Slope stability analysis method and system based on dynamic monitoring data

Abstract

The invention relates to the field of slope safety monitoring, in particular to a slope stability analysis method and system based on dynamic monitoring data. The invention discloses a slope stability analysis system based on dynamic monitoring data. The slope stability analysis system comprises a dynamic monitoring data acquisition module, a slope state judgment module and a slope collapse risk prediction module. According to the method, the maximum temperature difference value and the rainfall of the target slope area are counted, and when each environment monitoring period starts, early warning threshold values of part of monitoring parameters in each data set are adjusted in a targeted mode; the dynamic adjustment mechanism fully considers the influence of environmental factors on the slope stability monitoring parameters, so that the early warning threshold value is closer to the actual working condition, the accuracy and reliability of slope stability monitoring are effectively improved, the problem of false alarm or missing alarm caused by a fixed threshold value is avoided, and a more accurate monitoring basis is provided for slope safety protection.

Description

Technical Field

[0001] The invention relates to the field of slope safety monitoring, and in particular to a slope stability analysis method and system based on dynamic monitoring data. Background Art

[0002] Slope stability analysis is a key link in geological disaster prevention and engineering construction, and its results are directly related to the safety of people's lives and property and the stable operation of infrastructure. Traditional slope stability analysis methods mainly rely on static geological survey data and limited monitoring information. This method has many limitations when facing complex and changeable natural environments and engineering conditions.

[0003] With the continuous advancement of science and technology, slope monitoring technology has been significantly improved, and a variety of monitoring methods have emerged, which can obtain real-time slope displacement, stress, hydrology and other data; however, these monitoring data are often scattered and complex, lacking effective integration and analysis methods, and it is difficult to fully exert their value in slope stability assessment; at the same time, environmental factors (such as temperature changes and rainfall, etc.) have an impact on slope stability that cannot be ignored, but traditional methods find it difficult to fully incorporate these factors into the analysis system, resulting in key parameters such as warning thresholds being unable to be dynamically adjusted according to actual environmental conditions, reducing the accuracy and reliability of the monitoring results.

[0004] In addition, slope stability analysis not only needs to pay attention to the current status, but also needs to predict future risks; the existing technology has deficiencies in multi-source data fusion and in-depth analysis, and it is difficult to accurately grasp the complex relationship between each monitoring data group and slope collapse, and cannot provide strong support for risk prediction; in order to solve the above problems, the present invention proposes a slope stability analysis method and system based on dynamic monitoring data. Summary of the invention

[0005] The present invention makes targeted adjustments to the warning thresholds of some monitoring parameters in each data group at the beginning of each environmental monitoring cycle by statistically analyzing the maximum temperature difference and rainfall in the target slope area. This dynamic adjustment mechanism fully considers the impact of environmental factors on slope stability monitoring parameters, makes the warning thresholds more in line with actual working conditions, effectively improves the accuracy and reliability of slope stability monitoring, avoids the problem of false alarms or missed alarms caused by fixed thresholds, and provides a more accurate monitoring basis for slope safety protection.

[0006] A slope stability analysis method and system based on dynamic monitoring data, comprising: At the current monitoring time point, the first slope data group, the second slope data group, the third slope data group and the fourth slope data group of the target slope area are collected; the first slope data group includes surface horizontal displacement, surface vertical displacement and deep layer displacement; the second slope data group includes acoustic emission energy and microseismic wave propagation time difference; the third slope data group includes rock surface load stress and stress distribution gradient; the fourth slope data group includes pore water pressure and permeability rate; Set the environmental monitoring cycle. At the beginning of the current environmental monitoring cycle, calculate the maximum temperature difference of the target slope area in the last 12 hours, obtain the rainfall in the previous environmental monitoring cycle, and then adjust the warning thresholds of some monitoring parameters in each data group; then, in the current environmental monitoring cycle, determine whether each monitoring parameter obtained meets the corresponding adjusted warning thresholds. If so, no operation is performed; if not, the warning response measures are executed; Calculate the correlation between each data group and slope collapse, and then calculate the impact weight of each data group; at the beginning of the current environmental monitoring cycle, apply the slope collapse risk prediction model to obtain the slope collapse risk prediction results; apply the slope collapse risk prediction results to implement corresponding slope collapse prevention measures.

