Shear wall design method based on graph node classification graph neural network

Abstract

The invention discloses a shear wall design method based on a graph node classification graph neural network, and particularly relates to the technical field of graph node classification. Symmetrical node pairs in the shear wall are identified through geometric coordinates and connection relations and marked in a graph structure, then shear response data of the nodes under a horizontal load and material creep data caused by stress differences under a long-term load are obtained and converted into feature vectors, the feature vectors are input into a machine learning model for training, and the shear response data and the material creep data are obtained. Judging the accuracy of stress distribution prediction, dividing symmetric nodes into accurate, possibly accurate and inaccurate prediction results according to prediction results, extracting local sub-graphs for the possibly accurate nodes, and dynamically adjusting edge weights according to the degree of abnormal prediction so as to further optimize the model prediction precision; through accurate identification and dynamic optimization of the symmetric nodes, the problem of inaccurate prediction of the mechanical performance of the symmetric nodes of the shear wall in the prior art is effectively solved, and the prediction precision and design reliability of the model are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of graph node classification, and in particular to a shear wall design method based on a graph node classification graph neural network. Background Art

[0002] The use of graph neural networks based on graph node classification for shear wall design refers to modeling the mechanical properties of building structures (such as shear walls) as graph structures, where nodes represent key points or components of shear walls, and edges represent the connection relationship or mechanical action between them. By applying graph neural networks (GNNs), nodes can be classified, their mechanical properties, stress distribution, or other structural behaviors can be predicted, and the design of shear walls can be optimized.

[0003] In the prior art, graph neural networks based on graph node classification are used in shear wall design. First, the shear wall structure is modeled as a graph structure, where nodes represent key points or components of the shear wall, and edges represent the mechanical relationship between components. Next, data on the mechanical properties of the structure are collected and input into the graph neural network model as node features. Subsequently, the graph neural network is used to classify the nodes and predict their mechanical performance or stress distribution. Finally, the shear wall is optimized based on the classification results to identify structural weaknesses and enhance overall performance.

[0004] The prior art has the following deficiencies:

[0005] In the prior art, when using graph neural network models to classify nodes and predict their stress distribution, for certain symmetrical parts of shear walls (such as left-right symmetrical wall parts), GNN may not be able to effectively distinguish the mechanical performance of these symmetrical nodes. Even if these nodes actually carry different loads or stress conditions, the model may treat them as the same nodes, thereby producing the same prediction results. And because symmetrical structures are often related to critical mechanical balance, if the symmetry problem is not handled properly, it may lead to misjudgment of key nodes, which in turn may cause weak links in the design to be ignored, especially when boundary conditions or loads are complex, the error may be amplified. Summary of the invention

[0006] The purpose of the present invention is to provide a shear wall design method based on graph node classification graph neural network to solve the shortcomings of the background technology.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a shear wall design method based on graph node classification graph neural network, comprising the following steps:

[0008] S1: Determine whether the node pairs in the shear wall structure are symmetrical by comparing the geometric coordinates and the connection relationship, mark the symmetrical node pairs identified in the shear wall structure, and construct the graph structure of the shear wall to keep the symmetrical node pairs in the same graph;

[0009] S2: After identifying the symmetrical nodes, obtain the horizontal shear response data of the symmetrical nodes of the wall under horizontal loads, as well as the material creep data generated based on the stress difference of the symmetrical nodes under long-term loads;

[0010] S3: Convert the acquired horizontal shear response data and material creep data into feature vectors, use the feature vectors as inputs of the machine learning model, train the machine learning model, and determine the accuracy of the prediction results of the symmetrical node stress distribution based on the model output results;

[0011] S4: classifying the accuracy of the prediction results of the stress distribution of the symmetric nodes into different levels, namely, accurate prediction results, possibly accurate prediction results and inaccurate prediction results;

[0012] S5: For accurate prediction results, the stress distribution of the node is directly used as the reference for shear wall design; for inaccurate prediction results, the local graph structure of the symmetrical node is retrained;

[0013] S6: From the overall shear wall graph, extract each node that may accurately predict the result and its direct neighbor nodes, construct a local subgraph, and dynamically adjust the edge weights according to the abnormal degree of the accuracy of the prediction results of the stress distribution of the symmetric nodes.

