A spatiotemporal correlation prediction method for service performance of bridge groups based on graph-selective state space model

Abstract

The present invention proposes a spatiotemporal correlation prediction method for the service performance of bridge groups based on a graph-selective state-space model. This method targets regional bridge group service performance prediction tasks, constructs a service performance dataset of environmental effects and traffic flow of bridge groups, establishes a graph-selective state-space model for service performance spatiotemporal correlation prediction, designs a spatiotemporal graph convolution module to learn spatiotemporal correlation, constructs a graph-selective state-space module to learn spatiotemporal evolution characteristics, and trains the spatiotemporal correlation prediction model for bridge group service performance based on gradient descent error backpropagation. After training, the trained model is used to perform spatiotemporal correlation prediction on environmental effects and traffic flow of bridge groups. By decomposing and fusing the spatiotemporal features of service performance data of different complexities, the method can better adapt to the processing requirements of multi-type, multi-scale, and multi-granular spatiotemporal service performance data of bridge groups, thereby improving the versatility and prediction efficiency of the method.

Description

Technical Field

[0001] The present invention relates to the fields of bridge engineering, structural health monitoring, spatiotemporal data analysis, and deep learning technology, and in particular to a method for predicting the spatiotemporal correlation of service performance of a group of bridges based on a graph-selective state-space model. The method can be directly applied to intelligent bridges, intelligent bridge operation and maintenance, smart infrastructure, and intelligent disaster prevention and mitigation. Background Art

[0002] As a key component of urban transportation systems, the stability of bridge service performance is directly related to the smoothness and safety of urban traffic. Bridge clusters, as complex systems composed of multiple bridges, are inevitably affected by the coupling effects of multiple factors, such as the natural environment, traffic loads, and material aging, over their long-term service. This can lead to continuous structural degradation, and even extreme cases where the failure of a single bridge can cause a regional traffic accident. Therefore, accurate and efficient prediction of the service performance of regional bridge clusters is crucial for ensuring urban traffic safety and improving the effectiveness of bridge cluster operation and maintenance management.

[0003] Traditional bridge group service performance prediction methods mainly rely on the service performance prediction of individual bridges. The service performance they focus on is limited to the local components of individual bridges. They fail to integrate and utilize the shared characteristics of the environment and loads in the urban area where the bridge group is located. They ignore the spatiotemporal correlations between different individual bridges in the bridge group and the individual similarities in terms of structural type, service life, damage evolution, etc., resulting in the correlation and synergy effects between the individual bridges in the urban area bridge group not being fully explored.

[0004] At present, deep learning technology has achieved rapid development, and domestic and foreign research has been carried out on the use of deep learning methods to predict bridge service performance. However, current research mainly focuses on:

[0005] (1) Deep learning-based assessment of single bridge components: For example, the damage location and severity assessment of cable-stayed bridges based on message passing neural networks uses cable force data of multiple cables as input and outputs the location and cross-sectional area of ​​the damaged cables, considering only the spatial correlation of different cables on a single bridge.

[0006] (2) Road network performance prediction based on deep learning: For example, the GraphSAGE-based road deterioration modeling considers the spatial correlation and functional classification correlation of the road network. However, the actual prediction of road deterioration is often affected by both spatial and temporal factors. Spatial correlation is reflected in the mutual influence between adjacent road sections, while temporal correlation is reflected in the changing trend of road conditions over time. The above-mentioned studies also only considered spatial correlation but lacked consideration of spatiotemporal correlation.

[0007] (3) In addition, existing studies often focus on a single type of data, and a general deep learning method for spatiotemporal correlation prediction of multi-type, multi-scale, and multi-granular spatiotemporal data on the service performance of bridge groups (including environment, load, traffic flow, etc.) has not yet been established.

[0008] In recent years, spatiotemporal graph structures and state-space models have provided novel insights and advanced algorithms for studying spatiotemporal correlation prediction. Spatiotemporal graph neural networks have shown promising application prospects in predicting the service performance of bridge clusters. However, current research still faces significant challenges. Urgent challenges include: how to construct appropriate spatiotemporal graph structures to accurately reflect the complex spatiotemporal correlations between bridge clusters; how to design effective spatiotemporal graph neural network models to capture the spatiotemporal dependencies of bridge cluster service performance evolution; and how to fully utilize spatiotemporal data from bridge clusters to improve prediction accuracy and efficiency. Summary of the Invention

[0009] The purpose of the present invention is to solve the problems in the prior art and propose a spatiotemporal correlation prediction method for the service performance of a bridge group based on a graph selective state space model.