[0007] Preferably, the warning thresholds of some monitoring parameters in each data group are adjusted, and the specific operations are as follows: All monitoring parameters for each data set , =1, 2, …, 9; to Corresponding to surface horizontal displacement, surface vertical displacement, deep layer displacement, acoustic emission energy, microseismic wave propagation time difference, rock surface load stress, stress distribution gradient, pore water pressure and permeability rate; setting each monitoring parameter Conventional warning thresholds ; The maximum temperature difference obtained based on the current environmental monitoring cycle and rainfall , for the surface horizontal displacement , using the formula Calculate the surface horizontal displacement Adjusted warning threshold ;in, is the dynamic factor of thermal expansion of surface displacement; Rock surface load stress , using the formula Calculate and obtain the rock surface load stress Adjusted warning threshold ;in, is the surface stress temperature correction coefficient; For stress distribution gradient , using the formula Calculate the stress distribution gradient Adjusted warning threshold ;in, is the temperature gradient correction factor; For deep layer displacement , using the formula Calculate the displacement of deep layers Adjusted warning threshold ;in, is the rainfall accumulation coefficient of deep displacement; For acoustic emission energy , using the formula Calculate the acoustic emission energy Adjusted warning threshold ;in, is the acoustic emission energy level water pressure coupling coefficient; For pore water pressure , using the formula Calculate the pore water pressure Adjusted warning threshold ;in, is the rainfall response coefficient of pore water pressure; For penetration rate , using the formula Calculate the permeation rate Adjusted warning threshold ;in, is the rainfall multiplication factor of the infiltration rate.

[0008] Preferably, the correlation between each data group and the slope collapse is calculated, and the specific operation is as follows: Obtain several slope reference samples and monitor the parameters based on all slope reference samples. and slope collapse , =1, 2, …, ; represents the number of slope reference samples; based on Monitoring parameters included in the slope reference sample , calculate and obtain standardized monitoring parameters ; Set up multiple grid combinations , traverse any grid combination , calculate and obtain the current grid combination Time monitoring parameters Mutual information coefficient with slope collapse ; Based on the mutual information coefficients corresponding to all grid combinations obtained, the largest mutual information coefficient is selected as the monitoring parameter Maximum information coefficient with slope collapse ; Will to The maximum value in is taken as the correlation degree between the first slope data set and the slope collapse ; Will to The maximum value in is taken as the correlation degree between the second slope data set and the slope collapse ; Will to The maximum value of is taken as the correlation between the third slope data set and the slope collapse ; Will to The maximum value of is taken as the correlation between the fourth slope data set and the slope collapse .

[0009] Preferably, the influence weight of each data group is calculated and obtained, and the specific operation is as follows: Using the formula Calculate the influence weight of each data group , =1, 2, 3, 4.

[0010] Preferably, the slope collapse risk prediction model is applied to obtain the slope collapse risk prediction result, and the specific operation is as follows: At the beginning of the current environmental monitoring cycle, the first slope data group, the second slope data group, the third slope data group and the fourth slope data group obtained in the previous environmental monitoring cycle are sorted in time to form the first time series set, the second time series set, the third time series set and the fourth time series set; the obtained time series sets and the influence weights of each data group are used as inputs of the slope collapse risk prediction model, and the slope collapse risk prediction results are output.

[0011] Preferably, the slope collapse risk prediction model is established based on LSTM, including an input layer, an LSTM layer, a feature weighted fusion layer, a fully connected layer and an output layer.

[0012] Preferably, the specific operations for training the slope collapse risk prediction model are as follows: Obtain several model training samples with labeled slope collapse risk prediction results; divide all obtained model training samples into a training set and a validation set, use the training set to train the slope collapse risk prediction model with initialized parameters, and then verify the slope collapse risk prediction model through the validation set to obtain the verification results; set the training conditions to determine whether the obtained verification results meet the training conditions, and if so, output the trained slope collapse risk prediction model.

[0013] A slope stability analysis system based on dynamic monitoring data, comprising: A dynamic monitoring data acquisition module, used to collect a first slope data group, a second slope data group, a third slope data group and a fourth slope data group of a target slope area at any monitoring time point; The slope state discrimination module includes a warning threshold adjustment unit and a discrimination unit; the warning threshold adjustment unit is used to adjust the warning threshold of some monitoring parameters in each data group at the beginning of any environmental monitoring cycle; the discrimination unit is used to judge whether each acquired monitoring parameter meets the corresponding adjusted warning threshold within any environmental monitoring cycle, if so, no operation is performed; if not, the warning response measures are executed; The slope collapse risk prediction module applies the slope collapse risk prediction model to obtain the slope collapse risk prediction results; the slope collapse risk prediction results are applied to execute corresponding slope collapse prevention measures.

