Cooperative intelligent early warning method and system for easily-weathered rock slope

Abstract

The invention provides a cooperative intelligent early warning method and system for an easily-weathered rock slope, and relates to the technical field of landslide early warning, and the method comprises the steps: obtaining first information, second information and third information; according to the second information, a relation curve of the soil weight, the cohesive force and the internal friction angle changing along with the moisture content is established, a function is fitted, and an accumulation body soil parameter function is obtained; performing slope-accumulation body model construction processing according to the first information and an accumulation body soil body parameter function, and calculating a stability coefficient and a potential instability range of an accumulation body to obtain sample data; constructing an accumulation body water and soil loss prediction model based on a preset neural network model and the sample data; and inputting the third information into the accumulation body water and soil loss prediction model for prediction processing, and dividing threat levels of the accumulation body and performing stability early warning. According to the method, multiple factors such as the landform, the soil parameters and the water and soil loss of the slope are comprehensively considered, so that a more comprehensive and reliable early warning result can be provided.

Description

Technical Field

[0001] The present invention relates to the technical field of landslide early warning, and in particular, to a collaborative intelligent early warning method and system for weathered rock slopes. Background Art

[0002] At present, landslide monitoring and early warning technologies have been widely applied to slope stability analysis. Existing landslide early warning methods usually rely on a large amount of statistical analysis or make rough judgments by combining the apparent deformation of landslides. However, research shows that the formation of landslides is the result of the combined action of multiple factors, including topography, geological conditions, and ground loads, which makes traditional early warning methods face many challenges in practical applications. Especially in the monitoring of accumulations, the volume of accumulations is usually smaller than that of landslides, and due to the limited installation of monitoring equipment for the slope deformation of accumulations, it is often difficult to conduct comprehensive and effective monitoring. In addition, existing slope displacement detection devices are costly and have high maintenance costs, with limited measurement accuracy, resulting in inaccurate and untimely early warning results, thus affecting the effectiveness and application value of the landslide early warning system.

[0003] Based on the above disadvantages of the existing technology, there is an urgent need for a collaborative intelligent early warning method and system for weathered rock slopes. Summary of the Invention

[0004] The purpose of the present invention is to provide a collaborative intelligent early warning method and system for weathered rock slopes to improve the above problems. To achieve the above purpose, the technical solutions adopted by the present invention are as follows:

[0005] In a first aspect, the present application provides a collaborative intelligent early warning method for weathered rock slopes, including:

[0006] Obtaining first information, second information, and third information, where the first information includes the geological information of the target slope, on-site monitoring point data, and slope soil parameters, the second information is the test data of the accumulation soil samples under different water contents, and the third information includes the real-time geometric parameters of the accumulation and the real-time water content monitoring data;

[0007] According to the second information, by analyzing the influence of water content on the accumulation soil parameters, establishing the relationship curves of soil unit weight, cohesion, and internal friction angle varying with water content and fitting functions, to obtain the accumulation soil parameter functions;

[0008] Performing slope-accumulation model construction processing according to the first information and the accumulation soil parameter functions, by setting different accumulation widths and slopes and adjusting soil parameters based on the change of water content, calculating the stability coefficient and potential instability range of the accumulation, to obtain sample data;

[0009] Construct a prediction model for soil and water loss of the accumulation body based on a preset neural network model and the sample data;

[0010] Input the third information into the prediction model for soil and water loss of the accumulation body for prediction processing. Obtain the prediction result by predicting the stability coefficient and potential instability range information of the accumulation body, and classify the threat level of the accumulation body and give a stability warning based on the prediction result.

[0011] In a second aspect, the present application also provides a collaborative intelligent warning system for easily weathered rock slopes, including:

[0012] An acquisition module for acquiring the first information, the second information and the third information. The first information includes the geological information of the target slope, the on-site monitoring point data and the slope soil parameters. The second information is the test data of the accumulation body soil sample under different water contents. The third information includes the real-time geometric parameters and real-time water content monitoring data of the accumulation body;

[0013] A fitting module for establishing a relationship curve of soil unit weight, cohesion and internal friction angle varying with water content and fitting a function according to the second information by analyzing the influence of water content on the accumulation body soil parameters to obtain an accumulation body soil parameter function;

[0014] A calculation module for constructing a slope-accumulation body model according to the first information and the accumulation body soil parameter function. By setting different accumulation widths and slopes and adjusting the soil parameters based on the change of water content, calculate the stability coefficient and potential instability range of the accumulation body to obtain the sample data;

[0015] A construction module for constructing a prediction model for soil and water loss of the accumulation body based on a preset neural network model and the sample data;

[0016] A prediction module for inputting the third information into the prediction model for soil and water loss of the accumulation body for prediction processing. Obtain the prediction result by predicting the stability coefficient and potential instability range information of the accumulation body, and classify the threat level of the accumulation body and give a stability warning based on the prediction result.

