Spatiotemporal intelligent prediction method and system for full-space grouting in sandy and gravel strata

Abstract

The present invention relates to the field of grouting prediction technology, and in particular to a spatiotemporal intelligent prediction method and system for full-space grouting in sand and gravel formations, wherein the method comprises: obtaining the predicted geological conditions of each borehole; determining whether the current borehole is an un-grouted area based on the predicted geological conditions of each borehole; injecting slurry into the grouting holes in the un-grouted area, and after the grouting operation is completed, obtaining the predicted geological conditions of each borehole; judging whether the current borehole is a grouted area or an un-grouted area based on the obtained predicted geological conditions of each borehole; if it is an un-grouted area, using the dynamic update and prediction model of the un-grouted area to predict the predicted demand index of the un-grouted area; if it is a grouted area, inputting the predicted geological conditions of the current borehole into the fitting prediction model of the grouted area until the preset requirements are met, and then stopping the grouting. This improves the timeliness and accuracy of the prediction and provides real-time guidance for grouting construction.

Description

Technical Field

[0001] The present invention relates to the technical field of grouting prediction, and in particular to a method and system for intelligent spatiotemporal prediction of full-space grouting in sand and gravel strata. Background Art

[0002] As a special type of heterogeneous stratum, gravel and sand formations, with their unique pore structure and permeability characteristics, place higher technical demands on grouting projects. The spatial distribution of porosity and permeability in gravel and sand formations is significantly non-uniform, making it difficult to accurately predict the diffusion pattern of grouting slurry in the formation. This leads to significant uncertainty in flow control and diffusion range regulation during grouting construction. Furthermore, gravel and sand formations are often accompanied by water-rich characteristics and complex hydrogeological conditions, further increasing the difficulty of interpreting the coupling between slurry and groundwater. How to effectively predict the diffusion behavior of slurry during grouting and its effect on formation permeability has become a technical challenge that the engineering community urgently needs to solve.

[0003] Traditional grouting diffusion prediction methods rely primarily on empirical formulas and numerical simulation techniques. However, empirical formulas often overlook the impact of formation heterogeneity on grouting diffusion, making them difficult to adapt to complex sand and gravel formations. Numerical simulation methods, on the other hand, are limited by modeling and computational efficiency and require extensive simplification of formation physical parameters, resulting in low prediction accuracy. Furthermore, existing grouting monitoring systems rely primarily on discrete point data (such as borehole test data) for a posteriori prediction of diffusion range, lacking the ability to fully and real-timely predict the grouting process, making it difficult to meet the timeliness requirements of actual engineering projects.

[0004] In recent years, with the development of deep learning technology, data-driven approaches have been increasingly applied to solving complex engineering problems. In grouting projects, deep learning models can capture the nonlinear patterns of slurry diffusion through multi-source data fusion training, providing technical support for intelligent prediction of the grouting process. However, in predicting grouting in sandstone and gravel formations, the key challenge remains how to combine pre- and post-grouting drilling data with dynamic change data generated during the grouting process to construct a full-space-time prediction model. Summary of the Invention

[0005] In order to solve the deficiencies of the prior art, the present invention provides a spatiotemporal intelligent prediction method and system for full-space grouting in sand and gravel formations;

[0006] On the one hand, a spatiotemporal intelligent prediction method for full-space grouting in sandy and gravel formations is provided, including:

[0007] (1): Obtain the predicted geological conditions of each borehole; determine whether the current borehole is an un-grouted area based on the predicted geological conditions of each borehole;

[0008] (2): Inject grout into the grouting holes in the ungrouted area. After the grouting operation is completed, obtain the predicted geological conditions of each borehole again;

[0009] (3): Based on the predicted geological conditions of each borehole, determine whether the current borehole is a grouted area or an ungrouted area. If it is an ungrouted area, the dynamic update and prediction model of the ungrouted area is used to predict the prediction demand index of the ungrouted area. If the index is greater than the set threshold, return to (2); if it is a grouted area, the predicted geological conditions of the current borehole are input into the fitting prediction model of the grouting area to obtain the result of whether the grouting conditions of the current borehole meet the preset requirements; if it does not meet the preset requirements, return to (2); if it has met the preset requirements, stop grouting.

[0010] On the other hand, a spatiotemporal intelligent prediction system for full-space grouting in sand and gravel formations is provided, including:

[0011] An acquisition module is configured to: acquire predicted geological conditions of each borehole; and determine whether the current borehole is an un-grouted area based on the predicted geological conditions of each borehole;

[0012] A grouting module configured to: inject grout into the grouting holes in the ungrouted area, and after the grouting operation is completed, obtain the predicted geological conditions of each borehole again;

[0013] The prediction module is configured to: determine whether the current borehole is a grouted area or an ungrouted area based on the predicted geological conditions of each borehole; if it is an ungrouted area, use the dynamic update and prediction model of the ungrouted area to predict the predicted demand index of the ungrouted area; if the index is greater than the set threshold, return to the grouting module; if it is a grouted area, input the predicted geological conditions of the current borehole into the fitting prediction model of the grouting area to obtain the result of whether the grouting conditions of the current borehole meet the preset requirements; if it does not meet the preset requirements, return to the grouting module; if it has met the preset requirements, stop grouting.

[0014] The above technical solution has the following advantages or beneficial effects:

[0015] (1) This technical solution achieves dynamic prediction and real-time updating of drilling data by constructing a spatiotemporal graph convolutional network. By using drilling location and attribute information as nodes and combining them with time series data for modeling, it can accurately capture the dynamic changes in the grouting process. This method significantly improves the timeliness and accuracy of predictions, avoids the prediction bias caused by data lag in traditional static models, and provides real-time guidance for grouting construction.

[0016] (2) Multiple loss functions are introduced, including prediction error loss, physical consistency loss, regularization loss, and robustness loss, to ensure that the prediction results are not only highly accurate but also conform to geophysical laws. For example, the physical consistency loss is used to constrain the physical meaning of the prediction results in terms of properties such as porosity and fracture density, thus avoiding the occurrence of outliers or unreasonable results and providing reliable guarantees for practical engineering applications.

