comprehensive disturbance intensity are calculated. By setting a critical threshold, the two are compared to determine a high-risk state of slope instability, and relevant parameters are simultaneously recorded to form standardized high-risk event record entries. Real-time stress and displacement field data under high-risk conditions are acquired, their time-series trends are fitted, and combined with the high-risk event record entries, the critical moment of instability is predicted through trend extrapolation and critical feature matching. The remaining time of instability is calculated, and a real-time early warning command carrying core parameters is generated. This method realizes full-process quantitative analysis from load input to early warning output, effectively solving the problems of insufficient consideration of the coupling effect between wind field and slope, lack of dynamic risk assessment, and lack of quantitative basis for early warning in existing methods. Through precise data processing, simulation calculation and trend prediction, it improves the accuracy and reliability of early warning, provides scientific and technological support for the prevention and control of highway slope instability, improves the safety of highway operation and reduces disaster losses.

[0062] In one embodiment, the slope stability safety factor and comprehensive disturbance intensity are obtained through finite element numerical simulation based on internal pressure and surface wind thrust values, which may include the following steps:

[0063] Step S201: Construct a standardized multi-source input dataset based on the internal pressure value and the surface wind thrust value.

[0064] Step S202: Using the finite element numerical simulation method with a multi-source input dataset as the load input condition, the internal pressure value is used as the volume force and the surface wind thrust value is used as the surface load to perform numerical calculations on the slope, and obtain the slope stress field distribution data and displacement field distribution data.

[0065] Preferably, the finite element numerical simulation method is used with a multi-source input dataset as the load input condition. Internal pressure values ​​are used as volume forces, and surface wind thrust values ​​are used as surface loads. Numerical calculations are performed on the slope to obtain slope stress field and displacement field distribution data. First, based on the actual topographic and geological conditions and soil and rock mechanical parameters of the slope, a finite element numerical model consistent with the actual slope working conditions is constructed. The computational domain, mesh generation specifications, and boundary constraints of the model are defined, providing a basic framework for numerical calculations. The constructed standardized multi-source input dataset is used as the overall load input condition. Internal pressure values, as volume forces, are uniformly applied throughout the entire interior of the slope's soil and rock mass, conforming to the internal stress characteristics of the slope induced by wind loads. Surface wind thrust values, as surface loads, are uniformly applied throughout the entire slope surface, matching the action of wind loads on the slope surface. Iterative calculations are performed using finite element numerical simulation software to simulate the force balance process and deformation response process of the slope under this combined load, eliminating calculation biases. After the calculation is completed, the slope stress field distribution data and displacement field distribution data are output in the whole domain. The stress field distribution data includes the spatial distribution information of parameters such as principal stress and shear stress of each rock and soil unit, and the displacement field distribution data includes the spatial distribution information of parameters such as horizontal displacement and vertical displacement of each rock and soil unit.

[0066] Step S203: Using data fusion technology, the slope stress field distribution data and displacement field distribution data are coupled and integrated to extract the ratio of shear stress to shear strength at the potential sliding surface of the slope and the displacement increment of key points on the slope surface, and to calculate and determine the slope stability safety factor.

[0067] Step S204: Based on the slope stability safety factor combined with the coupled superposition effect of internal pressure value and surface wind thrust value, the comprehensive disturbance intensity is calculated through a preset coupled response model.

[0068] Specifically, based on internal pressure and surface wind thrust values, a standardized multi-source input dataset is constructed, clarifying the load parameter types and specifications, and unifying data format and accuracy. Using the finite element method (FEM), the constructed multi-source input dataset is used as the load input condition. Internal pressure is applied as a volume force within the slope's soil and rock mass, while surface wind thrust is applied as a surface load on the slope surface. Numerical calculations simulate the stress and deformation state of the slope under this load condition, obtaining complete slope stress and displacement field distribution data. Data fusion technology is employed to couple and integrate the obtained slope stress and displacement field distribution data, eliminating data redundancy and bias. Two core parameters are accurately extracted: the ratio of shear stress to shear strength at the potential sliding surface of the slope and the displacement increment at key points on the slope surface. These two parameters are then used to determine the slope stability safety factor through mechanical calculations, achieving a quantitative characterization of the slope's resistance to instability. Based on the calculated slope stability safety factor, and combined with the coupled superposition effect of internal pressure value and surface wind thrust value, the three are used as input parameters and substituted into the preset coupled response model. The comprehensive disturbance intensity is obtained through model calculation, thereby realizing the quantitative characterization of the slope disturbance degree under wind load.