[0017] The beneficial effects of the present invention are:

[0018] Based on the real-time obtained accumulation body morphology and soil and water loss data, the present invention improves the accuracy and timeliness of early warning by intelligently identifying the stability of the accumulation body. By comprehensively considering multiple factors such as the terrain of the slope, soil parameters, and soil and water loss, more comprehensive and reliable early warning results can be provided. At the same time, the advantages of the present invention are reflected in that relatively accurate and reasonable stability prediction and soil and water loss early warning can be made for the existing accumulation body without a large amount of historical monitoring data. When warning of soil and water loss, without arranging too many other monitoring devices, the stability of the accumulation body can be accurately warned to a great extent, effectively saving costs and shortening the prediction time. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can be obtained based on these drawings.

[0020] Figure 1 Schematic flow chart of a collaborative intelligent early warning method for a weathered rock slope described in an embodiment of the present invention;

[0021] Figure 2 Schematic structural diagram of a collaborative intelligent early warning system for a weathered rock slope described in an embodiment of the present invention;

[0022] Figure 3 Schematic diagram of a slope model;

[0023] Figure 4 Schematic diagram of using Fish language to cut an accumulation body with structural planes;

[0024] Figure 5 Schematic diagram of soil and water loss rate calculation.

[0025] Reference numerals in the figures: 901, acquisition module; 902, fitting module; 903, calculation module; 904, construction module; 905, prediction module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and illustrated herein generally may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0027] It should be noted that like reference numerals and letters denote like items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present invention, terms such as "first" and "second" are only used for descriptive distinction and cannot be construed as indicating or implying relative importance.

[0028] Embodiment 1:

[0029] This embodiment provides a collaborative intelligent early warning method for weathered rock slopes.

[0030] See Figure 1 , which shows that this method includes steps S100 to S500.

[0031] Step S100, obtain the first information, the second information, and the third information. The first information includes the geological information of the target slope, the on-site monitoring point data, and the slope soil body parameters. The second information is the test data of the accumulated soil body samples under different water contents. The third information includes the real-time geometric parameters of the accumulated body and the real-time water content monitoring data;

[0032] It can be understood that the geological information of the target slope includes data such as the slope gradient, slope aspect, elevation, landform type, and formation lithology of the slope; the on-site monitoring point data includes the displacement of all monitoring points on the slope in space, the distance between monitoring points, and the inclination angle of the connection line; the real-time geometric parameters of the accumulated body are collected by unmanned aerial vehicle (UAV) oblique photography; the real-time water content monitoring data

[0033] Step S200, according to the second information, by analyzing the influence of the water content on the accumulated soil body parameters, establish the relationship curves of the soil unit weight, cohesion, and internal friction angle changing with the water content and fit the functions to obtain the accumulated soil body parameter functions;

[0034] Further, step S200 includes steps S210 to S230.

[0035] Step S210: Based on the second piece of information, perform data extraction and processing on the changing trends of the unit weight, cohesion, and internal friction angle of the soil mass, extract the corresponding data points of each soil parameter and water content, and obtain the initial soil parameter dataset;

[0036] In this step, through the data obtained on-site and in the laboratory, detailed data collection was carried out on the basic physical parameters of the soil mass such as unit weight, cohesion, and internal friction angle, and these parameters were correlated with the corresponding water content to form an initial dataset. Specifically, by extracting weathered and exfoliated accumulative soil mass on-site and bringing it back to the laboratory to configure in-situ soil samples with different water contents, direct shear tests, triaxial tests, etc. were carried out to collect data. This dataset contains key soil parameters that change with the water content and provides a basis for subsequent analysis.