[0017] (3) By establishing a nonlinear mapping relationship between multiple attributes such as crack density, porosity, and elastic modulus and the grouting demand index, the grouting demand index of the ungrouted area is accurately assessed, and the grouting strategy is dynamically adjusted. By prioritizing and optimizing the allocation of high-demand areas, the efficiency of grouting construction is significantly improved, while the waste of slurry materials is reduced, achieving optimal resource allocation.

[0018] (4) Combining deep learning with online learning mechanisms, the system can update model parameters in real time during the construction process and dynamically adjust the prediction results, forming an intelligent grouting prediction and optimization system. Combined with real-time spatiotemporal visualization functions, the system can intuitively display the attribute distribution and demand index of the grouting area, providing clear guidance to construction personnel, thereby achieving precise construction, intelligent control, and scientific decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0020] Figure 1 This is a flow chart of the method of embodiment 1.

[0021] Figure 2 Schematic diagram of the internal structure of the spatiotemporal graph convolutional network of Example 1.

[0022] Figure 3 Schematic diagram of the tunnel face, fracture, borehole and aquifer in Example 1. DETAILED DESCRIPTION

[0023] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0024] Example 1, as Figure 1 As shown, this embodiment provides a spatiotemporal intelligent prediction method for full-space grouting in sand and gravel formations, including:

[0025] S101: Obtaining predicted geological conditions for each borehole; determining whether the current borehole is an un-grouted area based on the predicted geological conditions for each borehole;

[0026] S102: injecting grout into the grouting holes in the ungrouted area. After the grouting operation is completed, the predicted geological conditions of each borehole are obtained again;

[0027] S103: Based on the predicted geological conditions of each borehole obtained in S102, determine whether the current borehole is a grouted area or an ungrouted area. If it is an ungrouted area, the dynamic update and prediction model of the ungrouted area is used to predict the predicted demand index of the ungrouted area. If the index is greater than the set threshold, return to S102; if it is a grouted area, the predicted geological conditions of the current borehole are input into the fitting prediction model of the grouted area to obtain the result of whether the grouting conditions of the current borehole meet the preset requirements; if it does not meet the preset requirements, return to S102; if it has met the preset requirements, stop grouting.

[0028] Furthermore, obtaining the predicted geological conditions of each borehole includes: drilling a tunnel face to be grouted, the number of boreholes being n, obtaining geophysical information corresponding to each borehole, and inputting the geophysical information corresponding to each borehole into the trained spatiotemporal graph convolutional network in sequence according to the drilling time sequence to obtain the predicted geological conditions of each borehole;

[0029] The method of obtaining the predicted geological conditions of each borehole again includes: performing drilling operations on n boreholes in sequence to obtain geophysical information corresponding to each borehole, and inputting the geophysical information corresponding to each borehole into the trained spatiotemporal graph convolutional network in sequence according to the drilling time sequence to obtain the predicted geological conditions of each borehole.

[0030] Furthermore, in step S101, a drilling operation is performed on the tunnel face to be grouted, with the number of holes being n, and geophysical information corresponding to each hole being acquired. The geophysical information is collected using a sensor in front of the drill bit. The geophysical information includes fracture density, porosity, permeability, etc.

[0031] Furthermore, the geophysical information corresponding to each borehole is sequentially input into the trained spatiotemporal graph convolutional network in the order of drilling time to obtain the predicted geological conditions of each borehole. The training process of the trained spatiotemporal graph convolutional network includes:

[0032] Constructing a training set, wherein the training set is geophysical information corresponding to each borehole whose geological conditions are known;

[0033] The training set is input into the spatiotemporal graph convolutional network, and the spatiotemporal graph convolutional network is trained. When the loss function value of the spatiotemporal graph convolutional network no longer decreases, or the number of iterations exceeds the set number, the training is stopped to obtain the trained spatiotemporal graph convolutional network.

[0034] Furthermore, the loss function L of the spatiotemporal graph convolutional network is total , its formula expression is:

[0035] L total =α1·L prediction +α2·L consistency +α3·L regularization +α4·L robustness ;

[0036] Among them, α1, α2, α3, and α4 are hyperparameters used to balance the weights of the losses in each part.

[0037] Among them, L prediction The formula expression is:

[0038]

[0039] Among them, L prediction Represents the prediction error loss, which is used to measure the prediction value and the true value y i Error, dynamic weight ω i , used to increase attention to high deviation samples, β represents a dynamic adjustment parameter, used to control the impact of outliers, Represents the mean of the data set; the purpose of using prediction error loss is to dynamically adjust the focus on different samples and enhance the prediction ability of high deviation areas.

[0040] Furthermore, the L consistency The formula expression is:

[0041]

[0042] Among them, L consistency represents the physical consistency loss function, L consistency Used to constrain the prediction results to conform to geophysical laws; R min Represents R injection The physical lower limit, R max Represents R injection The physical upper limit of R injection,i Represents the predicted grouting demand index; the purpose of using the physical consistency loss function is to prevent the predicted value from being too large or too small and ensure that the physical meaning is reasonable.

[0043] Furthermore, the L regularization The formula expression is:

[0044]

[0045] Among them, λ1 represents the size of the control weight to prevent overfitting; λ2 represents the balance of the control weight to encourage uniform distribution. The purpose of using the weight regularization loss function is to avoid overfitting and unbalanced distribution caused by excessive weights.

[0046] Among them, L robustness The specific expression is:

[0047]

[0048] Among them, δ represents the outlier threshold, which controls the degree of penalty for excessive errors, and L robustness Represents the robustness loss function, which is used to enhance the robustness of the model to outliers. φ(z) represents the kernel function of the loss function, which is used to process the error between the model prediction value and the true value. z represents the difference (error) between the prediction value and the true value, and N represents the total number of data samples.

