Early warning method and system for predicting soil slope damage based on shear parameters

Abstract

The invention discloses an early warning method and system for predicting soil slope damage based on shear parameters, and the method comprises the steps: obtaining monitoring data of a target region at a target moment, and predicting the moisture content of the target region in combination with a moisture content prediction model, the monitoring data comprising consolidation condition data monitored by a pressure sensor; predicting a target shear strength parameter of the target area at the target moment based on a shear parameter prediction model in combination with the predicted water content and the consolidation condition data; and determining an early warning level corresponding to the target area according to the target shear strength parameter, and performing early warning according to an early warning mode corresponding to the early warning level.

Description

Technical Field

[0001] The present application relates to the technical field of slope deformation monitoring, and more specifically, to an early warning method and system for predicting soil slope failure based on shear parameters. Background Art

[0002] Traditional means of slope deformation monitoring mainly rely on displacement monitoring, groundwater level monitoring, etc., but there is currently a lack of direct monitoring methods for the shear parameters inside the soil, making it difficult to fully and accurately capture the shear parameter information inside the soil. Although these methods can roughly know the displacement of the slope, it is still difficult to grasp the appropriate degree of slope damage. If the complete deformation law of the slope cannot be accurately obtained, if the most critical point in the "pre-slip stage" of landslide monitoring and early warning research is not collected, it will be difficult to achieve accurate landslide monitoring and early warning.

[0003] In addition, the displacement data of each monitoring point on the slope is obtained in real time, and the deformation of the monitoring point is determined by the preset deformation mechanism. The dangerous deformation area is divided into regions based on the deformation amount and the preset processing mechanism, so as to realize the precise monitoring of the entire slope deformation and improve the accuracy of the slope deformation data. However, the surface deformation monitoring methods are often affected by meteorological conditions and satellite periodicity, which interferes with the continuous monitoring of the slope, and the direct monitoring of the internal shear parameters of the soil makes it difficult to fully grasp the stability of the slope.

[0004] In the related art, the measured horizontal displacement data of the slope and the soil sample data are obtained, and the inversion soil strength parameters are obtained by using the neural network algorithm inversion analysis, and the background model and user model of the relationship between the soil strength parameters and the slope safety factor value are constructed, and the stability prediction analysis of the slope is completed through the algorithm model. Although the present invention solves the problem that the static parameters obtained through the test are difficult to reflect the changes in the dynamic soil strength parameters, the displacement monitoring of the soil is easily affected by external conditions by inverting the mechanical parameters through the soil deformation, and the influence of soil pressure and water content on the mechanical parameters is not considered during the inversion. If rainfall conditions occur, it is inevitable that the prediction will be wrong. Summary of the invention

[0005] In response to at least one defect or improvement need in the prior art, the present invention provides an early warning method and system for predicting soil slope failure based on shear parameters, so as to solve the problem of insufficient warning sensitivity of existing devices in the pre-disaster early warning capability of geological slopes, thereby improving the safety and resilience of geological slopes.

[0006] To achieve the above-mentioned purpose, according to the first aspect of the present invention, there is provided an early warning method for predicting soil slope damage based on shear parameters, the method comprising: obtaining monitoring data of a target area at a target time, and predicting the moisture content of the target area in combination with a moisture content prediction model, wherein the monitoring data includes condition data monitored by a pressure sensor; based on the shear parameter prediction model, in combination with the predicted moisture content and the condition data, predicting the target shear strength parameters of the target area at the target time; determining the early warning level corresponding to the target area according to the target shear strength parameters, and issuing an early warning according to the early warning method corresponding to the early warning level.

[0007] In an exemplary embodiment, the acquisition of monitoring data of the target area at the target time and the prediction of the moisture content of the target area in combination with a moisture content prediction model include: acquiring the monitoring data through a monitoring sensor, wherein the monitoring data includes rainfall, drainage ditch flow, and pore water pressure; inputting the monitoring data into the moisture content prediction model for prediction to obtain the moisture content of the target area.

[0008] In an exemplary embodiment, determining the warning level corresponding to the target area according to the target shear strength parameter and issuing an early warning according to the early warning method corresponding to the early warning level include: determining early warning factors and weights corresponding to the early warning factors, wherein the early warning factors include target shear strength parameters, economic effect parameters, environmental effect parameters and safety requirement parameters; standardizing the original data of the early warning factors to obtain target data; determining the target score of the target area by combining the target data and the corresponding weights; and determining the early warning level corresponding to the target area based on the target score.

[0009] In an exemplary embodiment, the shear parameter prediction model, combined with the predicted moisture content and the consolidation condition data, predicts the target shear strength parameters of the target area at the target time, including: setting the moisture content and consolidation ratio parameters as characteristic data input into the XGboost model, and using the target shear strength parameters as predicted target data; repeatedly correcting the parameters of the XGboost model to obtain the shear parameter prediction model.