[0069] This embodiment ensures the standardization and uniformity of load input parameters by constructing a standardized multi-source input dataset. During the finite element numerical simulation, internal pressure and surface wind thrust are applied as volumetric forces and surface loads, respectively, closely reflecting the actual stress state of the slope and effectively improving the accuracy of stress and displacement field distribution data calculations. Data fusion technology is used to couple and integrate stress and displacement field data, effectively avoiding the limitations of single data dimensions. The extracted core parameters accurately reflect the potential risks of slope instability, ensuring the scientific validity of the slope stability safety factor calculation. The calculation of comprehensive disturbance intensity combines the coupled superposition effect with a pre-set coupled response model, taking into account both the slope's anti-instability capability and the effect of wind load disturbance. This achieves the coordinated calculation of two core quantitative indicators, effectively improving the reliability and relevance of subsequent risk analysis and providing solid technical support for highway slope instability prevention and control.

[0070] In one embodiment, the overall disturbance strength can be calculated using the following formula:

[0071]

[0072] in, Indicates the overall disturbance intensity. This represents the coupling coefficient between internal pressure and surface wind thrust, with a value range of... According to the slope lithology, This represents the safety factor correction factor, with a range of values. Based on the engineering geological conditions of the slope, This represents the standardized internal pressure value of the slope. This represents the standardized wind thrust value on the slope surface. This represents the slope stability safety factor. , , It is in a critical state of instability. This represents the shear stress at the potential sliding surface of the slope. This represents the shear strength at the potential sliding surface of the slope. This represents a combined correction factor for internal pressure and wind load, with a range of values. According to the calibration of slope rock and soil mechanical parameters, This represents the displacement increment influence coefficient, with a value range of... Based on the characteristics of the potential sliding surface of the slope, This indicates the displacement increment of key points on the slope surface.

[0073] This embodiment integrates the disturbance intensity calculation formula, using standardized internal pressure values, surface wind thrust values, and slope stability safety factors as core inputs, and employs a coupling coefficient... This reflects the combined effect of the two factors, combined with the safety factor correction factor. Optimize calculation accuracy; all correction coefficients are calibrated based on parameters such as actual slope lithology and engineering geological conditions, closely reflecting actual slope working conditions. Simultaneously, the slope stability safety factor... The calculation integrates core parameters such as shear stress, shear strength, and displacement increment at key points on the slope's potential sliding surface, taking into account both the slope's stress and deformation characteristics. It accurately reflects the synergistic relationship between the slope's resistance to instability and the effects of wind load disturbance. The comprehensive disturbance intensity calculated using this formula can comprehensively and accurately quantify the degree of slope disturbance under wind load, solving the problems of existing calculation methods neglecting multi-parameter coupling effects and lacking accuracy.

[0074] In one embodiment, the overall disturbance intensity is correlated with the slope stability safety factor, and the current high-risk instability state of the slope is determined by threshold comparison to obtain a high-risk slope instability event record. This may include the following steps:

[0075] Step S301: Based on the slope stability safety factor and the comprehensive disturbance intensity, construct a two-parameter coupled judgment model.

[0076] Step S302: Preset a safety threshold Disturbance threshold Cooperative determination coefficient and collaborative threshold .

[0077] in, , Calibration was performed using slope engineering geological parameters and historical instability data. , Calibration is based on the mechanical properties of the slope rock and soil.