[0010] The present invention is achieved through the following technical solutions. The present invention proposes a method for predicting the spatiotemporal correlation of service performance of a bridge group based on a graph-selective state space model. The method comprises the following steps:

[0011] Step 1: Determine the bridge group task object to be studied and establish a bridge group graph structure model that considers the effects of urban area environment and traffic flow;

[0012] Step 2: Design a spatiotemporal graph prediction task based on the multi-source perception data of the service performance of a group of bridges, and construct the corresponding input and output datasets. The bridge group service performance prediction task is designed to take the historical monitoring data of temperature, humidity, wind speed, wind direction, and corrosion ion concentration environmental variables and traffic flow as input, and predict the future bridge group environmental effects and traffic flow as output. The multi-type, multi-scale, and multi-granularity multi-source perception dataset of the service performance of a group of bridges is embedded and represented as Where N is the number of bridges, T is the input data time step, and D is the feature dimension; the corresponding output dataset embedding is expressed as Where T p is the time step of the predicted output data;

[0013] Step 3: Establish a graph-selective state-space model for predicting the spatiotemporal correlation of the serviceability of bridge groups. This model consists of two modules: a spatiotemporal graph convolution module and a graph-selective state-space module. The spatiotemporal graph convolution module is used to learn the spatiotemporal correlation of the serviceability of bridge groups, while the graph-selective state-space module is used to learn the spatiotemporal evolution characteristics of the serviceability of bridge groups. The outputs of the two modules are weighted and fused through a fully connected layer to output the final prediction result.

[0014] Step 4: Based on the gradient descent error back propagation, the graph selective state space model is trained and the trained model is used to predict the spatiotemporal correlation between the environmental effects of the bridge group and the traffic flow.

[0015] Furthermore, in step 1, the graph structure model is established as follows:

[0016] Node definition of the bridge group graph structure: Each bridge is considered as a node in the graph, and the node attributes include temperature, humidity, wind speed, wind direction, corrosion ion concentration, environmental variables and traffic flow;

[0017] Edge definition of the bridge group graph structure: Based on the spatial position relationship between different individual bridges in the bridge group, the edges between nodes are preliminarily defined; for temperature, humidity, and corrosion ion predictions, the edges are undirected; for wind speed and direction predictions, the edges are directed; for traffic flow predictions, the edges are directed, and the edge weights are determined based on the traffic flow size and the distance between bridges.

[0018] Bridge group graph structure generation: The bridge group graph structure is represented by G = (V; E), where V is the set of bridge nodes and E is the set of edges. Based on the definitions of nodes and edges, a bridge group graph structure model is generated to determine the adjacency matrix A of the bridge group graph structure.

[0019] Furthermore, in step 2, for the spatiotemporal data of the service performance of multi-type, multi-scale and multi-granular bridge groups, three different time granularities are used as input data, including recent data X r , periodic data X c and trend data X q ; Recent data is a historical time series directly adjacent to the forecast period, periodic data consists of segments whose past days in the same time period as the forecast period are integer multiples of α, and trend data consists of segments whose past days in the same time period as the forecast period are integer multiples of β; the lengths of the three types of input data, recent data, periodic data, and trend data, are set according to actual forecast needs to adapt to different forecast targets and historical data characteristics.

[0020] Furthermore, the step three is specifically as follows:

[0021] Step 31: Establish a spatiotemporal graph convolution module;

[0022] The bridge group environmental effects and traffic flow data are passed through 1×1 convolution and then sequentially passed to the gated temporal convolution layer and the self-attention diffusion graph convolution layer. After residual connection with the input, the output is obtained after batch normalization.

[0023] Step 32: Establish a graph-selective state space module;

[0024] The recent data on the environmental effects of bridge groups and traffic flow are used to r After layer normalization, they are passed to m dynamic filter graph convolution layers respectively. The outputs of the m graph convolution layers are concatenated and passed through the linear layer. The output of the linear layer is divided into a core sequence and a secondary sequence. The core sequence is passed to the graph state space selection mechanism after one-dimensional convolution and SiLU activation. Its output is multiplied element-by-element with the SiLU activated secondary sequence. Finally, after passing through the linear layer, it is multiplied with the layer normalized X r Residual connection to get the final output;

[0025] Step 3: Combine the three time-granularity data X of bridge group environmental effects and traffic flow r 、X c and X q The fusion result output by N spatiotemporal graph convolution modules is connected to the input X r The outputs of the M graph-selective state-space modules are weighted and summed, and the results are passed through the fully connected layer to obtain the final output.

