Slope monitoring method and monitoring system based on Internet artificial intelligence

Abstract

The invention discloses a slope monitoring method and system based on Internet artificial intelligence, particularly relates to the technical field of slope monitoring, and solves the problems of slope terrain remodeling and intrinsic stress field parameter drift caused by engineering activities. Firstly, slope three-dimensional laser point cloud data are collected, and terrain remodeling is judged through a registration algorithm; analyzing the stress data change by adopting a long-short-term memory network, and evaluating the potential instability risk in the side slope; then determining a combined influence range by combining judgment; when the combined influence range exceeds the safety range, analyzing the shallow groundwater data by using a random forest regression algorithm, and quantifying the deterioration degree of the permeability stability; and finally, evaluating the overall safety risk of the side slope according to the degradation degree, and judging whether to carry out early warning response or not. Real-time data updating and model self-adaption are achieved, and the early warning accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of slope monitoring, and more specifically, to a slope monitoring method and a monitoring system based on Internet artificial intelligence. Background Art

[0002] Existing slope monitoring methods are mostly aimed at natural slopes that are stable for a long time and have little human interference. The monitoring model is usually trained based on the initial landform and initial physical parameters. However, in actual engineering activities such as local excavation, anchoring, and support construction, the local topography and internal stress state of the slope often change rapidly, resulting in a misalignment between the distribution of training data and actual working conditions, and obvious drift and mismatch of model parameters, which reduces the accuracy of monitoring and early warning.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a slope monitoring method and a monitoring system based on Internet artificial intelligence to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A slope monitoring method based on Internet artificial intelligence includes the following steps: Collect three-dimensional laser point cloud data of the slope, calculate the spatial geometric change area caused by local terrain reshaping based on the point cloud registration algorithm, and determine whether slope terrain reshaping has occurred; By analyzing the stress data changes in the stress drift area, the long short-term memory neural network algorithm is used to evaluate the potential instability risk level inside the slope. Based on the judgment result of whether the slope topography remodeling occurs and the potential instability risk level inside the slope, determine the combined impact range of the slope topography remodeling and the slope stress drift; When the combined influence range of slope topography remodeling and slope stress drift exceeds the safety range, the random forest regression algorithm is used to analyze the real-time monitoring data of shallow groundwater within the combined influence range to evaluate the degree of degradation of the internal seepage stability of the slope. Based on the degree of degradation of the internal seepage stability of the slope, the overall safety risk of the slope is assessed, and it is determined whether the slope has reached a state requiring an early warning response.

[0006] In a preferred embodiment, three-dimensional laser point cloud data of the slope is collected, and the spatial geometric change area caused by local terrain reshaping is calculated based on the point cloud registration algorithm to determine whether the slope terrain reshaping occurs, specifically: Collect initial 3D laser point cloud data of slope; Real-time collection of current 3D laser point cloud data of the slope; Calculate the deviation based on the feature matching point cloud registration algorithm; Extract point cloud deviations and determine abnormal areas; Analyze the magnitude of spatial deviation in abnormal areas to determine whether topographic remodeling has occurred: compare the average deviation value with the critical deviation threshold. If there is at least one abnormal area such that the average deviation value is greater than the critical deviation threshold, it is determined that slope topographic remodeling has occurred in the abnormal area.

[0007] In a preferred embodiment, by analyzing the stress data changes in the stress drift area, a long short-term memory neural network algorithm is used to evaluate the potential instability risk level inside the slope, specifically: Collect slope stress sensor data and construct continuous time series stress data; Filter the stress data to remove noise; Use trend analysis method to filter out high-variation data in the stress drift area; The sliding window technique is used to construct the local stress series sample data; Construct a long short-term memory neural network model to extract the dynamic change characteristics of stress; The potential instability risk level inside the slope is quantitatively assessed based on the model output.

[0008] In a preferred embodiment, based on the judgment result of whether the slope topography remodeling occurs and the potential instability risk level inside the slope, the combined influence range of the slope topography remodeling and the slope stress drift is determined, specifically: Preset the joint impact threshold and compare the joint impact coefficient with the joint impact threshold: When the combined influence coefficient is greater than or equal to the combined influence threshold, the combined influence range of slope topography remodeling and slope stress drift exceeds the safety range; When the combined influence coefficient is less than the combined influence threshold, the combined influence range of slope topography remodeling and slope stress drift does not exceed the safety range.