[0078] Step S303: The safety factor is determined using a two-parameter coupled decision model. With safety critical threshold Comprehensive disturbance intensity With the critical threshold of disturbance Compare and judge to determine Is it less than or equal to? and Is it greater than or equal to? .

[0079] Step S304, if the determination result is and Then, the collaborative decision value is calculated through a two-parameter coupled decision model.

[0080] The formula for calculating the collaborative decision value is: Collaborative Decision Value D / K, This represents the preset collaborative decision coefficient.

[0081] Step S305: Compare the calculated collaboration determination value with the preset collaboration threshold. Perform a comparison to determine whether the collaborative decision value is greater than or equal to .

[0082] Step S306, if the collaborative determination value If the slope is in a high-risk instability state, a unique corresponding high-risk slope instability state identifier will be output.

[0083] Step S307: Extract the spatial location coordinates and monitoring timestamps of the slope monitoring sensors corresponding to the high-risk status of slope instability.

[0084] Step S308 involves associating and binding spatial location coordinates, monitoring timestamps, and collaborative judgment values, and standardizing and encapsulating them to form structured record entries for high-risk slope instability events.

[0085] The event log entries include a unique identifier, location information, time information, and risk quantification indicators.

[0086] Specifically, a two-parameter coupled judgment model is constructed based on the slope stability safety factor and the comprehensive disturbance intensity, serving as the core model for determining the high-risk state of slope instability. Simultaneously, the model presets the required safety critical threshold, disturbance critical threshold, collaborative judgment coefficient, and collaborative threshold. The safety critical threshold and disturbance critical threshold are calibrated based on slope engineering geological parameters and historical instability data, while the collaborative judgment coefficient and collaborative threshold are calibrated based on the slope's soil and rock mechanical properties. Through the constructed two-parameter coupled judgment model, the calculated slope stability safety factor is compared with the safety critical threshold, and the comprehensive disturbance intensity is compared with the disturbance critical threshold to determine if the judgment conditions are met. If the judgment result meets the conditions, the corresponding collaborative judgment value is calculated using the two-parameter coupled judgment model according to the formula. The calculated collaborative judgment value is then compared again with the preset collaborative threshold to determine if the collaborative judgment value is greater than or equal to the preset threshold. If it is, the slope is directly determined to be in a high-risk instability state, and a unique high-risk slope instability state identifier corresponding to this state is output. Based on this unique identifier, the spatial location coordinates of the slope monitoring sensors and the corresponding monitoring timestamps are extracted. The spatial location coordinates, monitoring timestamps and the previously calculated collaborative judgment values ​​are then linked and bound. At the same time, the bound multi-dimensional data is standardized and encapsulated to form a structured record of high-risk slope instability events. This record uniformly includes the unique identifier of the high-risk instability state, slope monitoring location information, risk judgment time information and the core risk quantification indicator of the collaborative judgment value.

[0087] This embodiment constructs a dual-parameter coupled judgment model with the slope stability safety factor and comprehensive disturbance intensity as the core, breaking through the limitations of single-parameter judgment of slope instability risk. It realizes the synergistic judgment of slope instability resistance and disturbance degree, making the risk judgment results more consistent with the coupling characteristics of actual slope stress and deformation. All thresholds and coefficients required by the model are calibrated based on slope engineering geological parameters, historical instability data, and soil mechanical properties, without empirical settings, ensuring the scientific and reasonable nature of the judgment criteria. Through the two-layer judgment logic of "initial judgment of dual-parameter thresholds + re-judgment of synergistic judgment values", high-risk states of slope instability are screened layer by layer, effectively reducing the probability of misjudgment and omission caused by single threshold comparison, and improving the accuracy of high-risk instability state judgment. At the same time, the synergistic judgment value quantifies the coupling relationship of the two parameters through formula, realizing quantitative judgment of slope instability risk, rather than qualitative judgment. In addition, by using unique identifiers to associate monitoring location coordinates, timestamps, and risk quantification indicators, and by standardizing and encapsulating them into structured event record entries, the standardized storage and traceability of high-risk information on slope instability are achieved, which also facilitates the subsequent retrieval, analysis, and reuse of high-risk event data.

