Guide wall space-time vibration trend prediction method

Abstract

The invention discloses a guide wall space-time vibration trend prediction method in the technical field of time sequence prediction, and the method comprises the steps: inputting data, of which the correlation with a guide wall transverse river direction vibration response characteristic exceeds a threshold value, into a CNN-BiLSTM-CBAM model, and obtaining a guide wall transverse river direction vibration mode component prediction value; the guide wall transverse river direction vibration mode component prediction values are added, a guide wall transverse river direction prediction vibration signal is obtained, input characteristics of the CNN-BiLSTM-CBAM model are data whose correlation with guide wall transverse river direction vibration response characteristics exceeds a threshold value, and output characteristics of the CNN-BiLSTM-CBAM model are multiple mode components obtained through decomposition of guide wall transverse river direction vibration response data. According to the method, the space-time vibration response data of the guide wall is decomposed into a plurality of modal components, the complexity of the vibration data of the guide wall is reduced, the transverse river direction prediction vibration signal of the guide wall is obtained based on the space-time vibration data and the transverse river direction vibration modal components of the guide wall, and the problem that the prediction precision of the space-time vibration trend of the vibration of the guide wall is inaccurate is solved.

Description

Technical Field

[0001] The invention relates to a guide wall spatiotemporal vibration trend prediction method, belonging to the technical field of time series prediction. Background Art

[0002] The discharge structure is an important part of the water conservancy hub project, and it bears the key responsibility of discharging excess water and ensuring the safety of key hydraulic structures such as dams. As an important component of the discharge structure, the guide wall is used to separate the downstream water flow from the outflow of the power station behind the dam, so as to reduce the impact of the jet flow and tailwater fluctuations on the power station during the high-speed discharge process. However, the light and thin-walled guide wall structure is subjected to the instantaneous alternating water flow load. When the amplitude exceeds the allowable value specified for the guide wall structure, the continuous and strong vibration is very likely to cause fatigue damage to the structure, thus posing a huge threat to the project and the safety of people's lives and property. Therefore, accurately predicting the vibration response of the guide wall is crucial to evaluating the safety of the guide wall and effectively controlling vibration.

[0003] There are a series of defects in the existing vibration prediction methods in the hydraulic field. For example, the guide wall vibration prediction method based on the finite element method has many artificial assumptions, high computational cost and low efficiency; most of the hydraulic structure vibration research methods based on machine learning do not consider the spatiotemporal coupling characteristics and evolution trends between different parts; the existing intelligent prediction models for hydraulic structure vibration often show complex structures, poor interpretability and the inability to fully capture the complex nonlinear relationships inherent in the vibration sequence characteristics, so that the prediction accuracy of the spatiotemporal vibration trend of the guide wall vibration is inaccurate.

[0004] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgement or any form of suggestion that the information constitutes the prior art already known to ordinary technicians in this field. Summary of the invention

[0005] The technical problem to be solved by the present invention is: how to solve the problem of inaccurate prediction accuracy of the temporal and spatial vibration trend of guide wall vibration.

[0006] In order to solve the above technical problems, the present invention is implemented by adopting the following technical solutions.

[0007] The present invention discloses a method for predicting the temporal and spatial vibration trend of a guide wall, comprising: Collect spatiotemporal vibration data of the guide wall and the area adjacent to the guide wall during flood discharge; Obtain the transverse vibration response characteristics of the guide wall in the spatiotemporal vibration data; Determine the spatiotemporal vibration data whose correlation with the transverse river vibration response characteristics of the guide wall exceeds a set threshold, and sequentially input the determined spatiotemporal vibration data into the pre-trained CNN-BiLSTM-CBAM model; Using the convolutional neural network (CNN) of the CNN-BiLSTM-CBAM model, the input spatiotemporal vibration data is convolved and pooled to obtain spatiotemporal features; Using the convolutional block attention module CBAM of the CNN-BiLSTM-CBAM model, focusing on the channel and spatial dimensions of the spatiotemporal features to obtain data features, reassembling and fitting the data features to obtain a first prediction value; Using the bidirectional long short-term memory BiLSTM network of the CNN-BiLSTM-CBAM model, the output result having a bidirectional long-term dependency relationship with the input spatiotemporal vibration data is captured to obtain a second prediction value; Using the splicing layer of the CNN-BiLSTM-CBAM model to splice the first prediction value and the second prediction value, a plurality of prediction values ​​of the transverse river vibration modal components of the guide wall are obtained; Adding the plurality of predicted values ​​of the transverse-river vibration modal components of the guide wall to obtain a predicted transverse-river vibration signal of the guide wall; The temporal and spatial vibration trend of the guide wall is predicted based on the predicted vibration signal of the guide wall in the transverse direction.

