Early warning method and device for geological disasters, storage medium and electronic equipment
Through the combination of displacement prediction model and microseismic and stress testing, the initial and target warning levels of geological disasters are determined, and the problem of low geological disaster warning efficiency in the existing technology is solved, and a more accurate and comprehensive geological disaster warning is achieved.
Patent Information
- Application Number
- CN202410994757.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-22
AI Technical Summary
The existing geological disaster warning system relies on a single type of data, resulting in low early warning efficiency, lack of comprehensiveness and accuracy, affecting the rigor of early warning.
The displacement data of geological changes is determined through the displacement prediction model, combined with microseismic monitoring and stress testing, the initial and target warning levels are determined, and the geological disaster warning instructions are triggered when the preset level is reached, and the warning information is sent to the terminal equipment.
Accurate early warning of geological disasters has been achieved, the early warning efficiency has been improved, and the comprehensiveness and accuracy of the early warning has been ensured.
Smart Images

Figure CN119007386A_ABST
Abstract
Description
Background Art
[0002] In the related technologies, the traditional geological disaster early warning system mainly relies on a single type of data, which may only reflect the current geological situation and ignore other potential factors related to it. This limitation may make the early warning system lack in comprehensiveness and accuracy, thus affecting the rigor of its overall early warning, and thus leading to low early warning efficiency of geological disasters.
[0003] There is currently no effective solution to the problem of low early warning efficiency of geological disasters in related technologies. Summary of the invention
[0004] The main purpose of this application is to provide a geological disaster early warning method, device, storage medium and electronic equipment to solve the problem of low efficiency of geological disaster early warning in related technologies.
[0005] In order to achieve the above-mentioned purpose, according to the first aspect of the present application, a geological disaster early warning method is provided. The method comprises: determining the displacement data of geological changes through a displacement prediction model; determining the initial early warning level of geological changes according to the displacement data; determining the target early warning level of geological changes under microseismic monitoring and stress testing respectively when at least one of the initial early warning levels is detected to be higher than the preset early warning level; triggering a geological disaster early warning instruction when at least one of the target early warning levels is detected to be higher than the preset early warning level, and sending early warning information corresponding to the target early warning level to a terminal device.
[0006] In some embodiments, determining the displacement data of geological changes through a displacement prediction model includes: monitoring geological characteristic data associated with the geological changes; inputting the geological characteristic data into the displacement prediction model, and outputting the displacement data of the geological changes.
[0007] In some embodiments, the initial warning level includes: a rate warning level, determining the initial warning level of geological changes based on displacement data, including: calculating the displacement rate of geological changes within a preset time period based on the displacement data; determining the rate warning level corresponding to the displacement rate, wherein the rate warning level includes one of the following: rate yellow warning, rate orange warning, rate red warning, wherein the warning levels of rate orange warning and rate red warning are higher than the preset warning level.
[0008] In some embodiments, the initial warning level includes: a tangent angle warning level, and the initial warning level of geological changes is determined based on the displacement data, including: calculating the displacement change time corresponding to the displacement data when the displacement rate is constant; calculating the ratio between the displacement change time and a preset time period to determine the displacement tangent angle of the geological change; determining the tangent angle warning level corresponding to the displacement tangent angle, wherein the tangent angle warning level includes one of the following: a yellow tangent angle warning, an orange tangent angle warning, and a red tangent angle warning, wherein the warning levels of the orange tangent angle warning and the red tangent angle warning are higher than the preset warning level.
[0009] In some embodiments, the target warning level includes: a microseismic warning level. When it is detected that at least one of the initial warning levels is higher than the preset warning level, the target warning level of geological changes under microseismic monitoring and stress testing is determined respectively, including: obtaining warning indicator data based on microseismic monitoring, wherein the warning indicator data includes: magnitude, energy, apparent volume, apparent stress, target factor, wherein the target factor is used to describe the relationship between magnitude and frequency; determining the microseismic warning level of geological changes according to the warning indicator data, wherein the microseismic warning level includes one of the following: microseismic yellow warning, microseismic orange warning, microseismic red warning, wherein the warning level of the microseismic orange warning and the microseismic red warning is higher than the preset warning level.
[0010] In some embodiments, the target warning level includes: a stress warning level. When it is detected that at least one of the initial warning levels is higher than the preset warning level, the target warning level of geological changes under microseismic monitoring and stress testing is determined respectively, including: a slowly varying increment value of sliding force based on stress testing to monitor geological changes; and a stress warning level of geological changes based on the slowly varying increment of sliding force, wherein the stress warning level includes one of the following: a yellow stress warning, an orange stress warning, and a red stress warning, wherein the warning levels of the orange stress warning and the red stress warning are higher than the preset warning level.
[0011] In some embodiments, before triggering a geological disaster warning instruction and sending warning information corresponding to the target warning level to a terminal device, the method also includes: when it is detected that at least one of the target warning levels is higher than a preset warning level, acquiring geological data of the target area where the geological changes are located based on sensors; if the data of the target warning level is verified to be true based on the geological data, triggering a geological disaster warning instruction.
[0012] In some embodiments, the displacement prediction model can be obtained through the following steps: collecting real-time displacement data of the monitoring site, wherein the real-time displacement data includes: displacement amount data and displacement speed data; normalizing the real-time displacement data to obtain processed data; training the initial displacement prediction model based on the processed data and historical displacement data to obtain the displacement prediction model.
[0013] In some embodiments, an initial displacement prediction model is trained based on processed data and historical displacement data to obtain a displacement prediction model, including: extracting feature data of the processed data and historical displacement data respectively; collecting data with periodic characteristics in the feature data; and collecting data with time series characteristics in the feature data, and optimizing the initial displacement prediction model based on the data with periodic characteristics and the data with time series characteristics to obtain a displacement prediction model.
[0014] In some embodiments, microseismic monitoring performs data acquisition operations through a microseismic prediction model, wherein the microseismic prediction model can be obtained through the following steps: determining the microseismic characteristic data of the monitoring site; processing the weights of the microseismic characteristic data by setting target parameters to obtain target microseismic characteristic data; inputting the target microseismic characteristic data into the initial microseismic neural network model for training iterations to obtain the microseismic prediction model.
[0015] In some embodiments, the stress test performs data acquisition operations through a stress prediction model, wherein the stress prediction model can be obtained through the following steps: determining the real-time characteristic data of stress at the monitoring site; and training and iterating based on the real-time characteristic data of stress input into an initial stress neural network model to obtain a stress prediction model.