[0088] In one embodiment, based on the changing trends of the stress field and displacement field under high-risk instability conditions, and combined with event record entries to predict the critical moment of slope instability, the remaining time of slope instability is calculated to obtain a real-time early warning command for slope instability. This may include the following steps:

[0089] Step S401: Obtain real-time stress field data and displacement field data under high-risk instability conditions.

[0090] Among them, the real-time stress field data is collected by stress sensors deployed on the slope; the displacement field data and the real-time stress field data are monitored simultaneously.

[0091] Step S402: Based on real-time stress field data and displacement field data, time series analysis algorithms are used to fit and obtain the time series variation trends of stress field and displacement field, respectively.

[0092] Step S403: Based on the established event record entries, a linear trend extrapolation algorithm is first used to extend the stress field time series change trend and the displacement field time series change trend to the future time period, thereby obtaining the stress and displacement prediction sequences.

[0093] Step S404: The real-time characteristic parameters in the stress and displacement prediction sequence are compared one by one with the critical thresholds for the transformation of historical high-risk working conditions into instability in the event record entries. When the characteristic parameters at a certain moment simultaneously reach the critical threshold and the matching degree exceeds the preset matching threshold, the corresponding moment is determined as the critical moment of slope instability.

[0094] Step S405: Compare the time difference between the critical moment of slope instability and the current monitoring moment with the preset instability warning time threshold. If the time difference exceeds the instability warning time threshold, calculate the remaining time for slope instability.

[0095] Step S406: Extract the remaining time of slope instability, the critical moment of slope instability, and the stress-displacement characteristic parameters corresponding to the critical moment of instability. After encapsulating the data in a preset structured data format and completing the integrity verification, generate a real-time early warning command for slope instability.

[0096] Specifically, real-time stress and displacement data are acquired under high-risk slope instability conditions. The real-time stress data is collected by stress sensors deployed at pre-defined monitoring points on the slope, while the displacement data is collected from concurrent monitoring data acquired during the same period, ensuring temporal consistency between the two types of data and providing a reliable data foundation for subsequent trend analysis. Based on the acquired real-time stress and displacement data, time series analysis algorithms are used to fit the two types of data respectively, obtaining the time series trends of stress and displacement, clearly characterizing the dynamic evolution of stress and displacement over time. Combining this with previously established records of high-risk slope instability events, a linear trend extrapolation algorithm is first used to extend the time series trends of stress and displacement to future time periods, generating stress and displacement prediction sequences to predict the future evolution of slope stress and displacement. The real-time characteristic parameters in the stress and displacement prediction sequence are compared one by one with the critical thresholds for the transformation of historical high-risk conditions into instability in the record of high-risk slope instability events. The actual matching degree is calculated. When the characteristic parameters at a certain moment simultaneously reach the historical critical threshold and the matching degree exceeds the preset matching threshold, that moment is determined as the critical moment of slope instability. The time difference between the determined critical moment of slope instability and the current monitoring moment is calculated and compared with the preset instability warning time threshold. If the time difference exceeds the instability warning time threshold, the remaining time of slope instability is calculated using a preset calculation formula. The remaining time of slope instability, the critical moment of slope instability, and the stress and displacement characteristic parameters corresponding to the critical moment of instability are extracted. The above parameters are encapsulated according to the preset structured data format, and the data integrity is verified. After confirming that all core parameters are complete and the format is normal, a real-time warning command for slope instability is generated, providing clear command support for slope instability prevention and control.