[0008] Furthermore, it also includes converting the corresponding spatiotemporal vibration data into continuous sub-time series data based on a sliding window iterative prediction mode before sequentially inputting the corresponding spatiotemporal vibration data into a pre-trained CNN-BiLSTM-CBAM model for prediction.

[0009] Furthermore, the collection of spatiotemporal vibration data of the guide wall and the area adjacent to the guide wall during flood discharge includes: The vertical, downstream and cross-river acceleration time history curves of eight different locations of the guide wall and the area adjacent to the guide wall were collected respectively; According to the vertical, downstream and cross-river acceleration time history curves of eight different parts of the guide wall and the area adjacent to the guide wall, the spatiotemporal vibration data are obtained; Among them, the eight different parts of the guide wall and the adjacent area of ​​the guide wall include: the right guide wall, the left guide wall, the right side of the grouting corridor, the left side of the grouting corridor, the junction of the right guide wall corridor and the ground, the right guide wall corridor extending to a depth of 100 meters, the junction of the left guide wall corridor and the ground, and the left guide wall corridor extending to a depth of 100 meters.

[0010] Further, the transverse vibration response characteristics of the guide wall include the transverse acceleration vibration response of the guide wall; The determining of the spatiotemporal vibration data having a correlation with the transverse vibration response characteristics of the guide wall exceeding a set threshold value comprises: The acceleration vibration response sequence of the guide wall in the transverse direction of the spatiotemporal vibration data is used as the second feature, and the other acceleration vibration response sequences are used as the first feature; The first feature and the second feature are combined into an ordered pair set, so that each ordered pair includes a first eigenvalue and a corresponding second eigenvalue; wherein the first eigenvalue refers to the maximum mutual information coefficient value of the first feature; and the second eigenvalue refers to the maximum mutual information coefficient value of the second feature; On a two-dimensional plane, the first feature is axis, the second feature is Axis, construct feature space; along The axis direction divides the feature space into intervals of equal width, along The axis direction divides the feature space into intervals of equal height, forming Grid ; According to the points in the ordered pair set fall on the grid The number of each grid is calculated to obtain the mutual information estimation value of the first feature and the second feature; According to the mutual information estimation value between the first feature and the second feature, using the maximum mutual information coefficient algorithm, calculate the maximum mutual information coefficient value of each pair of the first feature and the second feature, for characterizing the correlation; The first feature whose maximum mutual information coefficient value with the second feature exceeds the set threshold is taken as the spatiotemporal vibration data whose correlation with the transverse river vibration response characteristic of the guide wall exceeds the set threshold.

[0011] Furthermore, when the first feature With the second feature The larger the maximum mutual information coefficient value, the greater the first feature With the second feature The stronger the correlation between them, the smaller the maximum mutual information coefficient value is. With the second feature The smaller the correlation between them.

[0012] Furthermore, according to the points in the ordered pair set falling on the grid The number of each grid, the calculation formula for the mutual information estimation value of the first feature and the second feature is expressed as: (1); In the formula, Indicates the first feature With the second feature Ordered pair set In the cell number Grid The maximum mutual information estimate in , Representing a collection The points in the grid fall on The probability distribution on Represents the grid The maximum value of the data under the distribution, The first feature With the second feature Ordered pair set In the cell number Grid The mutual information estimate in .

[0013] Furthermore, the calculation formula of the maximum mutual information coefficient is expressed as: (2); In the formula, Indicates the first feature With the second feature The maximum mutual information coefficient value of is in the range of [0, 1]; The exponential function representing the total number of samples N of the first feature and the second feature, ; Representation Grid The number of cells in represents the logarithmic function with base 2, Indicates taking and The minimum value of represents the maximum value function, Indicates that the first feature X and the second feature Y form an ordered pair set In the cell number Grid The maximum mutual information estimate in .

[0014] Furthermore, the CNN-BiLSTM-CBAM model uses the spatiotemporal vibration data whose correlation with the vibration response characteristics of the guide wall in the transverse direction exceeds a set threshold as input and the corresponding vibration modal components of the guide wall in the transverse direction as output for training acquisition; The transverse-river vibration modal component of the guide wall is obtained by decomposing the transverse-river vibration response characteristics of the guide wall into eigenmode functions of different complexities using a variational mode decomposition algorithm.