[0026] Furthermore, in step 31,

[0027] Construct a gated temporal convolutional layer to learn the complex temporal dependencies of the bridge group service performance sequence data: the bridge group environmental effects and traffic flow data are input through a 1×1 convolution and then passed to the gated temporal convolutional layer:

[0028] Y=f(w1*X+b)⊙σ(w2*X+c) (4)

[0029] Where Y is the output of the gated temporal convolution of the bridge group environmental effects and traffic flow data input, w1, w2, b, and c are the parameters to be optimized; f is the tanh activation function, which transforms and extracts features from the bridge group environmental effects and traffic flow data input; σ is the sigmoid activation function, which outputs a gating weight between 0 and 1. The generated gating weight controls the proportion of information flow; ⊙ is element-by-element multiplication, w1*X+b represents convolutional layer 1, and w2*X+c represents convolutional layer 2.

[0030] Construct a self-attention diffusion graph convolution layer to learn the complex spatial dependencies of the service state sequence data of the bridge group: pass the output of the gated temporal convolution layer to the self-attention diffusion graph convolution layer:

[0031]

[0032] Where H is the output of the bridge group environmental effect and traffic flow data input after gated temporal convolution and self-attention diffusion graph convolution, and is the parameter to be optimized, and is the attention weight matrix of the bridge group graph structure, K is the number of diffusion steps, which is a hyperparameter and represents the diffusion process of K finite steps to simulate the service performance graph signal of the bridge group.

[0033] Furthermore, the attention weight matrix of the self-attention diffusion graph convolution layer of the spatiotemporal graph convolution module is calculated as follows:

[0034]

[0035] Where a k is the parameter matrix to be optimized; the propagation process of bridge group environmental effects and traffic flow data signals is divided into two directions, and the forward transformation matrix of bridge group environmental effects and traffic flow data signals is A f =A / rowsum(A), the inverse transformation matrix is ​​A b =A T / rowsum(A T ), Adaptive adjacency matrix of bridge group graph structure A k Represents the power level of the transformation matrix and the adaptive adjacency matrix. The columns are normalized during the operation and expressed as (·) / rowsum(·); the adaptive adjacency matrix The calculation of does not require prior knowledge and is end-to-end learned in the gradient descent process, thereby discovering the hidden spatial dependencies between the environmental effects of bridge groups and traffic flow data. The learnable parameters to be optimized are U, are two randomly initialized node embeddings; SoftMax represents the exponential normalization operation, and ReLU represents the rectified linear unit activation function.

[0036] Furthermore, in step 33, the output of each spatiotemporal graph convolution block is used as the input of the next spatiotemporal graph convolution block, and a total of N spatiotemporal graph convolution blocks are set; a residual connection is set in each spatiotemporal graph convolution block, and a jump connection is performed with the output layer, specifically: the result of the gated time convolution in each spatiotemporal graph convolution block is processed by a 1×1 convolution, and then added to the result of the gated time convolution in the previous spatiotemporal graph convolution block by a jump connection; finally, the accumulation is passed to the output layer, which consists of an activation function and a linear layer, and outputs the operation result of the spatiotemporal graph convolution block.

[0037] Furthermore, in step 33, the outputs of the spatiotemporal graph convolution module at three time granularities of the bridge group service performance are fused. The specific method is as follows:

[0038]

[0039] Where w r 、w c With w qis a learnable parameter to be optimized, is a scalar, and reflects the degree of influence of the three time granularity components on the spatiotemporal correlation prediction target of the service performance of bridge groups; and They represent the output of the spatiotemporal graph data of the bridge group service state after the spatiotemporal graph convolution block, Represents the output of the fused spatiotemporal graph convolution module.

[0040] The present invention also proposes an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for predicting the spatiotemporal correlation of the service performance of a group of bridges based on a graph selective state space model are implemented.

[0041] The present invention also proposes a computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the steps of the method for predicting the spatiotemporal correlation of the service performance of a group of bridges based on a graph-selective state space model.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] (1) By embedding perception data of different time granularities (recent data, periodic data, and trend data), the model can capture the dynamic changes of multi-type, multi-scale, and multi-granular bridge service performance data at different time scales, thereby improving the versatility, accuracy, and robustness of the model.

[0044] (2) Design a spatiotemporal graph convolution module, combine graph convolution with time series prediction network, effectively capture the spatial and temporal dependencies of bridge group service performance data, and realize efficient spatiotemporal correlation modeling.

[0045] (3) An adaptive adjacency matrix of the bridge group graph structure is introduced into the graph convolution module. This matrix is ​​obtained through end-to-end learning during the training process without any prior knowledge, enabling the model to automatically discover hidden spatial dependencies in the service performance data of the bridge group, further improving the accuracy of the prediction.

[0046] (4) The bridge group graph structure attention weight matrix is ​​introduced into the graph convolution module to determine the contribution of each part of information to the current node representation, thereby improving the model interpretability. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0048] Figure 1 This is a flow chart of the spatiotemporal correlation prediction method for the service performance of a group of bridges based on a graph-selective state space model.