[0097] This embodiment uses real-time stress and displacement field data collected concurrently to ensure the consistency and accuracy of trend analysis data. The changing trends obtained through time series analysis algorithms can accurately capture the dynamic evolution characteristics of slope stress and displacement. Combined with historical high-risk event records, a linear trend extrapolation algorithm is used to extend trends to future periods, balancing the reference value of historical data with the specificities of current conditions, thus improving the reliability of instability critical moment prediction. By comparing feature parameters with historical critical thresholds one by one and verifying the matching degree, the accuracy of instability critical moment determination is doubled, effectively reducing the probability of misjudgment. The remaining instability time is calculated only when the time difference exceeds the instability warning time threshold, avoiding invalid calculations and improving process efficiency. During the warning command generation process, structured encapsulation and integrity verification ensure the completeness and standardization of the parameters carried in the command. The remaining time, critical moment, and stress-displacement feature parameters included in the command provide accurate and comprehensive quantitative basis for subsequent emergency response, solving the problems of incomplete and unspecific parameters in existing warning commands. This improves the accuracy and timeliness of real-time slope instability warnings, ensuring highway operation safety.

[0098] In one embodiment, the remaining time for slope instability can be calculated using the following formula:

[0099]

[0100] in, Indicates the remaining time before slope instability. This indicates the critical moment of slope instability, which is when the characteristic parameters in the stress and displacement prediction sequences simultaneously reach the critical threshold and the actual matching degree is... Exceeding the preset matching threshold The corresponding timestamp, Indicates the current monitoring time of the slope. This represents the actual degree of matching between the characteristic parameters of the stress and displacement prediction sequence and the historical critical thresholds in the record entries of high-risk slope instability events. It is calculated by weighting the similarity after comparing each characteristic parameter. This indicates the preset matching threshold, with a range of values. It is calibrated based on the engineering geological conditions of the slope and historical high-risk event data.

[0101] The formula for calculating the remaining time of slope instability in this embodiment is based on the time difference between the critical moment of instability and the current monitoring moment. It introduces the ratio of the actual matching degree to a preset matching threshold as a correction term, overcoming the limitations of simply calculating the time difference in conventional methods. This achieves a linkage between the reliability of remaining time calculation and critical moment determination. The higher the matching degree, the closer the correction term is to 1, and the more accurate the remaining time calculation result, effectively avoiding miscalculation of the remaining time due to insufficient matching degree. Simultaneously, Based on the actual engineering geological conditions and historical data of the slope, and tailored to the different working conditions of various slopes, the applicability of the formula and the reliability of the calculation results are improved. The remaining time for slope instability calculated by this formula is precisely quantified and based on sufficient evidence, providing core quantitative parameters for the generation of subsequent real-time early warning commands for slope instability. This effectively solves the problem of the lack of clear time quantification basis in existing early warnings, supports the pertinence and timeliness of early warning commands, provides accurate time reference for emergency response to sudden instability of highway slopes, and further enhances the scientific and efficient nature of slope instability risk prevention and control.

[0102] In one embodiment, such as Figure 2 As shown, this application also provides a highway slope sudden instability risk prediction system, which may include:

[0103] The wind field data processing module 501 is used to acquire real-time wind speed and direction data, perform time series filtering on the real-time wind speed and direction data and extract instantaneous wind speed to obtain smoothed internal pressure values ​​and surface wind thrust values.

[0104] The finite element simulation module 502 is used to obtain the slope stability safety factor and comprehensive disturbance intensity through finite element numerical simulation based on the internal pressure value and the surface wind thrust value.

[0105] The instability risk assessment module 503 is used to correlate and map the comprehensive disturbance intensity with the slope stability safety factor, and to determine the current high-risk instability state of the slope by threshold comparison, thereby obtaining the record entries of high-risk slope instability events.

[0106] The instability early warning generation module 504 is used to predict the critical moment of slope instability based on the stress field and displacement field change trends under high-risk instability conditions, combined with event record entries, and calculate the remaining time of slope instability to obtain real-time early warning instructions for slope instability.