[0049] Further, if Figure 2 As shown, the trained spatiotemporal graph convolutional network includes:

[0050] Spatial feature input layer, adjacency matrix input layer and temporal feature input layer;

[0051] The output of the spatial feature input layer and the output of the adjacency matrix input layer are both connected to the input of the graph convolution layer, the output of the graph convolution layer is connected to the input of the multi-layer graph convolution module, and the output of the multi-layer graph convolution module is connected to the input of the fusion layer;

[0052] The output of the temporal feature input layer and the output of the adjacency matrix input layer are both connected to the input of the temporal convolution layer, the output of the temporal convolution layer is connected to the input of the temporal recursive layer, and the output of the temporal recursive layer is connected to the input of the fusion layer;

[0053] The input end of the fusion layer is also connected to the output end of the attention mechanism layer; the output end of the fusion layer is respectively connected to the input end of the dynamic update module and the input end of the grouting demand index prediction layer, and the dynamic update module and the grouting demand index prediction layer are interconnected; the output end of the dynamic update module is also connected to the grouting demand index prediction layer through the attribute prediction layer.

[0054] Furthermore, the spatial feature input layer is used to input the static geological attribute feature matrix of each node in the space-time graph, with a shape of N×F s , where N is the number of nodes, F sIt is the attribute dimension of each node (such as crack density, porosity, etc.). A space-time diagram is a node connection diagram with both time and space dimensions. The time dimension refers to the different information collected by each node at different times. The space dimension refers to the different coordinates of each node in the tunnel. Each node corresponds to a borehole or geological observation point.

[0055] A static geological attribute matrix is ​​a quantitative information matrix describing the geological characteristics of a borehole or observation point (i.e., a node) at a specific point in time or before grouting. These characteristics are typically fundamental geological attributes that are relatively stable over time and do not change significantly with grouting operations. The static geological attribute matrix is ​​one of the inputs to the spatiotemporal model and is used to describe the basic geological conditions at the node.

[0056] The static geological attribute characteristic matrix is ​​expressed as follows:

[0057]

[0058] Where N is the number of nodes (number of holes), F s Represents the attribute dimension of each node, that is, the number of types of static geological attributes. i,j Represents the j-th geological attribute value of node i.

[0059] Furthermore, the time feature input layer is used to input the time series dynamic features of each node, with a shape of N×T×F t , where T is the number of time steps and F t It is the temporal characteristic dimension (such as the temporal variation of crack density).

[0060] Time series dynamic characteristics refer to the changes in the geological properties of a borehole or node (such as fracture density, porosity, permeability, water content, etc.) over time. They reflect the dynamic evolution of the grouting process or geological conditions over time.

[0061] Furthermore, the adjacency matrix input layer is used to input an adjacency matrix describing the spatial relationship between nodes, which has an N×N shape and whose weights reflect the spatial connection strength between nodes.

[0062] The adjacency matrix is ​​a mathematical representation used to describe the connectivity between nodes in a graph. It reflects the associations between boreholes (or nodes) in geological space, such as distance, attribute similarity, or connectivity. The adjacency matrix is ​​a crucial component of spatiotemporal graph convolutional networks, guiding the computation of graph convolutions.

[0063] The adjacency matrix is ​​expressed as follows:

[0064]

[0065] Where N is the number of nodes (number of holes), a ij Represents the connection strength or relationship weight between node i and node j.

[0066] Assume that the spatial coordinates of each node i and j are x i and x j , the connection strength a can be calculated based on the distance ij :

[0067]

[0068] Among them, ||x i -x j || represents the Euclidean distance between nodes i and j, and σ represents the distance scale parameter, which is used to control the decay rate of the connection strength.

[0069] Furthermore, the graph convolution layer (GCL) uses graph convolution to extract the spatial features of nodes. The formula is:

[0070]

[0071] Among them, H (l+1) is the node feature matrix of all nodes in the graph at the l+1 layer, D is the degree matrix, D ii =∑ j A ij , W (l) is the weight matrix of the lth layer; σ is the ReLU activation function, A is the adjacency matrix of the graph, and A represents the spatial relationship between the drilling nodes. In the spatiotemporal graph convolutional network, the drilling holes are regarded as nodes of the graph, and the adjacent relationship between the drilling holes is represented by edges.

[0072] Node and Edge Updates: The re-drilled borehole locations are added to the space-time graph as new nodes, connected to adjacent boreholes. The newly added time nodes reflect newly revealed grouting information, allowing the entire space-time graph to dynamically expand. Attribute Updates: Grouting attribute information for the new nodes is propagated throughout the space-time graph using spatial interpolation and temporal recursive updates, updating the status of both grouted and ungrouted areas.

[0073] Furthermore, the multi-layer graph convolution module, which includes several sequentially connected graph convolution layers, captures higher-order node correlation features by stacking multiple layers of GCL. The output of each layer serves as the input of the next layer. The multi-layer graph convolution module outputs the spatial feature matrix obtained after L layers of graph convolution operations.

[0074] Furthermore, the Temporal Convolution Layer (TCN) uses temporal convolution or LSTM to extract features in the time dimension to capture temporal variation features. To extract the dynamic variation features of time series data, a one-dimensional convolution operation is used:

[0075]

[0076] Among them, j represents the convolution kernel position index in the time series, is the output feature after temporal convolution; θ j are the parameters of the convolution kernel; Represents the input data at time rj, k is the convolution kernel width, and b is the bias. The output of the temporal convolution layer is the temporal feature matrix The shape of the time feature matrix is ​​N×F (L) ; Where N represents the number of nodes (number of holes), F (L) Represents the feature dimension of the last layer.

