An artificial intelligence-based risk monitoring and early warning system for subgrade slopes

Abstract

An artificial intelligence-based risk monitoring and early warning system for roadbed slopes, which relates to the field of risk monitoring technology; obtains three-dimensional terrain data of the roadbed slope and constructs a three-dimensional terrain model, obtains surface vegetation images and surface vegetation parameters of each monitoring sub-region, constructs a first evaluation model based on the three-dimensional terrain data, surface vegetation parameters and their monitoring data of different monitoring sub-regions under the same monitoring scenario, and constructs a second evaluation model based on the three-dimensional terrain data, surface vegetation parameters and historical monitoring data in different historical accident sets, uses the second evaluation model to judge whether there is a risk area and generate early warning information, and uses the first evaluation model to obtain recommended vegetation parameters and generate a vegetation optimization plan; can generate targeted vegetation optimization plans for each monitoring sub-region and can predict whether the corresponding roadbed slope will have a safety accident.

Description

Technical Field

[0001] The present invention relates to the technical field of risk monitoring, and specifically to a subgrade slope risk monitoring and early warning system based on artificial intelligence. Background Art

[0002] It is a mature existing technology to use an unmanned aerial vehicle (UAV) equipped with different devices to inspect a subgrade slope and determine whether there is a safety accident. By collecting the point cloud data and surface images of the subgrade slope, and using big data analysis technology combined with the monitoring data, the current state of the subgrade slope can be obtained in real time. When a safety accident occurs, relevant personnel are notified for maintenance, which can significantly reduce the cost of manual inspection.

[0003] Most of the existing monitoring means rely on a single sensor, lack the fusion analysis of multi-modal data, and cannot ensure the accuracy of risk monitoring. Moreover, the influence of surface vegetation on the stability of the subgrade slope is often ignored in the existing technology. Excessive or insufficient surface vegetation will indirectly affect the stability of the subgrade slope. How to adjust the surface vegetation of the subgrade slope has become a problem to be solved. In view of the deficiencies of the existing technology, the present invention provides a subgrade slope risk monitoring and early warning system based on artificial intelligence. Summary of the Invention

[0004] The purpose of the present invention is to provide a subgrade slope risk monitoring and early warning system based on artificial intelligence.

[0005] The purpose of the present invention can be achieved by the following technical solutions: A subgrade slope risk monitoring and early warning system based on artificial intelligence includes the following modules:

[0006] A data acquisition module, which is used to obtain the three-dimensional terrain data of the subgrade slope, construct a three-dimensional terrain model, divide the subgrade slope into several monitoring sub-areas, obtain the surface vegetation images of each monitoring sub-area, and obtain the surface vegetation parameters of each monitoring sub-area according to the surface vegetation images.

[0007] A data monitoring module, which is used to set different monitoring terminals in each monitoring sub-area respectively, obtain the monitoring data respectively, and construct a first evaluation model of the subgrade slope according to the three-dimensional terrain data, surface vegetation parameters and monitoring data of different monitoring sub-areas under the same monitoring scenario.

[0008] A data analysis module, which is used to obtain the historical accident set of the subgrade slope, and construct a second evaluation model of the subgrade slope according to the three-dimensional terrain data, surface vegetation parameters and historical monitoring data in different historical accident sets.

[0009] A data evaluation module, which is used to input the three-dimensional terrain data, surface vegetation parameters, and real-time monitoring data of each monitoring sub-region into a second evaluation model to determine whether there are risk regions and generate early warning information;

[0010] A data optimization module, which is used to utilize a first evaluation model to combine the three-dimensional terrain data and expected monitoring data of each risk region to obtain recommended vegetation parameters and generate a vegetation optimization plan.

[0011] Furthermore, the process of obtaining the three-dimensional terrain data of the subgrade slope and constructing a three-dimensional terrain model, and dividing the subgrade slope into several monitoring sub-regions includes:

[0012] Mount a high-precision lidar on a drone to collect the three-dimensional terrain data of the subgrade slope. The three-dimensional terrain data includes three-dimensional point cloud data, slope and aspect, slope length and height, geographical location, texture information, and color information;

[0013] Use three-dimensional modeling technology to construct a three-dimensional terrain model of the subgrade slope according to the three-dimensional terrain data. In the three-dimensional terrain model, divide the subgrade slope to obtain several monitoring sub-regions.

