Power transmission and transformation project slope stability assessment method and system based on neural network

Abstract

A power transmission and transformation project slope stability assessment method based on a neural network comprises the steps of obtaining original three-dimensional point cloud data of a power transmission and transformation project slope, and collecting original geological meteorological data of the power transmission and transformation project slope; generating a slope three-dimensional model according to the original three-dimensional point cloud data, and performing standardization processing on the original geological and meteorological data to obtain geological and meteorological data; geometric features and surface morphological features of the side slope are extracted from the side slope three-dimensional model, and side slope feature vectors are constructed in combination with the geometric features, the surface morphological features and geological and meteorological data; and constructing a slope stability prediction and evaluation model based on the recurrent neural network, identifying the slope feature vector through the slope stability prediction and evaluation model to obtain a slope stability evaluation result, judging the stability level of the slope according to the evaluation result, and taking corresponding prevention measures based on the stability level. According to the invention, the accuracy of slope stability evaluation is improved, the accident risk is reduced, and the intelligence of slope monitoring and management is promoted.

Description

Technical Field

[0001] The present invention relates to the technical field of slope stability assessment, and in particular to a method and system for assessing slope stability of a power transmission and transformation project based on a neural network. Background Art

[0002] In modern power transmission and transformation projects, slope stability assessment is an important part of ensuring the safety and reliable operation of the project. Although the existing technology has introduced some advanced tools and methods, such as monocular vision-based image processing technology and other automation equipment, there are still some significant defects.

[0003] First, although these technologies improve recognition efficiency, the lack of depth information makes it difficult to conduct accurate three-dimensional spatial quantitative analysis, which limits the accuracy of the evaluation results. In complex environments, they are easily affected by changes in lighting and occlusion, resulting in instability in the recognition results. Existing technologies still rely on limited field data and cannot fully reflect the actual situation of the slope, which in turn affects the reliability of the evaluation results. Summary of the invention

[0004] The purpose of the present invention is to overcome the problem in the prior art that the slope stability assessment of power transmission and transformation projects is too dependent on limited field data and cannot fully reflect the actual situation of the slope, and to provide a method and system for slope stability assessment of power transmission and transformation projects based on a neural network.

[0005] To achieve the above objectives, the technical solution of the present invention is:

[0006] In a first aspect, the present invention provides a method for evaluating slope stability of a power transmission and transformation project based on a neural network, comprising the following steps:

[0007] S1. Scan the slope of the power transmission and transformation project using a three-dimensional laser scanner to obtain original three-dimensional point cloud data of the slope of the power transmission and transformation project, and collect original geological and meteorological data of the slope of the power transmission and transformation project;

[0008] S2, denoising, filtering and reconstructing the original three-dimensional point cloud data to obtain a three-dimensional slope model, and standardizing the original geological and meteorological data to obtain geological and meteorological data;

[0009] S3, extracting the geometric features and surface morphological features of the slope of the power transmission and transformation project from the three-dimensional slope model, and constructing a slope feature vector by combining the geometric features, the surface morphological features and the geological and meteorological data;

[0010] S4. Construct a slope stability prediction and assessment model based on a recurrent neural network, identify the slope feature vector through the slope stability prediction and assessment model to obtain a slope stability assessment result, determine the stability level of the slope of the power transmission and transformation project according to the slope stability assessment result, and take corresponding preventive measures based on the stability level.

[0011] On the basis of the above technical solution, preferably, step S1 includes:

[0012] S11, selecting a plurality of optimal scanning positions according to the topographical characteristics of the slope of the power transmission and transformation project, setting a three-dimensional laser scanner at each optimal scanning position, performing horizontal calibration and angle adjustment on each three-dimensional laser scanner, and setting scanning parameters of the three-dimensional laser scanner, wherein the scanning parameters include scanning resolution, scanning range and scanning frequency, so as to obtain original three-dimensional point cloud data of the slope of the power transmission and transformation project;

[0013] S12. Determine the rock and soil type and stratigraphic structure of the slope of the power transmission and transformation project by drilling and sampling, install groundwater level monitoring equipment, regularly record the groundwater level data of the slope of the power transmission and transformation project by the groundwater level monitoring equipment, monitor the meteorological data of the slope of the power transmission and transformation project in real time by an automatic meteorological station, and obtain the original geological and meteorological data of the slope of the power transmission and transformation project by combining the rock and soil type, the stratigraphic structure, the groundwater level data and the meteorological data.

[0014] Based on the above technical solution, preferably, step S2 includes:

[0015] S21, performing denoising processing on the original 3D point cloud data by using a statistical outlier detection method, removing abnormal points and noise points of the original 3D point cloud data to obtain denoised 3D point cloud data, smoothing the denoised 3D point cloud data by using an adaptive bilateral filtering algorithm to obtain smoothed 3D point cloud data, and performing 3D reconstruction on the smoothed 3D point cloud data based on a Poisson reconstruction algorithm to obtain a 3D model of the slope;

[0016] S22. Normalize the original geological and meteorological data to obtain normalized geological and meteorological data under a unified scale, identify outliers in the normalized geological and meteorological data by the quartile method, interpolate the outliers to obtain interpolated geological and meteorological data, and use a mixed principal component analysis method to extract features and reduce the dimension of the interpolated geological and meteorological data to obtain standardized geological and meteorological data.