[0014] The present invention has the following advantages: 1. The present invention makes targeted adjustments to the warning thresholds of some monitoring parameters in each data group at the beginning of each environmental monitoring cycle by statistically analyzing the maximum temperature difference and rainfall in the target slope area. This dynamic adjustment mechanism fully considers the impact of environmental factors on slope stability monitoring parameters, makes the warning thresholds more in line with actual working conditions, effectively improves the accuracy and reliability of slope stability monitoring, avoids false alarms or missed alarms caused by fixed thresholds, and provides a more accurate monitoring basis for slope safety protection.

[0015] 2. The present invention collects multiple groups of data, and further calculates the correlation between these data groups and slope collapse to determine the influence weight of each data group, so that the information of each data group can be reasonably integrated in the slope collapse risk prediction model to highlight the role of key factors; this multi-source data fusion analysis method makes full use of the effective information in various monitoring data, improves the accuracy and reliability of slope stability prediction, and provides strong technical support for taking preventive measures in advance and ensuring slope safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1It is a schematic diagram of the structure of a slope stability analysis system based on dynamic monitoring data adopted in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to enable persons skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0018] Embodiment 1, a slope stability analysis method and system based on dynamic monitoring data, comprising: At the current monitoring time point, the first slope data group, the second slope data group, the third slope data group and the fourth slope data group of the target slope area are collected; the first slope data group includes surface horizontal displacement, surface vertical displacement and deep layer displacement, which can directly reflect the deformation of the slope at different depths and directions; surface horizontal displacement and vertical displacement monitoring can timely detect macroscopic changes on the slope surface, such as early signs of landslides; while deep layer displacement monitoring can deeply explore the displacement characteristics of each layer inside the slope, which helps to understand the stability state of the internal structure of the slope and provide a key basis for evaluating the overall stability of the slope; the second slope data group includes acoustic emission energy and microseismic wave propagation time difference. Acoustic emission energy monitoring can capture the elastic wave signal generated by microfractures inside the rock mass, thereby realizing real-time monitoring of the evolution of damage inside the rock mass and early warning of potential rock mass instability areas; monitoring of microseismic wave propagation time difference can analyze the changes in the propagation characteristics of seismic waves in the rock mass, and judge the integrity of the internal structure of the rock mass by the change in time difference, which provides a basis for evaluating the dynamic response and stability of the slope. For important reference; the third slope data group includes rock surface load stress and stress distribution gradient. Rock surface load stress monitoring can intuitively reflect the actual pressure on the slope surface and understand the mechanical state of the slope under various loads; stress distribution gradient monitoring further reveals the uneven distribution of stress inside the slope, which helps to identify stress concentration areas. These areas are often high-risk areas for slope instability. By monitoring these two data, the mechanical stability of the slope can be more accurately grasped; the fourth slope data group includes pore water pressure and permeability rate. Changes in pore water pressure will directly affect the effective stress of the rock and soil mass, and thus affect the stability of the slope; permeability rate monitoring can reflect the flow of groundwater in the slope. The seepage of groundwater will not only change the pore water pressure, but also may cause softening and strength reduction of the rock and soil mass. Therefore, the monitoring of these two data is crucial for evaluating the impact of hydrogeological conditions on slope stability, especially in the case of frequent hydrological activities such as rainfall and snowmelt, which can help to timely discover the risk of slope instability caused by water action; Set the environmental monitoring cycle. At the beginning of the current environmental monitoring cycle, calculate the maximum temperature difference of the target slope area in the last 12 hours, and obtain the rainfall in the previous environmental monitoring cycle. The calculation of this temperature difference is crucial because temperature changes will have significant physical and mechanical effects on the rock and soil of the slope. For example, drastic changes in temperature will cause thermal expansion and contraction of the rock and soil, which will in turn cause changes in displacement and stress. At the same time, it is also necessary to obtain the rainfall in the previous environmental monitoring cycle. Rainfall is one of the key factors affecting slope stability. The infiltration of rainwater will increase the pore water pressure and reduce the shear strength of the rock and soil, thereby improving the slope stability. The risk of instability; then adjust the warning thresholds of some monitoring parameters in each data group, the purpose is to consider the impact of environmental factors on the monitoring parameters, so that the warning thresholds are more in line with the actual working conditions, and improve the accuracy and reliability of monitoring; then in the current environmental monitoring cycle, determine whether the various monitoring parameters obtained meet the corresponding adjusted warning thresholds. If so, no operation is performed; if not, early warning response measures are implemented, which may include increasing the monitoring frequency, on-site investigation, expert consultation, etc., to further evaluate the stability of the slope, timely discover potential instability risks, and take corresponding preventive measures to ensure the safety and stability of the slope; The correlation between each data group and slope collapse is calculated, and then the influence weight of each data group is calculated. The influence weight reflects the relative importance of different data groups in the prediction of slope collapse risk. For example, if the correlation of the first slope data group (including surface horizontal displacement, surface vertical displacement and deep stratified displacement) is high, then its influence weight in the risk prediction model will be larger, which means that these displacement data contribute more to the prediction of slope collapse risk. At the beginning of the current environmental monitoring cycle, the slope collapse risk prediction model is applied to obtain the slope collapse risk prediction results. The slope collapse risk prediction results are applied to implement corresponding slope collapse prevention measures, such as increasing the monitoring frequency, setting up warning signs, evacuating surrounding personnel, etc., to reduce the losses that may be caused by the disaster. Through this method based on data-driven and model prediction, slope collapse prevention can be carried out more scientifically and effectively to ensure the safety of people's lives and property and the stable operation of infrastructure.