[0009] In a preferred embodiment, when the combined influence range of slope topography remodeling and slope stress drift exceeds the safety range, the random forest regression algorithm is used to analyze the real-time monitoring data of shallow groundwater within the combined influence range to evaluate the degree of degradation of the internal seepage stability of the slope, specifically: Collect real-time seepage data of shallow groundwater in the joint impact area; Carry out data correction on real-time seepage data; Construct a random forest regression model to train the groundwater seepage characteristic relationship; Predict groundwater seepage data by training models; The degree of slope seepage stability degradation is analyzed based on the predicted seepage data.

[0010] In a preferred embodiment, the overall safety risk of the slope is evaluated according to the degree of degradation of the seepage stability inside the slope, and it is determined whether the slope has reached a state requiring an early warning response, specifically: Integrate the seepage stability degradation coefficient and calculate the overall safety risk probability of the slope; A safety critical threshold is preset, and the overall safety risk probability of the slope is compared with the safety critical threshold to determine whether a state requiring an early warning response has been reached.

[0011] On the other hand, the present invention provides a slope monitoring system based on Internet artificial intelligence, including a terrain reshaping judgment unit, a risk level assessment unit, an impact range determination unit, a degradation degree assessment unit, and a safety risk assessment unit; The terrain reshaping judgment unit collects the three-dimensional laser point cloud data of the slope, calculates the spatial geometric change area caused by the local terrain reshaping based on the point cloud registration algorithm, and judges whether the slope terrain reshaping occurs; The risk level assessment unit analyzes the stress data changes in the stress drift area and uses the long short-term memory neural network algorithm to assess the potential instability risk level inside the slope; The impact range determination unit determines the combined impact range of slope topography remodeling and slope stress drift based on the judgment result of whether slope topography remodeling occurs and the potential instability risk level inside the slope; When the combined influence range of slope topography remodeling and slope stress drift exceeds the safety range, the deterioration degree assessment unit uses the random forest regression algorithm to analyze the real-time monitoring data of shallow groundwater within the combined influence range to assess the degree of degradation of the internal seepage stability of the slope; The safety risk assessment unit evaluates the overall safety risk of the slope based on the degree of degradation of the internal seepage stability of the slope, and determines whether the slope has reached a state requiring an early warning response.

[0012] The technical effects and advantages of the slope monitoring method and monitoring system based on Internet artificial intelligence of the present invention are as follows: By combining the three-dimensional laser point cloud registration algorithm with the long short-term memory network, real-time and accurate identification of local terrain remodeling and stress parameter drift of the slope is achieved, effectively solving the problems of parameter drift and model mismatch in existing models under severe human intervention scenarios; the random forest regression algorithm is introduced to analyze the degree of degradation of shallow groundwater seepage stability, thereby improving the accuracy of identifying hidden risks inside the slope; through real-time comparison of the overall safety risk probability with the preset safety critical threshold, it is possible to accurately judge whether the slope has entered the early warning response state, thereby improving the timeliness, accuracy and reliability of slope monitoring and early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A schematic diagram of a slope monitoring method based on Internet artificial intelligence of the present invention; Figure 2 The present invention is a schematic structural diagram of a slope monitoring system based on Internet artificial intelligence. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0015] Figure 1 The present invention provides a slope monitoring method based on Internet artificial intelligence, which includes the following steps: Collect three-dimensional laser point cloud data of the slope, calculate the spatial geometric change area caused by local terrain reshaping based on the point cloud registration algorithm, and determine whether slope terrain reshaping has occurred; By analyzing the stress data changes in the stress drift area, the long short-term memory neural network algorithm is used to evaluate the potential instability risk level inside the slope. Based on the judgment result of whether the slope topography remodeling occurs and the potential instability risk level inside the slope, determine the combined impact range of the slope topography remodeling and the slope stress drift; When the combined influence range of slope topography remodeling and slope stress drift exceeds the safety range, the random forest regression algorithm is used to analyze the real-time monitoring data of shallow groundwater within the combined influence range to evaluate the degree of degradation of the internal seepage stability of the slope. Based on the degree of degradation of the internal seepage stability of the slope, the overall safety risk of the slope is assessed, and it is determined whether the slope has reached a state requiring an early warning response.