[0037] Step S220: Perform curve fitting processing according to the initial soil parameter dataset. By constructing the relationship curves of the unit weight, cohesion, and internal friction angle of the soil mass changing with the water content, generate the soil parameter relationship curves;

[0038] Step S230: Perform fitting processing according to the soil parameter relationship curves. By establishing a parameter function model, generate a mathematical expression describing the relationship between the unit weight, cohesion, and internal friction angle and the water content change, and obtain the soil mass parameter function of the accumulative body.

[0039] It should be noted that in this step, by analyzing the specific influence of the water content on the soil mass parameters of the accumulative body, the quantitative relationship between these parameters and the water content is established. The soil mass parameter function of the accumulative body can accurately describe the response behavior of the soil parameters with respect to the water content, thus providing a necessary analysis basis when predicting the stability of the accumulative body.

[0040] Step S300: Perform slope-accumulative body model construction processing according to the first piece of information and the soil mass parameter function of the accumulative body. By setting different accumulation widths, accumulation slopes and adjusting the soil parameters based on the water content change, calculate the stability coefficient and potential instability range of the accumulative body to obtain the sample data;

[0041] Furthermore, step S300 includes steps S310 to S330.

[0042] Step S310: Establish the basic model of the slope according to the first piece of information, and construct the slope model part of the assumed accumulative body by connecting the platform edge and the slope top to obtain the slope-accumulative body model;

[0043] Step S320: Perform numerical processing according to the slope-accumulative body model. Based on the soil mass parameter function of the accumulative body, set different accumulation widths, accumulation slopes and water content change ranges, assign parameters to each structural plane and the lower region of the accumulative body, and treat the upper accumulative body region as an empty model to obtain the numerical calculation model;

[0044] Step S330: Based on the numerical calculation model, use the strength reduction method to calculate the stability of the accumulation body under different accumulation widths, accumulation slopes, and water contents, output the stability coefficient of the accumulation body, and calculate the potential instability range and the volume of the instability area for the models with stability less than the set threshold to generate sample data.

[0045] Specifically, in this step, by using the strength reduction method command in 3DEC, calculate the stability coefficient corresponding to each model. At the same time, for the models with stability less than 1.1, export the displacement isosurface and calculate the volume of the potential instability area.

[0046] It should be noted that in this process, first, based on the information such as the platform width, slope ratio, and slope height obtained previously, the basic part of the slope is constructed and connected to the assumed accumulation body part to form a complete slope model. Then, this model is converted into a detailed three-dimensional numerical model through digital software, including meshing the model, further cutting the structural plane of the accumulation body through programming in the numerical analysis software, and setting parameters according to different accumulation widths and slopes. In this model, the lower area of the accumulation body is given soil parameters that are precisely adjusted based on the change in water content, such as cohesion, internal friction angle, and unit weight, while the upper part is treated as an empty model.

[0047] Through such processing, the physical behavior of the slope and the accumulation body can be detailedly reproduced in the simulation environment, so as to accurately calculate the stability coefficient of the accumulation body and the potential instability range.

[0048] Furthermore, step S320 includes steps S321 to S323.

[0049] Step S321: Perform meshing processing according to the slope-accumulation body model. By dividing the slope and the accumulation body into multiple small units, a meshed model is obtained.

[0050] Step S322: According to the meshed model, based on the soil parameter function of the accumulation body, set different accumulation widths, accumulation slopes, and the range of water content changes, and perform soil parameter assignment processing on each structural plane and the lower area of the accumulation body to obtain the distribution of the assigned soil parameters.

[0051] Step S323: Perform empty model processing according to the distribution of the assigned soil parameters. By defining the upper area of the accumulation body as an empty model area, retaining the geometric structure and not assigning physical parameters, a numerical calculation model is obtained.