[0016] In order to achieve the above-mentioned purpose, according to the second aspect of the present application, a geological disaster early warning device is provided. The device includes: a first determination unit, which is used to determine the displacement data of geological changes through a displacement prediction model; a second determination unit, which is used to determine the initial early warning level of geological changes according to the displacement data; a third determination unit, which is used to determine the target early warning level of geological changes under microseismic monitoring and stress testing respectively when at least one of the initial early warning levels is detected to be higher than the preset early warning level; a sending unit, which is used to trigger a geological disaster early warning instruction when at least one of the target early warning levels is detected to be higher than the preset early warning level, and send the early warning information corresponding to the target early warning level to the terminal device.
[0017] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned geological disaster early warning methods is implemented.
[0018] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, an early warning method for geological disasters according to any one of the above items is implemented.
[0019] Through this application, the following steps are adopted: when it is detected that at least one of the initial warning levels is higher than the preset warning level, the target warning level of geological changes under microseismic monitoring and stress testing is determined respectively; when it is detected that at least one of the target warning levels is higher than the preset warning level, the geological disaster warning instruction is triggered, and the warning information corresponding to the target warning level is sent to the terminal device. This application realizes accurate early warning of geological disasters by determining the primary warning level and the target warning level, solves the problem of low early warning efficiency of geological disasters in related technologies, and thus achieves the effect of improving the early warning efficiency of geological disasters. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 It is a flow chart of a geological disaster early warning method provided according to an embodiment of the present application; Figure 2 is a schematic diagram of a geological disaster early warning method provided according to an embodiment of the present application; Figure 3 is a schematic diagram of a geological disaster early warning device provided according to an embodiment of the present application; Figure 4 It is a schematic diagram of the network architecture of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION
[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0024] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below: TimesNet network: is a deep learning model proposed for time series analysis, focusing on the multi-periodicity and time-varying two-dimensional changes of time series.
[0025] ReLU (Rectified Linear Unit): It is an activation function commonly used in deep learning, and its full name is linear rectification unit.
[0026] MSE (Mean Squared Error): is the abbreviation of mean square error, which is a loss function or error metric commonly used in regression problems.
[0027] Adaboost_LSTM network: a network model that combines the LSTM (Long Short-Term Memory Network) and AdaBoost (Adaptive Boosting) algorithms.
[0028] Adaboost: Also known as AdaBoost (Adaptive Boosting), is an ensemble learning algorithm used to improve the prediction accuracy of classification problems.
[0029] LSTM (Long Short-Term Memory): is a special recurrent neural network (RNN) structure.
[0030] Transformer model: A deep learning architecture proposed by Google in 2017, mainly used for natural language processing (NLP) tasks, especially sequence-to-sequence learning such as machine translation.
[0031] According to an embodiment of the present application, a geological disaster early warning method is provided.
[0032] Figure 1 FIG. 1 is a flow chart of a method for early warning of geological disasters according to an embodiment of the present application. Figure 1 As shown, the method comprises the following steps: comprising the following steps: S101, determining displacement data of geological changes through a displacement prediction model.
[0033] For example, during the measurement process of a landslide experiment, in order to predict the displacement of the landslide and assess its risk, a reliable displacement prediction model is established in advance, wherein the displacement data of the landslide area may be displacement amount, displacement direction, timestamp data related to the displacement, or other types of displacement data, which is not limited in this application.
[0034] In some embodiments, determining the displacement data of geological changes through the displacement prediction model can be achieved through the following steps: monitoring geological characteristic data associated with the geological changes; inputting the geological characteristic data into the displacement prediction model, and outputting the displacement data of the geological changes.
[0035] For example, in earthquake-prone areas, geological characteristic data may be information such as the elevation, slope, and slope direction of the terrain. The geological characteristic data is input into a displacement prediction model. When the model receives the input geological characteristic data, it calculates the displacement data of the predicted geological changes based on the internal algorithms and parameters. These data may include: displacement amount, displacement direction, displacement distribution and other information. This application provides important value for the subsequent assessment of geological disaster risks, formulation of rescue plans and restoration measures through the precise acquisition of displacement data.
[0036] Among them, the displacement prediction model mentioned above can be obtained through the following steps: collecting real-time displacement data of the monitoring site, wherein the real-time displacement data includes: displacement data and displacement speed data; normalizing the real-time displacement data to obtain processed data; training the initial displacement prediction model according to the processed data and historical displacement data to obtain the displacement prediction model.
[0037] In some embodiments, the displacement prediction model is mainly a soil displacement prediction model based on the TimesNet network. For example, by collecting real-time displacement data from monitoring sites, including displacement data and displacement velocity data, removing outliers and noise, processing missing values, normalizing or standardizing the data, and scaling the data to a fixed range so as to maintain a stable numerical range during the model training process, historical geological displacement data and other auxiliary features are extracted at the same time, and the initial displacement prediction model is trained by analyzing historical data and processed real-time displacement data to obtain a displacement prediction model. This application improves the measurement accuracy of displacement data and further ensures the accuracy of geological disaster warning by constructing a displacement prediction model.
[0038] Specifically, the initial displacement prediction model is trained according to the processed data and the historical displacement data to obtain the displacement prediction model, which can be achieved through the following steps: extracting feature data of the processed data and the historical displacement data respectively; collecting data with periodic characteristics in the feature data; and collecting data with time series characteristics in the feature data, and optimizing the initial displacement prediction model based on the data with periodic characteristics and the data with time series characteristics to obtain the displacement prediction model.
[0039] Exemplarily, first, capture the periodic pattern in the feature data in the time series, divide the time series data into multiple segments according to predefined period windows (such as daily, weekly), each window contains a complete period data, encode the data of each period window, convert it into a high-dimensional feature representation, use position encoding or other methods to mark the data of different time steps, and retain the information of the time step. Calculate the attention weights between each time step in the period window, capture the dependencies within the period, use the self-attention mechanism (Self-Attention) to calculate the attention weight matrix, calculate the weighted sum within the period through the attention weight matrix (A) and the value matrix (V), and obtain data with periodic characteristics. This application improves the accuracy of model training by determining the data with periodic characteristics.
[0040] Secondly, the present application can also use a one-dimensional convolutional neural network to process local features of time series data. Specifically, a one-dimensional convolution kernel is applied to slide on the time series to extract local features. The convolution kernel size and stride are adjusted according to the characteristics of the data. A nonlinear activation function (such as ReLU) is used to perform a nonlinear transformation on the convolved features. A pooling layer (such as maximum pooling or average pooling) is used to reduce the data dimension and retain important features to obtain the data of the time series features in the present application. The present application improves the accuracy of model training by determining the data of the time series features.