[0016] Specifically, the three-dimensional laser point cloud data of the slope is collected, and the spatial geometric change area caused by local terrain reshaping is calculated based on the point cloud registration algorithm to determine whether the slope terrain reshaping occurs, including: Collect the initial 3D laser point cloud data of the slope: Use a high-precision laser scanner to fully scan the slope and collect the 3D laser point cloud data at the initial moment. Define the initial point cloud data set as: ;in, represents the initial point cloud data set, that is, the set of all three-dimensional points on the slope surface collected by the laser scanner for the first time; Represents the first The collected 3D points; Represents the total number of 3D points in the initial point cloud data set.

[0017] Each point They are expressed in Cartesian coordinate form as: ;in, Indicates The coordinate value of each point along the horizontal direction (X axis) in the initial point cloud data collection; Indicates The coordinate value of each point along the lateral direction (Y axis) perpendicular to the X axis in the initial point cloud data collection; Indicates The height or depth coordinate value of a point along the vertical direction (Z axis) in the initial point cloud data collection.

[0018] At the same time, in order to ensure the measurement accuracy, the error of the laser scanner is controlled within the allowable value after calibration. The initial point cloud data is filtered using a statistical outlier removal algorithm to generate a preprocessed initial point cloud data set. .

[0019] Real-time collection of current 3D laser point cloud data of the slope: When it is necessary to determine whether the slope has undergone terrain reshaping, real-time (current) 3D laser point cloud data of the slope is usually collected in the same area during a new monitoring cycle. The current point cloud data set is defined as: ;in, Represents the current point cloud data set, that is, the set of all three-dimensional points on the slope surface acquired in real time by the laser scanner in the new monitoring cycle; Indicates the number of points in the current point cloud data set. The collected 3D points; Indicates the total number of 3D points in the current point cloud data set.

[0020] Similarly, each point All are expressed in Cartesian coordinate form as: ;in, Indicates The coordinate value of each point along the horizontal direction (X axis) in the initial point cloud data collection; Indicates The coordinate value of each point along the lateral direction (Y axis) perpendicular to the X axis in the initial point cloud data collection; Indicates The height or depth coordinate value of a point along the vertical direction (Z axis) in the initial point cloud data collection.

[0021] The current point cloud data set is also subjected to noise filtering using the statistical outlier removal algorithm to generate a preprocessed current point cloud data set. .

[0022] Point cloud registration algorithm based on feature matching, calculation deviation: In order to compare the changes in slope terrain, the initial point cloud data set is calibrated using a point cloud registration algorithm based on feature matching. and the current point cloud data set Perform spatial alignment. Define the rigid transformation matrix solved during the registration process as: ;in, Represents the rigid transformation matrix, which is used to map the current point cloud data to the coordinate system of the initial point cloud data through rotation and translation; It is a 3×3 rotation matrix, which describes the rotation relationship between the current point cloud data and the initial point cloud data; It is a 3×1 translation vector, which describes the translation relationship between the current point cloud data and the initial point cloud data.

[0023] The goal of the point cloud registration algorithm is to solve the optimal rigid transformation matrix so that each point in the initial point cloud data Matching points corresponding to the current point cloud data The sum of squares of the Euclidean distances between them is the smallest, that is, the minimum value of the following calculation formula is solved: ;in, represents the set of allowed rigid transformations; Indicates the total number of successfully matched point pairs, that is, the number of point pairs that successfully establish a corresponding relationship between the initial point cloud data and the current point cloud data; Represents the matching function, which defines how to select the initial point cloud data from the current point cloud data The corresponding points; Indicates the difference between the current point cloud data and the initial point cloud data The corresponding matching points; represents the Euclidean distance function; Indicates the difference between the current point cloud data and the initial point cloud data The coordinates of the corresponding matching points after rigid transformation.

[0024] The point cloud registration algorithm uses an iterative method, and the error between the previous and next iterations is reduced to a threshold value. Stop when:

[0025] Extract point cloud deviation and determine abnormal areas: The deviation of each point calculated after registration is defined as: ;in, Indicates The spatial deviation values ​​of the matching point pairs are calculated. For all spatial deviation values, a predefined deviation threshold is set and the points with deviation values ​​greater than the deviation threshold are marked as abnormal points.