[0014] Furthermore, the process of obtaining the surface vegetation images of each monitoring sub-region and obtaining the surface vegetation parameters of each monitoring sub-region according to the surface vegetation images includes:

[0015] Mount a multi-spectral camera on a drone to collect the surface vegetation images of each monitoring sub-region. Obtain the surface vegetation parameters according to the surface vegetation image and three-dimensional point cloud data of a single monitoring sub-region, including vegetation coverage rate S a 、leaf area index S b 、vegetation canopy volume density S c ;

[0016]

[0017] n is the number of vegetation regions divided in the surface vegetation image of the single monitoring sub-region by using a semantic segmentation algorithm, and i is the number of the divided vegetation regions, i = 1, 2,..., n;

[0018] is the vegetation existence coefficient of the i-th vegetation region, represents vegetation coverage, represents no vegetation coverage;

[0019] A p,i is the pixel area of the i-th vegetation region, which is converted into the actual area in combination with the ground resolution, and A t is the total area of the single monitoring sub-region;

[0020]

[0021] is a preset fixed parameter, are respectively the near-infrared band reflectance and the infrared band reflectance in the surface vegetation image of the single monitoring sub-region, is the solar zenith angle;

[0022]

[0023] m is the number of vegetation points in the vegetation area of the single monitoring sub-region in the three-dimensional point cloud data, j is the number of each vegetation point, j = 1, 2,..., m;

[0024] Z m,j is the elevation value of the j-th vegetation point, Z g,j is the ground elevation value of the vertical point of the j-th vegetation point on the ground, is the elevation layer thickness.

[0025] Further, the process of respectively setting different monitoring terminals in each monitoring sub-region and respectively obtaining monitoring data includes:

[0026] The monitoring terminal includes a rain gauge, a illuminance meter, a fiber Bragg grating displacement meter, a pore water pressure gauge, an earth pressure cell, a temperature and humidity sensor, and the monitoring data includes the rainfall, illuminance, displacement value, pore water pressure, stress value, temperature and humidity of each monitoring sub-region.

[0027] Further, the process of constructing the first evaluation model of the subgrade slope according to the three-dimensional terrain data, surface vegetation parameters and their monitoring data of different monitoring sub-regions under the same monitoring scenario includes:

[0028] The same monitoring scenario means that the rainfall and illuminance of each monitoring sub-region are the same. When the rainfall and illuminance of different monitoring sub-regions are the same, they are regarded as the same monitoring scenario;

[0029] Generate a first evaluation set according to the rainfall, illuminance, temperature and humidity, pore water pressure, three-dimensional terrain data, surface vegetation parameters, displacement value and stress value of different monitoring sub-regions under the same monitoring scenario, and divide the first evaluation set into a first training set and a first test set;

[0030] Construct a first convolutional neural network, use the rainfall, illuminance, temperature and humidity, pore water pressure, three-dimensional terrain data, and surface vegetation parameters in the first training set as the input data of the first convolutional neural network, and use the displacement value and stress value in the first training set as the output data of the first convolutional neural network;

[0031] Train the first convolutional neural network to obtain an initial first convolutional neural network, verify the model of the initial first convolutional neural network using a first test set, and output the initial first convolutional neural network with an error less than or equal to a preset first test error threshold as the first evaluation model.

[0032] Further, the process of obtaining the historical accident set of the subgrade slope and constructing the second evaluation model of the subgrade slope based on the three-dimensional terrain data, surface vegetation parameters, and historical monitoring data in different historical accident sets includes:

[0033] The historical accident set refers to the three-dimensional terrain data, surface vegetation parameters, and historical monitoring data corresponding to when a safety accident has occurred on the subgrade slope. The historical monitoring data refers to the monitoring data obtained when a safety accident occurs;

[0034] Generate a second evaluation set based on the three-dimensional terrain data, surface vegetation parameters, and historical monitoring data in different historical accident sets, and divide the second evaluation set into a second training set and a second test set;

[0035] Construct a second convolutional neural network, use the three-dimensional terrain data, surface vegetation parameters, and historical monitoring data in the second training set as the input data of the second convolutional neural network, and use whether a safety accident will occur on the subgrade slope as the output data of the second convolutional neural network;

[0036] Train the second convolutional neural network to obtain an initial second convolutional neural network, verify the model of the initial second convolutional neural network using a second test set, and output the initial second convolutional neural network with an error less than or equal to a preset second test error threshold as the second evaluation model.