[0019] Adjust the warning thresholds of some monitoring parameters in each data group. The specific operations are as follows: All monitoring parameters for each data set , =1, 2, …, 9; to Corresponding to surface horizontal displacement, surface vertical displacement, deep layer displacement, acoustic emission energy, microseismic wave propagation time difference, rock surface load stress, stress distribution gradient, pore water pressure and permeability rate; setting each monitoring parameter Conventional warning thresholds ; The maximum temperature difference obtained based on the current environmental monitoring cycle and rainfall , for the surface horizontal displacement , using the formula Calculate the surface horizontal displacement Adjusted warning threshold ;in, It is the dynamic factor of surface displacement thermal expansion, which is used to reflect the nonlinear growth of displacement rate caused by thermal expansion effect. Its value is dynamically optimized based on thermal cycle test and displacement correlation analysis when setting, and can be taken within 0.0015~0.0035. The value of sandstone is 0.002, and it is recommended to increase to 0.003 for rock mass containing joints; Rock surface load stress , using the formula Calculate and obtain the rock surface load stress Adjusted warning threshold ;in, It is the surface stress temperature correction coefficient, which is used to quantify the effect of temperature change on the load-bearing capacity of the rock mass. Its value is adjusted according to the measured value of the thermal expansion coefficient of the minerals that make up the rock mass when setting it. It can be set within the range of 0.001 to 0.003. The reference value for granite is 0.002. The lower limit for rocks with high quartz content (such as sandstone) is 0.004 for rocks containing clay minerals (such as shale). For stress distribution gradient , using the formula Calculate the stress distribution gradient Adjusted warning threshold ;in, It is the temperature gradient correction coefficient, which is used to quantify the change in the gradient of stress spatial distribution caused by temperature difference. Its value is corrected according to the thermal conductivity of the rock formation when setting, and can be taken within 0.04~0.08. The empirical value of limestone is 0.05, and the lower limit is taken for high thermal conductivity rock (such as basalt); For deep layer displacement , using the formula Calculate the displacement of deep layers Adjusted warning threshold ;in, is the cumulative coefficient of deep displacement rainfall, which is used to describe the cumulative increase in the displacement threshold caused by softening or expansion of deep rock mass due to unit rainfall. Its value is calibrated by linkage rock mass permeability during setting, and can be taken within 0.002~0.008. 6 m / s, Increase by 0.0015; the typical value for clay slope is 0.004, and the gravel soil layer can be 0.006; For acoustic emission energy , using the formula Calculate the acoustic emission energy Adjusted warning threshold ;in, It is the coupling coefficient of acoustic emission energy level with water pressure, which is used to characterize the amplification effect of fracture water pressure on microfracture energy in exponential form, reflecting the nonlinear contribution of water-rock action (such as hydraulic fracturing) to the energy threshold of rock mass instability precursor. Its value is adjusted according to the fracture water pressure fracturing test when setting, and can be taken within 0.003~0.008. The critical value of hydraulic fracturing decreases by 1MPa. Increase by 0.001, 0.005 for brittle limestone, and as low as 0.002 for mudstone; For pore water pressure , using the formula Calculate the pore water pressure Adjusted warning threshold ;in, The pore water pressure rainfall response coefficient is used to linearly reflect the pressure transmission efficiency of rainfall infiltration in the pores. Its value is adjusted according to the pore network connectivity when setting, and can be taken within 0.015~0.03. The initial value for weathered rock mass is 0.02; For penetration rate , using the formula Calculate the permeation rate Adjusted warning threshold ;in, It is the rainfall multiplication coefficient of infiltration rate, which is used to quantify the multiplication effect of rainfall-induced expansion of soil infiltration channels and control the dynamic amplification ratio of the seepage velocity threshold. Its value is corrected in combination with the infiltration test when setting, and can be taken within the range of 0.005 to 0.02. When the ratio of saturated to unsaturated permeability coefficient increases by 1 times, Increase by 0.005, 0.01 is recommended for sandy soil, and it is recommended to reduce to 0.003 for fractured rock.