[0077] Furthermore, the Gate Recurrent Unit (GRU) captures long-term dependencies in the time dimension, processes time series features through the recurrent neural network GRU, and outputs the updated time feature matrix

[0078] If the LSTM network is used, its core formula is:

[0079] f t =σ(W f ·[h t-1 ,x t ]+b f );i t =σ(W i ·[h t-1 ,x t ]+b i );

[0080]

[0081] o t =σ(W o ·[h t-1 ,x t ]+b o );h t =o t *tanh(C t );

[0082] Among them, f t ,i t ,o tare forget, input and output gates respectively, C t is the unit state, h t Hidden

[0083] Furthermore, the fusion layer transforms the spatial feature matrix and time feature matrix Perform feature fusion to generate a comprehensive spatiotemporal feature representation F:

[0084] F=concat(H spatial ,H temporal );

[0085] Furthermore, the attention mechanism layer assigns weights to different features and optimizes the feature fusion effect through the attention mechanism:

[0086]

[0087] Among them, α i represents the attention weight, e i It represents the score obtained by weighting the features with the attention weight matrix, e j represents the score of all features used for normalization, W attention It represents the weight matrix learned during training and is used to optimize the score calculation process. i The representation is a feature of the input that combines spatial and temporal information.

[0088] Furthermore, the dynamic update module includes: an adjacency matrix update unit, a node feature update unit and an online learning mechanism unit; the adjacency matrix update unit includes:

[0089] When new drilling data is added, the adjacency matrix A is dynamically adjusted:

[0090] A new =A old +ΔA;

[0091] Among them, A new represents the updated adjacency matrix, including the newly added drilling node and its spatial relationship with other nodes, A old represents the adjacency matrix before the update, describing the spatial relationship between existing drilling nodes, and ΔA represents the adjacency matrix before the update, describing the spatial relationship between existing drilling nodes.

[0092] The node feature updating unit includes: interpolating or dynamically updating the features of the newly added nodes:

[0093] H new =H old +ΔH;

[0094] Among them, H newRepresents the updated node feature matrix, including the features of the newly added nodes and the adjustment results of the existing node features, H old It represents the node feature matrix before the update, including the geological attribute characteristics of the existing drilling nodes. ΔH represents the incremental or updated information of the newly added node features.

[0095] The online learning mechanism unit includes: dynamically adjusting model parameters and optimizing weights through incremental training:

[0096]

[0097] Among them, θ t+1 represents the updated model parameters, including the weights and bias parameters of the graph convolution layer, temporal convolution layer, or fully connected layer, θ t Represents the model parameters before the update, which is the parameter set used by the model at the current moment. η represents the learning rate, which controls the step size of the model parameter update and is usually a small positive value. t Represents the predicted value of the model at the current time t, that is, the attribute prediction result of the newly added drilling node, Y true Indicates the true attribute value of the newly added drilling node, which is used to calculate the prediction error. It represents the gradient of the loss function L with respect to the model parameter θ, reflecting the influence of the current parameter on the error.

[0098] Furthermore, the grouting demand index prediction layer includes: calculating the grouting demand index based on the predicted attribute value:

[0099]

[0100] Among them, R injection (x) represents the grouting demand index, which reflects the comprehensive evaluation value of the grouting demand in the current drilling area, w i represents the weight of the i-th attribute in the grouting demand, f i (y i ) represents the i-th attribute value y i The nonlinear mapping function of n represents the total number of attributes, which usually includes multiple geological attributes such as fracture density, porosity, permeability, and elastic modulus.

[0101] Furthermore, the attribute prediction layer predicts the attributes of the drilling nodes in the future through the fully connected layer (MLP):

[0102] Y t+1 =MLP(F);

[0103] Among them, Y t+1 It represents the predicted value of the borehole node attribute at the future time t+1, including fracture density, porosity, etc. F represents the comprehensive feature representation, which integrates the information of spatial features and temporal features.

[0104] Furthermore, the method of determining whether the current borehole is an un-grouted area based on the predicted geological conditions of each borehole includes: using sensor monitoring or re-drilling to reveal data to detect whether there are traces of slurry in the current borehole. If there are traces of slurry, it indicates that the current borehole is a grouted area; if there are no traces of slurry, it indicates that the current borehole is an un-grouted area.

[0105] Furthermore, S102: injecting slurry into grouting holes in the ungrouted area, wherein grouting holes differ from boreholes in that grouting holes are holes specifically used to inject slurry to improve formation properties or control permeability. Grouting holes are typically designed and optimized to ensure that the slurry can be evenly distributed in the target area to achieve the desired reinforcement or water plugging effect. A borehole is a hole excavated in the formation using drilling technology, used to survey geological information, reveal formation characteristics, or provide conditions for subsequent construction (such as grouting, testing, etc.).

[0106] Furthermore, S103: based on the predicted geological conditions of each borehole obtained in S102, determine whether the current borehole is a grouted area or an ungrouted area. If there is slurry in the borehole, it means that the current borehole is a grouted area; if there is no slurry in the borehole, it means that the current borehole is an ungrouted area.

[0107] Furthermore, in step S103: if the area is not grouted, the predicted demand index of the area is predicted using the dynamic update and prediction model of the area not grouted. If the index is greater than a set threshold, the process returns to step S102. The dynamic update and prediction model of the area not grouted refers to:

[0108] Getting the predicted attribute value Finally, the grouting demand index is calculated by combining the nonlinear weighting function;

[0109]

[0110] Among them, R injection (x) represents the grouting demand index, f i (·) is a nonlinear mapping function, such as an exponential or logarithmic function, which reflects the influence of various geological attributes on grouting requirements; w i is the weight of each attribute, obtained through training or expert experience.

[0111] in, A nonlinear mapping that represents crack properties; the width and density of cracks are usually positively correlated with grouting requirements. The more developed the cracks, the greater the grouting requirements. Therefore, a piecewise nonlinear mapping can be selected:

[0112]

[0113] Among them, k1, k2 are coefficients, and T1 is the threshold of crack attributes.

[0114]

[0115] in, Representing the nonlinear mapping of water content, the effect of water content on grouting demand may be nonlinearly increasing or decreasing, depending on whether the water richness of the formation hinders or promotes the diffusion of slurry.

[0116]

[0117] in, Represents the nonlinear mapping of porosity. The effect of porosity on grouting demand is usually positively correlated, but the effect may tend to saturate at high porosity. The nonlinear mapping of porosity adopts the form of a saturation function.