[0052] It should be noted that the weathered and exfoliated particles of weathered rock slopes usually form loose accumulations with low cohesion, so the slope shape of the accumulation is usually linear. On this premise, the basic part of the slope model is constructed based on the obtained platform width, slope ratio and slope height of the slope. Connect the edge of the platform with the top of the slope to construct the slope model part of the assumed accumulation, forming a complete slope model as shown in Figure 3 . The model is established by Rhinoceros software, then the mesh is divided by using the Griddle plug-in, and finally imported into 3DEC. In 3DEC, Fish language programming is used to cut the accumulation with structural planes. The settings of the cutting program adopt different platform accumulation widths (n) and accumulation slopes (m). At the same time, the Fish language automatically assigns parameters (o) to the accumulation below the cutting surface and an empty model to the upper accumulation to establish a numerical calculation model. As shown in Figure 4 , in the figure, P1, P i , P n represent the points in the platform width direction, R1, R i , R n represent the cutting angles, O represents the intersection of the bottom of the slope and the platform. The calling process of the Fish language is as follows: First, import the basic model; then, take the P i point at the end of the platform accumulation width as the necessary point, and cut according to the angle R1 at the end of the platform accumulation width; after the cutting is completed, assign parameters that gradually change from low to high according to the water content to the accumulation part below the cutting surface. At the same time, the upper area of the accumulation is set as an empty model to simulate the uncompacted part in reality. During the process of assigning model parameters, if the situation of parameter non-convergence is encountered, the system will suspend the current parameter assignment, return to the cutting step, adjust to the new R2 angle for re-cutting, and repeat the parameter assignment process. This cycle continues until all the combinations of the preset accumulation widths and angles are completed, ensuring the accuracy and reliability of the model. Such step-by-step processing not only enhances the adaptability of the model, but also improves the overall analysis efficiency and accuracy.

[0053] Step S400: Construct a prediction model for soil and water loss of the accumulation based on the preset neural network model and sample data;

[0054] Furthermore, step S400 includes steps S410 to S430.

[0055] Step S410: Use the platform accumulation width, accumulation height, slope ratio of the slope and the soil parameters of the accumulation in the sample data as the input features of the preset neural network model, and use the stability coefficient and potential instability range of the accumulation as the output labels of the model to construct a data set;

[0056] Step S420: Divide the data set into a training set and a test set according to a preset ratio, where 80% of the samples are used for training and 20% of the samples are used for testing;

[0057] Step S430: Input the training set into a preset neural network model for training. Through multiple iterations and model parameter optimization, and use the test set to verify the model, a prediction model for soil and water loss of the accumulation body is constructed.

[0058] In this embodiment, all samples are divided according to a ratio of 4:1, that is, 80% of the samples are used for training and 20% of the samples are used for prediction. By dividing the samples into a training set and a test set, the prediction accuracy of the model can be improved, making the model have higher prediction ability and better adaptability.

[0059] Step S500: Input the third information into the prediction model for soil and water loss of the accumulation body for prediction processing. Obtain the prediction result by predicting the stability coefficient and potential instability range information of the accumulation body, and divide the threat level of the accumulation body and conduct stability early warning based on the prediction result.

[0060] Further, step S500 includes step S510 to step S530.

[0061] Step S510: Extract the real-time geometric features of the accumulation body according to the third information. The real-time geometric features include the platform accumulation width, accumulation height, and accumulation area at the position of the typical section. Calculate the change amount of the accumulation area in two adjacent monitors, and combine the distance and time data to calculate the soil and water loss amount and soil and water loss rate of the accumulation body to obtain the soil and water loss calculation result;

[0062] It can be understood that the third information is the data collected by the UAV oblique photography technology. In this step, the original image data is exported and a three-dimensional model of the slope is constructed. This process includes the platform edge feature points based on the UAV data, import the original platform and slope information, and accurately extract the three-dimensional coordinates of the feature points on the slope surface of the accumulation body. These coordinate data enable us to calculate the platform accumulation width, height, and accumulation area at the position of the typical section of the accumulation body, providing basic data for further analysis. Immediately afterwards, calculate the soil and water loss amount and loss rate based on the accumulation area at the position of the typical section, and conduct soil and water loss early warning. As Figure 5 shown, where l in the figure represents the distance from the top of the previous accumulation body to the top of the slope, A2 and B2 respectively represent the two endpoints of the typical section position in the previous monitor, A1 and B1 respectively represent the two endpoints of the typical section position in the next monitor, O represents the intersection point of the bottom of the slope and the platform, and the soil and water loss amount is directly represented by the accumulation area S AOB at the position of the typical section; the soil and water loss rate is calculated by the following formula:

[0063]

[0064] Among them, v represents the soil and water loss rate; S A2OB2 and S A1OB1 respectively represent the increments of the accumulated areas at the positions of the typical cross-sections in the two consecutive monitoring times; l represents the distance from the top of the previous accumulation body to the top of the slope; t represents the time difference between the two consecutive monitoring times.