[0010] According to the second aspect of the present invention, there is also provided an early warning system for predicting soil slope failure based on shear parameters, which uses the early warning method for predicting soil slope failure based on shear parameters as mentioned above, including: a monitoring module, a prediction module and an early warning module; wherein the monitoring module is used to collect monitoring data and transmit the monitoring data to a computer for processing, the prediction module is used to predict the target shear strength parameters of the target area at the target time, and the early warning module is used to issue an early warning based on the early warning method corresponding to the early warning level.

[0011] According to the third aspect of the present invention, there is also provided an early warning device for predicting soil slope damage based on shear parameters, which includes: an acquisition unit, used to acquire monitoring data of a target area at a target time, and predict the moisture content of the target area in combination with a moisture content prediction model, wherein the monitoring data includes consolidation condition data monitored by a pressure sensor; a prediction unit, used to predict a target shear strength parameter of the target area at the target time based on a shear parameter prediction model in combination with the predicted moisture content and the consolidation condition data; an early warning unit, used to determine the early warning level corresponding to the target area according to the target shear strength parameter, and to issue an early warning according to the early warning method corresponding to the early warning level.

[0012] According to a fourth aspect of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned early warning method for predicting soil slope failure based on shear parameters when running.

[0013] According to the fifth aspect of the present invention, there is also provided an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-mentioned early warning method for predicting soil slope failure based on shear resistance parameters through the computer program.

[0014] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0015] (1) The present invention provides an early warning method for predicting soil slope damage based on shear parameters. Through the prediction of shear parameters, the potential damage risk of soil slopes can be perceived in advance, thereby providing sufficient time to take appropriate preventive and response measures to reduce potential losses; the system obtains the influence relationship between water content, soil consolidation state, surrounding pressure of soil and shear parameters through indoor experiments, and combines machine learning methods to achieve accurate prediction of shear parameters under different environmental influences; the system adopts multi-criteria decision analysis method for early warning, and the early warning of slopes can fully consider the economic effect, environmental effect, project type and use, monitoring data and safety requirements of slope damage.

[0016] (2) Adopt the early warning method for predicting soil slope failure based on shear parameters provided in this application, through the real-time data obtained by the monitoring system and the influence relationship between moisture content, confining pressure and shear parameters obtained by indoor experiments, and combine with machine learning methods to achieve accurate prediction of shear parameters under different environmental conditions. By comprehensively considering multiple factors, early and accurate early warning information is provided for slope failure, which helps to take preventive and response measures in advance, thereby reducing potential losses. Automatic monitoring data transmission technology is used to automatically obtain key data of the slope, avoiding the need for traditional manual monitoring. Based on intelligent prediction and early warning systems, human intervention and manual labor input can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A schematic flow chart of an optional early warning method for predicting soil slope failure based on shear parameters provided in an embodiment of the present application;

[0019] Figure 2 A schematic diagram of an optional prediction of the moisture content of soil in a slope provided in an embodiment of the present application;

[0020] Figure 3 A schematic diagram of an optional soil shear strength parameter prediction provided in an embodiment of the present application;

[0021] Figure 4 A schematic diagram of an optional soil slope monitoring system provided in an embodiment of the present application;

[0022] Figure 5 A schematic flow chart of another optional early warning method for predicting soil slope failure based on shear resistance parameters provided in an embodiment of the present application;

[0023] Figure 6 A schematic diagram of an optional early warning system flow provided for an embodiment of the present application;

[0024] Figure 7 A schematic structural diagram of an optional early warning device for predicting soil slope failure based on shear resistance parameters provided in an embodiment of the present application;

[0025] Figure 8 A schematic diagram of the structure of an optional electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0027] The terms "first", "second", "third", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0028] According to one aspect of the embodiments of the present application, a warning method for predicting soil slope failure based on shear parameters is provided. Figure 1 The present invention describes an early warning method for predicting soil slope failure based on shear resistance parameters provided in an embodiment of the present application.

[0029] Figure 1 is a flow chart of an optional early warning method for predicting soil slope failure based on shear parameters provided in an embodiment of the present application, such as Figure 1 As shown, the process of the method may include the following steps:

[0030] S102, acquiring monitoring data of a target area at a target time, and predicting the moisture content of the target area in combination with a moisture content prediction model, wherein the monitoring data includes consolidation condition data monitored by a pressure sensor;

[0031] S104, predicting a target shear strength parameter of a target area at a target time based on a shear parameter prediction model and in combination with predicted moisture content and consolidation condition data;

[0032] S106, determining a warning level corresponding to the target area according to the target shear strength parameter, and issuing a warning according to a warning method corresponding to the warning level.