[0037] Further, the process of inputting the three-dimensional terrain data, surface vegetation parameters, and real-time monitoring data of each monitoring sub-region into the second evaluation model to determine whether there is a risk area and generating a warning message includes:

[0038] Use the current monitoring data of a single monitoring sub-region as the real-time monitoring data, combine the three-dimensional terrain data and surface vegetation parameters of this single monitoring sub-region, and input them into the second evaluation model to use the second evaluation model to determine whether a safety accident will occur in this single monitoring sub-region;

[0039] If so, mark it as a risk area, generate a corresponding warning message, and feedback the warning message to relevant personnel. If not, mark it as a non-risk area.

[0040] Further, the process of using the first evaluation model to combine the three-dimensional terrain data and expected monitoring data of each risk area to obtain recommended vegetation parameters and generate a vegetation optimization plan includes:

[0041] Take the mean of the monitoring data corresponding to each non-risk area in the same monitoring scenario as the single risk area as the expected monitoring data of the single risk area;

[0042] Take the rainfall, light intensity, temperature and humidity, pore water pressure in the expected monitoring data of the single risk area and its three-dimensional terrain data and surface vegetation parameters as the input data of the first evaluation model;

[0043] Continuously adjust the input surface vegetation parameters until the output data of the first evaluation model is equal to the displacement value and stress value in the expected monitoring data of the single risk area, and take the surface vegetation parameters at this time as the recommended vegetation parameters;

[0044] Optimize the surface vegetation of the single risk area, including replacing the vegetation type, changing the vegetation spacing, pruning the vegetation branches and leaves, take the optimization plan that meets the recommended vegetation parameters as the vegetation optimization plan, and feedback it to the relevant personnel.

[0045] Compared with the prior art, the beneficial effects of the present invention are:

[0046] By dividing the subgrade slope into several monitoring sub-areas and obtaining the surface vegetation parameters of each monitoring sub-area, the present invention can incorporate the influence of surface vegetation on the stability of the subgrade slope into the monitoring scope. By setting different monitoring terminals and obtaining different monitoring data, and then constructing the first evaluation model of the subgrade slope, it can obtain the influence degree of different surface vegetation parameters on the monitoring data in the same monitoring scenario, and combine the expected monitoring data to obtain the recommended vegetation parameters of each monitoring sub-area, and can generate a targeted vegetation optimization plan for each monitoring sub-area;

[0047] By obtaining the historical accident set of the subgrade slope and constructing the second evaluation model of the subgrade slope according to the three-dimensional terrain data, surface vegetation parameters and historical monitoring data in different historical accident sets, and inputting the current data into the second evaluation model, it can predict whether the corresponding subgrade slope will have a safety accident and generate corresponding early warning information for feedback, which can timely remind the relevant personnel to repair it. Brief Description of the Drawings

[0048] Figure 1 It is a schematic diagram of the present invention. Detailed Embodiment

[0049] As Figure 1 shown, an artificial intelligence-based subgrade slope risk monitoring and early warning system includes the following modules:

[0050] The data acquisition module is used to obtain the three-dimensional terrain data of the roadbed slope, construct a three-dimensional terrain model, divide the roadbed slope into several monitoring sub-areas, obtain the surface vegetation images of each monitoring sub-area, and obtain the surface vegetation parameters of each monitoring sub-area according to the surface vegetation images;

[0051] The data monitoring module is used to respectively set different monitoring terminals in each monitoring sub-area, respectively obtain monitoring data, and construct the first evaluation model of the roadbed slope according to the three-dimensional terrain data, surface vegetation parameters and monitoring data of different monitoring sub-areas under the same monitoring scenario;

[0052] The data analysis module is used to obtain the historical accident set of the roadbed slope, and construct the second evaluation model of the roadbed slope according to the three-dimensional terrain data, surface vegetation parameters and historical monitoring data in different historical accident sets;

[0053] The data evaluation module is used to input the three-dimensional terrain data, surface vegetation parameters and real-time monitoring data of each monitoring sub-area into the second evaluation model to judge whether there are risk areas and generate early warning information;

[0054] The data optimization module is used to use the first evaluation model to combine the three-dimensional terrain data and expected monitoring data of each risk area to obtain recommended vegetation parameters and generate a vegetation optimization plan.