[0014] Preferably, in S2, a shear response anomaly index is generated according to the shear force data at the extracted symmetric nodes, wherein the shear response deviation index is obtained by:

[0015] Extract the shear response data of all symmetrical nodes in the shear wall and construct a feature matrix. The feature matrix of the shear response data of each symmetrical node i is as follows: the shear response τ of node i in the horizontal shear direction i,xy and the shear response τ of node i in the vertical shear direction i,xz , the shear response eigenvector f of each node i i is: f i =[τ i,xy ,τ i,xz ]; for N nodes, form a feature matrix X, X = [f1, f2, ..., f N ] T ; Where X is an N×d-dimensional matrix, d is the dimension of the feature, T is the matrix transpose, and it is standardized. For the standardized feature matrix X′, its covariance matrix C is calculated, and the expression is: Among them, C is a d×d dimensional matrix, which represents the covariance between the shear response characteristics. The covariance matrix C is subjected to eigenvalue decomposition to obtain the eigenvalues ​​λ1,λ2,…,λ d and the corresponding eigenvectors v1,v2,…,v d ; The eigenvalue represents the variance contribution in the direction of each principal component, while the eigenvector represents the direction of the principal component. The expression is: Cv i =λ i v i ; Among them, the eigenvalue λ i represents the importance of the i-th principal component, v i is the corresponding eigenvector, and the principal components v1, v2, …, v corresponding to the first g largest eigenvalues ​​are selected. g To reduce the dimension, the original feature vector f i Project it into the principal component space, and reconstruct the approximate value Sf of the original eigenvector through the principal component vector. i , calculate the difference between the original eigenvector and the reconstructed eigenvector, that is, calculate the shear response deviation index, the expression is: HK = || f i -Sf i ||2; where HK is the shear response deviation index.

[0016] Preferably, the creep rate anomaly index is generated after analyzing the creep rate of each node under long-term load, and the method for obtaining the creep rate anomaly index is:

[0017] Construct the creep rate feature vector of each node. For each node, its creep rate vector Q i Contains creep rates at multiple times: in: Node i at time t n The creep rate of n is the number of time points. For N nodes, an N×n creep rate matrix Y is constructed. The Euclidean distance between each node is calculated. For node i and node j, the Euclidean distance d(i, j) is: Where d(i,j) represents the Euclidean distance between the creep rate feature vectors of nodes i and j. For each node i, a parameter k is selected to represent the number of nearest neighbor nodes to be considered. The k-distance d of node i is k (i refers to the distance from node i to its kth nearest neighbor node: Among them, N i Represents the k nearest neighbor nodes of node i, d(i,j) is the Euclidean distance from node i to node j, and calculates the reach-dist of node i to node j k (i,j), the expression is: Reach-dist k (i,j)=max{dk (j), d(i, j)}; Calculate the local reachability density. The local reachability density of node i is the average LRD of the reciprocal of its reachability distance to its nearest neighbor node. k (i) The creep rate anomaly index is calculated based on the average value of the inverse of the calculated reachable distance, and the expression is: Where, LRD k (j) is the local reachability density of node j, LRD k (i) is the local reachability density of node i, and KM is the creep rate anomaly index.

[0018] Preferably, in S3, the acquired horizontal shear response data and material creep data are converted into feature vectors, the feature vectors are used as inputs of the machine learning model, the machine learning model is trained, and the accuracy of the prediction results of the symmetric node stress distribution is determined according to the model output results, specifically:

[0019] The shear response deviation index and the creep rate anomaly index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses the accuracy value label of the symmetric node stress distribution prediction results predicted by each group of first eigenvectors as the prediction target, and minimizes the sum of the prediction errors of the accuracy value labels of all symmetric node stress distribution prediction results as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The accuracy value of the symmetric node stress distribution prediction results is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0020] Preferably, in S4, the accuracy of the prediction results of the stress distribution of the symmetric nodes is divided into different levels, namely, accurate prediction results, possibly accurate prediction results and inaccurate prediction results, specifically:

[0021] The obtained accuracy value of the symmetric node stress distribution prediction result is compared with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the accuracy value of the symmetric node stress distribution prediction result is compared with the first standard threshold and the second standard threshold respectively;

[0022] If the accuracy value of the symmetric node stress distribution prediction result is greater than the second standard threshold value, it means that the accuracy of the symmetric node stress distribution prediction result is high, and a high accuracy signal is generated at this time, and the symmetric node stress distribution prediction result under which the high accuracy signal is generated is classified as an accurate prediction result;

[0023] If the accuracy value of the symmetric node stress distribution prediction result is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the accuracy of the symmetric node stress distribution prediction result is general, and a medium accuracy signal is generated at this time, and the symmetric node stress distribution prediction result under the medium accuracy signal is classified as a possible accurate prediction result;

[0024] If the accuracy value of the symmetric node stress distribution prediction result is less than the first standard threshold, it means that the accuracy of the symmetric node stress distribution prediction result is low. At this time, a low accuracy signal is generated, and the symmetric node stress distribution prediction result under the low accuracy signal is classified as an inaccurate prediction result.

[0025] Preferably, in S6, each node that may accurately predict the result and its direct neighbor nodes are extracted from the overall shear wall diagram, a local subgraph is constructed, and the edge weights are dynamically adjusted according to the abnormal degree of the accuracy of the prediction results of the symmetric node stress distribution, specifically:

[0026] Symmetric node i is a node that may accurately predict the result. The node and its direct neighbor nodes are extracted to form a local subgraph. The node set V of the local subgraph is i Includes: V i ={i}∪{j| ( i,j ) ∈E}; where E is the edge set of the graph, and j is the neighbor node directly connected to node i;

[0027] In the local subgraph, the initial weight of each edge (i, j) is defined according to the geometric distance. is a fixed value, and the expression is: Where d(i,j) is the measure of the geometric distance between nodes i and j;

[0028] If the accuracy value of the symmetric node stress distribution prediction result is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the symmetric node stress distribution prediction result under the generated medium accuracy signal is divided into possible accurate prediction results, and the accuracy values ​​of the symmetric node stress distribution prediction results generated in the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected and the corresponding data set is established, and the standard deviation of the data set is calculated as the abnormality degree of stress distribution prediction, marked as A(i); the prediction accuracy adjustment factor α(i) of node i is defined according to A(i), which is negatively correlated with A(i), and the expression is: α ( i ) =1-A ( i ) ; Among them, α(i)∈[0,1], represents the accuracy of node prediction.

[0029] Preferably, in a local subgraph, the edge weight According to the dynamic adjustment of the abnormal degree of the stress distribution prediction result of the node, the edge weight is dynamically adjusted as follows by combining the prediction accuracy adjustment factor α(i) of node i and its neighbor node j: is the adjusted edge weight; after dynamically adjusting the edge weight, the weight matrix of the local subgraph is updated.

[0030] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0031] 1. The present invention compares the geometric coordinates and connection relationships of the nodes, marks the symmetrical nodes and obtains detailed shear response and creep data, further constructs feature vectors and inputs them into the machine learning model for training and accuracy prediction. The model output results not only improve the prediction accuracy of the node stress distribution, but also provide a more accurate reference for the shear wall structure design by grading the prediction results, especially in the case of complex boundary conditions, reducing misjudgment and improving the reliability of the structural design.

[0032] 2. The present invention can effectively improve the processing accuracy of nodes that may be accurately predicted by dynamically adjusting the edge weights in the local graph structure, ensuring that the model performs refined prediction and optimization around nodes with greater uncertainty. This solution dynamically adjusts the edge weights by analyzing the abnormalities of creep rate and shear response, which not only improves the retraining effect of inaccurate nodes, but also reduces the risk of potential weak links in the overall shear wall structure design, thereby greatly enhancing the overall mechanical resistance and long-term structural stability of the shear wall. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0034] Figure 1 The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] For examples, see Figure 1 As shown, the shear wall design method based on graph node classification graph neural network described in this embodiment includes the following steps:

[0037] S1: Determine whether the node pairs in the shear wall structure are symmetrical by comparing the geometric coordinates and the connection relationship, mark the symmetrical node pairs identified in the shear wall structure, and construct the graph structure of the shear wall to keep the symmetrical node pairs in the same graph;

[0038] S2: After identifying the symmetrical nodes, obtain the horizontal shear response data of the symmetrical nodes of the wall under horizontal loads, as well as the material creep data generated based on the stress difference of the symmetrical nodes under long-term loads;

[0039] S3: Convert the acquired horizontal shear response data and material creep data into feature vectors, use the feature vectors as inputs of the machine learning model, train the machine learning model, and determine the accuracy of the prediction results of the symmetrical node stress distribution based on the model output results;

[0040] S4: classifying the accuracy of the prediction results of the stress distribution of the symmetric nodes into different levels, namely, accurate prediction results, possibly accurate prediction results and inaccurate prediction results;

[0041] S5: For accurate prediction results, the stress distribution of the node is directly used as the reference for shear wall design; for inaccurate prediction results, the local graph structure of the symmetrical node is retrained;

[0042] S6: From the overall shear wall graph, extract each node that may accurately predict the result and its direct neighbor nodes, construct a local subgraph, and dynamically adjust the edge weights according to the abnormal degree of the accuracy of the prediction results of the stress distribution of the symmetric nodes.

[0043] Among them, in S1, the symmetry of the node pairs in the shear wall structure is determined by comparing the geometric coordinates and the connection relationship, the symmetric node pairs identified in the shear wall structure are marked, and the graph structure of the shear wall is constructed to retain the symmetric node pairs in the same graph.

[0044] First, it is necessary to obtain the geometric coordinates of all nodes in the shear wall structure. Geometric coordinates usually include the three-dimensional spatial position of each node, such as (x, y, z) coordinates. For shear wall design, common node coordinate information is generally two-dimensional plane coordinates (x, y) because shear walls are usually located in the building plane. Extract the geometric coordinate information of each node from the design model (such as a CAD model or a finite element model). If a finite element model is used, software such as ABAQUS, ANSYS, or ETABS can export the coordinate data of the structural nodes. The nodes and their geometric coordinate information are stored in a matrix form [N×2], where N is the number of nodes and the coordinates are the x and y values, respectively.

[0045] In graph neural networks, nodes are connected by edges, which represent mechanical associations or physical connections between components. Therefore, it is necessary to clarify the connection relationship between nodes in the shear wall structure. Node connections can usually reflect the force transmission path. Construct the adjacency matrix A of the nodes, where A[i,j]=1 means that there is a connection between node i and node j, and A[i,j]=0 means there is no connection. The connection relationship can be determined based on the topology of the structural diagram, which is usually exported by the design software or generated based on the meshing of the finite element method. The adjacency matrix can be generated and processed using a graph processing library such as NetworkX or DGL to ensure that the node connection relationship correctly reflects the mechanical connection.

[0046] Use the node's geometric coordinates and connection relationships to identify symmetrical node pairs in shear walls. Symmetric node pairs usually have the same geometric features (such as the axis of symmetry relative to the wall) and similar connection relationships. For symmetrical nodes, the geometric coordinates usually reflect their mirror image relationship on the axis of symmetry.

[0047] For example, assuming that the shear wall is symmetrical along the x-axis, the following conditions can be used to determine whether nodes i and j are symmetrical:

[0048] xi=-xj and yi=yj;

[0049] By comparing the geometric coordinates, find the node pairs that satisfy the above symmetry relationship.

[0050] After the geometric symmetry is judged, the similarity of these symmetric nodes is further verified through the connection relationship. Ideally, symmetric nodes should have similar connection topology (the distribution and connection strength of adjacent nodes should be similar). For each pair of geometrically symmetric nodes, check the connection in their adjacency matrix, that is, check whether their direct neighbors maintain a symmetric relationship with the neighbors of their geometrically symmetric points. For example, if node i and node j are identified as geometrically symmetric nodes, check whether the neighbor nodes ik and jk of the symmetric node pair also satisfy the symmetry. If not, it can be considered that the node pair does not meet the symmetry requirements.