[0017] On the basis of the above technical solution, preferably, denoising the original three-dimensional point cloud data by using a statistical outlier detection method comprises:

[0018] Calculating statistical outlier values ​​of each data point in the original three-dimensional point cloud data, and removing outlier points in the original three-dimensional point cloud data according to the statistical outlier values;

[0019] The calculation formula for the statistical outlier value of each data point in the original three-dimensional point cloud data is:

[0020]

[0021] Among them, Z i is the statistical outlier value of the i-th data point in the original 3D point cloud data, X i is the i-th data point in the original 3D point cloud data, μ is the mean of the original 3D point cloud data, σ is the standard deviation of the original 3D point cloud data, and n is the number of data points in the original 3D point cloud data;

[0022] The mixed principal component analysis method is used to extract features and reduce the dimension of the interpolated geological and meteorological data, including:

[0023] Performing dimension reduction on the interpolated geological and meteorological data by principal component analysis to obtain principal component characteristics of the interpolated geological and meteorological data;

[0024] Using independent component analysis to process the principal component characteristics, to obtain standardized geological and meteorological data;

[0025] The calculation formula of the geological and meteorological data is:

[0026] F=w1PC j +w2IC k ;

[0027] Among them, F is the geological and meteorological data, w1 and w2 are the weights of principal component analysis and independent component analysis, respectively. j and IC k They are the j-th principal component feature of the principal component analysis method and the k-th independent component feature of the independent component analysis method respectively.

[0028] On the basis of the above technical solution, preferably, step S3 includes:

[0029] S31, dividing the three-dimensional model of the slope into a plurality of grid units by a three-dimensional grid division algorithm, calculating the local slope, local slope aspect and local elevation value of each grid unit, calculating the curvature characteristics of the surface of the three-dimensional model of the slope based on Gaussian curvature and mean curvature, calculating the roughness index of the slope surface by a multi-scale analysis method, and generating a distribution map of the overall geometric characteristics and surface morphological characteristics of the slope of the power transmission and transformation project by statistical analysis and spatial interpolation methods;

[0030] S32. Normalize the geometric features and the surface morphological features to obtain first geometric features and first surface morphological features, use principal component analysis to reduce the dimensions of the first geometric features and the first surface morphological features, extract the principal component features of the first geometric features and the first surface morphological features, obtain second geometric features and second surface morphological features, concatenate the second geometric features and the second surface morphological features with the geological and meteorological data, introduce an attention mechanism, assign different weights to different features, and construct a multi-level slope feature vector, wherein the slope feature vector includes global features and local features.

[0031] Based on the above technical solution, preferably, step S4 includes:

[0032] S41, constructing an initial slope stability prediction and evaluation model based on a recurrent neural network, initializing model parameters, the model parameters including a weight matrix and a bias vector, setting a training strategy and hyperparameters, the hyperparameters including a learning rate, a batch size, and a number of iterations;

[0033] S42, acquiring historical slope stability data, and using the historical slope stability data to train the initial slope stability prediction and evaluation model through a gradient descent algorithm to obtain a slope stability prediction and evaluation model;

[0034] S43, pre-processing the slope characteristic vector to obtain a unified slope characteristic vector consistent with the data format of historical slope stability data, inputting the unified slope characteristic vector into the slope stability prediction and evaluation model, performing stability prediction to obtain a prediction result, and smoothing the prediction result through a post-processing algorithm to obtain a slope stability evaluation result;

[0035] S44. According to the preset stability grade classification standard, the slope stability assessment result is mapped to the corresponding stability grade. According to the different stability grades, corresponding preventive and control measures are formulated, and the relevant management personnel are notified to implement the corresponding preventive and control measures. A slope monitoring and feedback mechanism is established to monitor the stability grade changes of the slope of the power transmission and transformation project in real time.

[0036] On the basis of the above technical solution, preferably, step S4 further includes:

[0037] The state update calculation formula of the initial slope stability prediction and evaluation model is:

[0038] h t =tanh(W x x t +W h h t-1 + b);

[0039] Among them, h tis the hidden state vector at time t, x t is the input feature vector at time t, h t-1 is the hidden state vector at time t-1, W x and W h are the weights of the input feature vector at time t and the hidden state vector at time t-1, b is the bias vector, and tanh(·) is the hyperbolic tangent activation function;

[0040] The loss function calculation formula of the initial slope stability prediction and evaluation model is:

[0041]

[0042] Among them, L is the loss function value, N is the number of samples of the initial slope stability prediction and evaluation model, and y l is the true value of the lth sample of the initial slope stability prediction and evaluation model, is the predicted value of the lth sample of the initial slope stability prediction and evaluation model, w l is the weight of the lth sample of the initial slope stability prediction and evaluation model, λ is the regularization coefficient, θ is the model parameter vector, is the L2 norm square of θ;

[0043] The calculation formula of the gradient descent algorithm is:

[0044]

[0045] θ (m+1) =θ (m) +v (m+1) ;

[0046] Among them, v (m+1) and v (m) are the velocity vectors of the m+1th iteration and the mth iteration, respectively, η is the momentum coefficient, τ is the learning rate, is the loss function for θ (m) The gradient of θ (m+1) and θ (m) are the parameter vector of the m+1th iteration and the parameter vector of the mth iteration respectively.