[0015] Furthermore, the expression of the variational mode decomposition algorithm is: (3); In the formula, represents the first modal components, represents the first The center frequency, , represents the total number of modal components decomposed by the variational mode decomposition algorithm, represents the imaginary unit, express The Dirac function at time , express The partial derivative operation at time, represents the convolution operation, express The transverse vibration response data of the guide wall at all times, Indicates constraints; It represents the minimum value operation. express The moment is decomposed by the variational mode decomposition algorithm. modal components.

[0016] Furthermore, the convolutional neural network CNN includes a convolutional layer, an activation function and a pooling layer connected in sequence; The convolutional block attention module CBAM includes a channel attention mechanism CAM and a spatial attention mechanism SAM, which are used to respectively focus on the channel and spatial dimensions of the spatiotemporal features to obtain data features; The bidirectional long short-term memory BiLSTM network includes a forward long short-term memory LSTM network and a backward long short-term memory LSTM network.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention decomposes the complex lateral vibration response data of the guide wall into multiple modal components, significantly reducing the complexity of the spatiotemporal vibration response data of the guide wall. Compared with directly predicting the guide wall vibration signal, the present invention decomposes the complex lateral vibration response data of the guide wall into simpler modal components, and then inputs the data with correlation exceeding the threshold with the lateral vibration response characteristics of the guide wall into the CNN-BiLSTM-CBAM model for prediction, obtains the predicted value of the lateral vibration modal component of the guide wall, and then integrates the predicted value of the lateral vibration modal component of the guide wall to obtain the predicted vibration signal of the guide wall, which can further improve the accuracy and stability of the overall prediction.

[0018] The CNN-BiLSTM-CBAM model provided by the present invention overcomes the shortcomings of the existing time prediction model, such as weak ability to capture nonlinearity and data features, low prediction accuracy, etc., by integrating a convolutional neural network CNN, a convolutional block attention module CBAM and a bidirectional long short-term memory BiLSTM network, and provides a technical reference for improving the nonlinear feature capture capability and data prediction accuracy of the guide wall vibration response. At the same time, the present invention also solves the problem of inaccurate prediction accuracy of the spatiotemporal vibration trend of the guide wall vibration in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of a method for predicting the spatiotemporal vibration trend of a guide wall provided by an embodiment of the present invention; Figure 2 Schematic diagram of the network architecture of the CNN-BiLSTM-CBAM model provided by an embodiment of the present invention; Figure 3 Schematic diagram of the network structure of the convolutional block attention module CBAM provided in an embodiment of the present invention; Figure 4 It is a schematic diagram of calculation results of the maximum mutual information coefficient value of the guide wall spatiotemporal vibration response data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0021] Example 1

[0022] This embodiment introduces a method for predicting the spatiotemporal vibration trend of a guide wall. Figure 1 As shown, including:

[0023] Step 101: Collecting spatiotemporal vibration data of the guide wall and the area adjacent to the guide wall during flood discharge;

[0024] In an embodiment of the present invention, the spatiotemporal vibration data of the guide wall and its adjacent areas during flood discharge can be obtained through sensors and other equipment, and the spatiotemporal vibration data includes vibration information of the guide wall at different time points and spatial positions. In this embodiment, the adjacent area of ​​the guide wall can be determined based on the collected guide wall area in combination with preset adjacent area determination conditions. As an embodiment, the adjacent area of ​​the guide wall can be determined as the right side of the grouting corridor, the left side of the grouting corridor, the junction of the right guide wall corridor and the ground, the right guide wall corridor extending to a depth of 100 meters, the junction of the left guide wall corridor and the ground, and the left guide wall corridor extending to a depth of 100 meters. The guide wall area may include: right guide wall, left guide wall.

[0025] Step 102: Obtaining the transverse river vibration response characteristics of the guide wall in the spatiotemporal vibration data;

[0026] The so-called transverse river vibration response characteristics of the guide wall refer to the vibration response characteristics in the direction perpendicular to the river flow direction.

[0027] Step 103: determining the spatiotemporal vibration data whose correlation with the vibration response characteristics of the guide wall in the transverse direction exceeds a set threshold, and sequentially inputting the determined spatiotemporal vibration data into the pre-trained CNN-BiLSTM-CBAM model, and using the CNN-BiLSTM-CBAM model to predict the modal components of the vibration response of the guide wall in the transverse direction, to obtain multiple predicted values ​​of the modal components of the vibration of the guide wall in the transverse direction;

[0028] The purpose of determining the spatiotemporal vibration data whose correlation with the transverse vibration response characteristics of the guide wall exceeds a set threshold is to screen out data with high correlation with the transverse direction of the guide wall from the collected spatiotemporal vibration data. In order to improve the prediction accuracy, the spatiotemporal vibration data can also be preprocessed, for example: by removing data that is not directly related to the prediction target, data redundancy can be reduced.