[0051] The identified symmetric node pairs are retained in the overall graph structure of the shear wall. The constructed graph needs to reflect the geometric position, connection relationship and symmetry relationship of each node in the shear wall. Use graph processing tools such as NetworkX or DGL to import all nodes and their connection relationships into the graph. Add special marks to symmetric node pairs, such as assigning labels to symmetric node pairs through node attributes, so as to distinguish symmetric nodes from asymmetric nodes in subsequent model training. In the constructed graph, the feature vector of each node includes not only basic geometric information and connection information, but also symmetry relationships (such as "symmetric" or "asymmetric" labels). Visualize the constructed graph, check the distribution of symmetric node pairs in the graph, and verify whether the geometric symmetry and connection relationship are accurately reflected in the graph structure. Visualization tools such as Matplotlib and NetworkX's drawing function can be used to display nodes and connections. The verification process includes manually checking several important node pairs to ensure that their symmetry is correctly identified.

[0052] In this application, the symmetry of the node pairs in the shear wall structure is determined by geometric coordinates and connection relationships, and the symmetric nodes are marked to construct a shear wall structure containing symmetric nodes. This process ensures that the graph neural network can correctly identify and process symmetric nodes, so that the symmetry factor is considered when predicting the mechanical performance of the nodes, avoiding misjudgment of key nodes and improving prediction accuracy.

[0053] S2: After identifying the symmetrical nodes, obtain the horizontal shear response data of the symmetrical nodes of the wall under horizontal loads, as well as the material creep data generated based on the stress difference of the symmetrical nodes under long-term loads.

[0054] In building structures (such as shear walls), horizontal loads usually include wind loads, earthquake effects, external impacts, etc. These loads will exert lateral forces on the wall and generate horizontal shear forces. Horizontal shear refers to the force parallel to the plane of the wall, which will induce different force responses at symmetrical nodes. Determine the source and intensity of horizontal loads. For example, for seismic design, horizontal loads can be defined based on seismic parameters (such as peak acceleration, peak velocity, etc.); for wind loads, horizontal forces can be defined based on wind speed and wind pressure. Determine the direction and location of the load. Horizontal loads are usually applied in a direction parallel to the wall and can act on the top of the wall, around the opening, or on the entire structure.

[0055] Use a finite element model (FEM) to simulate the mechanical response of shear walls under horizontal loads. FEM can accurately calculate the stress, strain, and shear force at each node under external loads. Use finite element analysis software (such as ABAQUS, ANSYS, or ETABS) to build a three-dimensional or two-dimensional model of the shear wall. Define the material properties of the nodes, boundary conditions (such as the fixed relationship between the wall and the foundation), and set the load conditions. At the symmetrical node positions, define the displacement boundary conditions of the structure to ensure that the model reasonably reflects the actual engineering conditions. Apply horizontal loads to the wall structure. The applied loads can be static loads with linear growth or loads based on dynamic conditions, such as time-varying loads to simulate earthquakes.

[0056] Run the finite element simulation to calculate the horizontal shear response of each symmetric node under the load. The shear force can be obtained through the force matrix or stress components of the node, which represent the shear stress of the node in the horizontal plane. Use the software's result processing tools (such as ABAQUS's "Field Output" or ANSYS's "Postprocessing" tool) to directly extract the shear data at the symmetric nodes. At this time, the focus is on extracting the shear response of the symmetric nodes.

[0057] The shear response anomaly index is generated according to the shear data at the extracted symmetric nodes, wherein the shear response deviation index is obtained as follows:

[0058] Extract the shear response data of all symmetrical nodes in the shear wall and construct a feature matrix. The feature matrix of the shear response data of each symmetrical node i is as follows: the shear response τ of node i in the horizontal shear direction i,xy and the shear response τ of node i in the vertical shear direction i,xz , the shear response eigenvector f of each node i i is: f i =[τ i,xy ,τ i,xz ]; for N nodes, form a feature matrix X, X = [f1, f2, ..., f N ] T ; Where X is an N×d-dimensional matrix, d is the dimension of the feature, T is the matrix transpose, and it is standardized. For the standardized feature matrix X′, its covariance matrix C is calculated, and the expression is: Among them, C is a d×d dimensional matrix, which represents the covariance between the shear response characteristics. The covariance matrix C is subjected to eigenvalue decomposition to obtain the eigenvalues ​​λ1,λ2,…,λ d and the corresponding eigenvectors (i.e. principal components) v1, v2,…, v d ; The eigenvalue represents the variance contribution in the direction of each principal component, while the eigenvector represents the direction of the principal component. The expression is: Cv i=λ i v i ; Among them, the eigenvalue λ i represents the importance of the i-th principal component, v i is the corresponding eigenvector. In order to capture the main shear response characteristics, the principal components v1, v2, …, v corresponding to the first g largest eigenvalues ​​are selected. g To reduce the dimension, the original feature vector f i Project it into the principal component space, and reconstruct the approximate value Sf of the original eigenvector through the principal component vector. i , calculate the difference between the original eigenvector and the reconstructed eigenvector, that is, calculate the shear response deviation index, the expression is: HK = || f i -Sf i ||2; where HK is the shear response deviation index.

[0059] When the shear response deviation index is larger, it means that the stress distribution of the symmetrical nodes deviates greatly from the predicted results, indicating that the model's prediction of the stress distribution of these nodes is inaccurate. This deviation may mean that the node has abnormal behavior under actual stress conditions, such as stress concentration or material property differences, and the model fails to correctly capture these changes. Therefore, a larger shear response deviation index indicates that these nodes should be further paid attention to, and reinforcement design or model readjustment may be needed to improve the prediction accuracy.

[0060] On the contrary, when the shear response deviation index is smaller, it means that the actual stress distribution of the symmetrical nodes is very close to the model prediction results, indicating that the model's prediction results at these nodes have a high accuracy. This means that the model can effectively capture the mechanical differences and stress states between symmetrical nodes, and the prediction results are relatively reliable. At this point, it can be considered that the stress distribution of these nodes is reasonable and can be directly used for the design and evaluation of shear wall structures without additional corrections.

[0061] In building structures, shear walls are usually subjected to long-term loads such as deadweight, dead loads, and service loads. These loads will produce continuous stress on the materials of the shear walls (such as concrete, steel bars, etc.), and over time, the materials will creep. Creep is the gradual permanent deformation of materials under constant stress over time, usually manifested in three stages: initial stage (rapid deformation), secondary stage (slow, steady deformation) and final stage (accelerated deformation, material may fail). Symmetrical nodes may experience different creep behaviors if they are subjected to different stress states.

[0062] Use finite element analysis (such as ABAQUS, ANSYS and other software) to simulate creep behavior under long-term loads. Input the creep characteristics of the material into the simulation model, and based on creep theory and empirical formulas (such as Norton-Bailey, Findley creep model), the creep data of the symmetrical nodes of the shear wall under long-term loads can be calculated. Common creep equations can describe the law of creep strain changing with time. For example, the Norton-Bailey creep model can be expressed as: ∈ c( t ) =∈0+A·t n ; where ∈ c( t ) is the creep strain, ∈0 is the initial strain, A is the material constant, n is the creep exponent, and t is the time.

[0063] By extracting the stress state of each symmetric node (such as axial force, bending moment, shear force, etc.), the stress difference is calculated. Assume that the stress of symmetric nodes i and j is σ i and σ j , stress difference Δσ ij It can be defined as: Δσ ij =|σ i -σ j |; Combined with the stress difference, the creep model of the material is used to calculate the creep rate of each node under long-term load.