[0026] Use clustering algorithms (such as density-based DBSCAN algorithm) to group the outliers. Define the clustering results as: , ;in, Indicates A cluster, i.e., anomaly region, contains all the anomalies that are grouped into the same group by the clustering algorithm; Indicates the total number of identified abnormal regions.

[0027] Analyze the magnitude of spatial deviation in abnormal areas to determine whether terrain reshaping has occurred: For each cluster The deviation values ​​of all abnormal points in the statistic are counted and the average deviation value is calculated: ;in, Indicates The average deviation value of all points in the abnormal area; Indicates the midpoint of the abnormal area The spatial deviation value of Indicates the number of points in the anomaly area.

[0028] Compare the mean deviation value with the critical deviation threshold: If there is at least one abnormal area , so that the average deviation value is greater than the critical deviation threshold, then the abnormal area is judged Slope topography remodeling occurs.

[0029] In order to ensure the validity of the abnormal region, it is also necessary to verify the spatial continuity and scale of the abnormal region. The abnormal region boundary size is used for judgment, and the minimum boundary size is defined as and the maximum border size is ;in, The minimum boundary size required for the anomaly region to be spatially coherent; Indicates the maximum boundary size required for an anomaly region to be spatially coherent.

[0030] Only when the abnormal region boundary size meets The abnormal area is considered valid only when the slope topography is reshaped. Indicates the size of the abnormal area boundary.

[0031] Specifically, by analyzing the stress data changes in the stress drift area, the long short-term memory neural network algorithm is used to evaluate the potential instability risk level inside the slope, including: Collect slope stress sensor data and construct continuous time series stress data: Stress sensors are deployed in the slope, and each sensor uploads stress measurement values ​​in real time through the Internet. The number of stress sensors is defined as , the number of sampling points is The original collected stress data is defined as: , ; .in, Indicates The stress sensor is Stress measurement values ​​at sampling points; represents the total number of stress sensors; Indicates the total number of sampling points.

[0032] Filter the stress data to remove noise interference: In order to improve the accuracy of the analysis, it is necessary to filter the original time series stress data to remove high-frequency noise or outliers. The filtered data is: ;in, Represents the stress data obtained after filtering; Represents a filter function, which is used for noise suppression and smoothing. Algorithms such as Kalman filtering and wavelet threshold filtering can be used.

[0033] Use trend analysis to filter out high-variation data in the stress drift area: After filtering, trend analysis is required to identify whether there is local stress drift. Define a trend function to determine the direction and magnitude of stress change of the same stress sensor over a period of time. After applying it to the data of each stress sensor, we get ;in, Indicates The stress sensor is The stress change trend value of each sampling point. The larger the value, the stronger the stress change, and the smaller the value, the relatively gentle stress change. Represents a trend analysis function, which is used to calculate the changing trend of input data, using statistical indicators such as linear regression slope and moving average change rate; Indicates the The sampling point is the center, and the front and back are and The stress data segment obtained after filtering is composed of sampling points.

[0034] Set a high change threshold. If the stress change trend value is greater than the high change threshold, it means that If the stress of a sampling point changes significantly, it can be considered that there is a sign of potential stress drift. At this time, the stress data of this point can be marked as high-variation data.

[0035] Use sliding window technology to construct local stress sequence sample data: After obtaining high-variation data through screening, it is necessary to analyze the local time series of high-variation data to capture the dynamic evolution characteristics of stress. , for each high-variation data, extract the total before and after The stress data at each moment constructs a sequence sample. ;in, Indicates The sampling point is the center, A stress data sequence collected by a stress sensor; Indicates the length of the sliding window; Respectively expressed in Among the stress sensors, the central sampling point Forward and backward Stress data of the sampling points.

[0036] Through the sliding window technology, the continuously changing segments in the time dimension can be retained, providing temporal context information for the training or prediction of deep recurrent networks.

[0037] Construct a long short-term memory neural network model to extract the dynamic change characteristics of stress: In order to capture the long-term and short-term correlation characteristics of slope stress in the time domain, a long short-term memory network structure is used. The data vector corresponding to each moment of the input stress data sequence is defined as: ;in, Represents the stress data sequence input into the long short-term memory network; Time index, ranging from 0 to .