[0047] In a second aspect, the present invention provides a neural network-based slope stability assessment system for power transmission and transformation projects, the system comprising:

[0048] A data acquisition module is used to scan the slope of the power transmission and transformation project using a three-dimensional laser scanner to obtain the original three-dimensional point cloud data of the slope of the power transmission and transformation project, and to collect the original geological and meteorological data of the slope of the power transmission and transformation project;

[0049] A three-dimensional model module is used to perform denoising, filtering and reconstruction on the original three-dimensional point cloud data to obtain a three-dimensional slope model, and to perform standardization processing on the original geological and meteorological data to obtain geological and meteorological data;

[0050] A feature vector module is used to extract the geometric features and surface morphological features of the slope of the power transmission and transformation project from the three-dimensional slope model, and to construct a slope feature vector by combining the geometric features, the surface morphological features and the geological and meteorological data;

[0051] The stability assessment module is used to construct a slope stability prediction and assessment model based on a recurrent neural network, identify the slope feature vector through the slope stability prediction and assessment model, obtain a slope stability assessment result, judge the stability level of the slope of the power transmission and transformation project according to the slope stability assessment result, and take corresponding preventive measures based on the stability level.

[0052] In a third aspect, the present invention further provides an electronic device, comprising: at least one processor, at least one memory, a communication interface and a bus;

[0053] Among them, the processor, memory, and communication interface communicate with each other through the bus, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement steps such as a slope stability assessment method for power transmission and transformation projects based on neural networks.

[0054] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions enable a computer to implement steps of a method for slope stability assessment of a power transmission and transformation project based on a neural network.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] 1. In a method for evaluating the slope stability of a power transmission and transformation project based on a neural network, a three-dimensional laser scanner is used to obtain high-precision three-dimensional point cloud data, and combined with geological and meteorological data, geometric features and surface morphological features are extracted to construct a slope feature vector, thereby enhancing a comprehensive understanding of the slope characteristics and comprehensively reflecting the actual situation of the slope. The data is denoised, filtered and reconstructed to ensure the accuracy of the data, a three-dimensional model of the slope is constructed, and the geological and meteorological data is standardized to improve the consistency of the data. Stability prediction is performed based on a stability prediction and evaluation model to improve the accuracy of the evaluation. Preventive measures are taken in a timely manner through a real-time monitoring and feedback mechanism to reduce safety risks, thereby improving the accuracy of slope stability evaluation, reducing accident risks, and promoting the intelligence of slope monitoring and management.

[0057] 2. In a method for evaluating the slope stability of a power transmission and transformation project based on a neural network, the original three-dimensional point cloud data is denoised by using a statistical outlier detection method to remove abnormal points and noise points, and the denoised three-dimensional point cloud data is smoothed using an adaptive bilateral filtering algorithm. The smoothed three-dimensional point cloud data is three-dimensionally reconstructed based on a Poisson reconstruction algorithm to obtain a three-dimensional model of the slope. The original geological and meteorological data is subjected to normalization processing, outlier identification and interpolation, and a mixed principal component analysis method for feature extraction and dimensionality reduction to obtain standardized geological and meteorological data, thereby improving the accuracy of slope feature extraction and stability assessment.

[0058] 3. In a method for evaluating slope stability of power transmission and transformation projects based on a neural network of the present invention, a gradient descent algorithm is used to train and optimize the initial model to obtain a slope stability prediction and evaluation model, thereby identifying the slope characteristic vector and giving a prediction result of the slope stability. A post-processing algorithm is used to smooth the prediction result to obtain a final slope stability evaluation result. The slope stability is divided into different levels according to the evaluation result, corresponding preventive and control measures are formulated for different levels, and a monitoring and feedback mechanism is established to monitor the changes in slope stability in real time and achieve accurate prediction of slope stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 The present invention provides a flowchart of a method for evaluating slope stability of a power transmission and transformation project based on a neural network.

[0060] Figure 2 The present invention is a schematic diagram of a structure of a neural network-based slope stability assessment system for power transmission and transformation projects provided by an embodiment of the present invention.

[0061] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The following will be combined with 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.

[0063] See also Figure 1 The present invention provides a method for evaluating slope stability of power transmission and transformation projects based on a neural network, comprising the following steps:

[0064] S1. Scanning the slope of the power transmission and transformation project using a three-dimensional laser scanner to obtain original three-dimensional point cloud data of the slope of the power transmission and transformation project, and collecting original geological and meteorological data of the slope of the power transmission and transformation project;

[0065] S2, denoising, filtering and reconstructing the original three-dimensional point cloud data to obtain a three-dimensional slope model, and standardizing the original geological and meteorological data to obtain geological and meteorological data;

[0066] S3, extracting the geometric features and surface morphological features of the slope of the power transmission and transformation project from the three-dimensional slope model, and constructing a slope feature vector by combining the geometric features, the surface morphological features and the geological and meteorological data;

[0067] S4. Construct a slope stability prediction and assessment model based on a recurrent neural network, identify the slope feature vector through the slope stability prediction and assessment model to obtain a slope stability assessment result, determine the stability level of the slope of the power transmission and transformation project according to the slope stability assessment result, and take corresponding preventive measures based on the stability level.

[0068] Specifically, this embodiment uses a 3D laser scanner to obtain high-precision 3D point cloud data, and combines it with geological and meteorological data to extract geometric features and surface morphological features, construct slope feature vectors, enhance the comprehensive understanding of slope characteristics, and comprehensively reflect the actual situation of the slope. The data is denoised, filtered, and reconstructed to ensure data accuracy, a 3D model of the slope is constructed, and the geological and meteorological data is standardized to improve data consistency. Stability prediction is performed based on a stability prediction and evaluation model to improve the accuracy of the evaluation. Through a real-time monitoring and feedback mechanism, preventive measures are taken in a timely manner to reduce safety risks, thereby improving the accuracy of slope stability evaluation, reducing accident risks, and promoting the intelligence of slope monitoring and management.

