A monitoring system for the slope stability of a waste dump

Abstract

The present invention discloses a monitoring system for the slope stability of a waste dump, comprising: a data acquisition module: responsible for collecting the deformation data of the slope in real time through various sensors deployed on the slope of the waste dump. Meanwhile, the macroscopic information of the slope is obtained by using aerial images and digital elevation images; a data transmission module: responsible for transmitting the collected data to the data processing center in real time by using Internet of Things technology; the data processing center includes a data processing and analysis module, an early warning and decision support module, and a user interaction module; the data processing and analysis module: responsible for processing and analyzing the transmitted data. By constructing a slope stability model, the stability state of the slope is evaluated. During the process of constructing the slope stability model, based on the known characteristics of unstable slopes, some new and virtual unstable slope data are generated by GAN to supplement the training set.

Description

Technical Field

[0001] The present invention relates to the technical field of security monitoring, and particularly to a monitoring system for the slope stability of a waste dump site. Background Art

[0002] A waste dump site is a place for piling up waste earth and stone generated during the process of engineering construction, such as earth and stone excavation, tunnel development, etc., and is usually composed of a loose accumulation of earth-rock mixtures. Such slopes are characterized by loose structures, low shear strength, easy deformation, etc., so their stability is relatively poor. At the same time, due to the complex formation and evolution process of the waste dump site slope, which is affected by various factors, such as rainfall, maintenance of drainage facilities, earthquakes, human activities, etc., the stability monitoring thereof is particularly important.

[0003] In the prior art, when processing and analyzing the data obtained from monitoring, it may encounter the situation of unbalanced data distribution of different categories. Under normal working conditions (i.e., non-earthquake, extreme disasters, wars and other special working conditions), most slopes are stable, so the data of stable slopes collected are often much more than the data of unstable slopes. Using these data for the prediction training of the slope stability model will cause the trained model to pay more attention to the data of the dominant stable slopes, resulting in the model tending to judge the slope as stable during prediction, and some slopes with poor stability may also be misjudged as stable. Such misjudgments will bring serious potential safety hazards to the lives and property of the people downstream. To solve this problem, the present invention proposes a monitoring system for the slope stability of a waste dump site. Summary of the Invention

[0004] The present invention aims to solve the problem of inaccurate prediction results of the slope stability prediction model caused by the fact that the data of stable slopes are much more than the data of unstable slopes in the prior art, and proposes a monitoring system for the slope stability of a waste dump site.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] A monitoring system for the slope stability of a waste dump site, comprising:

[0007] A data acquisition module: responsible for collecting the deformation data of the slope in real time through various sensors (such as displacement sensors, stress sensors, inclination sensors, etc.) deployed on the waste dump site slope. At the same time, the macroscopic information of the slope is obtained by using aerial images and digital elevation images;

[0008] A data transmission module: responsible for using Internet of Things technology to transmit the collected data to the data processing center in real time, which includes two methods: wired transmission and wireless transmission, to ensure the real-time and reliability of the data;

[0009] The data processing center includes a data processing and analysis module, a warning and decision support module, and a user interaction module;

[0010] Data processing and analysis module: responsible for processing and analyzing the transmitted data. By constructing a slope stability model, it evaluates the stability state of the slope. During the process of constructing the slope stability model, based on the known characteristics of unstable slopes, some new and virtual unstable slope data are generated by GAN to supplement the training set;

[0011] Warning and decision support module: responsible for setting warning thresholds. By comparing the output result of the slope stability model with the warning threshold, once the output result exceeds the threshold, the warning mechanism will be automatically triggered, and warning information will be sent to relevant personnel through the user interaction module. At the same time, it provides a decision support function to provide a basis for the reinforcement and treatment of the slope;

[0012] User interaction module: responsible for providing an operation interface and a visualization display function. Users can view the slope monitoring data, stability evaluation results, warning information, and decision support in real time through the operation interface;