[0055] It should be further noted that in the specific implementation process, the process of obtaining the three-dimensional terrain data of the roadbed slope, constructing a three-dimensional terrain model, and dividing the roadbed slope into several monitoring sub-areas includes:

[0056] Mount a high-precision lidar on the unmanned aerial vehicle, and use the high-precision lidar to collect the three-dimensional terrain data of the roadbed slope. The three-dimensional terrain data includes three-dimensional point cloud data, slope and aspect, slope length and height, geographical location, texture information, color information, etc.;

[0057] Use three-dimensional modeling technology to construct a three-dimensional terrain model of the roadbed slope according to the collected three-dimensional terrain data. In the constructed three-dimensional terrain model, divide the roadbed slope to obtain several sub-areas with approximately equal areas, and mark the obtained sub-areas as monitoring sub-areas.

[0058] It should be further noted that in the specific implementation process, the process of obtaining the surface vegetation images of each monitoring sub-area and obtaining the surface vegetation parameters of each monitoring sub-area according to the surface vegetation images includes:

[0059] Mount a multispectral camera on the unmanned aerial vehicle, and use the multispectral camera to collect the surface vegetation images of each monitoring sub-area. The surface vegetation images can reflect the vegetation type, vegetation coverage, vegetation health status, vegetation height and density;

[0060] Taking a single monitoring sub-region as an example, surface vegetation parameters are obtained based on the surface vegetation image and its three-dimensional point cloud data of the single monitoring sub-region. The surface vegetation parameters include vegetation coverage rate, leaf area index, and vegetation canopy volume density, which are denoted as S a 、S b 、S c ;

[0061]

[0062] where n is the number of vegetation regions divided in the surface vegetation image of the single monitoring sub-region by using the semantic segmentation algorithm, i is the number of the divided vegetation regions, and i = 1, 2,..., n;

[0063] is the vegetation existence coefficient of the i-th vegetation region, represents vegetation coverage, represents no vegetation coverage;

[0064] A p,i is the pixel area of the i-th vegetation region, which is converted into the actual area by combining the ground resolution, and A t is the total area of the single monitoring sub-region;

[0065]

[0066] where, is a preset fixed parameter, are the near-infrared band reflectance and the infrared band reflectance in the surface vegetation image of the single monitoring sub-region respectively, is the solar zenith angle when the UAV is collecting images;

[0067]

[0068] where m is the number of vegetation points in the vegetation region of the single monitoring sub-region in the three-dimensional point cloud data, and j is the number of each vegetation point, and j = 1, 2,..., m;

[0069] Z m,j is the elevation value of the j-th vegetation point, and Z g,j is the ground elevation value of the vertical point of the j-th vegetation point on the ground, is the elevation layer thickness, and the value is 0.1 meter.

[0070] It should be further noted that in the specific implementation process, different monitoring terminals are set in each monitoring sub-region respectively, and the process of obtaining monitoring data respectively includes:

[0071] The monitoring terminal includes a rain gauge, a light intensity meter, a fiber Bragg grating displacement meter, a pore water pressure gauge, an earth pressure cell, and a temperature and humidity sensor. The monitoring data includes rainfall, light intensity, displacement value, pore water pressure, stress value, temperature and humidity of each monitoring sub-region.

[0072] The rainfall of the corresponding monitoring sub-region is obtained in real time through the rain gauge, the light intensity of the corresponding monitoring sub-region is obtained in real time through the light intensity meter, and the displacement value of the corresponding monitoring sub-region is obtained in real time through the fiber Bragg grating displacement meter.