[0033] The early warning method for predicting soil slope damage based on shear parameters provided in this application can be applied to slope deformation monitoring scenarios. Furthermore, it can also be applied to soil roadbed slopes and their protective structures in the fields of newly built and rebuilt railways, urban rail transit, urban roads, highways, etc.; soil roadbed slopes and their protective structures in geological disaster control projects such as landslides; urban rail transit geological slope safety and toughness evaluation and analysis, etc. The destruction of the slope is sudden. If only the deformation is monitored, it is difficult to predict whether the slope will be destroyed or the time of destruction. Moreover, deformation monitoring is easily affected by meteorological conditions and satellite periodicity. If the shear parameter information inside the soil body can be accurately captured and the complete deformation law of the slope can be accurately obtained, it will be possible to determine whether the slope deformation will be destroyed, and even predict the conditions of destruction. Compared with deformation monitoring, the prediction of shear strength parameters under different conditions can achieve advance prediction for slope monitoring and early warning, which is of greater significance for slope engineering rescue and disaster relief. The machine learning method can be combined with the monitoring system to achieve high early warning efficiency and advance prediction.

[0034] In the embodiment of the present application, in order to achieve the accuracy of shear parameter prediction, it is necessary to fully consider the dynamic changes of physical conditions that have a controlling influence on the shear strength parameters, such as the moisture content and the consolidation state of the soil. Optionally, the monitoring data of the target area at the target time can be first obtained through the monitoring system, and the moisture content of the target area can be predicted in combination with the moisture content prediction model. Here, the monitoring data includes the consolidation condition data monitored by the pressure sensor, and the target shear strength parameters of the target area at the target time are predicted based on the shear parameter prediction model in combination with the predicted moisture content and consolidation condition data. The warning level corresponding to the target area is determined according to the target shear strength parameters, and an early warning is issued according to the early warning method corresponding to the early warning level.

[0035] For example, the stability prediction of the slope can be achieved by dynamically predicting the shear strength parameters. According to the Moore-Coulomb theory, the shear strength of the soil is not a constant, but increases with the increase of the normal stress on the shear surface. Therefore, the shear strength parameters can be used to determine whether the soil will be damaged. However, the size of the shear strength parameters is often affected by many factors, such as water content, soil consolidation conditions, particle size and shape, and pore structure of the soil. In the same slope, the type of soil is the same, the particle size, shape and pore structure are roughly the same, and will not change with time. However, the water content of the soil in the slope will change with the change of rainfall conditions, and the consolidation conditions of the soil will also be affected by the change of the overburden pressure on the slope. In order to dynamically predict the shear strength parameters of the soil, first, the water content and consolidation conditions of the soil can be monitored; then the quantitative relationship between the water content, consolidation conditions and shear strength parameters of the slope soil is determined.

[0036] Through the above steps S102 to S106, the monitoring data of the target area at the target time is obtained, and the moisture content of the target area is predicted in combination with the moisture content prediction model, wherein the monitoring data includes the consolidation condition data monitored by the pressure sensor; based on the shear parameter prediction model, the target shear strength parameter of the target area at the target time is predicted in combination with the predicted moisture content and consolidation condition data; the warning level corresponding to the target area is determined according to the target shear strength parameter, and an early warning is given according to the early warning method corresponding to the early warning level, and the real-time data obtained by the monitoring system and the influence relationship between the moisture content, confining pressure and shear parameters obtained by indoor experiments are combined with machine learning methods to achieve accurate prediction of shear parameters under different environmental conditions. By comprehensively considering multiple factors, early and accurate early warning information is provided for slope failure, which helps to take preventive and response measures in advance, thereby reducing potential losses.

[0037] In an exemplary embodiment, acquiring monitoring data of a target area at a target time and predicting the moisture content of the target area in combination with a moisture content prediction model includes:

[0038] S11, obtaining monitoring data through monitoring sensors, wherein the monitoring data includes rainfall, drainage ditch flow, and pore water pressure;

[0039] S12, inputting the monitoring data into a moisture content prediction model for prediction to obtain the moisture content of the target area.

[0040] In this embodiment, Figure 2 An optional schematic diagram of predicting the moisture content of soil in a slope provided in an embodiment of the present application is shown in FIG. Figure 2 As shown in the figure, when determining the moisture content of the target area, specifically, the moisture content has a huge impact on the shear strength parameters. Too high a moisture content may cause a water film to adhere to the soil surface, thereby reducing the friction strength between soil bodies. An appropriate moisture content can increase the bonding force and van der Waals force between soil bodies, and increase the cohesion of the soil. Generally speaking, an appropriate amount of water can improve the shear strength of the soil, but too much or too little water may lead to a decrease in shear strength. Therefore, the prediction of shear strength parameters must take into account the moisture content factor, and the moisture content needs to be dynamically predicted first.

[0041] In slope engineering, possible conditions that affect soil moisture content include rainfall, drainage ditch flow, and pore water pressure in the soil. Therefore, the above data are brought into the XGboost model as feature data, and the real-time data measured by the tubular moisture meter is used as the target data for prediction. By repeatedly correcting the parameters, dynamic prediction of the moisture content in the slope soil can be achieved.