[0065] In this embodiment, a soil and water loss early warning level division standard is provided as shown in Table 1:

[0066] Table 1 Early warning level division

[0067] <![CDATA[Soil and water loss rate (×10 -5 )]]> Warning level v>50 Red: Warning level Ⅳ 10<v<＝50 Yellow: Warning level Ⅲ 5<v<＝10 Purple: Warning level Ⅱ v<＝5 Blue: Warning level Ⅰ

[0068] Step S520: Input the third information into the accumulation body soil and water loss prediction model, and combine with the neural network calculation result of the model to obtain a prediction result, where the prediction result includes the stability coefficient and the potential instability range of the current accumulation body;

[0069] Step S530: Perform threat level division processing according to the prediction result and the prediction result to obtain the threat level division result of the current accumulation body, and perform processing based on the division result to generate a soil and water loss early warning level and a stability early warning information.

[0070] Furthermore, the constructed neural network model and the geometric features of the accumulation body in the UAV oblique photography analysis result in the sample, the parameters of the accumulation body soil and rock mass of the moisture content monitoring value pointer of the accumulation body, and the slope ratio of the slope are used to predict the stability coefficient and the potential instability range information of the accumulation body in the model to obtain a prediction result. Finally, the potential threat level of the accumulation body is divided according to the obtained prediction result, and a stability early warning is carried out.

[0071] In this embodiment, an accumulation body early warning level division standard is provided as shown in Tables 2 - 4:

[0072] Table 2 Early warning level division

[0073] Stability coefficient Fs (toe platform) Warning level Fs ≤ 1.05 Yellow: Warning level Ⅲ 1.05 < Fs <= 1.10 Purple: Warning level Ⅱ 1.10 < Fs <= 1.20 Blue: Warning level Ⅰ Fs > 1.20 Blue: Warning level Ⅰ

[0074] Table 3 Early warning level division

[0075]

[0076] Table 4 Early warning level division

[0077] Stability coefficient Fs (> second-class slope) Warning level Fs ≤ 1.05 Red: Warning level Ⅳ 1.05 < Fs <= 1.10 Red: Warning level Ⅳ 1.10 < Fs <= 1.20 Yellow: Warning level Ⅲ Fs > 1.20 Purple: Warning level Ⅱ

[0078] Embodiment 2:

[0079] Such as Figure 2As shown in the figure, this embodiment provides a collaborative intelligent early warning system for weathered rock slopes, and the system includes:

[0080] An acquisition module 901, configured to acquire first information, second information, and third information. The first information includes geological information of the target slope, on-site monitoring point data, and slope soil parameters. The second information is test data under different water contents of the accumulated body soil sample. The third information includes real-time geometric parameters of the accumulated body and real-time water content monitoring data;

[0081] A fitting module 902, configured to, according to the second information, by analyzing the influence of water content on the soil parameters of the accumulated body, establish relationship curves of soil unit weight, cohesion, and internal friction angle varying with water content and fit functions, so as to obtain a soil parameter function of the accumulated body;

[0082] A calculation module 903, configured to perform slope-accumulated body model construction processing according to the first information and the soil parameter function of the accumulated body, calculate the stability coefficient and potential instability range of the accumulated body by setting different accumulated widths and slopes and adjusting soil parameters based on water content changes, so as to obtain sample data;

[0083] A construction module 904, configured to construct an accumulated body soil and water loss prediction model based on a preset neural network model and sample data;

[0084] A prediction module 905, configured to input the third information into the accumulated body soil and water loss prediction model for prediction processing, predict the stability coefficient and potential instability range information of the accumulated body to obtain a prediction result, and classify the threat level of the accumulated body and perform stability early warning based on the prediction result.

[0085] In a specific embodiment of the present invention, the fitting module 902 includes:

[0086] A first fitting unit, configured to, based on the second information, perform data extraction processing on the change trends of soil unit weight, cohesion, and internal friction angle, extract corresponding data points of each soil parameter and water content, so as to obtain an initial soil parameter data set;

[0087] A second fitting unit, configured to perform curve fitting processing according to the initial soil parameter data set, and generate a soil parameter relationship curve by constructing relationship curves of soil unit weight, cohesion, and internal friction angle varying with water content;

[0088] A third fitting unit, configured to perform fitting processing according to the soil parameter relationship curve, and generate a mathematical expression describing the relationship between unit weight, cohesion, and internal friction angle and water content change by establishing a parameter function model, so as to obtain a soil parameter function of the accumulated body.