[0107] The aforementioned highway slope sudden instability risk prediction system comprises four collaborative functional modules that work together to achieve accurate prediction and real-time early warning of slope instability risks. The wind field data processing module acquires real-time wind speed and direction data for the slope area, performs time-series filtering on this data to remove noise interference, extracts instantaneous wind speed parameters, and combines this with the stress characteristics of the slope's soil and rock mass through mechanical calculations to obtain smoothed internal pressure and surface wind thrust values, which serve as core input parameters for subsequent modules. The finite element simulation module receives the internal pressure and surface wind thrust values ​​output by the wind field data processing module, uses them as load input conditions, and employs finite element numerical simulation to calculate the slope stability safety factor and comprehensive disturbance intensity, providing a quantitative basis for assessing slope instability risks. The instability risk assessment module receives the comprehensive disturbance intensity and slope stability safety factor output by the finite element simulation module, correlates and maps these two core quantitative indicators, and determines whether the current slope is in a high-risk instability state by comparing it with a preset critical threshold. If it is determined to be in a high-risk instability state, a standardized high-risk slope instability event record entry is generated. The instability early warning generation module receives the high-risk instability state signal and event record entry output by the instability risk assessment module, acquires real-time stress field and displacement field data under this high-risk instability state and fits their time series change trends, predicts the critical moment of slope instability by combining the high-risk slope instability event record entry, calculates the remaining time of slope instability using a preset calculation formula, and finally generates a real-time slope instability early warning command.

[0108] This embodiment features four modules working in synergy to automate the entire process from raw wind field data acquisition and processing to core parameter simulation calculations, risk assessment, and early warning generation, ensuring a closed-loop data flow and efficient transmission. The wind field data processing module guarantees the accuracy of input load parameters, providing a reliable foundation for subsequent simulation calculations. The finite element simulation module ensures the scientific validity and reliability of the calculation of slope stability safety factors and comprehensive disturbance intensity through standardized numerical calculations. The instability risk assessment module improves the accuracy of identifying high-risk slope instability states through dual-parameter correlation mapping and threshold comparison, avoiding misjudgments and omissions; the generated event log entries provide a complete historical reference for subsequent early warnings. The instability early warning generation module combines real-time trends and historical data to accurately calculate the critical moment of instability and the remaining time of instability, ensuring the timeliness and relevance of early warning commands. The overall module design closely matches the actual working conditions of highway slopes, effectively solving the problems of module disconnect, low data utilization, and insufficient early warning accuracy in existing systems. It significantly improves the efficiency and reliability of predicting sudden instability risks of highway slopes, providing efficient and comprehensive technical support for the safe operation and control of highway slopes.

[0109] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0110] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method for predicting the sudden instability risk of a highway slope as described above.

[0111] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0112] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0113] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A method for predicting the risk of sudden instability of highway slopes, characterized in that, The method includes: Real-time wind speed and direction data are acquired, and time-series filtering and instantaneous wind speed extraction are performed on the real-time wind speed and direction data to obtain smoothed internal pressure values ​​and surface wind thrust values. Based on the internal pressure and surface wind thrust values, the slope stability safety factor is obtained through finite element numerical simulation. and overall disturbance intensity ; The combined disturbance intensity With the slope stability safety factor Perform correlation mapping, determine the current high-risk instability state of the slope by threshold comparison, and obtain the record entries of high-risk slope instability events; Based on the stress field and displacement field change trends under the high-risk instability state, combined with the event record entries, the critical moment of slope instability is predicted, and the remaining time of slope instability is calculated to obtain a real-time early warning instruction for slope instability. The slope stability safety factor is obtained through finite element numerical simulation based on the internal pressure value and the surface wind thrust value. and overall disturbance intensity ,include: A standardized multi-source input dataset is constructed based on the internal pressure value and the surface wind thrust value; Using the finite element numerical simulation method with the multi-source input dataset as the load input condition, the internal pressure value as the volume force and the surface wind thrust value as the surface load, numerical calculations are performed on the slope to obtain slope stress field distribution data and displacement field distribution data. Data fusion technology is used to couple and integrate the slope stress field distribution data and the displacement field distribution data, extract the ratio of shear stress to shear strength at the potential sliding surface of the slope and the displacement increment of key points on the slope surface, and calculate and determine the slope stability safety factor. Based on the slope stability safety factor combined with the coupled superposition effect of the internal pressure value and the surface wind thrust value, the comprehensive disturbance intensity is calculated through a preset coupled response model. Among them, the comprehensive disturbance intensity It is calculated using the following formula: ； in, Indicates the overall disturbance intensity. This represents the coupling coefficient between internal pressure and surface wind thrust, calibrated based on the slope lithology. This represents the safety factor correction factor, which is determined based on the engineering geological conditions of the slope. This represents the standardized internal pressure value of the slope. This represents the standardized wind thrust value on the slope surface. This represents the slope stability safety factor. , , This is a critical state of instability. This represents the shear stress at the potential sliding surface of the slope. This represents the shear strength at the potential sliding surface of the slope. This represents a comprehensive correction factor for internal pressure and wind load, calibrated based on the slope's soil and rock mechanical parameters. This represents the displacement increment influence coefficient, calibrated based on the characteristics of the potential sliding surface of the slope. This indicates the displacement increment of key points on the slope surface.