[0042] Through this embodiment, the dynamically predicted water content in the soil is obtained, thereby improving the ability to accurately predict shear parameters.

[0043] In an exemplary embodiment, determining the warning level corresponding to the target area according to the target shear strength parameter, and issuing a warning according to the warning method corresponding to the warning level includes:

[0044] S21, determining early warning factors and weights corresponding to the early warning factors, wherein the early warning factors include target shear strength parameters, economic effect parameters, environmental effect parameters, and safety requirement parameters;

[0045] S22, standardize the original data of the warning factors to obtain target data;

[0046] S23, combining the target data with the corresponding weight, determining the target score of the target area;

[0047] S24, determining a warning level corresponding to the target area based on the target score.

[0048] In this embodiment, combined with Figure 5 and Figure 6 As shown in the figure, the multi-criteria decision analysis method can be used to formulate early warning rules and standards by combining the economic effect, environmental effect, engineering type and purpose, monitoring data and safety requirements of slope damage. The shear parameter prediction data obtained by the prediction module is integrated with the real-time data obtained in the monitoring system to form a comprehensive slope status assessment. According to the results of the multi-criteria decision analysis, different early warning levels are divided, such as blue warning, orange warning, yellow warning and red warning. Finally, when the system determines that there is a potential risk of damage to the slope, the corresponding early warning level is triggered and early warning information is issued in a timely manner so that appropriate preventive and response measures can be taken.

[0049] Furthermore, an early warning system can be established, for example, using Multi-Criteria Decision Analysis (MCDA) for early warning. The specific steps are as follows:

[0050] ① This application can select four factors: economic effect, environmental effect, safety requirements, and monitoring data. Assign weights to each factor according to its importance, usually expressed as a percentage between 0 and 1, and the sum of the weights should be equal to 1. For example, the weight of economic effect can be set to 20%, the weight of environmental effect can be set to 10%, the weight of safety requirements can be set to 30%, and the weight of monitoring data can be set to 40%.

[0051] ② Data standardization: Standardize the raw data of the factors and scale the data to a range between 0 and 1 to ensure that they are on the same scale. The standardization formula is:

[0052]

[0053] ③ Comprehensive evaluation: Combine the weights of the three factors and the standardized data to calculate the comprehensive score of each monitoring point. Comprehensive score = (economic effect score * economic effect weight) + (environmental effect score * environmental effect weight) + (safety requirement score * safety requirement weight) + (monitoring data * monitoring data weight). The score of each factor can be calculated based on its actual value and importance weight, and a comprehensive score will be generated, which can be used to determine the warning level.

[0054] ④ Warning level division: Different warning levels are divided according to the range of the comprehensive score, such as red, orange, yellow, blue, etc. Specific red warning: dangerous level, emergency measures need to be taken immediately, such as road closures, traffic control, etc. Orange warning: high risk level, immediate control measures need to be taken, which may include traffic restrictions or partial road closures. Yellow warning: medium risk level, close monitoring is required, and regular inspections and maintenance may be required. Blue warning: low risk level, continued monitoring is still required, but no immediate emergency measures are required.

[0055] After completing the construction of the monitoring system, prediction system and early warning system, the moisture content of the soil in the slope under the current conditions can be predicted by monitoring the rainfall data, groundwater data and drainage ditch flow data at time t, and then combined with the soil pressure, the shear strength parameters of the slope soil under the conditions at time t can be predicted. Through the application of multi-source monitoring and XGBoost model, the moisture content and shear strength parameters of the slope can be accurately predicted, making road maintenance work more targeted and reducing the risk of sudden disasters.

[0056] Through this embodiment, the moisture content and shear strength parameters of the slope are accurately predicted, making road maintenance work more targeted. At the same time, the multi-level warning mechanism of the early warning system allows different measures to be taken for different situations, thereby better guiding maintenance and emergency response work. This invention is expected to improve the quality of slope engineering, improve public safety, reduce the incidence of accidents, and have a positive impact on transportation and land management departments and the general public.

[0057] In an exemplary embodiment, based on the shear parameter prediction model, combined with the predicted moisture content and consolidation condition data, the target shear strength parameter of the target area at the target time is predicted, including:

[0058] S31, setting the water content and consolidation ratio parameters as characteristic data and inputting them into the XGboost model, and taking the target shear strength parameter as the target data for prediction;

[0059] S32, repeatedly correcting the parameters of the XGboost model to obtain a shear parameter prediction model.

[0060] In the embodiment of the present application, the consolidation state of the soil refers to the arrangement density between soil particles. When the slope is excavated or the overburden pressure on the slope increases, as the internal pressure of the slope soil changes, the degree of compression between soil particles will also change, and thus the friction strength of the soil will also change. Figure 3 As shown in the figure, when determining the shear parameter prediction model, different gradient moisture content and different gradient consolidation ratio can be set to conduct triaxial consolidation drainage test to obtain the quantitative relationship between moisture content, consolidation ratio and soil shear strength parameters. The moisture content and consolidation ratio are set as characteristic data, and the shear strength parameters are used as target data. By repeatedly correcting the parameters, the purpose of using moisture content and consolidation ratio to predict shear strength parameters can be achieved.