[0038] The LSTM network contains structures such as forget gate, input gate and output gate to control the accumulation and forgetting of information in the time series, so as to better learn the hidden pattern of stress evolution over time. The output of the LSTM network is defined as ;in, It means that after being processed by the long short-term memory neural network The stress sensor is The characteristic output of each sampling point may be a scalar, vector or high-dimensional feature representation, which is used to reflect the implicit pattern of the dynamic change of stress at the sampling point; It represents the long short-term memory neural network model, which is a neural network operation that processes the input sequence. It contains gating mechanisms such as forget gate, input gate and output gate to capture long-term and short-term dependencies in time series data.

[0039] Quantitative evaluation of the potential instability risk level inside the slope based on model output: After obtaining the characteristic output of the long short-term memory neural network for the stress sequence Finally, the risk assessment function is defined to normalize the characteristic output, so as to quantitatively assess the potential instability risk level inside the slope. Its expression is: ;in, Indicates The stress sensor is The instability risk value of each sampling point is in the range of 0 to 1; represents the risk assessment function, which can be implemented based on a multilayer perceptron, a normalization method, or a pre-trained rule.

[0040] The first instability risk threshold and the second instability risk threshold are preset, and the first instability risk threshold is smaller than the second instability risk threshold. Different risk levels are divided according to the size range of the instability risk value: When the instability risk value is less than the first instability risk threshold, the potential instability risk level inside the slope is classified as a safe state; When the instability risk value is greater than or equal to the first instability risk threshold and less than the second instability risk threshold, the potential instability risk level inside the slope is classified as low risk; When the instability risk value is greater than or equal to the second instability risk threshold and less than 1, the potential instability risk level inside the slope is classified as high risk.

[0041] Specifically, based on the judgment result of whether the slope topography remodeling occurs and the potential instability risk level inside the slope, the combined impact range of the slope topography remodeling and the slope stress drift is determined, including: Defining slope remodeling indicators ,when When , it indicates that the slope topography is reshaped. , indicating that no slope topography remodeling has occurred.

[0042] The potential instability risk levels within the slope include safe state, low risk and high risk. Similarly, the instability risk level indicator will be defined ,when When the potential instability risk level inside the slope is safe; when When , the potential instability risk level inside the slope is low risk; when When , the potential instability risk level inside the slope is high.

[0043] According to the slope topography remodeling indicator and the instability risk level indicator, the joint influence coefficient is calculated, and the calculation formula is: ;in, It represents the combined influence coefficient, which is used to determine the combined influence range of slope topography remodeling and slope stress drift; and They are the weight coefficients of the slope topography remodeling indicator and the instability risk level indicator, respectively. Their values ​​are determined according to the actual project conditions to reflect the relative importance of the slope geometry change and stress change in the overall impact. It represents the slope topography remodeling indicator; Indicates the instability risk level indicator.

[0044] Preset the joint impact threshold and compare the joint impact coefficient with the joint impact threshold: When the combined influence coefficient is greater than or equal to the combined influence threshold, it indicates that the slope area has significant geometric terrain remodeling and a high potential instability risk at the same time, indicating that the slope area is facing a potential deterioration of stability under the combined influence, which is very likely to develop into actual instability; at this time, the combined influence range of slope terrain remodeling and slope stress drift exceeds the safety range; When the combined influence coefficient is less than the combined influence threshold, it indicates that a certain degree of topographic remodeling or stress drift may have occurred locally on the slope, but the combined impact of the two has not reached a critical level; the slope area is generally within a controllable or safe range, and no emergency intervention measures are needed immediately; at this time, the combined influence range of slope topographic remodeling and slope stress drift does not exceed the safety range.

[0045] The setting of the combined impact threshold is a key parameter determined based on historical monitoring data, field experiments and expert evaluation, which is used to classify whether the combined effects of slope topography remodeling and stress drift have reached a dangerous level.

[0046] Specifically, when the combined influence range of slope topography remodeling and slope stress drift exceeds the safety range, the random forest regression algorithm is used to analyze the real-time monitoring data of shallow groundwater within the combined influence range to evaluate the degree of degradation of the internal seepage stability of the slope, including: Collect real-time seepage data of shallow groundwater in the joint influence area: Deploy shallow groundwater monitoring devices in the determined joint influence area (i.e., the intersection of the slope area where slope topography reshaping occurs and the stress drift area), and use wireless transmission technology to collect groundwater seepage data in real time. The data collected by each groundwater monitoring device in a continuous period of time constitutes a time series data set. Groundwater monitoring equipment is in The groundwater seepage rate collected at the sampling points is: ;in, Indicates Groundwater monitoring equipment is in Groundwater seepage rate collected at sampling points; Indicates the total number of groundwater monitoring devices; It indicates the total number of sampling points of each groundwater monitoring equipment during the monitoring period.