[0069] Step S1 includes:

[0070] S11, selecting a plurality of optimal scanning positions according to the topographical characteristics of the slope of the power transmission and transformation project, setting a three-dimensional laser scanner at each optimal scanning position, performing horizontal calibration and angle adjustment on each three-dimensional laser scanner, and setting scanning parameters of the three-dimensional laser scanner, wherein the scanning parameters include scanning resolution, scanning range and scanning frequency, so as to obtain original three-dimensional point cloud data of the slope of the power transmission and transformation project;

[0071] S12. Determine the rock and soil type and stratigraphic structure of the slope of the power transmission and transformation project by drilling and sampling, install groundwater level monitoring equipment, regularly record the groundwater level data of the slope of the power transmission and transformation project by the groundwater level monitoring equipment, monitor the meteorological data of the slope of the power transmission and transformation project in real time by an automatic meteorological station, and obtain the original geological and meteorological data of the slope of the power transmission and transformation project by combining the rock and soil type, the stratigraphic structure, the groundwater level data and the meteorological data.

[0072] Specifically, this embodiment selects multiple optimal scanning positions and performs horizontal calibration and angle adjustment, so that the three-dimensional laser scanner can obtain more comprehensive and accurate original three-dimensional point cloud data of the slope of the power transmission and transformation project, and reasonably sets the scanning parameters, including resolution, range, and frequency, to ensure that the acquired three-dimensional point cloud data has sufficient detail information and time resolution.

[0073] The rock and soil type and stratigraphic structure of the slope are determined by drilling and sampling to better understand the geological conditions of the slope. Groundwater level monitoring equipment and automatic weather stations are installed to obtain real-time groundwater level and meteorological data of the slope, providing key environmental factor data for slope stability assessment. Ultimately, the rock and soil type, stratigraphic structure, groundwater level and meteorological data are comprehensively utilized to construct more comprehensive and accurate original geological and meteorological data.

[0074] Step S2 includes:

[0075] S21, performing denoising processing on the original 3D point cloud data by using a statistical outlier detection method, removing abnormal points and noise points of the original 3D point cloud data to obtain denoised 3D point cloud data, smoothing the denoised 3D point cloud data by using an adaptive bilateral filtering algorithm to obtain smoothed 3D point cloud data, and performing 3D reconstruction on the smoothed 3D point cloud data based on a Poisson reconstruction algorithm to obtain a 3D model of the slope;

[0076] S22. Normalize the original geological and meteorological data to obtain normalized geological and meteorological data under a unified scale, identify outliers in the normalized geological and meteorological data by the quartile method, interpolate the outliers to obtain interpolated geological and meteorological data, and use a mixed principal component analysis method to extract features and reduce the dimension of the interpolated geological and meteorological data to obtain standardized geological and meteorological data.

[0077] Specifically, this embodiment uses a statistical outlier detection method to denoise the original three-dimensional point cloud data, removes abnormal points and noise points, uses an adaptive bilateral filtering algorithm to smooth the denoised three-dimensional point cloud data to reduce the noise in the data, and reconstructs the smoothed three-dimensional point cloud data based on a Poisson reconstruction algorithm to generate a more realistic and complete three-dimensional slope model.

[0078] Through normalization processing, the original geological and meteorological data are mapped to a unified scale range, eliminating the influence of dimensional differences. The quartile method is used to identify and interpolate outliers in the normalized geological and meteorological data, reducing the impact of noise on the analysis results. The mixed principal component analysis method is used to extract features and reduce the dimension of the interpolated geological and meteorological data to capture the potential characteristics of the data.

[0079] Step S2 also includes:

[0080] The calculation formula of the statistical outlier detection method is:

[0081]

[0082] Among them, Z i is the statistical outlier value of the i-th data point in the original 3D point cloud data, X i is the i-th data point in the original 3D point cloud data, μ is the mean of the original 3D point cloud data, σ is the standard deviation of the original 3D point cloud data, and n is the number of data points in the original 3D point cloud data;

[0083] The calculation formula for the normalization process is:

[0084]

[0085] Among them, Y norm is the data point of normalized geological and meteorological data, Y i is the i-th data point of the normalized geological and meteorological data, Y min is the minimum data point of the normalized geological and meteorological data, Y max is the maximum value data point of normalized geological and meteorological data, and α is a zero-proof positive number;

[0086] The mixed principal component analysis method comprises:

[0087] The interpolated geological and meteorological data are reduced in dimension by principal component analysis to obtain the principal component characteristics of the interpolated geological and meteorological data. The principal component characteristics are processed by independent component analysis to obtain the standardized geological and meteorological data. The calculation formula of the geological and meteorological data is:

[0088] F=w1PC j +w2IC k ;

[0089] Among them, F is the geological and meteorological data, w1 and w2 are the weights of principal component analysis and independent component analysis, respectively. j and IC k They are the j-th principal component feature of the principal component analysis method and the k-th independent component feature of the independent component analysis method respectively.

[0090] Specifically, this embodiment identifies outliers by calculating the relationship between each data point and the mean and standard deviation of the data set, and uses statistical methods to improve the accuracy of outlier detection to avoid misjudging normal data as abnormal. For example, this embodiment can introduce more complex statistical models (such as Z-score or IQR method) to enhance the ability to identify outliers.