[0029] The CNN-BiLSTM-CBAM model integrates the advantages of convolutional neural network CNN, bidirectional long short-term memory BiLSTM network and convolutional block attention module CBAM, and can simultaneously capture the spatial characteristics, temporal dependencies and important feature information of the data. Specifically, the convolutional neural network CNN of the CNN-BiLSTM-CBAM model is used to convolve and pool the input spatiotemporal vibration data to obtain spatiotemporal features; the convolutional block attention module CBAM of the CNN-BiLSTM-CBAM model is used to focus on the channels and spatial dimensions of the spatiotemporal features to obtain data features, and the data features are reassembled and fitted to obtain a first prediction value; the bidirectional long short-term memory BiLSTM network of the CNN-BiLSTM-CBAM model is used to capture the output results that have a bidirectional long-term dependency relationship with the input spatiotemporal vibration data to obtain a second prediction value; the splicing layer of the CNN-BiLSTM-CBAM model is used to splice the first prediction value and the second prediction value to obtain multiple prediction values ​​of the transverse river vibration modal components of the guide wall;

[0030] Through the prediction of the CNN-BiLSTM-CBAM model, the predicted value of each modal component at a future time point can be obtained, and the predicted value reflects the vibration trend of the guide wall at different frequencies or time scales.

[0031] Step 104: adding the plurality of predicted values ​​of the transverse-river vibration modal components of the guide wall to obtain a predicted transverse-river vibration signal of the guide wall;

[0032] Step 105: Predict the temporal and spatial vibration trend of the guide wall based on the predicted vibration signal of the guide wall in the transverse direction.

[0033] In summary, the embodiment of the present invention can obtain the overall guide wall predicted vibration signal of the guide wall at a future time point by integrating the predicted values ​​of each guide wall transverse vibration modal component of the guide wall transverse vibration response into an overall prediction result.

[0034] The stability and safety of the guide wall can be evaluated or other related engineering analysis can be performed based on the predicted vibration signal of the guide wall.

[0035] In step 103, before applying the CNN-BiLSTM-CBAM model, a training set should be first constructed. The training set includes input features and output features. In an embodiment of the present invention, the input features are data whose correlation with the transverse-river vibration response characteristics of the guide wall exceeds a threshold, and the output features are multiple modal components obtained by decomposing the transverse-river vibration response data of the guide wall.

[0036] Signal processing technology is used to decompose the vibration response data of the guide wall into multiple modal components as the target value of the prediction model. Each modal component represents the vibration characteristics of the guide wall's lateral vibration response data at different frequencies or time scales, which helps to capture the nonlinear and non-stationary characteristics of the guide wall's lateral vibration response data.

[0037] Example 2 Based on the same inventive concept as Example 1, this example introduces a method for predicting the spatiotemporal vibration trend of a guide wall, which specifically includes the following steps: Step 1: Input feature selection: Collect spatiotemporal vibration data of the guide wall and the area adjacent to the guide wall during flood discharge, including: The vertical, downstream and cross-river acceleration time history curves of eight different locations of the guide wall and the area adjacent to the guide wall were collected respectively; The spatiotemporal vibration data were obtained based on the vertical, downstream and transverse acceleration time history curves of eight different parts of the guide wall and the area adjacent to the guide wall.

[0038] The transverse vibration response characteristics of the guide wall include the transverse acceleration vibration response of the guide wall. Further, the determining of the spatiotemporal vibration data having a correlation with the transverse vibration response characteristics of the guide wall exceeding a set threshold value includes: The acceleration vibration response sequence of the guide wall in the transverse direction of the spatiotemporal vibration data is used as the second feature, and the other acceleration vibration response sequences are used as the first feature; The first feature and the second feature are combined into an ordered pair set, so that each ordered pair includes a first eigenvalue and a corresponding second eigenvalue; wherein the first eigenvalue refers to the maximum mutual information coefficient value of the first feature; and the second eigenvalue refers to the maximum mutual information coefficient value of the second feature; On a two-dimensional plane, the first feature is axis, the second feature is Axis, construct feature space; along The axis direction divides the feature space into intervals of equal width, along The axis direction divides the feature space into intervals of equal height, forming Grid ; According to the points in the ordered pair set fall on the grid The number of each grid is calculated to obtain the mutual information estimation value of the first feature and the second feature; According to the mutual information estimation value between the first feature and the second feature, using the maximum mutual information coefficient algorithm, calculate the maximum mutual information coefficient value of each pair of the first feature and the second feature, for characterizing the correlation; The first feature whose maximum mutual information coefficient value with the second feature exceeds the set threshold is taken as the spatiotemporal vibration data whose correlation with the transverse river vibration response characteristic of the guide wall exceeds the set threshold.