[0047] Data correction of real-time seepage data: Since there may be instrument drift, environmental interference and data noise in the actual measurement process, the original seepage data needs to be corrected and preprocessed. The data correction function is introduced to process each collected original seepage data, and the corrected seepage data is obtained as follows: ;in, Indicates the corrected Groundwater monitoring equipment is in Seepage data of sampling points; represents the correction function, which usually adopts an algorithm based on sliding average or Kalman filtering.

[0048] The purpose of the calibration process is to eliminate the interference of instrument deviation and outliers and obtain more stable and accurate groundwater seepage rate data. It can be used as a reliable input for model training and prediction.

[0049] Construct a random forest regression model to train the characteristic relationship of groundwater seepage: Use the corrected seepage data to construct a random forest regression model to establish the characteristic relationship between groundwater seepage and slope seepage state. First, construct a training sample set. Set the feature vector and the target variable They are: , ;in, Indicates Groundwater monitoring equipment is in The feature vector constructed from the sampling points contains the current and previous Correction data for each sampling point; is the length of the feature vector; Represents the corresponding target vector, that is, predicting the next sampling point (i.e. The seepage data of the sampling points.

[0050] After building the random forest regression model, the goal of model training is to minimize the prediction error, which is expressed as: ;in, Represents the set of parameters for all trees in the random forest regression model; Represents the random forest regression model based on model parameters For the input feature vector Predicted seepage data; Represents the set of all adjustable parameters in the random forest regression model, including the threshold for dividing nodes in each tree, the selected features, the predicted value of leaf nodes, etc. During model training, parameters It will be continuously optimized so that the model can more accurately map the input features to the target prediction values, thereby minimizing the prediction error.

[0051] After the random forest regression model is trained, the model can fully capture the nonlinear relationship and multi-time correlation characteristics of groundwater seepage data, providing data support for prediction.

[0052] Predict groundwater seepage data through training models: Use the trained random forest regression model to predict groundwater seepage in the joint impact area. Groundwater monitoring equipment is in sampling points, using the feature vector Calculate the predicted value: ;in, Indicates Groundwater monitoring equipment is in Predicted seepage data of sampling points; A function map representing a random forest regression model.

[0053] The prediction results can reveal the changes in groundwater seepage paths and the changing trends in seepage velocity. By comparing the predicted data with historical data, the dynamic evolution of groundwater movement can be determined.

[0054] Analyze the degradation degree of slope seepage stability based on predicted seepage data: Based on the predicted groundwater seepage data, use trend analysis and statistical methods to evaluate the degradation degree of the internal seepage stability of the slope. Set the seepage stability degradation evaluation function to calculate the predicted results: ;in, It represents the seepage stability degradation coefficient, reflecting the impact of seepage data changes on slope stability; It represents the seepage stability degradation assessment function, which is used to map the predicted seepage data into the seepage stability degradation coefficient. It is designed based on statistical indicators (such as standard deviation, change rate, cumulative change, etc.) or combined with expert experience rules to quantitatively reflect the relationship between groundwater seepage changes and slope seepage stability.

[0055] The larger the permeability stability degradation coefficient, the more abnormal water infiltration in the slope is, and the more significant the impact of water erosion on the rock and soil structure is. A larger permeability stability degradation coefficient usually indicates that local saturation and decreased shear strength may have occurred inside the slope, which in turn increases the risk of landslide instability. It is necessary to take measures such as engineering reinforcement and drainage to ensure the overall safety of the slope.

[0056] Specifically, according to the degree of degradation of the seepage stability inside the slope, the overall safety risk of the slope is assessed, and it is determined whether the slope has reached a state requiring an early warning response, including: Integrate the seepage stability degradation coefficient and calculate the overall safety risk probability of the slope: Integrate the seepage stability degradation coefficients obtained by various groundwater monitoring equipment in the joint impact area: , ;in, Represents the total number of groundwater monitoring devices.