[0013] The data processing and analysis module includes a data receiving unit, a data preprocessing unit, a data augmentation unit, a feature extraction unit, a model training and optimization unit, and a stability evaluation unit. The data receiving unit is responsible for receiving the slope deformation data and the macroscopic information of the slope transmitted from the data transmission module, and performing preprocessing operations such as cleaning, denoising, and filtering on the received data to improve the accuracy and reliability of the data. The processed data is transmitted to the subsequent feature extraction unit or data augmentation unit. The data augmentation unit generates new virtual data based on the known characteristics of unstable slopes using GAN, receives the data from the data preprocessing unit, and transmits the generated virtual data to the model training unit after generation. The feature extraction unit extracts feature information using PCA, receives the data from the data preprocessing unit, and transmits the extracted features to the model training unit after extraction. The model training and optimization unit uses the received features and virtual data for training and optimization, and outputs a trained slope stability model. The stability evaluation unit uses the trained slope stability model to evaluate the stability of new slope deformation data.

[0014] The above technical solution further includes:

[0015] Furthermore, in the data acquisition module, a displacement sensor is used to monitor the horizontal and vertical displacements of the slope to understand the overall deformation of the slope; a stress sensor is used to monitor the stress distribution inside the slope to help determine whether the slope is in a stress equilibrium state. If the stress distribution is abnormal, it indicates that the slope is about to become unstable; by combining the macroscopic information and deformation data of the slope, a comprehensive assessment of the slope stability is carried out. For example, if the overall shape of the slope is steep, the slope is large, and the geological structure is complex, then its stability may be poor; on the contrary, if the overall shape of the slope is gentle, the slope is moderate, and the geological structure is simple, then its stability may be good.

[0016] Furthermore, the specific steps for the data enhancement unit to generate new virtual data using GAN are as follows:

[0017] Data collection: Collect existing processed slope feature data, such as geological structure, topography, rainfall, soil moisture, etc.;

[0018] Feature extraction: Extract key features related to slope stability from the preprocessed data. These features may include the slope of the slope, height, soil type, groundwater level, etc.;

[0019] GAN model training: Construct a GAN model, including a generator and a discriminator. The task of the generator is to generate virtual data similar to the real data, while the task of the discriminator is to distinguish between real data and virtual data. Through training, the generator generates virtual data that is increasingly close to the real data;

[0020] Virtual data generation: Use the trained generator to generate new virtual data based on the known unstable slope features.

[0021] Furthermore, key features related to slope stability are selected through correlation analysis, and the Pearson correlation coefficient between each feature and slope stability is calculated. The Pearson correlation coefficient formula is

[0022]

[0023] where x i and g i are the feature value and slope stability value of the i-th sample respectively, and are the mean values of the feature value and slope stability value respectively, and n is the number of samples;

[0024] According to the value of the Pearson correlation coefficient, explain the degree of association between each feature and slope stability. The larger the absolute value of the Pearson correlation coefficient, the higher the degree of association between the feature and slope stability. When |r|≈1, it indicates a strong linear relationship between the feature and slope stability. When |r|≈0, it indicates that there is almost no linear relationship between the feature and slope stability.

[0025] Furthermore, the specific steps for training the GAN model are as follows:

[0026] Construct a GAN model: Generator: Design a neural network structure whose input is a random noise vector and output is virtual data similar to real slope feature data; Discriminator: Another neural network structure whose input is real data or virtual data generated by the generator, and output is the probability that the data is real data.

[0027] Define the loss function: Generator loss: Measure the difference between the virtual data generated by the generator and real data. The generator loss function is where z represents the random noise vector, G(z) represents the virtual data generated by the generator, and D(G(z)) represents the predicted probability of the discriminator for the virtual data generated by the generator; Discriminator loss: Measure the ability of the discriminator to distinguish between real data and virtual data. The discriminator loss function is where x represents real data and D(x) represents the predicted probability of the discriminator for real data.