[0061] Specifically, data collection and data preprocessing can be performed first, and after missing values ​​are filled in the original data, the cleaned monitoring data can be integrated and classified according to different monitoring points and stored. Statistical analysis can be performed on the stored monitoring data, and a local monitoring curve can be generated within a preset time range and displayed through visualization technology.

[0062] Exemplarily, the data may be preprocessed using a Criteria Importance Through Intercriteria Correlation (CRITIC) algorithm.

[0063] The CRITIC algorithm is: the jth indicator value xij of the i-th object of u samples and v indicators constitutes the original sample data matrix x = (xij)u × v. The Z-score method is used to standardize the values ​​of each indicator in x to obtain a standardized matrix:

[0064]

[0065] Where: and sj are the mean and standard deviation of the jth indicator respectively, and the calculation formula is:

[0066]

[0067] Then the coefficient of variation of each indicator can be calculated:

[0068]

[0069] Where: vj is the coefficient of variation of the j-th indicator.

[0070] Calculate the correlation coefficient of each indicator of the standardized matrix X* and obtain the correlation coefficient matrix:

[0071] R=(rkl)v×v(k=1,2,…,v; l=1,2,…,v)

[0072] Where: rkl is the correlation coefficient between the kth and lth indicators.

[0073] Calculate the coefficient reflecting the degree of independence of each indicator:

[0074]

[0075] Finally, calculate the weight of each indicator:

[0076]

[0077] Get the final sample matrix Xf

[0078]

[0079] Furthermore, the preprocessed data and geological environment information encoding can be brought into the machine learning algorithm to train the prediction model. Through this step, the prediction model of slope soil moisture content and the prediction model of slope soil shear strength parameters are obtained. Specifically, the machine learning model construction process of the prediction module is as follows:

[0080] 1) Data representation: Create a feature matrix where each row represents a sample (time point) and each column represents a feature (e.g., rainfall, gutter flow, water pressure, etc.).

[0081] Here is an example of how rainfall, flow, and soil moisture data might be represented:

[0082] #Create feature matrix

[0083] data = {'Timestamp':['2023-10-01','2023-10-02','2023-10-03',...], #Timestamp

[0084] 'Rainfall':[0.5,0.3,0.8,...],#Rainfall data

[0085] 'Groundwater':[5.2,5.5,5.8,...],#Flow data

[0086] #Create DataFrame

[0087] df = pd.DataFrame(data)

[0088] #Add moisture content as a label

[0089] df['WaterContent'] = [10.2, 10.5, 10.8, ...] # Water content data

[0090] # Ensure that the time series are in chronological order

[0091] df['Timestamp']=pd.to_datetime(df['Timestamp'])

[0092] df=df.sort_values(by='Timestamp')

[0093] #Feature matrix

[0094] X=df[['Rainfall','Groundwater']]

[0095] #Target variable

[0096] y = df['WaterContent']

[0097] In this example, X represents the feature matrix, including rainfall and flow as features, and y is the moisture content to be predicted as the label. Make sure the time series data is arranged in chronological order for time series analysis.

[0098] 2) Perform feature engineering on the data: Create lag features: Use the lagged values ​​of rainfall and flow data as features to account for time lag effects. Add seasonal features: Consider seasonal changes, you can add features such as month and season. Statistical features: Calculate statistical features of rainfall data, such as mean and variance. Improve the performance of the model.

[0099] 3) Data Split: Split the dataset into training and test sets to evaluate model performance. Use most of the data for training and a small portion for testing.

[0100] 4) Convert the data into XGBoost’s DMatrix format.

[0101] 5) Define model parameters: Define the hyperparameters of the XGBoost model, such as learning rate, number of trees, maximum depth, etc., and adjust these parameters based on actual conditions.

[0102] Define model parameters, params = 'objective':'reg:squarederror',

[0103] #Regression task 'max_depth': 5,

[0104] #Maximum depth of the tree 'learning_rate': 0.1,

[0105] #Learning rate 'n_estimators': 100,

[0106] #Number of trees 'min_child_weight': 1,

[0107] #Minimum sample weight and 'subsample' of leaf nodes: 0.8,

[0108] #Subsample ratio 'colsample_bytree': 0.8,

[0109] #Column sampling ratio 'gamma': 0,

[0110] #The minimum loss reduction value required for leaf node splitting 'lambda': 1,

[0111] #L2 regularization parameter 'alpha': 0,

[0112] #L1 regularization parameter 'eval_metric': 'rmse'

[0113] #Evaluation indicator, root mean square error

[0114] 6) Train the model: Use the training data and defined parameters to train the XGBoost model.