[0039] The calculation formula of the mutual information estimation value of the first feature and the second feature is expressed as: (1); In the formula, Indicates the first feature With the second feature Ordered pair set In the cell number Grid The maximum mutual information estimate in , Representing a collection The points in the grid fall on The probability distribution on Represents the grid The maximum value of the data under the distribution, The first feature With the second feature Ordered pair set In the cell number Grid The mutual information estimate in .

[0040] According to the mutual information estimation value of the first feature and the second feature, the maximum mutual information coefficient value of each pair of the first feature and the second feature is calculated using the maximum mutual information coefficient algorithm; the calculation formula of the maximum mutual information coefficient is expressed as: (2); In the formula, Indicates the first feature With the second feature The maximum mutual information coefficient value of is in the range of [0, 1]; The exponential function representing the total number of samples N of the first feature and the second feature, ; Representation Grid The number of cells in represents the logarithmic function with base 2, Indicates taking and The minimum value of represents the maximum value function, Indicates that the first feature X and the second feature Y form an ordered pair set In the cell number Grid The maximum mutual information estimate in .

[0041] The first feature whose maximum mutual information coefficient value with the second feature exceeds the threshold is regarded as data whose correlation with the transverse river vibration response feature of the guide wall exceeds the threshold.

[0042] When the first feature With the second feature The larger the maximum mutual information coefficient value, the greater the first feature With the second feature The stronger the correlation between them, the smaller the maximum mutual information coefficient value is. With the second feature The smaller the correlation between them.

[0043] In this embodiment, the threshold of the maximum mutual information coefficient is defined as 0.86.

[0044] like Figure 4 As shown, the data whose correlation with the transverse vibration response characteristics of the guide wall exceeds the threshold are: feature 14, feature 19, feature 20, feature 22, feature 23, and feature 24 as input features. It should be noted that the maximum mutual information coefficient is dimensionless data.

[0045] Step 2: Data decomposition: Since the spatiotemporal vibration data is highly complex, this embodiment uses a variational mode decomposition algorithm to stabilize the transverse vibration response data of the guide wall.

[0046] The CNN-BiLSTM-CBAM model uses the spatiotemporal vibration data with a correlation with the vibration response characteristics of the guide wall in the transverse direction exceeding a set threshold as input and the corresponding vibration modal component of the guide wall in the transverse direction as output for training and acquisition; The transverse-river vibration modal component of the guide wall is obtained by decomposing the transverse-river vibration response characteristics of the guide wall into eigenmode functions of different complexities using a variational mode decomposition algorithm.

[0047] The variational mode decomposition algorithm can be expressed by the following formula: (3); In the formula, represents the first modal components, represents the first The center frequency, , represents the total number of modal components decomposed by the variational mode decomposition algorithm, represents the imaginary unit, express The Dirac function at time , express The partial derivative operation at time, represents the convolution operation, express The transverse vibration response data of the guide wall at all times, Indicates constraints; It represents the minimum value operation. express The moment is decomposed by the variational mode decomposition algorithm. modal components.

[0048] Step 3: Data preprocessing: Before the corresponding spatiotemporal vibration data are sequentially input into the pre-trained CNN-BiLSTM-CBAM model for prediction, the corresponding spatiotemporal vibration data are converted into continuous sub-time series data based on the sliding window iterative prediction mode, and the obtained continuous sub-time series data are divided into a training set and a test set in a ratio of 0.8:0.2.

[0049] In this embodiment, batch normalization is adopted, the sliding window length is set to 10, and data preprocessing is performed on the data whose correlation with the transverse vibration response characteristics of the guide wall exceeds the threshold. The formula for batch normalization is: (4); In the formula, Indicates Data with correlations with the transverse vibration response characteristics of the guide wall exceeding the threshold The normalized value of represents the mean of all the data whose correlation with the guide wall transverse river vibration response characteristics exceeds the threshold, σ represents the standard deviation of all the data whose correlation with the guide wall transverse river vibration response characteristics exceeds the threshold, γ and β represent the weight scaling parameter and weight offset parameter respectively, which are used to adjust the output of batch normalization. Usually, γ is initialized to 1 and β is initialized to 0. ε represents the minimum value to prevent division by zero.