[0091] The normalization calculation formula scales the data to a uniform scale to ensure that different features have the same influence in model training. It adopts more flexible normalization methods, such as Z-score standardization or Min-Max scaling, to adapt to the characteristics of different data distributions and reduce the instability of model training caused by differences in feature scales.

[0092] By combining principal component analysis and independent component analysis, the principal component features and independent component features of the original three-dimensional point cloud data are extracted. After dimensionality reduction using principal component analysis, the correlation between features is removed using independent component analysis, thereby obtaining a more independent feature representation, improving the effectiveness of feature extraction, and enhancing the generalization ability of the model.

[0093] This embodiment improves the quality of input data and reduces the impact of noise on model training through outlier detection and processing. Normalization processing ensures that all features are on the same scale, reducing training instability caused by feature scale differences. The hybrid principal component analysis method is applied to make the feature vector more representative and better capture the inherent structure of the data. Through accurate slope stability assessment results, more reliable decision support is provided for the safety management of power transmission and transformation projects, thereby reducing potential risks.

[0094] Step S3 includes:

[0095] S31, dividing the three-dimensional model of the slope into a plurality of grid units by a three-dimensional grid division algorithm, calculating the local slope, local slope aspect and local elevation value of each grid unit, calculating the curvature characteristics of the surface of the three-dimensional model of the slope based on Gaussian curvature and mean curvature, calculating the roughness index of the slope surface by a multi-scale analysis method, and generating a distribution map of the overall geometric characteristics and surface morphological characteristics of the slope of the power transmission and transformation project by statistical analysis and spatial interpolation methods;

[0096] S32. Normalize the geometric features and the surface morphological features to obtain first geometric features and first surface morphological features, use principal component analysis to reduce the dimensions of the first geometric features and the first surface morphological features, extract the principal component features of the first geometric features and the first surface morphological features, obtain second geometric features and second surface morphological features, concatenate the second geometric features and the second surface morphological features with the geological and meteorological data, introduce an attention mechanism, assign different weights to different features, and construct a multi-level slope feature vector, wherein the slope feature vector includes global features and local features.

[0097] Specifically, this embodiment divides the three-dimensional model of the slope into multiple grid units through a three-dimensional grid division algorithm, calculates the local slope, local slope aspect and local elevation value of each grid unit, comprehensively captures the geometric characteristics of the slope, calculates the curvature characteristics of the surface of the three-dimensional model of the slope based on Gaussian curvature and mean curvature, and uses a multi-scale analysis method to calculate the roughness index of the slope surface. The surface morphological characteristics of the slope can be extracted, and through statistical analysis and spatial interpolation methods, a distribution map of the geometric characteristics and surface morphological characteristics of the slope is generated.

[0098] The extracted geometric features and surface morphological features are normalized, and the principal component analysis method is used to reduce the dimension to obtain a more effective feature vector. The geometric features, surface morphological features and geological and meteorological data are spliced ​​to construct a multi-level slope feature vector. The attention mechanism is introduced to give different weights to different features, thereby enhancing the expressive power of the features.

[0099] Step S4 includes:

[0100] S41, constructing an initial slope stability prediction and evaluation model based on a recurrent neural network, initializing model parameters, the model parameters including a weight matrix and a bias vector, setting a training strategy and hyperparameters, the hyperparameters including a learning rate, a batch size, and a number of iterations;

[0101] S42, acquiring historical slope stability data, and using the historical slope stability data to train the initial slope stability prediction and evaluation model through a gradient descent algorithm to obtain a slope stability prediction and evaluation model;

[0102] S43, pre-processing the slope characteristic vector to obtain a unified slope characteristic vector consistent with the data format of historical slope stability data, inputting the unified slope characteristic vector into the slope stability prediction and evaluation model, performing stability prediction to obtain a prediction result, and smoothing the prediction result through a post-processing algorithm to obtain a slope stability evaluation result;

[0103] S44. According to the preset stability grade classification standard, the slope stability assessment result is mapped to the corresponding stability grade. According to the different stability grades, corresponding preventive and control measures are formulated, and the relevant management personnel are notified to implement the corresponding preventive and control measures. A slope monitoring and feedback mechanism is established to monitor the stability grade changes of the slope of the power transmission and transformation project in real time.

[0104] Specifically, this embodiment ensures the effectiveness of the initial slope stability prediction and evaluation model by initializing the parameters of the recurrent neural network model, including the weight matrix and the bias vector, and setting a reasonable training strategy and hyperparameters, wherein the hyperparameters include the learning rate, the batch size, and the number of iterations. The initial slope stability prediction and evaluation model is trained by using a gradient descent algorithm in combination with historical slope stability data. The gradient descent algorithm with a momentum term is introduced to accelerate the convergence process of the model and improve the training efficiency. The input feature vector is preprocessed to make it consistent with the format of the historical slope stability data, and the model prediction results are smoothed by a post-processing algorithm, which can effectively reduce the volatility of the prediction results.

[0105] According to the mapping of slope stability assessment results to different stability levels, corresponding preventive and control measures are formulated in a targeted manner, a slope monitoring and feedback mechanism is established, and changes in slope stability levels are monitored in real time to ensure that effective preventive measures are taken in a timely manner, thereby improving the safety of the project.

[0106] In a specific embodiment, corresponding preventive measures are formulated for different stability levels:

[0107] According to the slope stability assessment results, the slope stability is divided into different levels: high, medium and low.