[0115] 7) Model evaluation: Use the test dataset to evaluate the model performance and use the root mean square error for evaluation.

[0116] Specifically, the root square error is:

[0117]

[0118] 8) Use the model: train the model and predict the moisture content data.

[0119] 9) Parameter adjustment and optimization: Adjust hyperparameters and feature engineering methods according to model performance and actual needs. These steps are the general process of building an XGBoost regression model to predict moisture content. Make sure to make appropriate adjustments and optimizations according to actual data and needs to obtain the best model performance.

[0120] 4. Through indoor geotechnical tests, the quantitative relationship between soil shear strength parameters and soil moisture content and soil consolidation conditions is obtained. Then, as described in step 3, all the obtained test data are preprocessed, all the data are normalized, and the data is brought into the XGboost model for training to obtain the shear strength parameter prediction model of slope soil. At the same time, combined with the dynamic monitoring model of moisture content, the shear strength parameters are combined with monitoring rainfall, flow data, soil pressure and other data, and the shear strength of the slope soil can be predicted through the data obtained by the detection module. After the shear strength parameters are determined, the Moore-Coulomb criterion and monitoring data can be combined to predict whether the slope will be damaged.

[0121] In the prediction module, the moisture content can be predicted and the consolidation conditions can be monitored. The moisture content and consolidation conditions can then be used to predict the shear strength parameters. Finally, the two models can be combined to predict the shear strength parameters by monitoring rainfall, soil pressure, drainage ditch flow and other data.

[0122] Through this embodiment, the relationship between soil moisture content, soil consolidation conditions and shear parameters is obtained, thereby improving the ability to accurately predict the shear parameters.

[0123] According to another aspect of the embodiment of the present application, there is also provided an early warning system using the early warning method for predicting soil slope failure based on shear parameters as described above, the system may include:

[0124] Monitoring module, prediction module and early warning module;

[0125] Among them, the monitoring module is used to collect monitoring data and transmit the monitoring data to the computer for processing. The prediction module is used to predict the target shear strength parameters of the target area at the target time. The early warning module is used to issue an early warning based on the early warning method corresponding to the early warning level.

[0126] In an exemplary embodiment, the monitoring module includes a tubular moisture meter for soil slope monitoring, a pore water pressure sensor, an earth pressure sensor, a flow monitoring instrument, and an integrated rainfall monitoring station for monitoring rainfall; the early warning module uses a multi-criteria decision analysis method to form a slope status assessment of the target area.

[0127] In the embodiment of the present application, Figure 4 As shown, the present invention is based on the urban rail transit safety and resilience evaluation theory and provides an early warning method and system device for soil slope damage based on shear parameter prediction to solve the problem of insufficient warning sensitivity of existing devices in the pre-disaster early warning capability of geological slopes, thereby improving the safety and resilience of geological slopes.

[0128] Specifically, the early warning system may include a monitoring system (detection module), a prediction module and an early warning module.

[0129] The monitoring system includes a tubular moisture meter for soil slope monitoring, a pore water pressure sensor, an earth pressure sensor, a flow monitoring instrument, and an integrated rainfall monitoring station for monitoring rainfall. Real-time dynamic monitoring of the slope environment is achieved through multi-source monitoring. The tubular moisture meter is an integrated multi-parameter monitoring device that can be used to monitor changes in soil moisture content, soil temperature, and micro-electro-mechanical systems (MEMS) tilt sensor in real time; it can achieve continuous monitoring at multiple depths, one layer every 10 cm, and continuous monitoring at each depth, which is much higher than the monitoring continuity of the pin-type.

[0130] The water pressure sensor and earth pressure sensor are integrated into a signal box, powered by a mobile power supply, and buried at different depths as the construction progresses. The flow monitoring instrument is installed in the drainage troughs on both sides of the slope to monitor the flow of the surrounding environment. The integrated rainfall monitoring station is an automatic rainfall monitoring device that can monitor rainfall in real time and record data. It consists of sensors and data collectors. The sensor can measure rainfall and transmit data to the data collector. The data collector is responsible for collecting and storing rainfall data and transmitting the data to the central monitoring system or cloud platform through the communication module. Each monitoring instrument is powered by a mobile power supply, and the data is transmitted wirelessly to the base station, which is then transmitted to the computer. The base station is installed next to the roadbed for real-time wireless transmission of sensor monitoring data.

[0131] Through this embodiment, the monitoring system and the prediction module are integrated, and a comprehensive evaluation of the slope status is provided by comprehensively evaluating the real-time monitoring data and the prediction results, thereby improving the accuracy and credibility of the early warning.