[0049] Figure 2 Schematic diagram of the bridge group structure model considering environmental effects and traffic flow.

[0050] Figure 3 A time series relationship diagram of recent data, periodic data and trend data sampling for the service performance of a group of bridges.

[0051] Figure 4 Schematic diagram of the spatiotemporal graph convolution module architecture in the spatiotemporal correlation prediction method for bridge group service performance.

[0052] Figure 5 Schematic diagram of the gated temporal convolutional layer architecture in the spatiotemporal correlation prediction method for bridge group service performance.

[0053] Figure 6 Schematic diagram of the self-attention diffusion graph convolutional layer architecture in the spatiotemporal correlation prediction method for bridge group service performance.

[0054] Figure 7 Schematic diagram of the attention weight matrix calculation process in the spatiotemporal correlation prediction method for the service performance of bridge groups. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0056] Combine Figure 1-Figure 7 The present invention proposes a spatiotemporal correlation prediction method for the service performance of a bridge group based on a graph selective state space model, the method comprising the following steps:

[0057] Step 1: Determine the bridge group task object to be studied and establish a bridge group graph structure model that considers the effects of urban area environment and traffic flow;

[0058] In step one, multi-source sensing data on the service performance of the bridge cluster is collected and preprocessed. Data collection for the bridge cluster involves collecting historical data on environmental factors such as temperature, humidity, wind speed, wind direction, and corrosive ion concentration, as well as traffic flow, for each bridge in the cluster. Preprocessing of the data involves cleaning the collected data to remove outliers and missing values, and normalizing the multi-type data to ensure consistency and accuracy.

[0059] In step 1, the graph structure model is established as follows:

[0060] Node definition of the bridge group graph structure: Each bridge is considered as a node in the graph, and the node attributes include temperature, humidity, wind speed, wind direction, corrosion ion concentration, environmental variables and traffic flow;

[0061] Edge definition of the bridge group graph structure: Based on the spatial positional relationship between different individual bridges in the bridge group, the edges between nodes are preliminarily defined. For temperature, humidity, and corrosion ion prediction, the edges are undirected. For wind speed and wind direction prediction, considering that wind direction has a significant impact on wind speed, the edges are directed. For traffic flow prediction, considering that traffic direction has a significant impact on the prediction results, the edges are directed. If only the overall traffic flow between the bridge group is of interest and the specific direction of the flow is not important, the edges can be set as undirected edges. The edge weight is determined by the traffic flow volume and the distance between the bridges.

[0062] Bridge group graph structure generation: The bridge group graph structure is represented by G = (V; E), where V is the set of bridge nodes and E is the set of edges. Based on the definitions of nodes and edges, a bridge group graph structure model is generated to determine the adjacency matrix A of the bridge group graph structure.

[0063] The schematic diagram of the bridge group structure model considering environmental effects and traffic flow is as follows: Figure 2 As shown in Figure 2, each bridge in a certain urban area (including different types of cable-stayed bridges, suspension bridges, beam bridges, arch bridges, etc.) is modeled as a node v in the graph, and the roads connecting the bridges are modeled as edges E between two nodes, forming a regional bridge group graph structure, where node v4 is a cable-stayed bridge, v6 is a beam bridge, v8 is a suspension bridge, and v 10 It is an arch bridge.

[0064] Step 2: Design a spatiotemporal graph prediction task based on the multi-source perception data of the service performance of a group of bridges, and construct the corresponding input and output datasets. The bridge group service performance prediction task is designed to take the historical monitoring data of temperature, humidity, wind speed, wind direction, and corrosion ion concentration environmental variables and traffic flow as input, and predict the future bridge group environmental effects and traffic flow as output. The multi-type, multi-scale, and multi-granularity multi-source perception dataset of the service performance of a group of bridges is embedded and represented as Where N is the number of bridges, T is the time step of the input data, and D is the feature dimension (including the total number of environmental variables such as temperature, humidity, wind speed, wind direction, and corrosive ion concentration studied, as well as the total number of traffic flow types); the corresponding output dataset embedding is expressed as Where T p is the time step of the predicted output data;

[0065] In step 2, for the spatiotemporal data of multi-type, multi-scale and multi-granular bridge group service performance, three different time granularities are used as input data, including recent data X r , periodic data X c and trend data X q ; Recent data is a historical time series directly adjacent to the forecast period. Periodic data consists of segments whose past days in the same time period as the forecast period are integer multiples of α. Trend data consists of segments whose past days in the same time period as the forecast period are integer multiples of β. Among them, the period window is expressed by variables α and β respectively, and the possible values ​​are: 1 for 1 day, 7 for 1 week, 30 for 1 month, 365 for 1 year, etc. Similar settings will not be stated one by one in the future. The length of the three types of input data, recent data, periodic data, and trend data (that is, the number of time steps T contained in each data segment) is set according to actual forecast needs to adapt to different forecast targets and historical data characteristics.