[0020] Calculate the correlation between each data group and slope collapse. The specific operations are as follows: Acquire a number of stable slope samples, each of which includes a first slope data group, a second slope data group, a third slope data group, and a fourth slope data group acquired in a slope area without slope collapse for a long time; and acquire a number of collapsed slope samples, each of which includes a first slope data group, a second slope data group, a third slope data group, and a fourth slope data group acquired in a slope area most recently before slope collapse occurs; All the obtained stable slope samples and collapsed slope samples are used as slope reference samples, and the monitoring parameters of all slope reference samples are and slope collapse , =1, 2, …, ; represents the number of slope reference samples; based on Monitoring parameters included in the slope reference sample , and slope collapse status , using the formula Calculation acquisition Standardized monitoring parameters for slope reference samples ,in, and Respectively Monitoring parameters The maximum and minimum values ​​in ; Set up multiple grid combinations , traverse any grid combination , for each slope reference sample , determine the value combination of the slope reference sample in the current grid combination position; using the formula Calculate the joint probability distribution ; Indicated in The slope reference samples fall into the grid The number of samples; then use the formula and Calculate the marginal probability distribution and ,in, Represents the current grid combination value; finally, using the formula Calculate and obtain the current grid combination of the application Time monitoring parameters Mutual information coefficient with slope collapse ; Based on the mutual information coefficients corresponding to all grid combinations obtained, the largest mutual information coefficient is selected as the monitoring parameter Maximum information coefficient with slope collapse ; Will to The maximum value in is taken as the correlation degree between the first slope data set and the slope collapse ; Will to The maximum value in is taken as the correlation degree between the second slope data set and the slope collapse ; Will to The maximum value of is taken as the correlation between the third slope data set and the slope collapse ; Will to The maximum value of is taken as the correlation between the fourth slope data set and the slope collapse .

[0021] Calculate and obtain the influence weight of each data group. The specific operations are as follows: Using the formula Calculate the influence weight of each data group , =1, 2, 3, 4.

[0022] Apply the slope collapse risk prediction model to obtain the slope collapse risk prediction results. The specific operations are as follows: At the beginning of the current environmental monitoring cycle, the first slope data group, the second slope data group, the third slope data group and the fourth slope data group obtained in the previous environmental monitoring cycle are sorted in time to form the first time series set, the second time series set, the third time series set and the fourth time series set; the obtained time series sets and the influence weights of each data group are used as inputs of the slope collapse risk prediction model, and the slope collapse risk prediction results are output.

[0023] The slope collapse risk prediction model is established based on LSTM, including input layer, LSTM layer, feature weighted fusion layer, fully connected layer and output layer; The input layer is used to receive the first time series set, the second time series set, the third time series set and the fourth time series set as well as the influence weights of each data group; The LSTM layer is used to extract the time series feature vectors of the first time series set, the second time series set, the third time series set, and the fourth time series set respectively; The feature weighted fusion layer is used to apply the influence weights of each data group to perform weighted fusion on the time series feature vectors corresponding to each time series set to obtain a weighted fused time series feature vector; The fully connected layer is used to perform nonlinear transformation and high-order abstraction on the weighted fusion time series feature vector and output high-dimensional feature representation; The output layer is used to output the slope collapse risk prediction results.