2. The method according to claim 1, characterized in that, The overall disturbance intensity With the slope stability safety factor A correlation mapping is performed, and the current slope instability high-risk state is determined by threshold comparison, resulting in slope instability high-risk event record entries, including: Based on the slope stability safety factor and the combined disturbance intensity Construct a two-parameter coupled decision model; Preset safety threshold Disturbance threshold Cooperative determination coefficient and collaborative threshold ; in, , Calibration was performed using slope engineering geological parameters and historical instability data. , Calibrated based on the mechanical properties of the slope's rock and soil; The slope stability safety factor is determined using the two-parameter coupled judgment model. With the aforementioned safety threshold The overall disturbance intensity With the aforementioned perturbation critical threshold Compare and judge to determine Is it less than or equal to? and Is it greater than or equal to? ; If the judgment result is and Then, the collaborative judgment value is calculated through the two-parameter coupling judgment model; The formula for calculating the collaborative determination value is: Collaborative Determination Value D / K, This represents the preset collaborative decision coefficient; The calculated collaboration determination value is compared with the preset collaboration threshold. The comparison is performed to determine whether the collaborative determination value is greater than or equal to... ; If the collaborative determination value If the slope is in a high-risk state of instability, a unique corresponding high-risk slope instability status identifier will be output. Extract the spatial coordinates of the slope monitoring sensor deployment and the monitoring timestamps corresponding to the high-risk slope instability status identifier; The spatial location coordinates, monitoring timestamps, and collaborative judgment values ​​are associated, bound, and standardized and encapsulated to form a structured record of high-risk slope instability events. The event log entries include a unique identifier, location information, time information, and risk quantification indicators.

3. The method according to claim 1, characterized in that, The method, based on the stress field and displacement field variation trends under the high-risk instability state, combined with the event record entries to predict the critical moment of slope instability, calculates the remaining time of slope instability to obtain a real-time early warning command for slope instability, including: Acquire real-time stress field and displacement field data under the aforementioned high-risk instability state; The real-time stress field data is collected by stress sensors deployed on the slope; the displacement field data and the real-time stress field data are monitored simultaneously. Based on the real-time stress field data and displacement field data, time series analysis algorithms are used to fit the time series variation trends of the stress field and displacement field respectively. Based on the established event record entries, a linear trend extrapolation algorithm is first used to extend the stress field time series change trend and the displacement field time series change trend to future time periods, thereby obtaining stress and displacement prediction sequences. The real-time feature parameters in the stress and displacement prediction sequence are compared one by one with the critical thresholds for the transformation of historical high-risk working conditions into instability in the event record entries. When the feature parameters at a certain moment simultaneously reach the critical threshold and the matching degree exceeds the preset matching threshold, the corresponding moment is determined as the critical moment of slope instability. The time difference between the critical moment of slope instability and the current monitoring moment is compared with the preset instability warning time threshold. If the time difference exceeds the instability warning time threshold, the remaining time of slope instability is calculated. The remaining time of slope instability, the critical moment of slope instability, and the stress-displacement characteristic parameters corresponding to the critical moment of instability are extracted, encapsulated in a preset structured data format, and after integrity verification is completed, a real-time early warning command for slope instability is generated.