[0041] For another example, the present application fuses the data of periodic features and the data of time series features, and splices the two in the feature dimension. The spliced features contain periodic information and local features. The fused features are mapped to the prediction space through a fully connected layer to optimize the initial displacement prediction model. Specifically, by selecting the mean square error (MSE) as the loss function, the difference between the model prediction value and the true value is measured, and the data sets of periodic features and time series features are divided into a training set, a validation set, and a test set. The model is trained on the training set and hyperparameters are tuned on the validation set to improve the generalization ability of the model. The trained model is used to predict new data to obtain the geological displacement value of the future time step. The prediction accuracy and performance of the model are evaluated by calculating indicators such as the root mean square error (RMSE) and the mean absolute error (MAE) between the predicted value and the true value.
[0042] S102, determining an initial warning level of geological changes according to the displacement data.
[0043] Specifically, the determination of the initial warning level of this application can be understood as the result of the initial warning test on geological changes. The determination of the initial warning level includes two dimensions, one is the displacement rate dimension, and the other is the displacement tangent angle dimension. This application, through the determination of the initial warning level, plays an effective warning role in the subsequent geological disasters caused by geological changes.
[0044] In some embodiments, the initial warning level includes: a rate warning level. The initial warning level of geological changes is determined based on the displacement data, which can be achieved through the following steps: calculating the displacement rate of geological changes within a preset time period based on the displacement data; determining the rate warning level corresponding to the displacement rate, wherein the rate warning level includes one of the following: yellow rate warning, orange rate warning, and red rate warning, wherein the warning levels of orange rate warning and red rate warning are higher than the preset warning level.
[0045] Exemplarily, the displacement data of the landslide body in a certain area within one month is collected, including the daily displacement amount, the daily displacement rate is calculated according to the obtained displacement amount, and the rate warning level is determined according to the displacement rate. For example, when the displacement rate (unit: mm / d) is 1.4≤v ≤2.8, it corresponds to a yellow rate warning, when the displacement rate (unit: mm / d) is 2.8≤v ≤4, it corresponds to an orange rate warning, and when the displacement rate (unit: mm / d) is 4≤v, it corresponds to a red rate warning. The level of the warning can be used to describe the degree of danger of geological disasters. The higher the warning level, the greater the risk of geological disasters. The warning level of the yellow rate warning is lower than the warning level of the orange rate warning, and the warning level of the orange rate warning is lower than the red rate warning. The present application can effectively improve the accuracy of geological disaster warnings by determining the rate warning level.
[0046] In some embodiments, the initial warning level includes: a tangent angle warning level, and the initial warning level of geological changes is determined based on the displacement data, including: calculating the displacement change time corresponding to the displacement data when the displacement rate is constant; calculating the ratio between the displacement change time and a preset time period to determine the displacement tangent angle of the geological change; determining the tangent angle warning level corresponding to the displacement tangent angle, wherein the tangent angle warning level includes one of the following: a yellow tangent angle warning, an orange tangent angle warning, and a red tangent angle warning, wherein the warning levels of the orange tangent angle warning and the red tangent angle warning are higher than the preset warning level.
[0047] For example, assuming that during the landslide test, the deformation rate v in the constant deformation stage is a constant value, the ordinate of the deformation-time curve is transformed into the same time dimension as the abscissa by dividing the displacement by v: T=∆S / v, where is the slope deformation in a certain monitoring period; v is the displacement rate in the constant deformation stage; T is the ordinate value with the same dimension as time after transformation, and the displacement tangent angle of the deformation curve is defined as: tanα=∆T / ∆t. Obviously, at that time, the slope was in the initial deformation stage; at that time, the slope was in the uniform deformation stage; at that time, the slope was in the accelerated deformation stage. Therefore, it can be set here that when the displacement tangent angle (unit: °) is 45≤α<65, the corresponding tangent angle yellow warning is given, when the displacement tangent angle (unit: °) is 65≤α<85, the corresponding tangent angle orange warning is given, and when the displacement tangent angle (unit: °) is 85≤α, the corresponding tangent angle red warning is given. The warning level can be used to describe the degree of danger of geological disasters. The higher the warning level, the greater the risk of geological disasters. The warning level of the yellow tangent angle warning is lower than that of the orange tangent angle warning, and the warning level of the orange tangent angle warning is lower than that of the red tangent angle warning. This application can effectively improve the accuracy of geological disaster warnings by determining the tangent angle warning level.
[0048] S103, when it is detected that at least one of the initial warning levels is higher than the preset warning level, respectively determining the target warning level of geological changes under microseismic monitoring and stress testing.
[0049] Among them, at least one of the initial warning levels that is higher than the preset warning level may be a case where the rate warning level is a yellow warning for rate and the tangent angle warning level is an orange warning for tangent angle, or a case where the rate warning level is a yellow warning for rate and the tangent angle warning level is a red warning for tangent angle, or a case where the rate warning level is an orange warning for rate and the tangent angle warning level is a yellow warning for tangent angle, or a case where the rate warning level is an orange warning for rate and the tangent angle warning level is a yellow warning for tangent angle, etc., wherein the preset warning level may be a warning level with a yellow warning mark, for example, the preset warning level may be the yellow warning for tangent angle in the present application, or it may be the yellow warning for rate, which is not limited here.
[0050] Among them, the above-mentioned target warning level can be a microseismic warning level or a stress warning level. The microseismic warning level determined by microseismic monitoring and the stress warning level determined by stress testing in this application effectively ensure the reliability of the warning accuracy when facing geological disasters.
[0051] In some embodiments, the target warning level includes: a microseismic warning level. When it is detected that at least one of the initial warning levels is higher than the preset warning level, the target warning level of geological changes under microseismic monitoring and stress testing is determined respectively, including: obtaining warning indicator data based on microseismic monitoring, wherein the warning indicator data includes: magnitude, energy, apparent volume, apparent stress, target factor, wherein the target factor is used to describe the relationship between magnitude and frequency; determining the microseismic warning level of geological changes according to the warning indicator data, wherein the microseismic warning level includes one of the following: microseismic yellow warning, microseismic orange warning, microseismic red warning, wherein the warning level of the microseismic orange warning and the microseismic red warning is higher than the preset warning level.