[0028] Training process: Initialize model parameters: Assign random weights to the generator and discriminator; Iterative training: Train the discriminator: Use real data and virtual data generated by the generator to train the discriminator to accurately distinguish between the two; Train the generator: Use the feedback of the discriminator to train the generator to make the virtual data it generates closer and closer to real data; Update weights: After each iteration, update the weights of the generator and discriminator according to the gradient of the loss function; Through the iterative training process, continuously optimize the weights of the generator and discriminator to make the generator generate virtual data closer and closer to real data.

[0029] Furthermore, the feature extraction unit extracts feature information using PCA and sets the processed data as M slope samples {X 1 , X 2 ,..., X M}, and each slope sample has N-dimensional slope features Each slope feature X j has its own slope feature value;

[0030] First, decentralize all slope features, that is, remove the mean value, calculate the mean value of each slope feature, and then for all slope samples, subtract the mean value of each slope feature from itself. The respective mean values are After decentralization, calculate the covariance matrix Among them, the variances of slope features X1 and X2 are respectively on the diagonal, and the covariance is on the non-diagonal. The calculation formula of cov(X1, X1) is Thus, the covariance matrix C of M slope samples under these N-dimensional slope features is obtained;

[0031] After obtaining the covariance matrix, according to the characteristic equation Cμ = λμ, find its eigenvalues and the corresponding eigenvectors, where λ is the eigenvalue and μ is the corresponding eigenvector. Select the top k largest eigenvalues and the corresponding eigenvectors for projection. The projection is the process of dimensionality reduction, which reduces the original slope features from high dimension to low dimension. After dimensionality reduction, a large amount of redundant information is removed, and at least more than 85% of the original information is retained. The processed slope features are then passed to the model training unit.

[0032] Furthermore, the model training and optimization unit uses the received features and virtual data for training and optimization, and outputs the trained slope stability model, including the following steps:

[0033] Select the model: According to the data characteristics and task requirements of the waste dump slope stability monitoring, select the attention mechanism model based on Transformer as the slope stability model;

[0034] Initialize parameters: Randomly initialize parameters such as the weights and biases of the model;

[0035] Data preparation: Input the preprocessed features, virtual data, and the actual observed values of slope stability into the model;

[0036] Define the loss function: Select the mean squared error as the loss function. The mean squared error formula is

[0037]

[0038] Among them, y i is the actual observed value, is the model prediction value, and n is the number of samples;

[0039] Select the optimization algorithm: Use the Adam optimization algorithm for iterative training;

[0040] Iterative training: Calculate the loss through forward propagation, and then update the model parameters through backward propagation. Repeat this process until the loss function converges or reaches the preset number of iterations;

[0041] Evaluation model: Use the validation set to evaluate the performance of the model, and use accuracy as the evaluation metric;

[0042] Model tuning: According to the evaluation results, adjust the hyperparameters of the model or improve the model structure to improve the prediction accuracy of the model. For example, we can increase the number of layers of the attention mechanism or adjust the learning rate to further optimize the performance of the model;

[0043] Save the model: Save the trained slope stability model to the specified path or database. The saved content includes parameters such as the weights and biases of the model, as well as the structural information of the model;

[0044] Model deployment: Deploy the trained slope stability model to the stability evaluation unit.

[0045] The present invention has the following beneficial effects:

[0046] In the present invention, based on the known characteristics of unstable slopes, some new and virtual unstable slope data are generated by GAN to supplement the training set. The new and virtual unstable slope data can make up for the deficiency of real data, enabling the model to come into contact with more slope characteristics during training to ensure data balance. This helps the model learn a more comprehensive feature representation, thereby improving the prediction accuracy. Description of the drawings

[0047] Figure 1 It is a system architecture diagram of a waste dump slope stability monitoring system proposed by the present invention. Detailed implementation manners

[0048] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0049] As Figure 1 shown, a waste dump slope stability monitoring system includes:

[0050] Data acquisition module: Responsible for collecting the deformation data of the slope in real time through various sensors (such as displacement sensors, stress sensors, inclination sensors, etc.) deployed on the waste dump slope. At the same time, obtain the macroscopic information of the slope by using aerial images and digital elevation images;