[0024] The specific operations for training the slope collapse risk prediction model are as follows: A number of model training samples with labeled slope collapse risk prediction results are obtained, each model training sample stores the first slope data group, the second slope data group, the third slope data group and the fourth slope data group of a certain slope area sorted by time within an environmental monitoring cycle; all the obtained model training samples are divided into a training set and a verification set, the training set is used to train the slope collapse risk prediction model with initialized parameters, and then the slope collapse risk prediction model is verified by the verification set to obtain the verification result; the training conditions are set to determine whether the obtained verification results meet the training conditions, and if so, the trained slope collapse risk prediction model is output.

[0025] Embodiment 2, a slope stability analysis system based on dynamic monitoring data, such as Figure 1 As shown, including: A dynamic monitoring data acquisition module, used to collect a first slope data group, a second slope data group, a third slope data group and a fourth slope data group of a target slope area at any monitoring time point; The slope state discrimination module includes a warning threshold adjustment unit and a discrimination unit; the warning threshold adjustment unit is used to calculate the maximum temperature difference of the target slope area in the last 12 hours at the beginning of any environmental monitoring cycle, and obtain the rainfall in the previous environmental monitoring cycle, and then adjust the warning thresholds of some monitoring parameters in each data group; the discrimination unit is used to determine whether each monitoring parameter obtained meets the corresponding adjusted warning threshold in any environmental monitoring cycle, if so, no operation is performed; if not, the warning response measures are executed; The slope collapse risk prediction module is used to calculate the correlation between each data group and slope collapse, and then calculate the impact weight of each data group; at the beginning of any environmental monitoring cycle, the slope collapse risk prediction model is applied to obtain the slope collapse risk prediction results; the slope collapse risk prediction results are applied to implement corresponding slope collapse prevention measures.

[0026] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention. Parts not described in detail in this specification belong to the prior art known to those skilled in the art.

Claims

1. A slope stability analysis method based on dynamic monitoring data, characterized in that: include: At the current monitoring time point, the first slope data group, the second slope data group, the third slope data group and the fourth slope data group of the target slope area are collected; the first slope data group includes surface horizontal displacement, surface vertical displacement and deep layer displacement; the second slope data group includes acoustic emission energy and microseismic wave propagation time difference; the third slope data group includes rock surface load stress and stress distribution gradient; the fourth slope data group includes pore water pressure and permeability rate; Set the environmental monitoring cycle. At the beginning of the current environmental monitoring cycle, calculate the maximum temperature difference of the target slope area in the last 12 hours, obtain the rainfall in the previous environmental monitoring cycle, and then adjust the warning thresholds of some monitoring parameters in each data group; Then, in the current environmental monitoring cycle, it is determined whether each acquired monitoring parameter meets the corresponding adjusted warning threshold value. If so, no operation is performed; if not, the warning response measures are executed; Calculate the correlation between each data group and slope collapse, and then calculate the impact weight of each data group; at the beginning of the current environmental monitoring cycle, apply the slope collapse risk prediction model to obtain the slope collapse risk prediction results; apply the slope collapse risk prediction results to implement corresponding slope collapse prevention measures.

2. A slope stability analysis method based on dynamic monitoring data according to claim 1, characterized in that: Adjust the warning thresholds of some monitoring parameters in each data group. The specific operations are as follows: All monitoring parameters for each data set , =1, 2, …, 9; to Corresponding to surface horizontal displacement, surface vertical displacement, deep layer displacement, acoustic emission energy, microseismic wave propagation time difference, rock surface load stress, stress distribution gradient, pore water pressure and permeability rate; setting each monitoring parameter Conventional warning thresholds ; The maximum temperature difference obtained based on the current environmental monitoring cycle and rainfall , for the surface horizontal displacement , using the formula Calculate the surface horizontal displacement Adjusted warning threshold ;in, is the dynamic factor of thermal expansion of surface displacement; Rock surface load stress , using the formula Calculate and obtain the rock surface load stress Adjusted warning threshold ;in, is the surface stress temperature correction coefficient; For stress distribution gradient , using the formula Calculate the stress distribution gradient Adjusted warning threshold ;in, is the temperature gradient correction factor; For deep layer displacement , using the formula Calculate the displacement of deep layers Adjusted warning threshold ;in, is the rainfall accumulation coefficient of deep displacement; For acoustic emission energy , using the formula Calculate the acoustic emission energy Adjusted warning threshold ;in, is the acoustic emission energy level water pressure coupling coefficient; For pore water pressure , using the formula Calculate the pore water pressure Adjusted warning threshold ;in, is the rainfall response coefficient of pore water pressure; For penetration rate , using the formula Calculate the permeation rate Adjusted warning threshold ;in, is the rainfall multiplication factor of the infiltration rate.