[0050] Step 4: CNN-BiLSTM-CBAM model prediction: like Figure 2 As shown, the convolutional neural network CNN includes a convolutional layer, an activation function and a pooling layer connected in sequence; The convolutional block attention module CBAM includes a channel attention mechanism CAM and a spatial attention mechanism SAM, which are used to respectively focus on the channel and spatial dimensions of the spatiotemporal features to obtain data features.

[0051] The bidirectional long short-term memory BiLSTM network includes a forward long short-term memory LSTM network and a backward long short-term memory LSTM network.

[0052] The convolutional neural network (CNN), including convolutional layers, activation functions and pooling layers, is used to perform convolution and pooling on the data whose correlation with the transverse vibration response characteristics of the guide wall exceeds a threshold, so as to obtain spatiotemporal features.

[0053] The convolutional block attention module CBAM includes a channel attention mechanism CAM and a spatial attention mechanism SAM, which is used to pay attention to the channel and spatial dimensions of the spatiotemporal features to obtain data features, reassemble and fit the data features to obtain a first prediction value. The network structure diagram of the convolutional block attention module CBAM is as follows: Figure 3 shown.

[0054] A bidirectional long short-term memory BiLSTM network includes a forward long short-term memory LSTM network and a backward long short-term memory LSTM network, which is used to splice the forward long short-term memory LSTM network and the backward long short-term memory LSTM network to capture the output results of the data with a bidirectional long-term dependency relationship whose correlation with the transverse river vibration response characteristics of the guide wall exceeds a threshold, and obtain a second prediction value.

[0055] A concatenation layer is used to concatenate the first prediction value and the second feature value.

[0056] In this embodiment, the global parameters of the CNN-BiLSTM-CBAM model are set to: time window T=10, number of features F=5; the training parameters of the CNN-BiLSTM-CBAM model are set to: batch size Batch size=2, number of cycles Epoch=100, optimizer Optimizer=Adam, loss function Loss function=MSE, and the parameters of the convolutional neural network CNN are set to: number of layers Filters=64, kernel size Kernel_size =3, dropout rate Dropout rate=0.1, activation function Activation=ReLU; the parameters of the bidirectional long short-term memory BiLSTM network are set to: hidden layer Units=64, network layer number Layer=1, dropout rate Dropout rate=0.3, activation function Activation=Sigmoid.

[0057] After the above parameters are set, the CNN-BiLSTM-CBAM model is trained using the training set to obtain a trained CNN-BiLSTM-CBAM model.

[0058] In this embodiment, after determining the spatiotemporal vibration data whose correlation with the transverse river vibration response characteristics of the guide wall exceeds a set threshold, the determined spatiotemporal vibration data are sequentially input into the pre-trained CNN-BiLSTM-CBAM model; The convolutional neural network CNN of the CNN-BiLSTM-CBAM model is used to convolve and pool the input spatiotemporal vibration data to obtain spatiotemporal features.

[0059] The convolutional block attention module CBAM of the CNN-BiLSTM-CBAM model is used to focus on the channel and spatial dimensions of the spatiotemporal features to obtain data features, and the data features are reassembled and fitted to obtain a first prediction value.

[0060] The bidirectional long short-term memory BiLSTM network of the CNN-BiLSTM-CBAM model is used to capture the output result having a bidirectional long-term dependency relationship with the input spatiotemporal vibration data to obtain a second prediction value.

[0061] The first prediction value and the second prediction value are spliced ​​using the splicing layer of the CNN-BiLSTM-CBAM model to obtain a plurality of prediction values ​​of the transverse river vibration modal components of the guide wall.

[0062] Adding the plurality of predicted values ​​of the transverse-river vibration modal components of the guide wall to obtain a predicted transverse-river vibration signal of the guide wall; The temporal and spatial vibration trend of the guide wall is predicted based on the predicted vibration signal of the guide wall in the transverse direction.

[0063] Step 5: Prediction performance evaluation: The CNN-BiLSTM-CBAM model was tested and its performance was evaluated using the test set. The prediction performance was compared with that of different baseline models based on the evaluation indicators to verify the generalization ability and accuracy of the CNN-BiLSTM-CBAM model.

[0064] The evaluation indicators include mean square error MSE, root mean square error RMSE, mean absolute error MAE and correlation coefficient R. The formula is as follows:

[0065] In the formula, represents the total number of samples of the spatiotemporal vibration response data of the guide wall, Indicates The true value of the spatiotemporal vibration response data of the guide wall, Indicates The predicted value of the spatiotemporal vibration response data of the guide wall, Indicates The true value of the spatiotemporal vibration response data of the guide wall and Prediction value of the spatiotemporal vibration response data of the guide wall The covariance between Indicates The true value of the spatiotemporal vibration response data of the guide wall The variance of Indicates The variance of the predicted value of the spatiotemporal vibration response data of the guide wall.