[0052] For example, based on microseismic monitoring information, the early warning indicator data mainly include magnitude, energy, apparent volume, apparent stress, and b-value factor (i.e., the target factor in this application). According to the microseismic activity parameters, it is divided into three levels of warning: "yellow, orange, and red", i.e., the microseismic yellow warning, microseismic orange warning, and microseismic red warning in this application. The judgment conditions for the microseismic yellow warning are as follows: within a 120s period, ① two high-energy level events occur continuously in the monitoring area, ② the b-value continues to decrease, and at least one of the indicators is met, then a microseismic yellow warning is issued. Warning; The judgment conditions for the microseismic orange warning are as follows: within a 120s period, ① two high-energy events occur in succession in the monitoring area, ② the b value continues to decrease, ③ the magnitude is greater than 1.0, and the above three indicators are met, then the microseismic orange warning is issued; The judgment conditions for the microseismic red warning are as follows: within a 120s period, ① two high-energy events occur in succession in the monitoring area, ② the b value continues to decrease, ③ the magnitude is greater than 1.0, ④ the apparent stress decreases sharply and the apparent volume increases sharply, and the above four indicators are met, then the microseismic red warning is issued. Among them, the level of the warning can be used to describe the degree of danger of geological disasters. The higher the warning level, the greater the risk of geological disasters. The warning level of the microseismic yellow warning is lower than the warning level of the microseismic orange warning, and the warning level of the microseismic orange warning is lower than the microseismic red warning. This application can effectively improve the accuracy of geological disaster warnings by determining the microseismic warning level.
[0053] Among them, the above-mentioned microseismic monitoring performs data acquisition operations through a microseismic prediction model, wherein the microseismic prediction model can be obtained through the following steps: determining the microseismic characteristic data of the monitoring site; processing the weights of the microseismic characteristic data by setting target parameters to obtain target microseismic characteristic data; inputting the target microseismic characteristic data into the initial microseismic neural network model for training iteration to obtain the microseismic prediction model.
[0054] First, the microseismic early warning prediction data obtains the microseismic data prediction model based on the Adaboost_LSTM network. By collecting real-time microseismic data from the site, the data is divided into training set and test set according to time series, and the microseismic data is feature extracted. The time domain features, frequency domain features, and time series features are extracted and converted into microseismic feature data suitable for LSTM model processing. All feature data are scaled to the same range to prevent certain features from having too much impact on the model during the training process.
[0055] Secondly, initialize the Adaboost parameters (corresponding to the target parameters in this application), including setting the number of iterations and sample weight initialization. In each iteration, the Adaboost algorithm adjusts the weight of the sample as the target microseismic feature data, and trains a new LSTM (initial microseismic neural network) model based on the target microseismic feature data. Then, based on the current weight distribution, design the architecture of the LSTM model, including the input layer, LSTM layer (there can be multiple), fully connected layer, etc., and set the hyperparameters of the LSTM model, such as the number of hidden layer nodes, learning rate, optimizer, etc. The LSTM model is trained through the back propagation algorithm. After the training is completed, the performance of the model is tested using the training data, the error rate is calculated, and the weight of the sample is updated according to the error rate, so that samples with larger errors obtain higher weights in the next round of iterations, thereby having more influence on the training of the next LSTM model. After all iterations are completed, the weak classifiers are combined into a strong classifier, and the output of each weak classifier is weighted averaged according to its weight. The final prediction result is the average of the weighted outputs of all weak classifiers, and the microseismic prediction model of this application is trained and iterated. The microseismic prediction model will use the previously learned time series features and time series relationships to predict future microseismic activities, and evaluate the prediction results, mainly using common prediction performance indicators such as root mean square error (RMSE), mean absolute error (MAE), etc. to evaluate the accuracy and generalization ability of the model. This application improves the accuracy of geological disaster measurement by accurately acquiring microseismic data through the microseismic prediction model.
[0056] In some embodiments, the target warning level includes: a stress warning level. When it is detected that at least one of the initial warning levels is higher than the preset warning level, the target warning level of geological changes under microseismic monitoring and stress testing is determined respectively, which can be obtained by the following steps: monitoring the slowly varying increment value of the sliding force of geological changes based on the stress test; determining the stress warning level of geological changes based on the slowly varying increment of the sliding force, wherein the stress warning level includes one of the following: a yellow stress warning, an orange stress warning, and a red stress warning, wherein the warning levels of the orange stress warning and the red stress warning are higher than the preset warning level.
[0057] Exemplarily, the stress yellow warning mark of the stress testing system is: when the sliding force slow-changing increment T in the monitoring area is greater than 300kN, the system automatically issues a long-term warning message; the stress orange warning mark is: when the sliding force slow-changing increment T in the monitoring area is greater than 600kN, the system automatically issues a medium-term warning, and the staff and large equipment are evacuated; the stress red warning mark is: when the sliding force slow-changing increment T in the monitoring area is greater than 900kN, the system automatically issues a medium-term warning, and all personnel (including monitoring personnel and investigators) and small equipment must be evacuated. Among them, the level of warning can be used to describe the degree of danger of geological disasters. The higher the warning level, the greater the risk of geological disasters. The warning level of the stress yellow warning is lower than the warning level of the stress orange warning, and the warning level of the stress orange warning is lower than the stress red warning. This application can effectively improve the accuracy of geological disaster warnings by determining the stress warning level.
[0058] Among them, the stress test performs data acquisition operations through the stress prediction model, wherein the stress prediction model can be obtained through the following steps: determining the real-time characteristic data of stress at the monitoring site; inputting the real-time characteristic data of stress into the initial stress neural network model for training iteration to obtain the stress prediction model.
[0059] Specifically, first, real-time stress data from the site is collected, the time series data is cut into time windows of fixed length, logarithmic transformation is applied to reduce the skew or non-constant variance in the data, and the most relevant features are selected based on business understanding or feature importance. The time series data is standardized to an acceptable range, and the dataset is divided into training set, validation set, and test set to evaluate the performance and generalization ability of the model.
[0060] Secondly, define the Transformer model (that is, the initial stress neural network model in this application), use linear transformation to map the original time series data to the vector space that the model can process, convert the original data into a representation of a specific dimension that the model can process, and construct a Transformer encoder, including a self-attention mechanism, a feedforward neural network, residual connections, and layer normalization. Finally, map the output of the Transformer encoder to the final prediction dimension through a linear layer.
[0061] Then, the real-time stress feature data is divided into a training set and a test set according to the time series, and converted into a PyTorch tensor format acceptable to the model. The mean square error loss and an Adam optimizer are selected to train the model. The training data is input into the Transformer model to obtain the prediction result. The prediction result is compared with the actual target, the loss value is calculated, the gradient is calculated according to the loss value, and the iterative model parameters are updated. Future time series data can also be used for prediction. The new time series data is converted into a format accepted by the model, and the trained Transformer model is used for prediction, and the prediction results are obtained. According to the prediction results and evaluation indicators, the model is automatically adjusted and optimized, such as adjusting hyperparameters, increasing the amount of training data, or improving the model architecture, etc., to obtain the final stress prediction model. The stress prediction model can realize the accurate acquisition of stress test data, effectively improving the accuracy of geological disaster risk assessment.