[0118]

[0119] in, It represents the nonlinear mapping of elastic modulus. The elastic modulus is negatively correlated with the grouting demand. The greater the rigidity, the lower the grouting demand. The nonlinear mapping of elastic modulus adopts a logarithmic decreasing function.

[0120] Furthermore, in step S103, if the area is already grouted, the predicted geological conditions of the current borehole are input into the fitting prediction model of the grouted area to obtain a result of whether the grouting conditions of the current borehole meet the preset requirements; if not, the process returns to step S102; if it meets the preset requirements, the grouting is stopped; wherein the fitting prediction model of the grouted area refers to:

[0121] Use radial basis function (RBF) or kriging interpolation to fit the grouting distribution to obtain the spatial variation of the properties of the area. For the prediction of the grouting distribution at point x, the interpolation formula is as follows:

[0122]

[0123] Among them, α i is the weight coefficient, obtained by the fitting process; φ(||xx i ||) is the radial basis function, usually a Gaussian kernel or a polynomial kernel function is selected; x i represents the known borehole location. f(x) represents the slurry distribution fitting function.

[0124] Gradient fitting optimization: In the grouting area, the refined interpolation of the control area is performed through gradient fitting, using the following gradient formula:

[0125]

[0126] in, represents the gradient of the radial basis function, represents the gradient of the fitting function f(x), α i Represents the weight coefficient.

[0127] The gradient information is used to optimize the distribution of interpolation and improve the fitting accuracy of data in the grouting area.

[0128] Based on engineering design requirements, define reference values ​​for grouting effectiveness, such as target permeability reduction, slurry coverage radius, and crack density reduction. Set physically meaningful threshold ranges for each reference indicator, such as: permeability reduction must be greater than or equal to a target value; slurry coverage must be greater than or equal to a certain distance; and crack density reduction must be greater than or equal to a certain percentage. Figure 3 Schematic diagram of the tunnel face, fracture, borehole and aquifer in Example 1.

[0129] The newly added boreholes are regarded as the time of the spatiotemporal sequence, and the attribute information is regarded as the information to be predicted. The dynamic spatiotemporal graph update and attribute information prediction are realized through the deep learning model.

[0130] 1. Spatiotemporal data construction and initial model generation: Initial borehole data integration: Use existing borehole data to obtain attribute information (such as fracture density, porosity, permeability, etc.), build an initial 3D spatiotemporal grid model, standardize this data and map it into a unified 3D coordinate system.

[0131] Creation of spatiotemporal series: The attribute value of each borehole data is used as a data point in the time series, and arranged in sequence according to the exposure time or construction time of the borehole to form a spatiotemporal series.

[0132] 2. Deep learning modeling of space-time graphs. The space-time graph is defined as follows: borehole information and spatial locations are used as nodes, and the relative spatial distances between boreholes are used as edges to construct a dynamic space-time graph. The attribute information of each node (such as fracture density and permeability) is used as the feature to be predicted.

[0133] Deep learning model selection: Combine spatiotemporal graph neural networks (such as ST-GCN, ASTGCN) or spatiotemporal convolutional neural networks (such as T-GCN) to model spatiotemporal graphs. This model updates and predicts attribute information based on node features and temporal relationships.

[0134] 3. Data preprocessing and feature engineering, including data standardization: All newly added borehole data is standardized to ensure consistent dimensions across data collected at different time points, enabling the model to effectively identify features across different time series. Fusion of temporal and spatial features: Temporal features (such as changes in fracture density and water seepage rate at different time points) and spatial features (such as spatial relationships between boreholes and differences in adjacent attributes) are extracted and fed into the model for feature extraction.

[0135] 4. Model training and prediction, dynamic updates, and online training: When new borehole data is added, the spatiotemporal graph is updated in real time, using the new data points as new time nodes. The model is trained using online learning, enabling the model to continuously learn from new data and improve prediction accuracy.

[0136] Predicting attribute information: The model predicts the spatiotemporal sequence of newly added borehole nodes, outputting attribute values ​​for each node at future moments, such as fracture density, porosity, and permeability, to construct dynamic prediction results. Data increment and model iteration: Through incremental training, new borehole data and real-time monitoring information are introduced, and model parameters are updated to enable prediction of spatiotemporal changes.

[0137] 5. Prediction-based intelligent grouting demand assessment, nonlinear mapping of attribute information and grouting demand: By constructing a nonlinear relationship function between attribute information (such as fracture density and porosity) and grouting demand, the model-predicted attribute information is converted into a grouting demand index. Dynamic adjustment of demand based on spatiotemporal prediction: As drilling data and real-time monitoring are updated, the grouting demand threshold is dynamically adjusted to identify emerging high-demand areas.

[0138] 6. Dynamic visualization and model verification, spatiotemporal visualization: Real-time display of predicted spatiotemporal attribute maps, showing attribute changes at each location and the regional distribution of grouting requirements, supporting decision-making during the construction process.

[0139] Model validation and physical consistency checks: Validate the model's predictions using historical data and borehole monitoring data to ensure the physical consistency of the predictions (e.g., the relationship between permeability and porosity, and the relationship between fracture density and grouting requirements).

[0140] 7. After grouting, dynamic updates and real-time guidance based on re-drilling information, dynamic updates of grouting areas: In the post-grouting stage, based on the slurry distribution revealed by the new drill holes, the attribute information of the grouting area (such as the reduction of fracture density, porosity change, etc.) is updated, and this new data is added to the spatiotemporal map.

[0141] Fitting prediction update: Through radial basis function interpolation or Kriging interpolation, the attribute distribution of the grouting area is fitted and predicted to capture the geological changes after grouting and adjust the characteristic values ​​of each node.

[0142] Time series update of re-drilling nodes: The new borehole data generated by re-drilling are regarded as new time nodes in the space-time graph. These data are continuously added to the space-time graph to dynamically reflect the changes in the grouting area and the un-grouting area.