[0089] In a specific embodiment of the present invention, the calculation module 903 includes:

[0090] The first calculation unit is configured to establish a basic model of the slope according to the first information, and obtain a slope-accumulation body model by constructing a part of the slope model of the assumed accumulation body by connecting the edge of the connecting platform and the top of the slope;

[0091] The second calculation unit is configured to perform numerical processing according to the slope-accumulation body model, set different accumulation widths, accumulation slopes and moisture content change ranges based on the accumulation body soil parameter function, assign parameters to each structural plane and the lower area of the accumulation body, and treat the upper accumulation body area as an empty model to obtain a numerical calculation model;

[0092] The third calculation unit, based on the numerical calculation model, uses the strength reduction method to calculate the stability of the accumulation body under different accumulation widths, accumulation slopes and moisture content conditions, outputs the stability coefficient of the accumulation body, and calculates the potential instability range and the volume of the instability area for the model with stability less than the set threshold to generate sample data.

[0093] In a specific embodiment of the present invention, the second calculation unit includes:

[0094] The fourth calculation unit is configured to perform mesh division processing according to the slope-accumulation body model, and obtain a meshed model by dividing the slope and the accumulation body into multiple small units;

[0095] The fifth calculation unit is configured to, according to the meshed model, set different accumulation widths, accumulation slopes and moisture content change ranges based on the accumulation body soil parameter function, and perform soil parameter assignment processing on each structural plane and the lower area of the accumulation body to obtain the soil parameter distribution after assignment;

[0096] The sixth calculation unit is configured to perform empty model processing according to the soil parameter distribution after assignment, and obtain a numerical calculation model by defining the upper area of the accumulation body as an empty model area, retaining the geometric structure and not assigning physical parameters.

[0097] In a specific embodiment of the present invention, the construction module 904 includes:

[0098] The first construction unit is configured to use the accumulation body platform accumulation width, accumulation height, slope gradient of the slope and the soil parameters of the accumulation body in the sample data as input features of a preset neural network model, and use the stability coefficient and potential instability range of the accumulation body as output labels of the model to construct a data set;

[0099] The second construction unit is configured to divide the data set into a training set and a test set according to a preset ratio, where 80% of the samples are used for training and 20% of the samples are used for testing;

[0100] The third construction unit is used to input the training set into a preset neural network model for training. Through multiple iterations and model parameter optimization, and using the test set to verify the model, a prediction model for soil and water loss of the accumulation body is constructed.

[0101] In a specific embodiment of the present invention, the prediction module 905 includes:

[0102] The first prediction unit is used to extract the real-time geometric features of the accumulation body according to the third information. The real-time geometric features include the platform accumulation width, the accumulation height, and the accumulation area at the typical cross-section position, calculate the change amount of the accumulation area in two adjacent monitors, and calculate the soil and water loss amount and the soil and water loss rate of the accumulation body in combination with the distance and time data to obtain the soil and water loss calculation result;

[0103] The second prediction unit is used to input the third information into the prediction model for soil and water loss of the accumulation body, and combine the neural network calculation result of the model to obtain the prediction result. The prediction result includes the stability coefficient and the potential instability range of the current accumulation body;

[0104] The third prediction unit is used to perform threat level classification processing according to the prediction result and the prediction result to obtain the threat level classification result of the current accumulation body, and process based on the classification result to generate the soil and water loss warning level and the stability warning information.

[0105] As described above, it is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should be covered within the protection scope of the present invention.

Claims

1. A collaborative intelligent early warning method for weathered rock slopes, characterized in that, Including: Obtain the first information, the second information, and the third information. The first information includes the geological information of the target slope, the on-site monitoring point data, and the slope soil parameters. The second information is the test data of the accumulated soil samples under different water contents. The third information includes the real-time geometric parameters of the accumulated body and the real-time water content monitoring data; According to the second information, by analyzing the influence of the water content on the accumulated body soil parameters, establish the relationship curves of the soil unit weight, cohesion, and internal friction angle varying with the water content and fit the functions to obtain the accumulated body soil parameter functions; Perform slope-accumulated body model construction processing according to the first information and the accumulated body soil parameter functions. By setting different accumulation widths, accumulation slopes, and adjusting the soil parameters based on the water content change, calculate the stability coefficient and potential instability range of the accumulated body to obtain the sample data; Construct an accumulated body soil erosion prediction model based on a preset neural network model and the sample data; Input the third information into the accumulated body soil erosion prediction model for prediction processing. Obtain the prediction result by predicting the stability coefficient and potential instability range information of the accumulated body, and classify the threat level of the accumulated body and give a stability warning based on the prediction result.