[0066] Recent data on service performance of bridge groups X r , periodic data X c and trend data X q The embedding representation of is as follows:

[0067] (1) Recent data:

[0068]

[0069] (2) Periodic data:

[0070]

[0071] (3) Trend data:

[0072]

[0073] Where f s is the sampling frequency of a certain type of sensory data analyzed within a day, t0 is the current time, and the prediction window size is T p ; The intercept length along the time axis is T r 、T c and T q The three time series segments are respectively used as recent data, periodic data and trend data, where T r 、T c and T q All T p An integer multiple of .

[0074] The relationship between the sampling time series of recent data, periodic data and trend data of the service performance of bridge groups is as follows: Figure 3 shown. Figure 3In the example, the sampling frequency of a service performance perception variable (such as temperature) of a bridge group is 48 times a day and the sampling interval is 30 minutes. p is a time step, T r 、T c and T q All T p twice as much.

[0075] Step 3: Establish a graph-selective state-space model for predicting the spatiotemporal correlation of the serviceability of bridge groups. This model consists of two modules: a spatiotemporal graph convolution module and a graph-selective state-space module. The spatiotemporal graph convolution module is used to learn the spatiotemporal correlation of the serviceability of bridge groups, while the graph-selective state-space module is used to learn the spatiotemporal evolution characteristics of the serviceability of bridge groups. The outputs of the two modules are weighted and fused through a fully connected layer to output the final prediction result.

[0076] The step three is specifically as follows:

[0077] Step 31: Establish a spatiotemporal graph convolution module;

[0078] The bridge group environmental effects and traffic flow data are passed through 1×1 convolution and then sequentially passed to the gated temporal convolution layer and the self-attention diffusion graph convolution layer. After residual connection with the input, the output is obtained after batch normalization.

[0079] In step 31,

[0080] Construct a gated temporal convolutional layer to learn the complex temporal dependencies of the bridge group service performance sequence data: the bridge group environmental effects and traffic flow data are input through a 1×1 convolution and then passed to the gated temporal convolutional layer:

[0081] Y=f(w1*X+b)⊙σ(w2*X+c) (4)

[0082] Where Y is the output of the gated temporal convolution of the bridge group environmental effects and traffic flow data input, w1, w2, b, and c are the parameters to be optimized; f is the tanh activation function, which transforms and extracts features from the bridge group environmental effects and traffic flow data input; σ is the sigmoid activation function, which outputs a gating weight between 0 and 1. The generated gating weight controls the proportion of information flow; ⊙ is element-by-element multiplication, w1*X+b represents convolutional layer 1, and w2*X+c represents convolutional layer 2.

[0083] Construct a self-attention diffusion graph convolution layer to learn the complex spatial dependencies of the service state sequence data of the bridge group: pass the output of the gated temporal convolution layer to the self-attention diffusion graph convolution layer:

[0084]

[0085] Where H is the output of the bridge group environmental effect and traffic flow data input after gated temporal convolution and self-attention diffusion graph convolution, and is the parameter to be optimized, and is the attention weight matrix of the bridge group graph structure, K is the number of diffusion steps, which is a hyperparameter and represents the diffusion process of K finite steps to simulate the service performance graph signal of the bridge group.

[0086] The attention weight matrix of the self-attention diffusion graph convolution layer of the spatiotemporal graph convolution module is calculated as follows:

[0087]

[0088] Where a k is the parameter matrix to be optimized; the propagation process of bridge group environmental effects and traffic flow data signals is divided into two directions, and the forward transformation matrix of bridge group environmental effects and traffic flow data signals is A f =A / rowsum(A), the inverse transformation matrix is ​​A b =A T / rowsum(A T ), Adaptive adjacency matrix of bridge group graph structure A k Represents the power level of the transformation matrix and the adaptive adjacency matrix. The columns are normalized during the operation and expressed as (·) / rowsum(·); the adaptive adjacency matrix The calculation of does not require prior knowledge and is end-to-end learned in the gradient descent process, thereby discovering the hidden spatial dependencies between the environmental effects of bridge groups and traffic flow data. The learnable parameters to be optimized are U, are two randomly initialized node embeddings; SoftMax represents the exponential normalization operation, and ReLU represents the rectified linear unit activation function.