[0143] Adjustment of demand forecast for ungrouted areas: Real-time forecast update of demand in ungrouted areas. Through time series convolution and spatiotemporal graph prediction methods, the demand index of ungrouted areas is adjusted using new data, and areas that require priority grouting are dynamically divided.

[0144] Consistency and Visualization: Verify the physical consistency of the model (such as the porosity and permeability relationship) and display the demand index of grouted and ungrouted areas in real time in a space-time diagram to help project decision makers clearly understand the current demand.

[0145] A spatiotemporal prediction model is constructed using a graph convolutional neural network (GCN) and a time series neural network (such as LSTM and GRU). The spatio-temporal graph convolutional network (ST-GCN) structure is used to integrate node (drilling data) information of the spatiotemporal graph with time series features.

[0146] Spatial Convolution Layer: This layer extracts the spatial features of each borehole node through graph convolution, processing the geological attributes between boreholes (such as fracture density and porosity) and the correlation between adjacent boreholes. Temporal Convolution Layer: This layer performs time series convolution or LSTM processing on the changes in the node in the time dimension, extracting temporal features and modeling the evolution of node characteristics over time. Fusion Layer: This layer fuses the features of spatial convolution and temporal convolution to generate a comprehensive spatiotemporal feature representation.

[0147] Spatial feature input: The geological attributes of each borehole node (such as fracture density, porosity, permeability, elastic modulus), which can be expressed as a feature vector X = [x1, x2, ..., x n ].

[0148] Time feature input: The attribute changes observed in each borehole in the time series are expressed as a time series matrix T = [t1, t2, ..., t m ], the attributes of each time point include the geological characteristics of the drilling area and dynamically updated information. Model output:

[0149] Prediction time t n+1 Attribute information of each drill hole These predicted values ​​are the attribute information of each drilling node at future moments, such as fracture density, porosity, permeability, etc.

[0150] The final output grouting demand index R injection (x), a comprehensive grouting demand index is generated based on the predicted attribute information of each node.

[0151] As new drilling data is added, the model is dynamically adjusted during training through online learning or recursive iterative updates. If recursive updates are used, the following formula can be used:

[0152]

[0153] Among them, θ represents the model parameters; is the predicted value and the true value Y t The loss function between them; η is the learning rate, which controls the update step size.

[0154] Dynamic update of spatiotemporal data and time series construction after grouting, initial modeling: In the pre-grouting stage, a three-dimensional spatial model is established based on the existing drilling data, and information such as cracks, porosity, and permeability are standardized to construct a basic attribute distribution model.

[0155] Post-grouting area update: After grouting, the attribute data of the grouting area (such as porosity and permeability changes) is updated according to the revealed grouting slurry information, and marked as a "grouted" node in the space-time diagram.

[0156] Re-drilling and time series updating: Re-drilling is treated as a new node in the time series, and an incremental time series is constructed. The grouting data added to the new node is integrated with the updated spatiotemporal graph of the time series to achieve dynamic adjustment of grouting and non-grouting areas.

[0157] Post-grouting node and edge updates: The re-drilled borehole location is added to the spatiotemporal graph as a new node, connected to the adjacent boreholes. The newly added time nodes reflect the newly revealed grouting information, allowing the entire spatiotemporal graph to dynamically expand.

[0158] Post-grouting attribute update: The grouting attribute information of the new node is propagated in the space-time graph through spatial interpolation and temporal recursive update methods to achieve status updates of grouting and ungrouting areas.

[0159] Each time a new node is added, the state of the graph node is dynamically updated using the following formula:

[0160]

[0161] Among them: H (l) is the feature matrix of all nodes in the graph at layer l; A is the adjacency matrix of the graph, which represents the spatial neighborhood relationship; W (l) is the weight matrix of the lth layer, which updates the feature information of the graph; σ is the activation function, which is used to introduce nonlinear transformation.

[0162] After grouting, the demand forecast of the un-grouted area is made: the un-grouted area is predicted based on the grouting information on the time-space diagram. The grouting demand of each area (such as crack density and porosity change) is used as the weight to comprehensively calculate its grouting demand index R injection (x).

[0163]

[0164] Time series prediction of new re-drilling nodes: Using time series neural networks such as LSTM, input the current time series data T = [t1, t2, ..., t n ], predict the next time node The property value of and the demand forecast of the un-grouting area are updated in real time. The update formula is as follows:

[0165] h t+1 =σ(W·[h t ,x t ]+b)

[0166] Dynamic Optimization and Consistency Verification: Physical consistency check: To ensure the rationality of the prediction of the grouting area, the consistency of physical properties such as porosity and permeability is verified. The consistency relationship between properties is evaluated using the following formula:

[0167] k fracture =k0·φ m ;

[0168] Where: k fracture is the permeability of the crack, k0 is the benchmark permeability, φ is the porosity, m is the empirical index, and the dynamic optimization criterion is: the rate of change of each attribute Gradient descent optimization was performed to ensure a smooth transition between grouting and ungrouting areas.

[0169] Spatiotemporal visualization: Displays the fitted prediction of grouting areas and the demand index of ungrouted areas in real time, marks grouting areas that require attention, and supports real-time decision-making during construction.

[0170] Engineering applications of dynamic prediction: A real-time, updated spatiotemporal map guides future drilling layout and grouting operations. Based on the temporal changes in re-drilling node data, risk assessment and construction optimization are performed for ungrouted areas. This method enables continuous tracking and prediction of grouted and ungrouted areas, guiding project layout and grouting decisions based on real-time data during the grouting process.