[0051] Data transmission module: Responsible for using Internet of Things technology to transmit the collected data to the data processing center in real time. This includes two methods: wired transmission and wireless transmission, to ensure the real-time and reliability of the data;

[0052] The data processing center includes a data processing and analysis module, a warning and decision support module, and a user interaction module;

[0053] Data processing and analysis module: Responsible for processing and analyzing the transmitted data. By constructing a slope stability model, it evaluates the stability state of the slope. During the process of constructing the slope stability model, based on the known characteristics of unstable slopes, some new and virtual unstable slope data are generated through GAN to supplement the training set;

[0054] Warning and decision support module: Responsible for setting warning thresholds. By comparing the output results of the slope stability model with the warning thresholds, once the output results exceed the thresholds, the warning mechanism will be automatically triggered, and warning messages will be sent to relevant personnel through the user interaction module. At the same time, it provides decision support functions to provide a basis for the reinforcement and treatment of slopes;

[0055] User interaction module: Responsible for providing an operation interface and a visualization display function. Users can view the monitoring data of slopes, stability evaluation results, warning messages, and decision support in real time through the operation interface;

[0056] The data processing and analysis module includes a data receiving unit, a data preprocessing unit, a data augmentation unit, a feature extraction unit, a model training and optimization unit, and a stability evaluation unit. The data receiving unit is responsible for receiving slope deformation data and macroscopic information of slopes transmitted from the data transmission module, and performing preprocessing operations such as cleaning, denoising, and filtering on the received data to improve the accuracy and reliability of the data. The processed data is transmitted to the subsequent feature extraction unit or data augmentation unit. The data augmentation unit generates new virtual data based on the known characteristics of unstable slopes using GAN, receives data from the data preprocessing unit, and transmits the generated virtual data to the model training unit after generating the virtual data. The feature extraction unit extracts feature information using PCA, receives data from the data preprocessing unit, and transmits the extracted features to the model training unit after extraction. The model training and optimization unit uses the received features and virtual data for training and optimization, and outputs a trained slope stability model. The stability evaluation unit uses the trained slope stability model to evaluate the stability of new slope deformation data.

[0057] In one embodiment, in the data acquisition module, a displacement sensor is used to monitor the horizontal and vertical displacements of the slope to understand the overall deformation of the slope; a stress sensor is used to monitor the stress distribution inside the slope to help determine whether the slope is in a stress balance state. If the stress distribution is abnormal, it indicates that the slope is about to become unstable; by combining the macroscopic information and deformation data of the slope, a comprehensive assessment of the slope stability is carried out. For example, if the overall shape of the slope is steep, the slope is large, and the geological structure is complex, its stability may be poor; on the contrary, if the overall shape of the slope is gentle, the slope is moderate, and the geological structure is simple, its stability may be good.

[0058] In one embodiment, the specific steps for the data enhancement unit to generate new virtual data using GAN are as follows:

[0059] Data collection: Collect existing processed slope feature data, such as geological structure, topography, rainfall, soil humidity, etc.;

[0060] Feature extraction: Extract key features related to slope stability from the preprocessed data. These features may include the slope of the slope, height, soil type, groundwater level, etc.;

[0061] GAN model training: Construct a GAN model, including a generator and a discriminator. The task of the generator is to generate virtual data similar to the real data, while the task of the discriminator is to distinguish between real data and virtual data. Through training, the generator generates virtual data that is increasingly close to the real data;

[0062] Virtual data generation: Use the trained generator to generate new virtual data based on the known unstable slope features.

[0063] In one embodiment, key features related to slope stability are screened out through correlation analysis, and the Pearson correlation coefficient between each feature and slope stability is calculated. The Pearson correlation coefficient formula is

[0064]

[0065] where x i and y i are the feature value and slope stability value of the i-th sample respectively, and are the mean values of the feature value and slope stability value respectively, and n is the number of samples;

[0066] According to the value of the Pearson correlation coefficient, explain the degree of association between each feature and slope stability. The larger the absolute value of the Pearson correlation coefficient, the higher the degree of association between the feature and slope stability. When |r| ≈ 1, it indicates a strong linear relationship between the feature and slope stability. When |r| ≈ 0, it indicates that there is almost no linear relationship between the feature and slope stability.