[0073] The pore water pressure of the corresponding monitoring sub-region is obtained in real time through the pore water pressure gauge, the stress value of the corresponding monitoring sub-region is obtained in real time through the earth pressure cell, and the temperature and humidity of the corresponding monitoring sub-region are obtained in real time through the temperature and humidity sensor.

[0074] It should be further noted that in the specific implementation process, the process of constructing the first evaluation model of the subgrade slope according to the three-dimensional terrain data, surface vegetation parameters and monitoring data of different monitoring sub-regions under the same monitoring scenario includes:

[0075] The same monitoring scenario means that the weather conditions of each monitoring sub-region are the same, which is reflected in rainfall and light intensity. When the rainfall and light intensity of different monitoring sub-regions are the same, they are regarded as the same monitoring scenario.

[0076] A first evaluation set is generated according to the rainfall, light intensity, temperature and humidity, pore water pressure, three-dimensional terrain data, surface vegetation parameters and their corresponding displacement values and stress values of different monitoring sub-regions under the same monitoring scenario, and the first evaluation set is divided into a first training set and a first test set.

[0077] A first convolutional neural network is constructed. The different rainfall, light intensity, temperature and humidity, pore water pressure, three-dimensional terrain data, and surface vegetation parameters in the first training set are used as the input data of the first convolutional neural network, and the corresponding displacement values and stress values in the first training set are used as the output data of the first convolutional neural network.

[0078] The first convolutional neural network is trained to obtain an initial first convolutional neural network, and the initial first convolutional neural network is verified using the first test set. The initial first convolutional neural network with an output less than or equal to the preset first test error threshold is used as the corresponding first evaluation model.

[0079] It should be further noted that in the specific implementation process, the process of obtaining the historical accident set of the subgrade slope and constructing the second evaluation model of the subgrade slope according to the three-dimensional terrain data, surface vegetation parameters and historical monitoring data in different historical accident sets includes:

[0080] The set of historical accidents refers to the three-dimensional terrain data, surface vegetation parameters, and historical monitoring data corresponding to safety accidents that have occurred on the roadbed slope. The safety accidents include slope collapses, slope landslides, slope debris flows, slope surface erosion, etc. The historical monitoring data refers to the monitoring data obtained during safety accidents;

[0081] Generate a second evaluation set based on the three-dimensional terrain data, surface vegetation parameters, and historical monitoring data in different sets of historical accidents, and divide the second evaluation set into a second training set and a second test set;

[0082] Construct a second convolutional neural network, use the different three-dimensional terrain data, surface vegetation parameters, and historical monitoring data in the second training set as the input data of the second convolutional neural network, and use whether a safety accident will occur on the roadbed slope as the output data of the second convolutional neural network;

[0083] Train the second convolutional neural network to obtain an initial second convolutional neural network, use the second test set to verify the model of the initial second convolutional neural network, and output the initial second convolutional neural network with a second test error threshold less than or equal to the preset as the corresponding second evaluation model.

[0084] It should be further noted that in the specific implementation process, the process of inputting the three-dimensional terrain data, surface vegetation parameters, and real-time monitoring data of each monitoring sub-region into the second evaluation model to determine whether there is a risk area and generating a warning message includes:

[0085] Taking a single monitoring sub-region as an example, use the current monitoring data of this single monitoring sub-region as the real-time monitoring data, and combine the three-dimensional terrain data and surface vegetation parameters of this single monitoring sub-region and input them into the second evaluation model;

[0086] Use the second evaluation model to judge whether a safety accident will occur in this single monitoring sub-region according to the input data. If so, mark it as a risk area, generate a corresponding warning message, and feedback the generated warning message to relevant personnel to prompt relevant personnel to repair it in time. If not, mark it as a non-risk area and do not perform any other operations on it.