[0171] Example 2

[0172] This embodiment provides a spatiotemporal intelligent prediction system for full-space grouting in sand and gravel formations, including:

[0173] An acquisition module is configured to: acquire predicted geological conditions of each borehole; and determine whether the current borehole is an un-grouted area based on the predicted geological conditions of each borehole;

[0174] A grouting module configured to: inject grout into the grouting holes in the ungrouted area, and after the grouting operation is completed, obtain the predicted geological conditions of each borehole again;

[0175] The prediction module is configured to: determine whether the current borehole is a grouted area or an ungrouted area based on the predicted geological conditions of each borehole; if it is an ungrouted area, use the dynamic update and prediction model of the ungrouted area to predict the predicted demand index of the ungrouted area; if the index is greater than the set threshold, return to the grouting module; if it is a grouted area, input the predicted geological conditions of the current borehole into the fitting prediction model of the grouting area to obtain the result of whether the grouting conditions of the current borehole meet the preset requirements; if it does not meet the preset requirements, return to the grouting module; if it has met the preset requirements, stop grouting.

[0176] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A spatiotemporal intelligent prediction method for full-space grouting in sand and gravel formations, characterized by: include: (1): Obtain the predicted geological conditions of each borehole; determine whether the current borehole is an ungrouted area based on the predicted geological conditions of each borehole; (2): Inject grout into the grouting holes in the ungrouted area. After the grouting operation is completed, obtain the predicted geological conditions of each borehole again; (3): Based on the predicted geological conditions of each borehole, determine whether the current borehole is a grouting area or an un-grouting area. If it is an un-grouting area, the dynamic update and prediction model of the un-grouting area is used to predict the prediction demand index of the un-grouting area. If the index is greater than the set threshold, return to (2); if it is a grouting area, the predicted geological conditions of the current borehole are input into the fitting prediction model of the grouting area to obtain the result of whether the grouting conditions of the current borehole meet the preset requirements; If the preset requirements are not met, return to (2); if the preset requirements are met, stop grouting; The dynamic update and prediction model of the un-grouting area refers to: Getting the predicted attribute value Finally, the grouting demand index is calculated by combining the nonlinear weighting function; ； in, represents the grouting demand index, is a nonlinear mapping function, is the weight of each attribute; in, Nonlinear mapping representing fracture properties; ； in, is the coefficient, is the threshold of the crack attribute; ； in, Nonlinear mapping of water content; ； in, A nonlinear map representing porosity; ； in, A nonlinear map representing the elastic modulus.

2. The spatiotemporal intelligent prediction method for full-space grouting in sand and gravel strata according to claim 1, characterized in that: Obtaining the predicted geological conditions of each borehole includes: drilling a tunnel face to be grouted, the number of drill holes being m, obtaining geophysical information corresponding to each borehole, and inputting the geophysical information corresponding to each borehole into a trained spatiotemporal graph convolutional network in sequence according to the drilling time sequence to obtain the predicted geological conditions of each borehole; The method of obtaining the predicted geological conditions of each borehole again includes: drilling m boreholes in sequence to obtain geophysical information corresponding to each borehole, and inputting the geophysical information corresponding to each borehole into the trained spatiotemporal graph convolutional network in sequence according to the drilling time sequence to obtain the predicted geological conditions of each borehole.

3. The spatiotemporal intelligent prediction method for full-space grouting in sand and gravel formations according to claim 2, characterized in that: The geophysical information corresponding to each borehole is sequentially input into the trained spatiotemporal graph convolutional network in the order of drilling time to obtain the predicted geological conditions of each borehole. The training process of the trained spatiotemporal graph convolutional network includes: Constructing a training set, wherein the training set is geophysical information corresponding to each borehole whose geological conditions are known; The training set is input into the spatiotemporal graph convolutional network, and the spatiotemporal graph convolutional network is trained. When the loss function value of the spatiotemporal graph convolutional network no longer decreases, or when the number of iterations exceeds the set number, the training is stopped to obtain the trained spatiotemporal graph convolutional network; The loss function of the spatiotemporal graph convolutional network , its formula expression is: ； in, It is a hyperparameter used to balance the weight of each part of the loss; in, The formula expression is: ； ； in, Represents the prediction error loss, which is used to measure the prediction value and the true value The error, represents the dynamic weight, Represents a dynamic adjustment parameter, represents the mean of the data set; described The formula expression is: ； in, represents the physical consistency loss function, Used to constrain the prediction results to conform to geophysical laws; express The physical lower limit of express The physical upper limit of represents the predicted grouting demand index; described The formula expression is: ； in, Indicates the size of the control weight to prevent overfitting; Indicates the balance of control weights; in, The specific expression is: ； ； in, Indicates the outlier threshold, which controls the degree of penalty for excessive errors. Represents the robustness loss function, which is used to enhance the robustness of the model to outliers; The kernel function representing the loss function is used to process the error between the model prediction value and the true value. It represents the difference between the predicted value and the true value. Indicates the total number of data samples.

4. The spatiotemporal intelligent prediction method for full-space grouting in sand and gravel formations according to claim 2, characterized in that: The trained spatiotemporal graph convolutional network includes: Spatial feature input layer, adjacency matrix input layer and temporal feature input layer; The output of the spatial feature input layer and the output of the adjacency matrix input layer are both connected to the input of the graph convolution layer, the output of the graph convolution layer is connected to the input of the multi-layer graph convolution module, and the output of the multi-layer graph convolution module is connected to the input of the fusion layer; The output of the temporal feature input layer and the output of the adjacency matrix input layer are both connected to the input of the temporal convolution layer, the output of the temporal convolution layer is connected to the input of the temporal recursive layer, and the output of the temporal recursive layer is connected to the input of the fusion layer; The input of the fusion layer is also connected to the output of the attention mechanism layer; the output of the fusion layer is respectively connected to the input of the dynamic update module and the input of the grouting demand index prediction layer, and the dynamic update module and the grouting demand index prediction layer are interconnected; the output of the dynamic update module is also connected to the grouting demand index prediction layer through the attribute prediction layer; The spatial feature input layer is used to input the static geological attribute feature matrix of each node in the space-time graph, and the shape is ,in is the number of nodes, is the attribute dimension of each node; The time feature input layer is used to input the time series dynamic features of each node, and its shape is ,in, is the number of time steps, It is the time characteristic dimension; The adjacency matrix input layer is used to input the adjacency matrix describing the spatial relationship between nodes, and the shape is , whose weight reflects the spatial connection strength between nodes.