[0066] The verification results are shown in Table 1:

[0067] In summary, the embodiments of the present invention decompose the complex spatiotemporal vibration response data of the guide wall into multiple modal components, significantly reducing the complexity of the spatiotemporal vibration response data of the guide wall. Compared with directly predicting the guide wall vibration signal, the embodiments of the present invention decompose the complex vibration data into simpler modal components, and then predict the spatiotemporal data with the maximum mutual information coefficient exceeding the threshold through the CNN-BiLSTM-CBAM model to obtain the predicted value of the lateral vibration modal component of the guide wall, and integrate the predicted values ​​of the lateral vibration modal components of each guide wall to obtain the predicted vibration signal of the guide wall, which can further improve the accuracy and stability of the overall prediction.

[0068] The CNN-BiLSTM-CBAM model provided in the embodiment of the present invention overcomes the shortcomings of the existing time prediction model, such as weak ability to capture nonlinearity and data features and low prediction accuracy, by integrating a convolutional neural network CNN, a convolutional block attention module CBAM and a bidirectional long short-term memory BiLSTM network. It provides a technical reference for improving the nonlinear feature capture capability and data prediction accuracy of the guide wall vibration response. At the same time, the embodiment of the present invention also solves the problem of inaccurate prediction accuracy of the spatiotemporal vibration trend of the guide wall vibration in the prior art.

[0069] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0070] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0071] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0072] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0073] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A method for predicting the temporal and spatial vibration trend of a guide wall, characterized in that: include: Collect spatiotemporal vibration data of the guide wall and the area adjacent to the guide wall during flood discharge; Obtain the transverse vibration response characteristics of the guide wall in the spatiotemporal vibration data; Determine the spatiotemporal vibration data whose correlation with the transverse river vibration response characteristics of the guide wall exceeds a set threshold, and sequentially input the determined spatiotemporal vibration data into the pre-trained CNN-BiLSTM-CBAM model; Using the convolutional neural network (CNN) of the CNN-BiLSTM-CBAM model, the input spatiotemporal vibration data is convolved and pooled to obtain spatiotemporal features; Using the convolutional block attention module CBAM of the CNN-BiLSTM-CBAM model, focusing on the channel and spatial dimensions of the spatiotemporal features to obtain data features, reassembling and fitting the data features to obtain a first prediction value; Using the bidirectional long short-term memory BiLSTM network of the CNN-BiLSTM-CBAM model, the output result having a bidirectional long-term dependency relationship with the input spatiotemporal vibration data is captured to obtain a second prediction value; Using the splicing layer of the CNN-BiLSTM-CBAM model to splice the first prediction value and the second prediction value, a plurality of prediction values ​​of the transverse river vibration modal components of the guide wall are obtained; Adding the plurality of predicted values ​​of the transverse-river vibration modal components of the guide wall to obtain a predicted transverse-river vibration signal of the guide wall; The temporal and spatial vibration trend of the guide wall is predicted based on the predicted vibration signal of the guide wall in the transverse direction.

2. The method for predicting the temporal and spatial vibration trend of a guide wall according to claim 1, characterized in that: It also includes converting the corresponding spatiotemporal vibration data into continuous sub-time series data based on a sliding window iterative prediction mode before sequentially inputting the corresponding spatiotemporal vibration data into a pre-trained CNN-BiLSTM-CBAM model for prediction.

3. The method for predicting the temporal and spatial vibration trend of a guide wall according to claim 1, characterized in that: The collection of spatiotemporal vibration data of the guide wall and the area adjacent to the guide wall during flood discharge includes: The vertical, downstream and cross-river acceleration time history curves of eight different locations of the guide wall and the area adjacent to the guide wall were collected respectively; According to the vertical, downstream and cross-river acceleration time history curves of eight different parts of the guide wall and the area adjacent to the guide wall, the spatiotemporal vibration data are obtained; Among them, the eight different parts of the guide wall and the adjacent area of ​​the guide wall include: the right guide wall, the left guide wall, the right side of the grouting corridor, the left side of the grouting corridor, the junction of the right guide wall corridor and the ground, the right guide wall corridor extending to a depth of 100 meters, the junction of the left guide wall corridor and the ground, and the left guide wall corridor extending to a depth of 100 meters.