[0062] S104, when it is detected that at least one of the target warning levels is higher than the preset warning level, a geological disaster warning instruction is triggered, and warning information corresponding to the target warning level is sent to the terminal device.
[0063] Among them, the target warning level is divided into a microseismic warning level and a stress warning level. If at least one of the target warning levels is detected to be higher than the preset warning level, it may be that the microseismic warning level is a microseismic yellow warning and the stress warning level is a stress orange warning, or it may be that the microseismic warning level is a microseismic yellow warning and the stress warning level is a stress red warning, or it may be that the microseismic warning level is a microseismic orange warning and the stress warning level is a stress yellow warning, or it may be that the microseismic warning level is a microseismic orange warning and the stress warning level is a stress yellow warning, etc. Among them, the preset warning level may be a warning level with a yellow warning mark, for example, the preset warning level may be the tangent angle yellow warning in this application, or it may be the rate yellow warning, the stress yellow warning, the tangent angle yellow warning, etc., which is not limited here.
[0064] In some embodiments, before triggering a geological disaster warning instruction and sending the warning information corresponding to the target warning level to the terminal device, the present application also needs to verify the warning information through the following operations. When it is detected that at least one of the target warning levels is higher than the preset warning level, the geological data of the target area where the geological changes are located is obtained based on the sensor; if the data of the target warning level is verified to be true based on the geological data, the geological disaster warning instruction is triggered.
[0065] For example, if abnormal data is detected or early warning indicators are reached, such as an abnormal increase in slope displacement rate or anchor cable stress exceeding the safety threshold, the system will immediately start an internal and external joint verification program, which compares the data of adjacent sensors in the same area to confirm whether there is a real risk, thereby eliminating false alarms caused by occasional data fluctuations or equipment failures. After confirming the accuracy of the early warning information, the system automatically triggers relevant alarm measures according to the preset emergency response process and immediately issues an early warning alarm. The early warning alarm notifies relevant personnel and departments through mobile phone text messages, emails, alarm sounds, etc., so that timely measures can be taken to strengthen the support and stability of the slope to reduce the risk of landslides and ensure the safety of mine production.
[0066] Figure 2 A schematic diagram of a geological disaster early warning method according to an exemplary embodiment of the present application is shown. Figure 2 As shown, the displacement prediction data is divided into two dimensions: displacement tangent angle and displacement rate. Then, based on these two dimensions, corresponding warning level information is obtained, for example, yellow warning, orange warning, red warning, etc., to detect whether any factor reaches above the yellow warning. If so, microseismic monitoring and stress testing are started to obtain corresponding warning test results, that is, the target warning level in this application. If any factor reaches above the yellow warning, the warning information corresponding to the target warning level will be pushed via text message or email.
[0067] The geological disaster early warning method provided in the embodiment of the present application determines the displacement data of geological changes through a displacement prediction model; determines the initial early warning level of geological changes based on the displacement data; when it is detected that at least one of the initial warning levels is higher than the preset warning level, determines the target early warning level of geological changes under microseismic monitoring and stress testing respectively; when it is detected that at least one of the target warning levels is higher than the preset warning level, triggers the geological disaster early warning instruction, and sends the early warning information corresponding to the target warning level to the terminal device. The present application realizes accurate early warning of geological disasters by determining the primary warning level and the target warning level, solves the problem of low early warning efficiency of geological disasters in related technologies, and thus achieves the effect of improving the early warning efficiency of geological disasters.
[0068] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0069] The embodiment of the present application also provides an early warning device for geological disasters. It should be noted that the early warning device for geological disasters in the embodiment of the present application can be used to execute the early warning method for geological disasters provided in the embodiment of the present application. The early warning device for geological disasters provided in the embodiment of the present application is introduced below.
[0070] Figure 3 FIG. 3 is a schematic diagram of a geological disaster early warning device 300 according to an embodiment of the present application. Figure 3 As shown, the device 300 includes: In order to achieve the above purpose, according to the second aspect of the present application, a geological disaster early warning device is provided. The device 300 includes: a first determination unit 301, a second determination unit 302, a third determination unit 303, and a sending unit 304.
[0071] Specifically, the first determining unit 301 is used to determine the displacement data of the geological change through the displacement prediction model; A second determination unit 302 is used to determine the initial warning level of geological changes according to the displacement data; The third determination unit 303 is used to determine the target warning level of geological changes under microseismic monitoring and stress testing respectively when it is detected that at least one of the initial warning levels is higher than the preset warning level; The sending unit 304 is used to trigger a geological disaster warning instruction when it is detected that at least one of the target warning levels is higher than a preset warning level, and send warning information corresponding to the target warning level to the terminal device.
[0072] In summary, the early warning device for geological disasters provided in the embodiment of the present application determines the displacement data of geological changes through the displacement prediction model by the first determination unit 301; the second determination unit 302 determines the initial early warning level of geological changes according to the displacement data; the third determination unit 303 determines the target early warning level of geological changes under microseismic monitoring and stress testing respectively when at least one of the initial early warning levels is detected to be higher than the preset early warning level; the sending unit 304 triggers the geological disaster early warning instruction when at least one of the target early warning levels is detected to be higher than the preset early warning level, and sends the early warning information corresponding to the target early warning level to the terminal device. The present application achieves accurate early warning of geological disasters by determining the primary early warning level and the target early warning level, and solves the problem of low early warning efficiency of geological disasters in related technologies. Thus, the effect of improving the early warning efficiency of geological disasters is achieved.
[0073] In some embodiments, the first determination unit includes: a first monitoring module for monitoring geological characteristic data associated with geological changes; an output module for inputting the geological characteristic data into a displacement prediction model and outputting displacement data of geological changes.
[0074] In some embodiments, the initial warning level includes: a rate warning level, a second determination unit, including: a calculation module, used to calculate the displacement rate of geological changes within a preset time period based on the displacement data; a first determination module, used to determine the rate warning level corresponding to the displacement rate, wherein the rate warning level includes one of the following: rate yellow warning, rate orange warning, rate red warning, wherein the warning levels of rate orange warning and rate red warning are higher than the preset warning level.