[0067] In one embodiment, the specific steps of GAN model training are as follows:

[0068] Construct a GAN model: Generator: Design a neural network structure whose input is a random noise vector and output is virtual data similar to real slope feature data; Discriminator: Another neural network structure whose input is real data or virtual data generated by the generator, and output is the probability that this data is real data;

[0069] Define the loss function: Generator loss: Measure the difference between the virtual data generated by the generator and the real data. The generator loss function is where z represents the random noise vector, G(z) represents the virtual data generated by the generator, and D(G(z)) represents the predicted probability of the discriminator for the virtual data generated by the generator; Discriminator loss: Measure the ability of the discriminator to distinguish real data and virtual data. The discriminator loss function is where x represents the real data, and D(x) represents the predicted probability of the discriminator for the real data;

[0070] Training process: Initialize model parameters: Assign random weights to the generator and discriminator; Iterative training: Train the discriminator: Use real data and virtual data generated by the generator to train the discriminator to accurately distinguish between the two; Train the generator: Use the feedback of the discriminator to train the generator to make the virtual data it generates closer and closer to the real data; Update weights: After each iteration, update the weights of the generator and discriminator according to the gradient of the loss function; Through the iterative training process, continuously optimize the weights of the generator and discriminator to make the generator generate virtual data closer and closer to the real data.

[0071] In one embodiment, the feature extraction unit extracts feature information using PCA, and sets the processed data as M slope samples {X 1 , X 2 ,..., X M}, and each slope sample has N-dimensional slope features Each slope feature X j has its own slope feature value;

[0072] First, decentralize all slope features, that is, remove the mean value, calculate the mean value of each slope feature, and then for all slope samples, each slope feature subtracts its own mean value, where their respective mean values are After decentralization, calculate the covariance matrix Among them, the variances of slope features X1 and X2 are respectively on the diagonal, and the covariance is on the non - diagonal. The calculation formula of cov(X1,X1) is From this, the covariance matrix C of M slope samples under these N - dimensional slope features is obtained;

[0073] After obtaining the covariance matrix, according to the characteristic equation Cμ=λμ, find its eigenvalues and the corresponding eigenvectors, where λ is the eigenvalue and μ is the corresponding eigenvector. Select the top k largest eigenvalues and the corresponding eigenvectors for projection. The projection is the process of dimensionality reduction, which reduces the original slope features from high - dimension to low - dimension. After dimensionality reduction, a large amount of redundant information is removed, and at least more than 85% of the original information is retained. The processed slope features are then passed to the model training unit.

[0074] In one embodiment, the model training and optimization unit uses the received features and virtual data for training and optimization, and outputs a trained slope stability model, including the following steps:

[0075] Select a model: According to the data characteristics and task requirements of the waste dump slope stability monitoring, select the attention mechanism model based on Transformer as the slope stability model;

[0076] Initialize parameters: Randomly initialize parameters such as the weights and biases of the model;

[0077] Data preparation: Input the pre - processed features, virtual data, and actual observed values of slope stability into the model;

[0078] Define the loss function: Select the mean squared error as the loss function. The mean squared error formula is

[0079]

[0080] Among them, y i is the actual observed value, is the model prediction value, and n is the number of samples;

[0081] Select the optimization algorithm: Use the Adam optimization algorithm for iterative training;

[0082] Iterative training: Calculate the loss through forward propagation, and then update the model parameters through backpropagation. Repeat this process until the loss function converges or reaches the preset number of iterations;

[0083] Evaluation Model: Evaluate the performance of the model using the validation set, and use accuracy as the evaluation metric;

[0084] Model Tuning: According to the evaluation results, adjust the hyperparameters of the model or improve the model structure to enhance the prediction accuracy of the model. For example, we can increase the number of layers of the attention mechanism or adjust the learning rate to further optimize the performance of the model;

[0085] Save the Model: Save the trained slope stability model to the specified path or database. The saved content includes parameters such as the weights and biases of the model, as well as the structural information of the model;

[0086] Model Deployment: Deploy the trained slope stability model to the stability evaluation unit.