[0087] It should be further noted that in the specific implementation process, the process of using the first evaluation model to combine the three-dimensional terrain data and expected monitoring data of each risk area to obtain recommended vegetation parameters and generate a vegetation optimization plan includes:

[0088] In an embodiment of the present invention, the mean value of the monitoring data corresponding to each non-risk area in the same monitoring scenario as a single risk area is used as the expected monitoring data of the single risk area, and the rainfall, light intensity, temperature and humidity, pore water pressure in the expected monitoring data of the single risk area and their corresponding three-dimensional terrain data and surface vegetation parameters are used as the input data of the first evaluation model;

[0089] The input surface vegetation parameters are continuously adjusted until the output data of the first evaluation model is equal to the displacement value and stress value in the expected monitoring data of the single risk area, and the surface vegetation parameters at this time are used as the recommended vegetation parameters of the single risk area;

[0090] Vegetation optimization is carried out on the surface vegetation of the single risk area, including replacing the vegetation type, changing the vegetation spacing, pruning the vegetation branches and leaves, etc. The optimization plan that meets the recommended vegetation parameters is used as the corresponding vegetation optimization plan and is fed back to the relevant personnel to prompt the relevant personnel on how to optimize it.

[0091] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An artificial intelligence-based risk monitoring and early warning system for subgrade slopes, characterized in that, It includes the following modules: The data acquisition module is used to obtain the three-dimensional terrain data of the subgrade slope, construct a three-dimensional terrain model, divide the subgrade slope into several monitoring sub-areas, obtain the surface vegetation images of each monitoring sub-area, and obtain the surface vegetation parameters of each monitoring sub-area according to the surface vegetation images; The data monitoring module is used to set different monitoring terminals in each monitoring sub-area respectively, obtain the monitoring data respectively, and construct the first evaluation model of the subgrade slope according to the three-dimensional terrain data, surface vegetation parameters and monitoring data of different monitoring sub-areas under the same monitoring scenario; The data analysis module is used to obtain the historical accident set of the subgrade slope, and construct the second evaluation model of the subgrade slope according to the three-dimensional terrain data, surface vegetation parameters and historical monitoring data in different historical accident sets; The data evaluation module is used to input the three-dimensional terrain data, surface vegetation parameters and real-time monitoring data of each monitoring sub-area into the second evaluation model to judge whether there is a risk area, and generate a warning message; The data optimization module is used to use the first evaluation model to combine the three-dimensional terrain data and expected monitoring data of each risk area to obtain recommended vegetation parameters, and generate a vegetation optimization plan; The process of constructing the first evaluation model of the subgrade slope includes: The same monitoring scenario means that the rainfall and light intensity of each monitoring sub-area are the same. When the rainfall and light intensity of different monitoring sub-areas are the same, they are regarded as the same monitoring scenario; Generate the first evaluation set according to the rainfall, light intensity, temperature and humidity, pore water pressure, three-dimensional terrain data, surface vegetation parameters, displacement value and stress value of different monitoring sub-areas under the same monitoring scenario, and divide the first evaluation set into the first training set and the first test set; Construct the first convolutional neural network, use the rainfall, light intensity, temperature and humidity, pore water pressure, three-dimensional terrain data, surface vegetation parameters in the first training set as the input data of the first convolutional neural network, and use the displacement value and stress value in the first training set as the output data of the first convolutional neural network; Train the first convolutional neural network to obtain the initial first convolutional neural network, use the first test set to verify the model of the initial first convolutional neural network, and output the initial first convolutional neural network with the first test error threshold less than or equal to the preset value as the first evaluation model; The process of obtaining recommended vegetation parameters and generating a vegetation optimization plan includes: Take the mean value of the monitoring data corresponding to each non-risk area in the same monitoring scenario as the single risk area as the expected monitoring data of the single risk area; Use the rainfall, light intensity, temperature and humidity, pore water pressure in the expected monitoring data of the single risk area, its three-dimensional terrain data and surface vegetation parameters as the input data of the first evaluation model; Continuously adjust the input surface vegetation parameters until the output data of the first evaluation model is equal to the displacement value and stress value in the expected monitoring data of the single risk area, and take the surface vegetation parameters at this time as the recommended vegetation parameters; Optimize the surface vegetation of the single risk area, including replacing the vegetation type, changing the vegetation spacing, pruning the vegetation branches and leaves, taking the optimization plan that meets the recommended vegetation parameters as the vegetation optimization plan, and feeding it back to the relevant personnel.