[0089] Step 32: Establish a graph-selective state space module;

[0090] The recent data on the environmental effects of bridge groups and traffic flow are used to r After layer normalization, they are passed to m dynamic filter graph convolution layers respectively. The outputs of the m graph convolution layers are concatenated and passed through the linear layer. The output of the linear layer is divided into a core sequence and a secondary sequence. The core sequence is passed to the graph state space selection mechanism after one-dimensional convolution and SiLU activation. Its output is multiplied element-by-element with the SiLU activated secondary sequence. Finally, after passing through the linear layer, it is multiplied with the layer normalized X r Residual connection to get the final output;

[0091] Step 3: Combine the three time-granularity data X of bridge group environmental effects and traffic flow r 、X c and X q The fusion result output by N spatiotemporal graph convolution modules is connected to the input X r The outputs of the M graph-selective state-space modules are weighted and summed (the sum of the weighted coefficients of the two modules is equal to 1), and the result is passed through the fully connected layer to obtain the final output result.

[0092] In step 33, the output of each spatiotemporal graph convolution block is used as the input of the next spatiotemporal graph convolution block, and a total of N spatiotemporal graph convolution blocks are set; a residual connection is set in each spatiotemporal graph convolution block, and a jump connection is made with the output layer, specifically: the result of the gated time convolution in each spatiotemporal graph convolution block is processed by a 1×1 convolution, and then added to the result of the gated time convolution in the previous spatiotemporal graph convolution block by a jump connection; finally, the accumulation is passed to the output layer, which consists of an activation function and a linear layer, and outputs the operation result of the spatiotemporal graph convolution block.

[0093] In step 3, the outputs of the spatiotemporal graph convolution modules at three time granularities of the bridge group service performance are fused. The specific method is as follows:

[0094]

[0095] Where w r 、w c With w q is a learnable parameter to be optimized, is a scalar, and reflects the degree of influence of the three time granularity components on the spatiotemporal correlation prediction target of the service performance of bridge groups; and They represent the output of the spatiotemporal graph data of the bridge group service state after the spatiotemporal graph convolution block, Represents the output of the fused spatiotemporal graph convolution module.

[0096] Step 4: Based on the gradient descent error back propagation method, the graph-selective state space model is trained. The trained model is used to predict the spatiotemporal correlation between the environmental effects and traffic flow of the bridge group. A spatiotemporal correlation prediction system for the service performance of the bridge group is established.

[0097] Based on multi-source perception data of the service performance of bridge groups, including environmental effects (temperature, humidity, wind speed, wind direction, corrosive ion concentration, etc.) and traffic flow, a graph-selective state-space model for spatiotemporal correlation prediction of the service performance of bridge groups is trained. The trained model is used to predict the environmental effects and traffic flow of bridge groups in the future.

[0098] In step 4, a gradient descent-based optimization algorithm (including optimizers such as AdamW and SGD) is used to train the graph-selective state-space model for spatiotemporal correlation prediction of bridge group service performance. This ensures that the generated predicted values ​​of bridge group service performance data are as close as possible to the true values ​​of the actual perception data. The graph-selective state-space model for spatiotemporal correlation prediction is trained using supervised learning, and the mean squared error (MSE) is selected as the training objective function:

[0099]

[0100] Where, is the service performance of the bridge group in the future k steps predicted by the model, X (t+1):(t+k) is the actual service performance perception data of the bridge group in the future k steps; N is the number of bridges, k is the time step, and D is the feature dimension, including environmental variables such as temperature, humidity, wind speed, wind direction, and corrosion ion concentration, as well as traffic flow; B represents the batch size, λ is the regularization coefficient, and R(Θ) is the regularization term.

[0101] For the task of predicting the service performance of regional bridge groups, a service performance dataset of bridge group environmental effects (temperature, humidity, wind speed, wind direction, corrosive ion concentration, etc.) and traffic flow was constructed according to the above method. A spatiotemporal correlation prediction model for the service performance of bridge groups was trained based on gradient descent error back propagation. After training, the trained model was used to perform spatiotemporal correlation prediction of the environmental effects and traffic flow of bridge groups, and a spatiotemporal correlation prediction system for the service performance of bridge groups was established.

[0102] This paper proposes a spatiotemporal correlation prediction method for bridge group service performance based on a graph-selective state-space model. By capturing the complex spatiotemporal correlations and spatiotemporal evolution patterns inherent in bridge group service performance data, it aims to improve the accuracy and versatility of bridge group service performance prediction. The innovations are:

[0103] (1) Using a spatiotemporal graph structure, a spatiotemporal graph fusion learning module is constructed, combining graph neural networks with deep learning of time series data, while considering the data characteristics of the service performance of bridge groups in both spatial and temporal dimensions to more accurately model and predict the dynamic spatiotemporal evolution of bridge group systems;

[0104] (2) Using a state-space model, we construct a structured state-space sequence and introduce a selective mechanism to dynamically adjust the model behavior and optimize the use of computing resources;

[0105] (3) By decomposing and fusing the spatiotemporal characteristics of service performance data of different complexities, the method can better adapt to the processing requirements of spatiotemporal service performance data of multi-type, multi-scale, and multi-granular bridge groups, thereby improving the versatility and prediction efficiency of the method.