[0087] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A spoil site slope stability monitoring system, characterized in that: include: Data acquisition module: responsible for collecting slope deformation data in real time through various sensors deployed on the slope of the waste dump, and obtaining macro information of the slope using aerial images and digital elevation images; Data transmission module: responsible for using IoT technology to transmit the collected data to the data processing center in real time, including wired transmission and wireless transmission; The data processing center includes a data processing and analysis module, an early warning and decision support module, and a user interaction module; Data processing and analysis module: responsible for processing and analyzing the transmitted data, evaluating the stability of the slope by building a slope stability model. In the process of building the slope stability model, based on the known unstable slope characteristics, some new and virtual unstable slope data are generated through GAN to supplement the training set; Early warning and decision support module: responsible for setting the early warning threshold. The output result of the slope stability model is compared with the early warning threshold. Once the output result exceeds the threshold, the early warning mechanism will be automatically triggered, and the early warning information will be sent to relevant personnel through the user interaction module. At the same time, it provides decision support functions to provide a basis for slope reinforcement and management. User interaction module: responsible for providing the operation interface and visual display function. Users can view the slope monitoring data, stability assessment results, early warning information and decision support in real time through the operation interface; The data processing and analysis module includes a data receiving unit, a data preprocessing unit, a data enhancement unit, a feature extraction unit, a model training and optimization unit and a stability assessment unit. The data receiving unit is responsible for receiving the slope deformation data and the macro information of the slope transmitted from the data transmission module, performing preprocessing operations on the received data, and passing the processed data to the subsequent feature extraction unit or data enhancement unit. The data enhancement unit generates new virtual data based on known unstable slope features using GAN, receives data from the data preprocessing unit, and passes the generated virtual data to the model training unit. The feature extraction unit extracts feature information using PCA, receives data from the data preprocessing unit, extracts features and passes them to the model training unit. The model training and optimization unit performs training and optimization using the received features and virtual data, and outputs a trained slope stability model. The stability assessment unit performs stability assessment on new slope deformation data using the trained slope stability model.

2. A spoil dump slope stability monitoring system according to claim 1, characterized in that: In the data acquisition module, the horizontal and vertical displacements of the slope are monitored by displacement sensors to understand the overall deformation of the slope; the stress distribution inside the slope is monitored by stress sensors to help determine whether the slope is in a state of force balance. If the stress distribution is abnormal, it indicates that the slope is about to become unstable; the stability of the slope is comprehensively evaluated by combining the macroscopic information and deformation data of the slope.

3. A spoil dump slope stability monitoring system according to claim 1, characterized in that: The specific steps of the data enhancement unit generating new virtual data using GAN are as follows: Data collection: Collect the existing processed slope characteristic data; Feature extraction: extract key features related to slope stability from preprocessed data; GAN model training: Build a GAN model, including a generator and a discriminator. The task of the generator is to generate virtual data similar to real data, while the task of the discriminator is to distinguish between real data and virtual data. Through training, the generator can generate virtual data that is closer and closer to real data. Virtual data generation: New virtual data are generated based on known unstable slope characteristics using the trained generator.

4. A spoil dump slope stability monitoring system according to claim 3, characterized in that: The key features related to slope stability are screened out through correlation analysis, and the Pearson correlation coefficient between each feature and slope stability is calculated. The Pearson correlation coefficient formula is: Among them, x i and i are the characteristic value and slope stability value of the i-th sample, respectively. and are the means of the characteristic values ​​and slope stability values, respectively, and n is the number of samples; According to the value of Pearson's correlation coefficient, the degree of correlation between each feature and slope stability is explained. The larger the absolute value of Pearson's correlation coefficient is, the higher the degree of correlation between the feature and slope stability is. When |r|≈1, it means that there is a strong linear relationship between the feature and slope stability. When |r|≈0, it means that there is almost no linear relationship between the feature and slope stability.