2. The subgrade slope risk monitoring and early warning system based on artificial intelligence according to claim 1, wherein, The process of constructing a three-dimensional terrain model and dividing the monitoring sub-areas includes: Carry a high-precision lidar on the unmanned aerial vehicle to collect the three-dimensional terrain data of the roadbed slope, where the three-dimensional terrain data includes three-dimensional point cloud data, slope and aspect, slope length and height, geographical location, texture information, and color information; Use three-dimensional modeling technology to construct a three-dimensional terrain model of the roadbed slope based on the three-dimensional terrain data. In the three-dimensional terrain model, divide the roadbed slope to obtain several monitoring sub-areas.

3. The subgrade slope risk monitoring and early warning system based on artificial intelligence according to claim 2, characterized in that, The process of obtaining the surface vegetation image and its surface vegetation parameters includes: Mount a multispectral camera on a drone to collect surface vegetation images of each monitoring sub-region, and obtain surface vegetation parameters according to the surface vegetation images and three-dimensional point cloud data of a single monitoring sub-region, including vegetation coverage rate S a , leaf area index S b , vegetation canopy volume density S c ; n is the number of vegetation areas divided in the surface vegetation image of the single monitoring sub-area by using the semantic segmentation algorithm, and i is the number of the divided vegetation areas, i = 1, 2,..., n; is the vegetation existence coefficient of the i-th vegetation area, represents vegetation coverage, represents no vegetation coverage; A p,i is the pixel area of the i-th vegetation area, converted into the actual area by combining the ground resolution, A t is the total area of this single monitoring sub-region; is a preset fixed parameter, are respectively the near-infrared band reflectance and the infrared band reflectance in the surface vegetation image of the single monitoring sub-region, is the solar zenith angle; m is the number of vegetation points in the vegetation area of the single monitoring sub-area in the three-dimensional point cloud data, and j is the number of each vegetation point, j = 1, 2,..., m; Z m,j is the elevation value of the j-th vegetation point, Z g,j is the ground elevation value of the vertical point of the j-th vegetation point on the ground, is the elevation layer thickness.

4. The subgrade slope risk monitoring and early warning system based on artificial intelligence according to claim 3, characterized in that, The process of setting up the monitoring terminal and obtaining the monitoring data includes: The monitoring terminal includes a rain gauge, a light intensity meter, a fiber Bragg grating displacement meter, a pore water pressure gauge, an earth pressure cell, and a temperature and humidity sensor. The monitoring data includes the rainfall, light intensity, displacement value, pore water pressure, stress value, and temperature and humidity of each monitoring sub-area.

5. The subgrade slope risk monitoring and early warning system based on artificial intelligence according to claim 4, characterized in that, The process of constructing the second evaluation model of the roadbed slope includes: The historical accident set refers to the three-dimensional terrain data, surface vegetation parameters, and historical monitoring data corresponding to the safety accidents that have occurred on the roadbed slope. The historical monitoring data refers to the monitoring data obtained during the safety accidents; Generate a second evaluation set based on the three-dimensional terrain data, surface vegetation parameters, and historical monitoring data in different historical accident sets, and divide the second evaluation set into a second training set and a second test set; Construct a second convolutional neural network, take the three-dimensional terrain data, surface vegetation parameters, and historical monitoring data in the second training set as the input data of the second convolutional neural network, and take whether the roadbed slope will have a safety accident as the output data of the second convolutional neural network; Train the second convolutional neural network to obtain an initial second convolutional neural network, use the second test set to verify the model of the initial second convolutional neural network, and output the initial second convolutional neural network with an error less than or equal to the preset second test error threshold as the second evaluation model.

6. The subgrade slope risk monitoring and early warning system based on artificial intelligence according to claim 5, characterized in that, The process of judging whether there is a risk area and generating a warning message includes: Take the current monitoring data of the single monitoring sub-area as the real-time monitoring data, combine the three-dimensional terrain data and surface vegetation parameters of the single monitoring sub-area, input them into the second evaluation model, and use the second evaluation model to judge whether the single monitoring sub-area will have a safety accident; If so, mark it as a risk area, generate a corresponding warning message, and feed the warning message back to the relevant personnel. If not, mark it as a non-risk area.

Images