[0057] Through weighted average, the seepage stability degradation coefficient is integrated into the overall safety risk probability of the slope, and its calculation formula is: ;in, It represents the overall safety risk probability of the slope, and its value range is usually normalized to 0 to 1; Indicates The weight factor corresponding to the slope area monitored by each groundwater monitoring device is determined based on the area of ​​the area, the credibility of the monitoring data or other actual project parameters to ensure that the impact of each slope area on the overall risk assessment is distributed proportionally.

[0058] Preset the critical safety threshold, compare the overall safety risk probability of the slope with the critical safety threshold, and determine whether a state requiring an early warning response has been reached: When the overall safety risk probability of the slope is greater than or equal to the critical safety threshold, it means that the overall safety risk of the slope is high, the overall structural stability is seriously threatened, and a state is reached where an early warning response is required; the management department needs to immediately activate the early warning response mechanism, take emergency measures such as engineering reinforcement, drainage diversion, local support, and strengthen on-site inspections and monitoring; When the overall safety risk probability of the slope is greater than or equal to the critical safety threshold, it indicates that the overall state of the slope is relatively safe, the overall safety risk of the slope is low, and has not reached a state that requires an early warning response; at this time, routine monitoring work can be maintained, data can be reviewed regularly according to the normal monitoring cycle, the changing trend of the slope hydrological conditions can be recorded, and continuous attention can be paid to the deterioration of local seepage stability.

[0059] The setting of the critical safety threshold is based on a large amount of historical monitoring data, field test results and numerical simulation analysis. Statistical methods and expert experience are used to determine a risk probability value, which reflects the stability limit state of the slope under various working conditions. It takes into account factors such as geological conditions, rainfall impact, and engineering activities to ensure that it can truly reflect the overall stability of the slope. Example

[0060] The difference between Example 2 of the present invention and Example 1 is that this example introduces a slope monitoring system based on Internet artificial intelligence.

[0061] Figure 2A schematic structural diagram of a slope monitoring system based on Internet artificial intelligence of the present invention is given, and a slope monitoring system based on Internet artificial intelligence includes a terrain reshaping judgment unit, a risk level assessment unit, an impact range determination unit, a degradation degree assessment unit and a safety risk assessment unit; The terrain reshaping judgment unit collects the three-dimensional laser point cloud data of the slope, calculates the spatial geometric change area caused by the local terrain reshaping based on the point cloud registration algorithm, and judges whether the slope terrain reshaping occurs; The risk level assessment unit analyzes the stress data changes in the stress drift area and uses the long short-term memory neural network algorithm to assess the potential instability risk level inside the slope; The impact range determination unit determines the combined impact range of slope topography remodeling and slope stress drift based on the judgment result of whether slope topography remodeling occurs and the potential instability risk level inside the slope; When the combined influence range of slope topography remodeling and slope stress drift exceeds the safety range, the deterioration degree assessment unit uses the random forest regression algorithm to analyze the real-time monitoring data of shallow groundwater within the combined influence range to assess the degradation degree of the internal seepage stability of the slope; The safety risk assessment unit evaluates the overall safety risk of the slope based on the degree of degradation of the internal seepage stability of the slope, and determines whether the slope has reached a state requiring an early warning response.

[0062] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0063] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or may be transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0064] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0065] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0066] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules 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 interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0067] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0068] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0069] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0070] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0071] Finally: 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, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A slope monitoring method based on Internet artificial intelligence, characterized in that: The steps include: Collect three-dimensional laser point cloud data of the slope, calculate the spatial geometric change area caused by local terrain reshaping based on the point cloud registration algorithm, and determine whether slope terrain reshaping has occurred; By analyzing the stress data changes in the stress drift area, the long short-term memory neural network algorithm is used to evaluate the potential instability risk level inside the slope. Based on the judgment result of whether the slope topography remodeling occurs and the potential instability risk level inside the slope, determine the combined impact range of the slope topography remodeling and the slope stress drift; When the combined influence range of slope topography remodeling and slope stress drift exceeds the safety range, the random forest regression algorithm is used to analyze the real-time monitoring data of shallow groundwater within the combined influence range to evaluate the degree of degradation of the internal seepage stability of the slope. Based on the degree of degradation of the internal seepage stability of the slope, the overall safety risk of the slope is assessed, and it is determined whether the slope has reached a state requiring an early warning response.