4. The method according to claim 3, characterized in that, The remaining time for slope instability is calculated using the following formula: ； in, Indicates the remaining time before slope instability. This indicates the critical moment of slope instability, which is when the characteristic parameters in the stress and displacement prediction sequences simultaneously reach the critical threshold and the actual matching degree is... Exceeding the preset matching threshold The corresponding timestamp, Indicates the current monitoring time of the slope. This represents the actual degree of matching between the characteristic parameters of the stress and displacement prediction sequence and the historical critical thresholds in the record entries of high-risk slope instability events. It is calculated by weighting the similarity after comparing each characteristic parameter. This indicates the preset matching threshold, with a range of values. It is calibrated based on the engineering geological conditions of the slope and historical high-risk event data.

5. A system for predicting the risk of sudden instability of highway slopes, characterized in that, The system includes: The wind field data processing module is used to acquire real-time wind speed and direction data, perform time series filtering and instantaneous wind speed extraction on the real-time wind speed and direction data, and obtain smoothed internal pressure value and surface wind thrust value. The finite element simulation module is used to obtain the slope stability safety factor through finite element numerical simulation based on the internal pressure value and the surface wind thrust value. and overall disturbance intensity The slope stability safety factor is obtained through finite element numerical simulation based on the internal pressure value and the surface wind thrust value. and overall disturbance intensity ,include: A standardized multi-source input dataset is constructed based on the internal pressure value and the surface wind thrust value; Using the finite element numerical simulation method with the multi-source input dataset as the load input condition, the internal pressure value as the volume force and the surface wind thrust value as the surface load, numerical calculations are performed on the slope to obtain slope stress field distribution data and displacement field distribution data. Data fusion technology is used to couple and integrate the slope stress field distribution data and the displacement field distribution data, extract the ratio of shear stress to shear strength at the potential sliding surface of the slope and the displacement increment of key points on the slope surface, and calculate and determine the slope stability safety factor. Based on the slope stability safety factor combined with the coupled superposition effect of the internal pressure value and the surface wind thrust value, the comprehensive disturbance intensity is calculated through a preset coupled response model. Among them, the comprehensive disturbance intensity It is calculated using the following formula: ； in, Indicates the overall disturbance intensity. This represents the coupling coefficient between internal pressure and surface wind thrust, calibrated based on the slope lithology. This represents the safety factor correction factor, which is determined based on the engineering geological conditions of the slope. This represents the standardized internal pressure value of the slope. This represents the standardized wind thrust value on the slope surface. This represents the slope stability safety factor. , , This is a critical state of instability. This represents the shear stress at the potential sliding surface of the slope. This represents the shear strength at the potential sliding surface of the slope. This represents a comprehensive correction factor for internal pressure and wind load, calibrated based on the slope's soil and rock mechanical parameters. This represents the displacement increment influence coefficient, calibrated based on the characteristics of the potential sliding surface of the slope. This indicates the displacement increment of key points on the slope surface; The instability risk determination module is used to correlate and map the comprehensive disturbance intensity with the slope stability safety factor, determine the current high-risk instability state of the slope through threshold comparison, and obtain the high-risk instability event record entry of the slope. The instability early warning generation module is used to predict the critical moment of slope instability based on the stress field and displacement field change trends under the high-risk instability state, combined with the event record entries, and calculate the remaining time of slope instability to obtain a real-time early warning command for slope instability.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images