[0108] For slopes with high stability levels, conventional preventive measures such as regular inspections and vegetation maintenance are taken. For slopes with medium stability levels, enhanced preventive measures such as slope support and drainage system maintenance are taken. For slopes with low stability levels, control preventive measures such as slope reinforcement and slope reshaping are taken.

[0109] And notify relevant managers to implement corresponding preventive and control measures:

[0110] The slope stability assessment results and corresponding preventive and control measures shall be promptly notified to the management department and maintenance personnel of the transmission and transformation project, and relevant personnel shall be organized to formulate specific preventive and control plans and implement corresponding preventive and control measures.

[0111] Establish a slope monitoring and feedback mechanism to monitor the changes in slope stability levels in real time:

[0112] Monitoring equipment, including tilt monitors and displacement monitors, are installed at key locations on the slope to monitor slope deformation, displacement and other indicators in real time. An automatic collection, analysis and early warning mechanism for slope monitoring data is established to promptly detect changes in the slope stability grade. Once changes in the slope stability grade are detected, relevant management personnel are notified immediately and preventive measures are adjusted according to the changes.

[0113] Step S4 also includes:

[0114] The state update calculation formula of the initial slope stability prediction and evaluation model is:

[0115] h t =tanh(W x x t +W h h t-1 + b);

[0116] Among them, h t is the hidden state vector at time t, x t is the input feature vector at time t, h t-1 is the hidden state vector at time t-1, W x and W h are the weights of the input feature vector at time t and the hidden state vector at time t-1, b is the bias vector, and tanh(·) is the hyperbolic tangent activation function;

[0117] The loss function calculation formula of the initial slope stability prediction and evaluation model is:

[0118]

[0119] Among them, L is the loss function value, N is the number of samples of the initial slope stability prediction and evaluation model, and y l is the true value of the lth sample of the initial slope stability prediction and evaluation model, is the predicted value of the lth sample of the initial slope stability prediction and evaluation model, w l is the weight of the lth sample of the initial slope stability prediction and evaluation model, λ is the regularization coefficient, θ is the model parameter vector, is the L2 norm square of θ;

[0120] The calculation formula of the gradient descent algorithm is:

[0121]

[0122] θ (m+1) =θ (m) +v (m+1) ;

[0123] Among them, v (m+1) and v(m) are the velocity vectors of the m+1th iteration and the mth iteration, respectively, η is the momentum coefficient, τ is the learning rate, is the loss function for θ (m) The gradient of θ (m+1) and θ (m) are the parameter vector of the m+1th iteration and the parameter vector of the mth iteration respectively;

[0124] The calculation formula of the post-processing algorithm is:

[0125]

[0126] in, is the slope stability assessment result at time T, is the original predicted value at time T, is the smoothed prediction value at time T-1, and β is the smoothing coefficient.

[0127] Specifically, the state update calculation formula of this embodiment introduces the input feature vector at the current moment and the hidden state vector at the previous moment, combines weights and biases, updates the hidden state of the model, and captures the dynamic features in the time series data.

[0128] In this embodiment, the hyperbolic tangent activation function tanh(·) is used. Its nonlinear characteristics can effectively handle the nonlinear relationship of the input data and enhance the expressiveness of the model. The loss function is used to measure the difference between the model prediction value and the true value. By introducing the regularization term, the model is prevented from overfitting and the generalization ability of the model is improved. The L2 norm square regularization is used to control the model complexity and ensure that the model performs balanced on the training set and the test set.

[0129] The gradient descent algorithm of this embodiment accelerates convergence and reduces oscillation by introducing a momentum term. The momentum coefficient is used to allow the model to take into account the previous update direction when updating parameters, thereby improving the convergence speed. The learning rate and gradient information are combined to dynamically adjust the step size of the parameter update, making the optimization process more efficient.

[0130] The post-processing algorithm smoothes the prediction results through the smoothing coefficient, reduces the fluctuation of the prediction results, makes the final slope stability assessment results more stable, effectively reduces the impact of noise on the assessment results, and improves the credibility of the assessment results.

[0131] See also Figure 2 The present invention also provides a neural network-based slope stability assessment system for power transmission and transformation projects, the system comprising:

[0132] The data acquisition module is used to scan the slope of the power transmission and transformation project using a three-dimensional laser scanner to obtain the original three-dimensional point cloud data of the slope of the power transmission and transformation project, and collect the original geological and meteorological data of the slope of the power transmission and transformation project; the data acquisition module is used to execute the steps in S1.

[0133] The three-dimensional model module is used to denoise, filter and reconstruct the original three-dimensional point cloud data to obtain a three-dimensional model of the slope, and to standardize the original geological and meteorological data to obtain geological and meteorological data; the three-dimensional model module is used to execute the steps in S2.

[0134] The feature vector module is used to extract the geometric features and surface morphological features of the power transmission and transformation project slope from the three-dimensional slope model, and to construct a slope feature vector by combining the geometric features, the surface morphological features and the geological and meteorological data; the feature vector module is used to execute the steps in S3.

[0135] A stability assessment module is used to construct a slope stability prediction and assessment model based on a recurrent neural network, identify the slope feature vector through the slope stability prediction and assessment model, obtain a slope stability assessment result, judge the stability level of the slope of the power transmission and transformation project according to the slope stability assessment result, and take corresponding preventive measures based on the stability level. The stability assessment module is used to execute the steps in S4.