2. The slope monitoring method based on Internet artificial intelligence according to claim 1 is characterized in that: Collect the three-dimensional laser point cloud data of the slope, calculate the spatial geometric change area caused by local terrain reshaping based on the point cloud registration algorithm, and determine whether the slope terrain reshaping occurs. Specifically: Collect initial 3D laser point cloud data of slope; Real-time collection of current 3D laser point cloud data of the slope; Calculate the deviation based on the feature matching point cloud registration algorithm; Extract point cloud deviations and determine abnormal areas; Analyze the magnitude of spatial deviation in abnormal areas to determine whether topographic remodeling has occurred: compare the average deviation value with the critical deviation threshold. If there is at least one abnormal area such that the average deviation value is greater than the critical deviation threshold, it is determined that slope topographic remodeling has occurred in the abnormal area.

3. The slope monitoring method based on Internet artificial intelligence according to claim 2 is characterized in that: By analyzing the stress data changes in the stress drift area, the long short-term memory neural network algorithm is used to evaluate the potential instability risk level inside the slope, specifically: Collect slope stress sensor data and construct continuous time series stress data; Filter the stress data to remove noise; Use trend analysis method to filter out high-variation data in the stress drift area; The sliding window technique is used to construct the local stress series sample data; Construct a long short-term memory neural network model to extract the dynamic change characteristics of stress; The potential instability risk level inside the slope is quantitatively assessed based on the model output.

4. The slope monitoring method based on Internet artificial intelligence according to claim 3 is characterized in that: Based on the judgment result of whether the slope topography remodeling occurs and the potential instability risk level inside the slope, the combined influence range of the slope topography remodeling and the slope stress drift is determined, specifically: Preset the joint impact threshold and compare the joint impact coefficient with the joint impact threshold: When the combined influence coefficient is greater than or equal to the combined influence threshold, the combined influence range of slope topography remodeling and slope stress drift exceeds the safety range; When the combined influence coefficient is less than the combined influence threshold, the combined influence range of slope topography remodeling and slope stress drift does not exceed the safety range.

5. The slope monitoring method based on Internet artificial intelligence according to claim 4 is characterized in that: When the combined influence range of slope topography remodeling and slope stress drift exceeds the safety range, the random forest regression algorithm is used to analyze the real-time monitoring data of shallow groundwater within the combined influence range to evaluate the degree of degradation of the internal seepage stability of the slope, specifically: Collect real-time seepage data of shallow groundwater in the joint impact area; Carry out data correction on real-time seepage data; Construct a random forest regression model to train the groundwater seepage characteristic relationship; Predict groundwater seepage data by training models; The degree of slope seepage stability degradation is analyzed based on the predicted seepage data.

6. The slope monitoring method based on Internet artificial intelligence according to claim 5 is characterized in that: According to the degree of degradation of the seepage stability inside the slope, the overall safety risk of the slope is assessed, and it is determined whether the slope has reached a state that requires an early warning response, specifically: Integrate the seepage stability degradation coefficient and calculate the overall safety risk probability of the slope; A safety critical threshold is preset, and the overall safety risk probability of the slope is compared with the safety critical threshold to determine whether a state requiring an early warning response has been reached.

7. A slope monitoring system based on Internet artificial intelligence, used to implement a slope monitoring method based on Internet artificial intelligence as described in any one of claims 1 to 6, characterized in that: It includes terrain reshaping judgment unit, risk level assessment unit, impact range determination unit, degradation degree assessment unit and safety risk assessment unit; The terrain reshaping judgment unit collects the three-dimensional laser point cloud data of the slope, calculates the spatial geometric change area caused by the local terrain reshaping based on the point cloud registration algorithm, and judges whether the slope terrain reshaping occurs; The risk level assessment unit analyzes the stress data changes in the stress drift area and uses the long short-term memory neural network algorithm to assess the potential instability risk level inside the slope; The impact range determination unit determines the combined impact range of slope topography remodeling and slope stress drift based on the judgment result of whether slope topography remodeling occurs and the potential instability risk level inside the slope; When the combined influence range of slope topography remodeling and slope stress drift exceeds the safety range, the deterioration degree assessment unit uses the random forest regression algorithm to analyze the real-time monitoring data of shallow groundwater within the combined influence range to assess the degree of degradation of the internal seepage stability of the slope; The safety risk assessment unit evaluates the overall safety risk of the slope based on the degree of degradation of the internal seepage stability of the slope, and determines whether the slope has reached a state requiring an early warning response.

Images