[0075] In some embodiments, the initial warning level includes: a tangent angle warning level, a second determination unit, including: a first calculation module, used to calculate the displacement change time corresponding to the displacement data when the displacement rate is constant; a second calculation module, used to calculate the ratio between the displacement change time and the preset time period, and determine the displacement tangent angle of the geological change; a second determination module, used to determine the tangent angle warning level corresponding to the displacement tangent angle, wherein the tangent angle warning level includes one of the following: tangent angle yellow warning, tangent angle orange warning, tangent angle red warning, wherein the warning levels of the tangent angle orange warning and the tangent angle red warning are higher than the preset warning level.
[0076] In some embodiments, the target warning level includes: the microseismic warning level, the third determination unit includes: a third determination module, which is used to obtain warning index data based on microseismic monitoring, wherein the warning index data includes: magnitude, energy, apparent volume, apparent stress, target factor, wherein the target factor is used to describe the relationship between magnitude and frequency; a fourth determination module, which is used to determine the microseismic warning level of geological changes based on the warning index data, wherein the microseismic warning level includes one of the following: microseismic yellow warning, microseismic orange warning, microseismic red warning, wherein the warning levels of the microseismic orange warning and the microseismic red warning are higher than the preset warning level.
[0077] In some embodiments, the target warning level includes: a stress warning level, a third determination unit, including: a second monitoring module, used to monitor the slowly varying increment value of the sliding force of geological changes based on stress testing; a fifth determination module, used to determine the stress warning level of geological changes based on the slowly varying increment of the sliding force, wherein the stress warning level includes one of the following: a yellow stress warning, an orange stress warning, and a red stress warning, wherein the warning levels of the orange stress warning and the red stress warning are higher than the preset warning level.
[0078] In some embodiments, the device also includes: an acquisition unit, which is used to trigger a geological disaster warning instruction, and before sending the warning information corresponding to the target warning level to the terminal device, when it is detected that at least one of the target warning levels is higher than the preset warning level, obtain the geological data of the target area where the geological changes are located based on the sensor; if the data of the target warning level is verified to be true based on the geological data, the geological disaster warning instruction is triggered.
[0079] In some embodiments, the device also includes: a collection unit, used to collect real-time displacement data of the monitoring site, wherein the real-time displacement data includes: displacement data and displacement speed data; a first processing unit, used to normalize the real-time displacement data to obtain processed data; and a training unit, used to train the initial displacement prediction model according to the processed data and historical displacement data to obtain a displacement prediction model.
[0080] In some embodiments, the training unit includes: an extraction module for extracting feature data of processed data and historical displacement data respectively; a first acquisition module for collecting data with periodic characteristics in the feature data; and a second acquisition module for collecting data with time series characteristics in the feature data, and optimizing the initial displacement prediction model based on the data with periodic characteristics and the data with time series characteristics to obtain a displacement prediction model.
[0081] In some embodiments, microseismic monitoring performs data acquisition operations through a microseismic prediction model, wherein the device also includes: a fourth determination unit, used to determine the microseismic characteristic data of the monitoring site; a second processing unit, used to process the weights of the microseismic characteristic data by setting target parameters to obtain target microseismic characteristic data; and a first iteration unit, used to input the target microseismic characteristic data into the initial microseismic neural network model for training iteration to obtain the microseismic prediction model.
[0082] In some embodiments, the stress test performs data acquisition operations through a stress prediction model, wherein the device also includes: a fifth determination unit, used to determine the real-time characteristic data of stress at the monitoring site; a second iteration unit, which inputs the real-time characteristic data of stress into the initial stress neural network model for training iteration to obtain a stress prediction model.
[0083] The geological disaster warning device includes a processor and a memory. The first determination unit 301, the second determination unit 302, the third determination unit 303, the sending unit 304, etc. are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
[0084] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set to provide early warning of geological disasters by adjusting kernel parameters.
[0085] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.
[0086] In the exemplary embodiment of the present application, a computer storage medium capable of implementing the above method is also provided. A program product capable of implementing the above method of the present specification is stored thereon. In some possible embodiments, various aspects of the present application can also be implemented in the form of a program product, which includes a program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present application described in the above "Exemplary Method" section of this specification, such as, the following steps can be performed: determine the displacement data of geological changes through a displacement prediction model; determine the initial warning level of geological changes according to the displacement data; when it is detected that at least one of the initial warning levels is higher than the preset warning level, respectively determine the target warning level of geological changes under microseismic monitoring and stress testing; when it is detected that at least one of the target warning levels is higher than the preset warning level, trigger a geological disaster warning instruction, and send the warning information corresponding to the target warning level to the terminal device.
[0087] In some embodiments: geological characteristic data associated with geological changes are monitored; the geological characteristic data are input into a displacement prediction model, and displacement data of the geological changes are output.
[0088] In some embodiments: rate warning level, determining the initial warning level of geological changes based on displacement data, including: calculating the displacement rate of geological changes within a preset time period based on the displacement data; determining the rate warning level corresponding to the displacement rate, wherein the rate warning level includes one of the following: rate yellow warning, rate orange warning, rate red warning, wherein the warning levels of rate orange warning and rate red warning are higher than the preset warning level.
[0089] In some embodiments: the tangent angle warning level, determining the initial warning level of geological changes based on the displacement data, including: calculating the displacement change time corresponding to the displacement data when the displacement rate is constant; calculating the ratio between the displacement change time and the preset time period to determine the displacement tangent angle of the geological change; determining the tangent angle warning level corresponding to the displacement tangent angle, wherein the tangent angle warning level includes one of the following: tangent angle yellow warning, tangent angle orange warning, tangent angle red warning, wherein the warning levels of the tangent angle orange warning and the tangent angle red warning are higher than the preset warning level.
[0090] In some embodiments: microseismic warning level, when it is detected that at least one of the initial warning levels is higher than the preset warning level, the target warning level of geological changes under microseismic monitoring and stress testing is determined respectively, including: obtaining warning indicator data based on microseismic monitoring, wherein the warning indicator data include: magnitude, energy, apparent volume, apparent stress, target factor, wherein the target factor is used to describe the relationship between magnitude and frequency; determining the microseismic warning level of geological changes according to the warning indicator data, wherein the microseismic warning level includes one of the following: microseismic yellow warning, microseismic orange warning, microseismic red warning, wherein the warning level of microseismic orange warning and microseismic red warning is higher than the preset warning level.
[0091] In some embodiments: stress warning level, when it is detected that at least one of the initial warning levels is higher than the preset warning level, the target warning level of geological changes under microseismic monitoring and stress testing is determined respectively, including: the slowly varying increment value of the sliding force based on the stress test to monitor the geological changes; the stress warning level of the geological changes is determined based on the slowly varying increment of the sliding force, wherein the stress warning level includes one of the following: yellow stress warning, orange stress warning, and red stress warning, wherein the warning levels of the orange stress warning and the red stress warning are higher than the preset warning level.