[0132] According to another aspect of the embodiment of the present application, there is also provided an early warning device for implementing the above-mentioned early warning method for predicting soil slope failure based on shear resistance parameters. Figure 7 is a schematic structural diagram of an optional early warning device for predicting soil slope failure based on shear resistance parameters according to an embodiment of the present application, such as Figure 7 As shown, the device may include:

[0133] An acquisition unit 702 is used to acquire monitoring data of a target area at a target time, and predict the moisture content of the target area in combination with a moisture content prediction model, wherein the monitoring data includes consolidation condition data monitored by a pressure sensor;

[0134] A prediction unit 704 is used to predict a target shear strength parameter of the target area at the target time based on a shear parameter prediction model and in combination with the predicted moisture content and the consolidation condition data;

[0135] The early warning unit 706 is used to determine the early warning level corresponding to the target area according to the target shear strength parameter, and issue an early warning according to the early warning method corresponding to the early warning level.

[0136] It should be noted that the acquisition unit 902 in this embodiment can be used to execute the above step S102, the establishment unit 904 in this embodiment can be used to execute the above step S104, and the training unit 906 in this embodiment can be used to execute the above step S106.

[0137] Through the above modules, the monitoring data of the target area at the target time is obtained, and the moisture content of the target area is predicted in combination with the moisture content prediction model, wherein the monitoring data includes the consolidation condition data monitored by the pressure sensor; based on the shear parameter prediction model, the target shear strength parameters of the target area at the target time are predicted in combination with the predicted moisture content and consolidation condition data; the warning level corresponding to the target area is determined according to the target shear strength parameters, and the warning is given according to the warning method corresponding to the warning level. The real-time data obtained by the monitoring system and the influence relationship between moisture content, confining pressure and shear parameters obtained by indoor experiments are combined with machine learning methods to achieve accurate prediction of shear parameters under different environmental conditions. By comprehensively considering multiple factors, early and accurate warning information is provided for slope failure, which helps to take preventive and response measures in advance, thereby reducing potential losses.

[0138] In an exemplary embodiment, the acquiring unit includes:

[0139] A first acquisition module, used to acquire the monitoring data through a monitoring sensor, wherein the monitoring data includes rainfall, drainage ditch flow, and pore water pressure;

[0140] The second acquisition module is used to input the monitoring data into the moisture content prediction model for prediction to obtain the moisture content of the target area.

[0141] In an exemplary embodiment, the early warning unit comprises:

[0142] A determination module, used to determine early warning factors and weights corresponding to the early warning factors, wherein the early warning factors include target shear strength parameters, economic effect parameters, environmental effect parameters and safety requirement parameters;

[0143] A processing module, used for standardizing the raw data of the warning factors to obtain target data;

[0144] A first determination module, configured to determine a target score for the target area by combining the target data with a corresponding weight;

[0145] The second determination module is used to determine the warning level corresponding to the target area based on the target score.

[0146] In an exemplary embodiment, the prediction unit includes:

[0147] An input module, used to set the water content and consolidation ratio parameters as characteristic data and input them into the XGboost model, and use the target shear strength parameters as predicted target data;

[0148] The correction module is used to repeatedly correct the parameters of the XGboost model to obtain the shear parameter prediction model.

[0149] It should be noted here that the examples and scenarios implemented by the above-mentioned modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiments. It should be noted that the above-mentioned modules as part of the device can run in a hardware environment and can be implemented by software or hardware, wherein the hardware environment includes a network environment.

[0150] According to another aspect of the embodiment of the present application, a storage medium is further provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the above-mentioned early warning methods for predicting soil slope failure based on shear resistance parameters in the embodiment of the present application.

[0151] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps:

[0152] S1, obtaining monitoring data of a target area at a target time, and predicting the moisture content of the target area in combination with a moisture content prediction model, wherein the monitoring data includes consolidation condition data monitored by a pressure sensor;

[0153] S2, based on the shear parameter prediction model, combined with the predicted moisture content and consolidation condition data, predict the target shear strength parameters of the target area at the target time;

[0154] S3, determining the warning level corresponding to the target area according to the target shear strength parameter, and issuing a warning according to the warning method corresponding to the warning level.

[0155] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0156] Among them, computer-readable storage media may include, but are not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0157] According to another aspect of the embodiment of the present application, an electronic device for implementing the above-mentioned early warning method for predicting soil slope failure based on shear parameters is also provided. The electronic device can be a server, a terminal, or a combination thereof.

[0158] Figure 8 is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application, such as Figure 8 As shown, it includes a processor 802, a communication interface 804, a memory 806 and a communication bus 808, wherein the processor 802, the communication interface 804, and the memory 806 communicate with each other through the communication bus 808, wherein:

[0159] Memory 806, used for storing computer programs;

[0160] The processor 802 is used to execute the computer program stored in the memory 806 to implement the following steps:

[0161] S1, obtaining monitoring data of a target area at a target time, and predicting the moisture content of the target area in combination with a moisture content prediction model, wherein the monitoring data includes consolidation condition data monitored by a pressure sensor;

[0162] S2, based on the shear parameter prediction model, combined with the predicted moisture content and consolidation condition data, predict the target shear strength parameters of the target area at the target time;

[0163] S3, determining the warning level corresponding to the target area according to the target shear strength parameter, and issuing a warning according to the warning method corresponding to the warning level.