[0136] Specifically, the data acquisition module of this embodiment uses a three-dimensional laser scanner to perform high-precision scanning of the slope to obtain the original three-dimensional point cloud data and geological and meteorological data of the slope; the three-dimensional model module denoises, filters and reconstructs the original three-dimensional point cloud data to generate a high-quality three-dimensional slope model; the feature vector module extracts geometric features and surface morphological features from the three-dimensional slope model, and constructs a slope feature vector in combination with the geological and meteorological data; the stability assessment module constructs a slope stability prediction and assessment model based on a recurrent neural network, and intelligently identifies and analyzes the slope feature vectors, thereby improving the efficiency and accuracy of slope stability judgment, thereby timely identifying potential risks.

[0137] A neural network-based slope stability assessment system for power transmission and transformation projects in this embodiment can monitor the stability changes of the slope in real time and take corresponding preventive measures based on the assessment results. The real-time monitoring and feedback mechanism ensures the safety of the project and can respond to possible slope instability risks in a timely manner.

[0138] See also Figure 3The present invention also discloses an electronic device, comprising: at least one processor, at least one memory communication interface and a bus: wherein the processor, memory and communication interface communicate with each other through the bus; the memory stores program instructions executable by the processor, and the processor calls the program instructions to implement a slope stability assessment method for power transmission and transformation projects based on a neural network.

[0139] The present invention also discloses a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, wherein the computer instructions enable the computer to implement all or part of the steps of a method for evaluating slope stability of a power transmission and transformation project based on a neural network according to an embodiment of the present invention. The storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0140] 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 method for evaluating slope stability of power transmission and transformation projects based on neural networks, characterized in that: S1. Scanning the slope of the power transmission and transformation project using a three-dimensional laser scanner to obtain original three-dimensional point cloud data of the slope of the power transmission and transformation project, and collecting original geological and meteorological data of the slope of the power transmission and transformation project; S2, denoising, filtering and reconstructing the original three-dimensional point cloud data to obtain a three-dimensional slope model, and standardizing the original geological and meteorological data to obtain geological and meteorological data; S3, extracting the geometric features and surface morphological features of the slope of the power transmission and transformation project from the three-dimensional slope model, and constructing a slope feature vector by combining the geometric features, the surface morphological features and the geological and meteorological data; S4. Construct a slope stability prediction and assessment model based on a recurrent neural network, identify the slope feature vector through the slope stability prediction and assessment model to obtain a slope stability assessment result, determine the stability level of the slope of the power transmission and transformation project according to the slope stability assessment result, and take corresponding preventive measures based on the stability level.

2. A method for evaluating slope stability of power transmission and transformation projects based on neural network according to claim 1, characterized in that: S1 includes, S11, selecting multiple scanning positions according to the topographical characteristics of the slope of the power transmission and transformation project, setting a three-dimensional laser scanner at each scanning position, performing horizontal calibration and angle adjustment on each three-dimensional laser scanner, and setting scanning parameters of the three-dimensional laser scanner, wherein the scanning parameters include scanning resolution, scanning range and scanning frequency, so as to obtain original three-dimensional point cloud data of the slope of the power transmission and transformation project; S12. Determine the rock and soil type and stratigraphic structure of the slope of the power transmission and transformation project by drilling and sampling, install groundwater level monitoring equipment, regularly record the groundwater level data of the slope of the power transmission and transformation project by the groundwater level monitoring equipment, monitor the meteorological data of the slope of the power transmission and transformation project in real time by an automatic meteorological station, and obtain the original geological and meteorological data of the slope of the power transmission and transformation project by combining the rock and soil type, the stratigraphic structure, the groundwater level data and the meteorological data.

3. The method for evaluating slope stability of power transmission and transformation projects based on neural network according to claim 2, characterized in that: S2 includes, S21, performing denoising processing on the original 3D point cloud data by using a statistical outlier detection method, removing abnormal points and noise points of the original 3D point cloud data to obtain denoised 3D point cloud data, smoothing the denoised 3D point cloud data by using an adaptive bilateral filtering algorithm to obtain smoothed 3D point cloud data, and performing 3D reconstruction on the smoothed 3D point cloud data based on a Poisson reconstruction algorithm to obtain a 3D model of the slope; S22. Normalize the original geological and meteorological data to obtain normalized geological and meteorological data under a unified scale, identify outliers in the normalized geological and meteorological data by the quartile method, interpolate the outliers to obtain interpolated geological and meteorological data, and use a mixed principal component analysis method to extract features and reduce the dimension of the interpolated geological and meteorological data to obtain standardized geological and meteorological data.

4. The method for evaluating slope stability of power transmission and transformation projects based on neural network according to claim 3 is characterized by: In S21, the calculation formula of the statistical outlier detection method is: Among them, Z i is the statistical outlier value of the i-th data point in the original 3D point cloud data, X i is the i-th data point in the original 3D point cloud data, μ is the mean of the original 3D point cloud data, σ is the standard deviation of the original 3D point cloud data, and n is the number of data points in the original 3D point cloud data; In S22, the mixed principal component analysis method is used to extract features and reduce the dimension of the interpolated geological and meteorological data, including: The interpolated geological and meteorological data are reduced in dimension by principal component analysis to obtain the principal component characteristics of the interpolated geological and meteorological data. The principal component characteristics are processed by independent component analysis to obtain the standardized geological and meteorological data. The calculation formula of the geological and meteorological data is: F=w1PC j +w2IC k ; Among them, F is the geological and meteorological data, w1 and w2 are the weights of the principal component analysis method and the independent component analysis method, respectively. j and IC k They are the j-th principal component feature of the principal component analysis method and the k-th independent component feature of the independent component analysis method respectively.