[0092] In some embodiments: when it is detected that at least one of the target warning levels is higher than the preset warning level, geological data of the target area where the geological changes are located is acquired based on the sensor; if the data of the target warning level is verified to be true based on the geological data, a geological disaster warning instruction is triggered.
[0093] In some embodiments: real-time displacement data of the monitoring site is collected, wherein the real-time displacement data includes displacement amount data and displacement speed data; the real-time displacement data is normalized to obtain processed data; an initial displacement prediction model is trained based on the processed data and historical displacement data to obtain a displacement prediction model.
[0094] In some embodiments: feature data of processed data and historical displacement data are extracted respectively; data with periodic features in the feature data are collected; and data with time series features in the feature data are collected, and the initial displacement prediction model is optimized based on the data with periodic features and the data with time series features to obtain a displacement prediction model.
[0095] In some embodiments: determining the microseismic characteristic data of the monitoring site; processing the weights of the microseismic characteristic data by setting target parameters to obtain target microseismic characteristic data; inputting the target microseismic characteristic data into the initial microseismic neural network model for training iteration to obtain a microseismic prediction model.
[0096] In some embodiments: determining the real-time characteristic data of stress at the monitoring site; inputting the real-time characteristic data of stress into the initial stress neural network model for training iteration to obtain a stress prediction model.
[0097] In some embodiments, the embodiments of the present application may also include a program product for implementing the above method, which may be a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.
[0098] The program product may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.
[0099] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0100] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.
[0101] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).
[0102] In addition, in an exemplary embodiment of the present application, an electronic device capable of implementing the above method is also provided.
[0103] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.
[0104] Refer to the following Figure 4 The electronic device 400 according to this embodiment of the present application is described. Figure 4 The electronic device 400 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0105] like Figure 4 As shown, the electronic device 400 is in the form of a general computing device. The components of the electronic device 400 may include but are not limited to: at least one processing unit 410, at least one storage unit 420, a bus 430 connecting different system components (including the storage unit 420 and the processing unit 410), and a display unit 440.
[0106] The storage unit stores program codes, which can be executed by the processing unit 410, so that the processing unit 410 executes the steps described in the above "Exemplary Method" section of this specification according to various exemplary embodiments of the present application. For example, the processing unit 410 can execute the following steps: determine the displacement data of geological changes through the displacement prediction model; determine the initial warning level of geological changes according to the displacement data; when it is detected that at least one of the initial warning levels is higher than the preset warning level, determine the target warning level of geological changes under microseismic monitoring and stress testing respectively; when it is detected that at least one of the target warning levels is higher than the preset warning level, trigger the geological disaster warning instruction, and send the warning information corresponding to the target warning level to the terminal device.
[0107] In some embodiments: geological characteristic data associated with geological changes are monitored; the geological characteristic data are input into a displacement prediction model, and displacement data of the geological changes are output.
[0108] In some embodiments: rate warning level, determining the initial warning level of geological changes based on displacement data, including: calculating the displacement rate of geological changes within a preset time period based on the displacement data; determining the rate warning level corresponding to the displacement rate, wherein the rate warning level includes one of the following: rate yellow warning, rate orange warning, rate red warning, wherein the warning levels of rate orange warning and rate red warning are higher than the preset warning level.
[0109] In some embodiments: the tangent angle warning level, determining the initial warning level of geological changes based on the displacement data, including: calculating the displacement change time corresponding to the displacement data when the displacement rate is constant; calculating the ratio between the displacement change time and the preset time period to determine the displacement tangent angle of the geological change; determining the tangent angle warning level corresponding to the displacement tangent angle, wherein the tangent angle warning level includes one of the following: tangent angle yellow warning, tangent angle orange warning, tangent angle red warning, wherein the warning levels of the tangent angle orange warning and the tangent angle red warning are higher than the preset warning level.
[0110] In some embodiments: microseismic warning level, when it is detected that at least one of the initial warning levels is higher than the preset warning level, the target warning level of geological changes under microseismic monitoring and stress testing is determined respectively, including: obtaining warning indicator data based on microseismic monitoring, wherein the warning indicator data include: magnitude, energy, apparent volume, apparent stress, target factor, wherein the target factor is used to describe the relationship between magnitude and frequency; determining the microseismic warning level of geological changes according to the warning indicator data, wherein the microseismic warning level includes one of the following: microseismic yellow warning, microseismic orange warning, microseismic red warning, wherein the warning level of microseismic orange warning and microseismic red warning is higher than the preset warning level.
[0111] In some embodiments: stress warning level, when it is detected that at least one of the initial warning levels is higher than the preset warning level, the target warning level of geological changes under microseismic monitoring and stress testing is determined respectively, including: the slowly varying increment value of the sliding force based on the stress test to monitor the geological changes; the stress warning level of the geological changes is determined based on the slowly varying increment of the sliding force, wherein the stress warning level includes one of the following: yellow stress warning, orange stress warning, and red stress warning, wherein the warning levels of the orange stress warning and the red stress warning are higher than the preset warning level.
[0112] In some embodiments: when it is detected that at least one of the target warning levels is higher than the preset warning level, geological data of the target area where the geological changes are located is acquired based on the sensor; if the data of the target warning level is verified to be true based on the geological data, a geological disaster warning instruction is triggered.
[0113] In some embodiments: real-time displacement data of the monitoring site is collected, wherein the real-time displacement data includes displacement amount data and displacement speed data; the real-time displacement data is normalized to obtain processed data; an initial displacement prediction model is trained based on the processed data and historical displacement data to obtain a displacement prediction model.
[0114] In some embodiments: feature data of processed data and historical displacement data are extracted respectively; data with periodic features in the feature data are collected; and data with time series features in the feature data are collected, and the initial displacement prediction model is optimized based on the data with periodic features and the data with time series features to obtain a displacement prediction model.
[0115] In some embodiments: determining the microseismic characteristic data of the monitoring site; processing the weights of the microseismic characteristic data by setting target parameters to obtain target microseismic characteristic data; inputting the target microseismic characteristic data into the initial microseismic neural network model for training iteration to obtain a microseismic prediction model.
[0116] In some embodiments: determining the real-time characteristic data of stress at the monitoring site; inputting the real-time characteristic data of stress into the initial stress neural network model for training iteration to obtain a stress prediction model.
[0117] The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 4201 and / or a cache storage unit 4202 , and may further include a read-only storage unit (ROM) 4203 .