4. The method for predicting the temporal and spatial vibration trend of a guide wall according to claim 3, characterized in that: The transverse vibration response characteristics of the guide wall include the transverse acceleration vibration response of the guide wall; The determining of the spatiotemporal vibration data having a correlation with the transverse vibration response characteristics of the guide wall exceeding a set threshold value comprises: The acceleration vibration response sequence of the guide wall in the transverse direction of the spatiotemporal vibration data is used as the second feature, and the other acceleration vibration response sequences are used as the first feature; The first feature and the second feature are combined into an ordered pair set, so that each ordered pair includes a first eigenvalue and a corresponding second eigenvalue; wherein the first eigenvalue refers to the maximum mutual information coefficient value of the first feature; and the second eigenvalue refers to the maximum mutual information coefficient value of the second feature; On a two-dimensional plane, the first feature is axis, the second feature is Axis, construct feature space; along The axis direction divides the feature space into intervals of equal width, along The axis direction divides the feature space into intervals of equal height, forming Grid ; According to the points in the ordered pair set fall on the grid The number of each grid is calculated to obtain the mutual information estimation value of the first feature and the second feature; According to the mutual information estimation value between the first feature and the second feature, using the maximum mutual information coefficient algorithm, calculate the maximum mutual information coefficient value of each pair of the first feature and the second feature, for characterizing the correlation; The first feature whose maximum mutual information coefficient value with the second feature exceeds the set threshold is taken as the spatiotemporal vibration data whose correlation with the transverse river vibration response characteristic of the guide wall exceeds the set threshold.

5. The method for predicting the temporal and spatial vibration trend of a guide wall according to claim 4, characterized in that: When the first feature With the second feature The larger the maximum mutual information coefficient value, the greater the first feature With the second feature The stronger the correlation between them, the smaller the maximum mutual information coefficient value is. With the second feature The smaller the correlation between them.

6. The method for predicting the temporal and spatial vibration trend of a guide wall according to claim 4, characterized in that: According to the points in the ordered pair set fall on the grid The number of each grid, the calculation formula for the mutual information estimation value of the first feature and the second feature is expressed as: （1）； In the formula, Represents the first feature With the second feature Ordered pair set In the cell number Grid The maximum mutual information estimate in , Representing a collection The points in the grid fall on The probability distribution on Represents the grid The maximum value of the data under the distribution, The first feature With the second feature Ordered pair set In the cell number Grid The mutual information estimate in .

7. The method for predicting the temporal and spatial vibration trend of a guide wall according to claim 4, characterized in that: The calculation formula of the maximum mutual information coefficient is expressed as: （2）； In the formula, Represents the first feature With the second feature The maximum mutual information coefficient value of is in the range of [0,1]; The exponential function representing the total number of samples N of the first feature and the second feature, ; Representation Grid The number of cells in represents the logarithmic function with base 2, Indicates taking and The minimum value of represents the maximum value function, Indicates that the first feature X and the second feature Y form an ordered pair set In the cell number Grid The maximum mutual information estimate in .

8. The method for predicting the temporal and spatial vibration trend of a guide wall according to claim 1, characterized in that: The CNN-BiLSTM-CBAM model uses the spatiotemporal vibration data with a correlation with the vibration response characteristics of the guide wall in the transverse direction exceeding a set threshold as input and the corresponding vibration modal component of the guide wall in the transverse direction as output for training and acquisition; The transverse-river vibration modal component of the guide wall is obtained by decomposing the transverse-river vibration response characteristics of the guide wall into eigenmode functions of different complexities using a variational mode decomposition algorithm.

9. The method for predicting the temporal and spatial vibration trend of a guide wall according to claim 8, characterized in that: The expression of the variational mode decomposition algorithm is: （3）； In the formula, represents the first modal components, represents the first The center frequency, , represents the total number of modal components decomposed by the variational mode decomposition algorithm, represents the imaginary unit, express The Dirac function at time , express The partial derivative operation at time, represents the convolution operation, express The transverse vibration response data of the guide wall at all times, Indicates constraints; It represents the minimum value operation. express The moment is decomposed by the variational mode decomposition algorithm. modal components.

10. The method for predicting the temporal and spatial vibration trend of a guide wall according to claim 1, characterized in that: The convolutional neural network CNN includes a convolutional layer, an activation function and a pooling layer connected in sequence; The convolutional block attention module CBAM includes a channel attention mechanism CAM and a spatial attention mechanism SAM, which are used to respectively focus on the channel and spatial dimensions of the spatiotemporal features to obtain data features; The bidirectional long short-term memory BiLSTM network includes a forward long short-term memory LSTM network and a backward long short-term memory LSTM network.

Images