2. The collaborative intelligent early warning method for weathered rock slopes according to claim 1, characterized in that According to the second information, by analyzing the influence of the water content on the accumulated body soil parameters, establish the relationship curves of the soil unit weight, cohesion, and internal friction angle varying with the water content and fit the functions to obtain the accumulated body soil parameter functions, including: Based on the second information, perform data extraction processing on the change trends of the soil unit weight, cohesion, and internal friction angle, extract the corresponding data points of each soil parameter and the water content to obtain the initial soil parameter data set; Perform curve fitting processing according to the initial soil parameter data set. By constructing the relationship curves of the soil unit weight, cohesion, and internal friction angle varying with the water content, generate the soil parameter relationship curves; Perform fitting processing according to the soil parameter relationship curves. By establishing a parameter function model, generate a mathematical expression describing the relationship between the unit weight, cohesion, and internal friction angle and the water content change to obtain the accumulated body soil parameter functions.

3. The collaborative intelligent early warning method for weathered rock slopes according to claim 1, characterized in that Perform slope-accumulated body model construction processing according to the first information and the accumulated body soil parameter functions. By setting different accumulation widths, accumulation slopes, and adjusting the soil parameters based on the water content change, calculate the stability coefficient and potential instability range of the accumulated body to obtain the sample data, including: Establish the basic model of the slope according to the first information, and construct the slope model part of the assumed accumulated body by connecting the platform edge and the slope top to obtain the slope-accumulated body model; Perform numerical processing according to the slope-accumulated body model. Based on the accumulated body soil parameter functions, set different accumulation widths, accumulation slopes, and water content change ranges, assign parameters to each structural plane and the lower region of the accumulated body, and treat the upper accumulated body region as an empty model to obtain the numerical calculation model; Based on the numerical calculation model, the strength reduction method is used to calculate the stability of the accumulation body under different accumulation widths, accumulation slopes and water contents, and the stability coefficient of the accumulation body is output. For models with stability less than the set threshold, the potential instability range and the volume of the unstable area are calculated to generate sample data.

4. The collaborative intelligent early warning method for easily weathered rock slopes according to claim 1, characterized in that, Based on the preset neural network model and the sample data, a prediction model for soil and water loss of the accumulation body is constructed, including: Taking the accumulation width, accumulation height, slope ratio of the accumulation body platform and the soil parameters of the accumulation body in the sample data as the input features of the preset neural network model, and taking the stability coefficient and potential instability range of the accumulation body as the output labels of the model, a data set is constructed; The data set is divided into a training set and a test set according to a preset ratio, where 80% of the samples are used for training and 20% of the samples are used for testing; The training set is input into the preset neural network model for training. Through multiple iterations and model parameter optimization, and the test set is used to verify the model, a prediction model for soil and water loss of the accumulation body is constructed.

5. The collaborative intelligent early warning method for weathered rock slopes according to claim 1, characterized in that, Input the third information into the prediction model for soil and water loss of the accumulation body for prediction processing. The prediction result is obtained by predicting the stability coefficient and potential instability range information of the accumulation body, and the threat level of the accumulation body is divided and the stability early warning is carried out based on the prediction result, including: Extract the real-time geometric features of the accumulation body according to the third information. The real-time geometric features include the platform accumulation width, accumulation height and the accumulation area at the position of the typical section. Calculate the change amount of the accumulation area in two adjacent monitors, and combine the distance and time data to calculate the soil and water loss amount and soil and water loss rate of the accumulation body to obtain the soil and water loss calculation result; Input the third information into the prediction model for soil and water loss of the accumulation body, and combine the neural network calculation result of the model to obtain the prediction result, which includes the stability coefficient and potential instability range of the current accumulation body; Perform threat level division processing according to the prediction result and the prediction result to obtain the threat level division result of the current accumulation body, and generate the soil and water loss early warning level and stability early warning information based on the division result.