[0106] The present invention also proposes an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for predicting the spatiotemporal correlation of the service performance of a group of bridges based on a graph selective state space model are implemented.

[0107] The present invention also proposes a computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the steps of the method for predicting the spatiotemporal correlation of the service performance of a group of bridges based on a graph-selective state space model.

[0108] The memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus RAM (DRRAM). It should be noted that the memory of the methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0109] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a high-density digital video disc (DVD)), or a semiconductor medium (eg, a solid state disc (SSD)).

[0110] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor or by instructions in the form of software. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it will not be described in detail here.

[0111] It should be noted that the processor in the embodiments of the present application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by an integrated logic circuit of the hardware in the processor or by instructions in the form of software. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0112] The above is a detailed introduction to the spatiotemporal correlation prediction method for the service performance of a bridge group based on a graph-selective state-space model proposed in the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A spatiotemporal correlation prediction method for service performance of bridge groups based on a graph-selective state space model, characterized by: The method comprises the following steps: Step 1: Determine the bridge group task object to be studied and establish a bridge group graph structure model that considers the effects of urban area environment and traffic flow; Step 2: Design a spatiotemporal graph prediction task based on the multi-source perception data of the service performance of a group of bridges, and construct the corresponding input and output datasets. The bridge group service performance prediction task is designed to take the historical monitoring data of temperature, humidity, wind speed, wind direction, and corrosion ion concentration environmental variables and traffic flow as input, and predict the future bridge group environmental effects and traffic flow as output. The multi-type, multi-scale, and multi-granularity multi-source perception dataset of the service performance of a group of bridges is embedded and represented as Where N is the number of bridges, T is the input data time step, and D is the feature dimension; the corresponding output dataset embedding is expressed as Where T p is the time step of the predicted output data; Step 3: Establish a graph-selective state-space model for predicting the spatiotemporal correlation of the serviceability of bridge groups. This model consists of two modules: a spatiotemporal graph convolution module and a graph-selective state-space module. The spatiotemporal graph convolution module is used to learn the spatiotemporal correlation of the serviceability of bridge groups, while the graph-selective state-space module is used to learn the spatiotemporal evolution characteristics of the serviceability of bridge groups. The outputs of the two modules are weighted and fused through a fully connected layer to output the final prediction result. Step 4: Based on the gradient descent error back propagation, the graph selective state space model is trained and the trained model is used to predict the spatiotemporal correlation between the environmental effects of the bridge group and the traffic flow.

2. The method according to claim 1, characterized in that In step 1, the graph structure model is established as follows: Node definition of the bridge group graph structure: Each bridge is considered as a node in the graph, and the node attributes include temperature, humidity, wind speed, wind direction, corrosion ion concentration, environmental variables and traffic flow; Edge definition of the bridge group graph structure: Based on the spatial position relationship between different individual bridges in the bridge group, the edges between nodes are preliminarily defined; for temperature, humidity, and corrosion ion predictions, the edges are undirected; for wind speed and direction predictions, the edges are directed; for traffic flow predictions, the edges are directed, and the edge weights are determined based on the traffic flow size and the distance between bridges. Bridge group graph structure generation: The bridge group graph structure is represented by G = (V; E), where V is the set of bridge nodes and E is the set of edges. Based on the definitions of nodes and edges, a bridge group graph structure model is generated to determine the adjacency matrix A of the bridge group graph structure.

3. The method according to claim 2, characterized in that In step 2, for the spatiotemporal data of multi-type, multi-scale and multi-granular bridge group service performance, three different time granularities are used as input data, including recent data X r , periodic data X c and trend data X q ; Recent data is a historical time series directly adjacent to the forecast period, periodic data consists of segments whose past days in the same time period as the forecast period are integer multiples of α, and trend data consists of segments whose past days in the same time period as the forecast period are integer multiples of β; the lengths of the three types of input data, recent data, periodic data, and trend data, are set according to actual forecast needs to adapt to different forecast targets and historical data characteristics.