[0164] Optionally, the communication bus may be a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 The communication interface is used for communication between the electronic device and other devices.

[0165] The memory may include RAM, or may include non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0166] As an example, the memory 806 may include, but is not limited to, the acquisition unit 702, the prediction unit 704, and the warning unit 706 in the early warning device for predicting soil slope failure based on anti-shear parameters. In addition, it may also include, but is not limited to, other module units in the early warning device for predicting soil slope failure based on anti-shear parameters, which will not be repeated in this example.

[0167] The above-mentioned processor can be a general-purpose processor, which can include but not be limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0168] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0169] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0170] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0171] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0172] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0173] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0174] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program code.

[0175] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0176] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0177] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0178] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An early warning method for predicting soil slope failure based on shear parameters, characterized in that: include: Acquire monitoring data of a target area at a target time, and predict the moisture content of the target area in combination with a moisture content prediction model, wherein the monitoring data includes consolidation condition data monitored by a pressure sensor; Based on the shear parameter prediction model, combined with the predicted moisture content and the consolidation condition data, the target shear strength parameter of the target area at the target time is predicted; The warning level corresponding to the target area is determined according to the target shear strength parameter, and a warning is issued according to a warning method corresponding to the warning level.

2. The early warning method for predicting soil slope failure based on shear parameters according to claim 1, characterized in that: The acquiring of monitoring data of the target area at the target time and predicting the moisture content of the target area in combination with the moisture content prediction model comprises: The monitoring data is obtained through monitoring sensors, wherein the monitoring data includes rainfall, drainage ditch flow, and pore water pressure; The monitoring data is input into the moisture content prediction model for prediction to obtain the moisture content of the target area.

3. The early warning method for predicting soil slope failure based on shear parameters according to claim 1, characterized in that: Determining the warning level corresponding to the target area according to the target shear strength parameter, and issuing a warning according to the warning method corresponding to the warning level includes: Determining early warning factors and weights corresponding to the early warning factors, wherein the early warning factors include target shear strength parameters, economic effect parameters, environmental effect parameters, and safety requirement parameters; Standardizing the original data of the early warning factors to obtain target data; Determine the target score of the target area by combining the target data with the corresponding weight; A warning level corresponding to the target area is determined based on the target score.

4. The early warning method for predicting soil slope failure based on shear parameters according to claim 1, characterized in that: The method of predicting the target shear strength parameter of the target area at the target time based on the shear parameter prediction model and combining the predicted moisture content and the consolidation condition data includes: The water content and consolidation ratio parameters are set as characteristic data and input into the XGboost model, and the target shear strength parameter is used as the target data for prediction; The parameters of the XGboost model are repeatedly modified to obtain the shear parameter prediction model.

5. An early warning system for predicting soil slope failure based on shear parameters, using the early warning method for predicting soil slope failure based on shear parameters as claimed in any one of claims 1 to 4, comprising: Monitoring module, prediction module and early warning module; Among them, the monitoring module is used to collect monitoring data and transmit the monitoring data to the computer for processing. The prediction module is used to predict the target shear strength parameters of the target area at the target time. The early warning module is used to issue an early warning based on the early warning method corresponding to the early warning level.

6. The early warning system for predicting soil slope failure based on shear parameters according to claim 5, characterized in that: The monitoring module includes a tubular moisture meter for soil slope monitoring, a pore water pressure sensor, an earth pressure sensor, a flow monitoring instrument, and an integrated rainfall monitoring station for monitoring rainfall; The early warning module uses a multi-criteria decision analysis method to form a slope status assessment of the target area.

7. An early warning device for predicting soil slope failure based on shear resistance parameters, characterized in that: include: An acquisition unit is used to acquire monitoring data of a target area at a target time, and predict the moisture content of the target area in combination with a moisture content prediction model, wherein the monitoring data includes consolidation condition data monitored by a pressure sensor; A prediction unit, configured to predict a target shear strength parameter of the target area at the target time based on a shear parameter prediction model and in combination with the predicted moisture content and the consolidation condition data; The early warning unit is used to determine the early warning level corresponding to the target area according to the target shear strength parameter, and to issue an early warning according to the early warning method corresponding to the early warning level.

8. The early warning device for predicting soil slope failure based on shear resistance parameters according to claim 7, characterized in that: The acquisition unit comprises: A first acquisition module, used to acquire the monitoring data through a monitoring sensor, wherein the monitoring data includes rainfall, drainage ditch flow, and pore water pressure; The second acquisition module is used to input the monitoring data into the moisture content prediction model for prediction to obtain the moisture content of the target area.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 7 through the computer program.

Images