5. A spoil dump slope stability monitoring system according to claim 3, characterized in that: The specific steps of the GAN model training are: Construct the GAN model: Generator: Design a neural network structure whose input is a random noise vector and whose output is virtual data similar to the real slope feature data; Discriminator: Another neural network structure whose input is real data or virtual data generated by the generator, and whose output is the probability that the data is real data; Define the loss function: Generator loss: measures the difference between the virtual data generated by the generator and the real data. The generator loss function is Where z represents a random noise vector, G(z) represents virtual data generated by the generator, and D(G(z)) represents the predicted probability of the discriminator for the virtual data generated by the generator; discriminator loss: measures the ability of the discriminator to distinguish between real data and virtual data. The discriminator loss function is Among them, x represents the real data, and D(x) represents the predicted probability of the discriminator for the real data; Training process: Initialize model parameters: assign random weights to the generator and discriminator; iterative training: train the discriminator: use real data and virtual data generated by the generator to train the discriminator so that it can accurately distinguish between the two; train the generator: use the feedback from the discriminator to train the generator so that the virtual data it generates is closer and closer to the real data; update weights: after each iteration, update the weights of the generator and discriminator according to the gradient of the loss function; through the iterative training process, continuously optimize the weights of the generator and discriminator so that the generator generates virtual data that is closer and closer to the real data.

6. A spoil dump slope stability monitoring system according to claim 1, characterized in that: The feature extraction unit uses PCA to extract feature information and sets the processed data as M slope samples {X 1 , X 2 , ..., X M ,}, each slope sample has N-dimensional slope features Each slope feature X j Each has its own slope characteristic value; First, all slope features are decentralized, that is, the mean is removed, and the average value of each slope feature is calculated. Then, for all slope samples, each slope feature is subtracted from its own mean, where the respective means are Find the covariance matrix after decentralization The diagonal lines are the variances of the slope features X1 and X2, and the off-diagonal lines are the covariances. The calculation formula for cov(X1, X1) is: Thus, the covariance matrix C of M slope samples under the N-dimensional slope characteristics is obtained; After obtaining the covariance matrix, its eigenvalues ​​and their corresponding eigenvectors are calculated according to the characteristic equation Cμ=λμ, where λ is the eigenvalue and μ is its corresponding eigenvector. The largest first k eigenvalues ​​and corresponding eigenvectors are selected for projection. Projection is the process of dimensionality reduction, which reduces the original slope features from high dimensions to low dimensions. After dimensionality reduction, a large amount of redundant information is removed and at least 85% of the original information is retained. The processed slope features are then passed to the model training unit.

7. The system for monitoring the slope stability of a waste dump according to claim 1, characterized in that: The model training and optimization unit uses the received features and virtual data to perform training and optimization, and outputs a trained slope stability model, including the following steps: Model selection: According to the data characteristics and task requirements of the slope stability monitoring of the waste dump, the Transformer-based attention mechanism model is selected as the slope stability model; Initialization parameters: Randomly initialize the model’s weights, biases and other parameters; Data preparation: preprocessed features and virtual data as well as actual observations of slope stability are fed into the model; Define the loss function: Select mean square error as the loss function. The mean square error formula is Among them, y i is the actual observed value, is the model prediction value, n is the number of samples; Select optimization algorithm: Use Adam optimization algorithm for iterative training; Iterative training: Calculate the loss through forward propagation, then update the model parameters through back propagation, and repeat this process until the loss function converges or reaches the preset number of iterations; Evaluate the model: Use the validation set to evaluate the performance of the model, using accuracy as the evaluation metric; Model tuning: Adjust the model’s hyperparameters or improve the model structure based on the evaluation results; Save model: save the trained slope stability model to the specified path or database, including the model's weight, bias and other parameters as well as the model's structural information; Model deployment: Deploy the trained slope stability model to the stability assessment unit.

Images