6. A collaborative intelligent early warning system for easily weathered rock slopes, characterized in that, Including: An acquisition module for acquiring the first information, the second information and the third information. The first information includes the geological information of the target slope, the on-site monitoring point data and the slope soil parameters. The second information is the test data of the accumulation body soil sample under different water contents. The third information includes the real-time geometric parameters and real-time water content monitoring data of the accumulation body; A fitting module for establishing a relationship curve of the unit weight, cohesion and internal friction angle varying with the water content and fitting the function according to the second information by analyzing the influence of the water content on the soil parameters of the accumulation body to obtain the soil parameter function of the accumulation body; A calculation module for constructing a slope-accumulation body model according to the first information and the soil parameter function of the accumulation body. By setting different accumulation widths and accumulation slopes and adjusting the soil parameters based on the change of the water content, calculate the stability coefficient and potential instability range of the accumulation body to obtain the sample data; A construction module, which constructs a prediction model for soil and water loss of the accumulation body based on a preset neural network model and the sample data; A prediction module, which is used to input the third information into the prediction model for soil and water loss of the accumulation body for prediction processing, obtain a prediction result by predicting the stability coefficient and potential instability range information of the accumulation body, and classify the threat level of the accumulation body and give a stability warning based on the prediction result.

7. The collaborative intelligent early warning system for a weathered rock slope according to claim 6, wherein The fitting module includes: A first fitting unit, which performs data extraction processing on the change trends of the unit weight, cohesion, and internal friction angle of the soil mass based on the second information, extracts the corresponding data points of each soil parameter and the water content, and obtains an initial soil parameter data set; A second fitting unit, which is used to perform curve fitting processing according to the initial soil parameter data set, and generates a soil parameter relationship curve by constructing the relationship curves of the unit weight, cohesion, and internal friction angle of the soil mass changing with the water content; A third fitting unit, which is used to perform fitting processing according to the soil parameter relationship curve, and generates a mathematical expression describing the relationship between the unit weight, cohesion, and internal friction angle and the water content change by establishing a parameter function model, and obtains the soil parameter function of the accumulation body.

8. The collaborative intelligent early warning system for a weathered rock slope according to claim 6, characterized in that, The calculation module includes: A first calculation unit, which is used to establish a basic model of the slope according to the first information, and obtain a slope-accumulation body model by connecting the edge of the connecting platform and the slope top to construct a part of the slope model of the hypothetical accumulation body; A second calculation unit, which is used to perform numerical processing according to the slope-accumulation body model, set different accumulation widths, accumulation slopes, and water content change ranges based on the soil parameter function of the accumulation body, assign parameters to each structural surface and the lower area of the accumulation body, and treat the upper accumulation body area as an empty model to obtain a numerical calculation model; A third calculation unit, based on the numerical calculation model, uses the strength reduction method to calculate the stability of the accumulation body under different accumulation widths, accumulation slopes, and water content conditions, outputs the stability coefficient of the accumulation body, and calculates the potential instability range and the volume of the instability area for the model with stability less than the set threshold to generate sample data.

9. The collaborative intelligent early warning system for a weathered rock slope according to claim 6, characterized in that, The construction module includes: A first construction unit, which is used to use the accumulation width, accumulation height, slope ratio of the slope, and soil parameters of the accumulation body in the sample data as the input features of the preset neural network model, and use the stability coefficient and potential instability range of the accumulation body as the output labels of the model to construct a data set; A second construction unit, which is used to divide the data set into a training set and a test set according to a preset ratio, where 80% of the samples are used for training and 20% of the samples are used for testing; A third construction unit, which is used to input the training set into the preset neural network model for training, optimize the model parameters through multiple iterations, and use the test set to verify the model to construct a prediction model for soil and water loss of the accumulation body.

10. The collaborative intelligent early warning system for a weathered rock slope according to claim 6, characterized in that, The prediction module includes: The first prediction unit is used to extract the real-time geometric features of the accumulation body according to the third information. The real-time geometric features include the platform accumulation width, the accumulation height, and the accumulation area at the typical cross-section position, calculate the change in the accumulation area in two adjacent monitors, and calculate the soil and water loss amount and the soil and water loss rate of the accumulation body in combination with the distance and time data to obtain the soil and water loss calculation result; The second prediction unit is used to input the third information into the soil and water loss prediction model of the accumulation body, and combine the neural network calculation result of the model to obtain the prediction result. The prediction result includes the stability coefficient and the potential instability range of the current accumulation body; The third prediction unit is used to perform threat level classification processing according to the prediction result and the prediction result to obtain the threat level classification result of the current accumulation body, and perform processing based on the classification result to generate the soil and water loss warning level and the stability warning information.

Images