5. The method for evaluating slope stability of power transmission and transformation projects based on neural network according to claim 1, characterized in that: S3 includes, S31, dividing the three-dimensional model of the slope into a plurality of grid units by a three-dimensional grid division algorithm, calculating the local slope, local slope aspect and local elevation value of each grid unit, calculating the curvature characteristics of the surface of the three-dimensional model of the slope based on Gaussian curvature and mean curvature, calculating the roughness index of the slope surface by a multi-scale analysis method, and generating a distribution map of the overall geometric characteristics and surface morphological characteristics of the slope of the power transmission and transformation project by statistical analysis and spatial interpolation methods; S32. Normalize the geometric features and the surface morphological features to obtain first geometric features and first surface morphological features, use principal component analysis to reduce the dimensions of the first geometric features and the first surface morphological features, extract the principal component features of the first geometric features and the first surface morphological features, obtain second geometric features and second surface morphological features, concatenate the second geometric features and the second surface morphological features with the geological and meteorological data, introduce an attention mechanism, assign different weights to different features, and construct a multi-level slope feature vector, wherein the slope feature vector includes global features and local features.

6. The method for evaluating slope stability of power transmission and transformation projects based on neural network according to claim 1, characterized in that: S4 includes, S41, constructing an initial slope stability prediction and evaluation model based on a recurrent neural network, initializing model parameters, the model parameters including a weight matrix and a bias vector, setting a training strategy and hyperparameters, the hyperparameters including a learning rate, a batch size, and a number of iterations; S42, acquiring historical slope stability data, and using the historical slope stability data to train the initial slope stability prediction and evaluation model through a gradient descent algorithm to obtain a slope stability prediction and evaluation model; S43, pre-processing the slope characteristic vector to obtain a unified slope characteristic vector consistent with the data format of historical slope stability data, inputting the unified slope characteristic vector into the slope stability prediction and evaluation model, performing stability prediction to obtain a prediction result, and smoothing the prediction result through a post-processing algorithm to obtain a slope stability evaluation result; S44. According to the preset stability grade classification standard, the slope stability assessment result is mapped to the corresponding stability grade. According to the different stability grades, corresponding preventive and control measures are formulated, and the relevant management personnel are notified to implement the corresponding preventive and control measures. A slope monitoring and feedback mechanism is established to monitor the stability grade changes of the slope of the power transmission and transformation project in real time.

7. A method for evaluating slope stability of power transmission and transformation projects based on neural network according to claim 6, characterized in that: S4 also includes, The state update calculation formula of the initial slope stability prediction and evaluation model is: h t =tanh(W x x t +W h h t-1 +b); Among them, h t is the hidden state vector at time t, x t is the input feature vector at time t, h t-1 is the hidden state vector at time t-1, W x and W h are the weights of the input feature vector at time t and the hidden state vector at time t-1, b is the bias vector, and tanh(·) is the hyperbolic tangent activation function; The loss function calculation formula of the initial slope stability prediction and evaluation model is: Where L is the loss function value, N is the number of samples of the initial slope stability prediction and evaluation model, and y l is the true value of the lth sample of the initial slope stability prediction and evaluation model, is the predicted value of the lth sample of the initial slope stability prediction and evaluation model, w l is the weight of the lth sample of the initial slope stability prediction and evaluation model, λ is the regularization coefficient, θ is the model parameter vector, is the L2 norm square of θ; The calculation formula of the gradient descent algorithm is: i (m+1) =θ (m) +v (m+1) ; Among them, v (m+1) and v (m) are the velocity vectors of the m+1th iteration and the mth iteration, respectively, η is the momentum coefficient, τ is the learning rate, ▽L(θ (m) ) is the loss function for θ (m) The gradient of θ (m+1) and θ (m) are the parameter vector of the m+1th iteration and the parameter vector of the mth iteration respectively.

8. A neural network-based slope stability assessment system for power transmission and transformation projects, characterized in that: The system comprises: A data acquisition module is used to scan the slope of the power transmission and transformation project using a three-dimensional laser scanner to obtain the original three-dimensional point cloud data of the slope of the power transmission and transformation project, and to collect the original geological and meteorological data of the slope of the power transmission and transformation project; A three-dimensional model module is used to perform denoising, filtering and reconstruction on the original three-dimensional point cloud data to obtain a three-dimensional slope model, and to perform standardization processing on the original geological and meteorological data to obtain geological and meteorological data; A feature vector module is used to extract the geometric features and surface morphological features of the slope of the power transmission and transformation project from the three-dimensional slope model, and to construct a slope feature vector by combining the geometric features, the surface morphological features and the geological and meteorological data; The stability assessment module is used to construct a slope stability prediction and assessment model based on a recurrent neural network, identify the slope feature vector through the slope stability prediction and assessment model, obtain a slope stability assessment result, judge the stability level of the slope of the power transmission and transformation project according to the slope stability assessment result, and take corresponding preventive measures based on the stability level.

9. An electronic device, characterized in that: include: at least one processor, at least one memory, a communication interface, and a bus; The processor, memory, and communication interface communicate with each other via the bus, the memory stores program instructions executable by the processor, and the processor calls the program instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images