3. A slope stability analysis method based on dynamic monitoring data according to claim 2, characterized in that: Calculate the correlation between each data group and slope collapse. The specific operations are as follows: Obtain several slope reference samples and monitor the parameters based on all slope reference samples. and slope collapse , =1, 2, …, ; represents the number of slope reference samples; based on Monitoring parameters included in the slope reference sample , calculate and obtain standardized monitoring parameters ; Set up multiple grid combinations , traverse any grid combination , calculate and obtain the current grid combination Time monitoring parameters Mutual information coefficient with slope collapse ; Based on the mutual information coefficients corresponding to all grid combinations obtained, the largest mutual information coefficient is selected as the monitoring parameter Maximum information coefficient with slope collapse ; Will to The maximum value in is taken as the correlation degree between the first slope data set and the slope collapse ; Will to The maximum value in is taken as the correlation degree between the second slope data set and the slope collapse ; Will to The maximum value of is taken as the correlation between the third slope data set and the slope collapse ; Will to The maximum value of is taken as the correlation between the fourth slope data set and the slope collapse .

4. A slope stability analysis method based on dynamic monitoring data according to claim 3, characterized in that: Calculate and obtain the influence weight of each data group. The specific operations are as follows: Using the formula Calculate the influence weight of each data group , =1, 2, 3, 4.

5. A slope stability analysis method based on dynamic monitoring data according to claim 4, characterized in that: Apply the slope collapse risk prediction model to obtain the slope collapse risk prediction results. The specific operations are as follows: At the beginning of the current environmental monitoring cycle, the first slope data group, the second slope data group, the third slope data group and the fourth slope data group obtained in the previous environmental monitoring cycle are sorted in time to form the first time series set, the second time series set, the third time series set and the fourth time series set; the obtained time series sets and the influence weights of each data group are used as inputs of the slope collapse risk prediction model, and the slope collapse risk prediction results are output.

6. A slope stability analysis method based on dynamic monitoring data according to claim 5, characterized in that: The slope collapse risk prediction model is established based on LSTM, including input layer, LSTM layer, feature weighted fusion layer, fully connected layer and output layer.

7. A slope stability analysis method based on dynamic monitoring data according to claim 6, characterized in that: The specific operations for training the slope collapse risk prediction model are as follows: Obtain a number of model training samples with marked slope collapse risk prediction results; divide all the obtained model training samples into a training set and a validation set, use the training set to train the slope collapse risk prediction model with initialized parameters, and then verify the slope collapse risk prediction model through the validation set to obtain the verification results; Set the training conditions and determine whether the obtained verification results meet the training conditions. If so, output the trained slope collapse risk prediction model.

8. A slope stability analysis system based on dynamic monitoring data, characterized in that: The system is applied to a slope stability analysis method based on dynamic monitoring data as described in any one of claims 1 to 7, comprising: A dynamic monitoring data acquisition module, used to collect a first slope data group, a second slope data group, a third slope data group and a fourth slope data group of a target slope area at any monitoring time point; The slope state discrimination module includes a warning threshold adjustment unit and a discrimination unit; the warning threshold adjustment unit is used to adjust the warning threshold of some monitoring parameters in each data group at the beginning of any environmental monitoring cycle; the discrimination unit is used to judge whether each acquired monitoring parameter meets the corresponding adjusted warning threshold within any environmental monitoring cycle, if so, no operation is performed; if not, the warning response measures are executed; The slope collapse risk prediction module applies the slope collapse risk prediction model to obtain the slope collapse risk prediction results; the slope collapse risk prediction results are applied to execute corresponding slope collapse prevention measures.

Images