[0118] The storage unit 420 may also include a program / utility 4204 having a set (at least one) of program modules 4205, such program modules 4205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.
[0119] Bus 430 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
[0120] The electronic device 400 may also communicate with one or more external devices 500 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 400, and / or may communicate with any device that enables the electronic device 400 to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication may be performed through an input / output (I / O) interface 450. In addition, the electronic device 400 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 460. As shown, the network adapter 460 communicates with other modules of the electronic device 400 through a bus 430. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.
[0121] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation method of the present application.
[0122] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.
[0123] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application. The specification and embodiments are to be regarded as exemplary only, and the true scope and spirit of the present application are indicated by the claims.
Claims
1. A geological disaster early warning method, characterized in that: include: Determine the displacement data of geological changes through displacement prediction models; Determining an initial warning level of the geological change according to the displacement data; When it is detected that at least one of the initial warning levels is higher than the preset warning level, respectively determining the target warning level of the geological change under microseismic monitoring and stress testing; When it is detected that at least one of the target warning levels is higher than the preset warning level, a geological disaster warning instruction is triggered, and warning information corresponding to the target warning level is sent to the terminal device.
2. The early warning method for geological disasters according to claim 1, characterized in that: The displacement data of geological changes are determined by the displacement prediction model, including: Monitoring geological characteristic data associated with said geological changes; The geological characteristic data is input into the displacement prediction model, and the displacement data of the geological changes is output.
3. The early warning method for geological disasters according to claim 1, characterized in that: The initial warning level includes: a rate warning level, and the initial warning level of the geological change is determined according to the displacement data, including: Calculating the displacement rate of the geological change within a preset time period according to the displacement data; Determine the rate warning level corresponding to the displacement rate, wherein the rate warning level includes one of the following: yellow rate warning, orange rate warning, and red rate warning, wherein the warning levels of the orange rate warning and the red rate warning are higher than the preset warning level. Preferably, the initial warning level includes: a tangent angle warning level, and determining the initial warning level of the geological change according to the displacement data includes: When the displacement rate is constant, calculating the displacement change time corresponding to the displacement data; Calculate the ratio between the displacement change time and the preset time period to determine the displacement tangent angle of the geological change; Determine the tangent angle warning level corresponding to the displacement tangent angle, wherein the tangent angle warning level includes one of the following: tangent angle yellow warning, tangent angle orange warning, tangent angle red warning, wherein the warning level of the tangent angle orange warning and the tangent angle red warning is higher than the preset warning level.
4. The early warning method for geological disasters according to claim 1, characterized in that: The target warning level includes: a microseismic warning level. When it is detected that at least one of the initial warning levels is higher than the preset warning level, the target warning level of the geological change under microseismic monitoring and stress testing is determined respectively, including: Based on the microseismic monitoring, early warning indicator data is obtained, wherein the early warning indicator data includes: magnitude, energy, apparent volume, apparent stress, and target factor, wherein the target factor is used to describe the relationship between magnitude and frequency; The microseismic warning level of the geological changes is determined according to the warning indicator data, wherein the microseismic warning level includes one of the following: microseismic yellow warning, microseismic orange warning, and microseismic red warning, wherein the warning levels of the microseismic orange warning and the microseismic red warning are higher than the preset warning level.
5. The early warning method for geological disasters according to claim 1, characterized in that: The target warning level includes a stress warning level. When it is detected that at least one of the initial warning levels is higher than the preset warning level, the target warning level of the geological change under microseismic monitoring and stress testing is determined respectively, including: Monitoring the slowly varying increment of the sliding force of the geological changes based on the stress test; The stress warning level of the geological change is determined based on the slowly varying increment of the sliding force, wherein the stress warning level includes one of the following: yellow stress warning, orange stress warning, and red stress warning, wherein the warning levels of the orange stress warning and the red stress warning are higher than the preset warning level.
6. The geological disaster early warning method according to claim 1, characterized in that: Before triggering the geological disaster warning instruction and sending the warning information corresponding to the target warning level to the terminal device, the method further includes: When it is detected that at least one of the target warning levels is higher than the preset warning level, obtaining geological data of the target area where the geological change is located based on a sensor; If the data of the target warning level is verified to be true based on the geological data, a geological disaster warning instruction is triggered.
7. The geological disaster early warning method according to claim 1, characterized in that: The displacement prediction model can be obtained by the following steps: Collecting real-time displacement data of the monitoring site, wherein the real-time displacement data includes: displacement amount data and displacement speed data; Performing normalization processing on the real-time displacement data to obtain processed data; The initial displacement prediction model is trained according to the processed data and the historical displacement data to obtain the displacement prediction model. Preferably, the initial displacement prediction model is trained according to the processed data and the historical displacement data to obtain the displacement prediction model, including: respectively extracting characteristic data of the processed data and the historical displacement data; Collecting data with periodic characteristics from the characteristic data; and, The data with time series characteristics in the characteristic data are collected, and the initial displacement prediction model is optimized based on the data with periodic characteristics and the data with time series characteristics to obtain the displacement prediction model. Preferably, the microseismic monitoring performs data acquisition operation through a microseismic prediction model, wherein the microseismic prediction model can be obtained through the following steps: Determining microseismic characteristic data of the monitoring site; The weight of the microseismic characteristic data is processed by setting target parameters to obtain target microseismic characteristic data; The target microseismic characteristic data is input into the initial microseismic neural network model for training iteration to obtain the microseismic prediction model. Preferably, the stress test performs data acquisition operation through a stress prediction model, wherein the stress prediction model can be obtained through the following steps: Determining real-time stress characteristic data of the monitoring site; The stress prediction model is obtained by inputting the stress real-time characteristic data into the initial stress neural network model for training iteration.
8. A geological disaster early warning device, characterized in that: include: A first determining unit, used to determine displacement data of geological changes through a displacement prediction model; A second determining unit, configured to determine an initial warning level of the geological change according to the displacement data; A third determination unit is used to determine the target warning level of the geological change under microseismic monitoring and stress testing respectively when it is detected that at least one of the initial warning levels is higher than the preset warning level; The sending unit is used to trigger a geological disaster warning instruction when it is detected that at least one of the target warning levels is higher than the preset warning level, and send the warning information corresponding to the target warning level to the terminal device.
9. A computer-readable storage medium, characterized in that: The storage medium includes a stored program, wherein the program executes the geological disaster early warning method described in any one of claims 1 to 7.
10. An electronic device, characterized in that: include: One or more processors, a memory, a display device and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include a method for executing the geological disaster early warning method described in any one of claims 1 to 7.