4. The method according to claim 3, characterized in that The step three is specifically as follows: Step 31: Establish a spatiotemporal graph convolution module; The bridge group environmental effects and traffic flow data are passed through 1×1 convolution and then sequentially passed to the gated temporal convolution layer and the self-attention diffusion graph convolution layer. After residual connection with the input, the output is obtained after batch normalization. Step 32: Establish a graph-selective state space module; The recent data on the environmental effects of bridge groups and traffic flow are used to r After layer normalization, they are passed to m dynamic filter graph convolution layers respectively. The outputs of the m graph convolution layers are concatenated and passed through the linear layer. The output of the linear layer is divided into a core sequence and a secondary sequence. The core sequence is passed to the graph state space selection mechanism after one-dimensional convolution and SiLU activation. Its output is multiplied element-by-element with the SiLU activated secondary sequence. Finally, after passing through the linear layer, it is multiplied with the layer normalized X r Residual connection to get the final output; Step 3: Combine the three time-granularity data X of bridge group environmental effects and traffic flow r 、X c and X q The fusion result output by N spatiotemporal graph convolution modules is connected to the input X r The outputs of the M graph-selective state-space modules are weighted and summed, and the results are passed through the fully connected layer to obtain the final output.

5. The method according to claim 4, characterized in that In step 31, Construct a gated temporal convolutional layer to learn the complex temporal dependencies of the bridge group service performance sequence data: the bridge group environmental effects and traffic flow data are input through a 1×1 convolution and then passed to the gated temporal convolutional layer: Y=f(w1*X+b)⊙σ(w2*X+c) (4) Where Y is the output of the gated temporal convolution of the bridge group environmental effects and traffic flow data input, w1, w2, b, and c are the parameters to be optimized; f is the tanh activation function, which transforms and extracts features from the bridge group environmental effects and traffic flow data input; σ is the sigmoid activation function, which outputs a gating weight between 0 and 1. The generated gating weight controls the proportion of information flow; ⊙ is element-by-element multiplication, w1*X+b represents convolutional layer 1, and w2*X+c represents convolutional layer 2; Construct a self-attention diffusion graph convolution layer to learn the complex spatial dependencies of the service state sequence data of the bridge group: pass the output of the gated temporal convolution layer to the self-attention diffusion graph convolution layer: Where H is the output of the bridge group environmental effect and traffic flow data input after gated temporal convolution and self-attention diffusion graph convolution, and is the parameter to be optimized, and is the attention weight matrix of the bridge group graph structure, K is the number of diffusion steps, which is a hyperparameter and represents the diffusion process of K finite steps to simulate the service performance graph signal of the bridge group.

6. The method according to claim 5, characterized in that The attention weight matrix of the self-attention diffusion graph convolution layer of the spatiotemporal graph convolution module is calculated as follows: Where a k is the parameter matrix to be optimized; the propagation process of bridge group environmental effects and traffic flow data signals is divided into two directions, and the forward transformation matrix of bridge group environmental effects and traffic flow data signals is A f =A / rowsum(A), the inverse transformation matrix is ​​A b =A T / rowsum(A T ), Adaptive adjacency matrix of bridge group graph structure A k Represents the power level of the transformation matrix and the adaptive adjacency matrix. The columns are normalized during the operation and expressed as (·) / rowsum(·); the adaptive adjacency matrix The calculation of does not require prior knowledge and is end-to-end learned in the gradient descent process, thereby discovering the hidden spatial dependencies between the environmental effects of bridge groups and traffic flow data. The learnable parameters to be optimized are U, are two randomly initialized node embeddings; SoftMax represents the exponential normalization operation, and ReLU represents the rectified linear unit activation function.

7. The method according to claim 6, characterized in that In step 33, the output of each spatiotemporal graph convolution block is used as the input of the next spatiotemporal graph convolution block, and a total of N spatiotemporal graph convolution blocks are set; a residual connection is set in each spatiotemporal graph convolution block, and a jump connection is made with the output layer. Specifically, the result of the gated temporal convolution in each spatiotemporal graph convolution block is processed by a 1×1 convolution, and then added to the result of the gated temporal convolution in the previous spatiotemporal graph convolution block by a jump connection; Finally, the accumulation is passed to the output layer, which consists of an activation function and a linear layer, and outputs the operation results of the spatiotemporal graph convolution block.

8. The method according to claim 7, characterized in that In step 3, the outputs of the spatiotemporal graph convolution modules at three time granularities of the bridge group service performance are fused. The specific method is as follows: Where w r 、w c With w q is a learnable parameter to be optimized, is a scalar, and reflects the degree of influence of the three time granularity components on the spatiotemporal correlation prediction target of the service performance of bridge groups; and They represent the output of the spatiotemporal graph data of the bridge group service state after the spatiotemporal graph convolution block, Represents the output of the fused spatiotemporal graph convolution module.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium for storing computer instructions, characterized in that: When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images