5. The spatiotemporal intelligent prediction method for full-space grouting in sand and gravel formations according to claim 4 is characterized in that: Convolutional layer uses graph convolution to extract the spatial features of nodes. The formula is: ； in, For all nodes in the graph Layer node feature matrix, is the degree matrix, , It is The weight matrix of the layer; is the ReLU activation function, is the adjacency matrix of the graph, Represents the spatial relationship of drilling nodes; The temporal convolution layer uses temporal convolution or LSTM to extract features in the time dimension to capture temporal change features; it extracts the dynamic change features of time series data using a one-dimensional convolution operation: ； in, Represents the convolution kernel position index in the time series, It is the output feature after temporal convolution; are the parameters of the convolution kernel; Indicates time Input data at time, is the convolution kernel width, is the bias; the output of the temporal convolution layer is the temporal feature matrix , the shape of the time feature matrix is ;in, Indicates the number of nodes, Represents the feature dimension of the last layer.

6. The spatiotemporal intelligent prediction method for full-space grouting in sand and gravel formations according to claim 4, characterized in that: Fusion layer, the spatial feature matrix and time feature matrix Perform feature fusion to generate comprehensive spatiotemporal feature representation : ； The attention mechanism layer assigns weights to different features and optimizes the feature fusion effect through the attention mechanism: ； in, represents the attention weight, It represents the score obtained by weighting the features with the attention weight matrix. represents the scores of all features used for normalization, Represents the weight matrix learned during training, which is used to optimize the score calculation process. The representation is the feature of the input, fusing spatial and temporal information.

7. The spatiotemporal intelligent prediction method for full-space grouting in sand and gravel formations according to claim 4, characterized in that: The dynamic update module includes: an adjacency matrix update unit, a node feature update unit and an online learning mechanism unit; the adjacency matrix update unit includes: When new drilling data is added, the adjacency matrix is ​​dynamically adjusted ； in, represents the updated adjacency matrix, including the newly added drilling node and its spatial relationship with other nodes, Represents the adjacency matrix before the update, describing the spatial relationship between existing drilling nodes, represents the adjacency matrix before the update, describing the spatial relationship between existing drilling nodes; The node feature updating unit includes: interpolating or dynamically updating the features of the newly added nodes: ； in, Represents the updated node feature matrix, which includes the features of the newly added nodes and the adjusted results of the existing node features. Represents the node feature matrix before update, including the geological attribute characteristics of the existing drilling nodes, Indicates the incremental or updated information of newly added node features; The online learning mechanism unit includes: dynamically adjusting model parameters and optimizing weights through incremental training: ； in, Represents the updated model parameters, including the weights and bias parameters of the graph convolution layer, temporal convolution layer, or fully connected layer, Represents the model parameters before the update, which is the parameter set used by the model at the current moment. represents the learning rate, Represents the predicted value of the model at the current moment 𝑡, and the attribute prediction result of the newly added drilling node, Indicates the true attribute value of the newly added drilling node, which is used to calculate the prediction error. Represents the gradient of the loss function 𝐿 to the model parameter 𝜃, reflecting the influence of the current parameter on the error; The grouting demand index prediction layer includes: calculating the grouting demand index based on the predicted attribute values: ； in, Indicates the grouting demand index, which reflects the comprehensive evaluation value of the grouting demand in the current drilling area. represents the weight of the 𝑖th attribute in the grouting demand, represents the 𝑖th attribute value 𝑦 𝑖 The nonlinear mapping function, Indicates the total number of attributes; The attribute prediction layer predicts the attributes of drilling nodes in the future through the fully connected layer: ； in, represents the predicted value of the borehole node attributes at the future time 𝑡+1, including fracture density and porosity, Represents comprehensive feature representation.

8. The spatiotemporal intelligent prediction method for full-space grouting in sand and gravel formations according to claim 1, characterized in that: The fitting prediction model of the grouting area refers to: Use radial basis function or Kriging interpolation method to fit the grouting slurry distribution to obtain the spatial variation of the regional properties; The interpolation formula for grouting distribution prediction is as follows: ； in, is the weight coefficient, obtained by the fitting process; For radial basis function, choose Gaussian kernel or polynomial kernel function; Indicates known drill hole locations; represents the slurry distribution fitting function; Gradient fitting optimization: In the grouting area, the refined interpolation of the control area is performed through gradient fitting, using the following gradient formula: ； in, represents the gradient of the radial basis function, represents the gradient of the fitting function 𝑓(𝑥), Represents the weight coefficient.

9. The spatiotemporal intelligent prediction system for full-space grouting in sand and gravel formations is characterized by: include: An acquisition module is configured to: acquire predicted geological conditions of each borehole; and determine whether the current borehole is an un-grouted area based on the predicted geological conditions of each borehole; A grouting module configured to: inject grout into the grouting holes in the ungrouted area, and after the grouting operation is completed, obtain the predicted geological conditions of each borehole again; The prediction module is configured to: determine whether the current borehole is a grouted area or an ungrouted area based on the predicted geological conditions of each borehole; if it is an ungrouted area, use the dynamic update and prediction model of the ungrouted area to predict the predicted demand index of the ungrouted area; if the index is greater than a set threshold, return to the grouting module; if it is a grouted area, input the predicted geological conditions of the current borehole into the fitting prediction model of the grouting area to obtain a result of whether the grouting conditions of the current borehole meet the preset requirements; if not, return to the grouting module; if it has met the preset requirements, stop grouting; The dynamic update and prediction model of the un-grouting area refers to: Getting the predicted attribute value Finally, the grouting demand index is calculated by combining the nonlinear weighting function; ； in, represents the grouting demand index, is a nonlinear mapping function, is the weight of each attribute; in, Nonlinear mapping representing fracture properties; ； in, is the coefficient, is the threshold of the crack attribute; ； in, Nonlinear mapping of water content; ； in, A nonlinear map representing porosity; ； in, A nonlinear map representing the elastic modulus.

Images