[0064] After analyzing the creep rate of each node under long-term load, the creep rate anomaly index is generated. The method for obtaining the creep rate anomaly index is as follows:

[0065] Construct the creep rate feature vector of each node. For each node, its creep rate vector Q i Contains creep rates at multiple times: in: Node i at time t n The creep rate of n is the number of time points. For N nodes, an N×n creep rate matrix Y is constructed; the Euclidean distance between each node is calculated, which is used to measure the difference in creep rate between different nodes. For node i and node j, their Euclidean distance d(i,j) is: Where d(i,j) represents the Euclidean distance between the creep rate feature vectors of nodes i and j. For each node i, a parameter k (usually 5 or 10) is selected to represent the number of nearest neighbor nodes to be considered. The k-distance d of node i is k (i) refers to the distance from node i to its kth nearest neighbor: Among them, N iRepresents the k nearest neighbor nodes of node i, d(i,j) is the Euclidean distance from node i to node j, and Reach-dist is calculated for the reachable distance of node i relative to node j k (i,j), the expression is: Reach-dist k (i,j)=max{d k (j), d(i, j)}; the reachable distance is the larger value between the k-distance of node j and the distance from node i to node j. The purpose is to prevent misjudgment caused by the small distance between some data points and their neighbors. The local reachable density of node i is the average LRD of the reciprocal of its reachable distance to its nearest neighbor node. k (i) The creep rate anomaly index is calculated based on the average value of the inverse of the calculated reachable distance, and the expression is: Where, LRD k ( j) is the local reachability density of node j, LRD k (i) is the local reachability density of node i, and KM is the creep rate anomaly index.

[0066] When the creep rate anomaly index is larger, it means that the creep rate of the node is significantly different from that of its neighboring nodes under long-term load. This usually indicates that the model has a large deviation in the stress distribution prediction of these nodes. Nodes with large creep rate anomaly index may be subjected to excessive stress concentration, material aging, or increased local deformation in practice, and the model fails to fully capture these complex mechanical effects. Therefore, a larger anomaly index indicates that the prediction results are less accurate, and further analysis or model adjustment is required for these nodes.

[0067] On the contrary, when the creep rate anomaly index is smaller, it means that the creep rate of the node is very close to that of its neighboring nodes, which is consistent with the model's prediction of the stress distribution under long-term load. This means that the model can effectively capture the stress changes and creep behavior of the nodes, and the prediction results are relatively accurate. At this time, the nodes with small anomaly index are considered to be normal, indicating that the model's prediction results of the stress distribution of these nodes are relatively reliable and do not need further adjustment.

[0068] S3: Convert the acquired horizontal shear response data and material creep data into feature vectors, use the feature vectors as inputs of the machine learning model, train the machine learning model, and determine the accuracy of the prediction results of the symmetric node stress distribution based on the model output results.

[0069] The shear response deviation index and the creep rate anomaly index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses the accuracy value label of the symmetric node stress distribution prediction result predicted by each group of first eigenvectors as the prediction target, and minimizes the sum of the prediction errors of the accuracy value labels of all symmetric node stress distribution prediction results as the training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The accuracy value of the symmetric node stress distribution prediction result is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0070] The method for obtaining the accuracy value of the prediction result of the stress distribution of the symmetrical node is as follows: from the first eigenvector training data of the trained machine learning model, the corresponding function expression is obtained: KR=F(HK, KM); wherein F is the output function of the model, HK is the shear response deviation index, KM is the creep rate anomaly index, and KR is the accuracy value of the prediction result of the stress distribution of the symmetrical node.

[0071] S4: The accuracy of the prediction results of the stress distribution of the symmetric nodes is divided into different levels, namely, accurate prediction results, possibly accurate prediction results and inaccurate prediction results.

[0072] The obtained accuracy value of the symmetric node stress distribution prediction result is compared with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the accuracy value of the symmetric node stress distribution prediction result is compared with the first standard threshold and the second standard threshold respectively;

[0073] If the accuracy value of the symmetric node stress distribution prediction result is greater than the second standard threshold value, it means that the accuracy of the symmetric node stress distribution prediction result is high, and a high accuracy signal is generated at this time, and the symmetric node stress distribution prediction result under which the high accuracy signal is generated is classified as an accurate prediction result;

[0074] If the accuracy value of the symmetric node stress distribution prediction result is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the accuracy of the symmetric node stress distribution prediction result is general, and a medium accuracy signal is generated at this time, and the symmetric node stress distribution prediction result under the medium accuracy signal is classified as a possible accurate prediction result;

[0075] If the accuracy value of the symmetric node stress distribution prediction result is less than the first standard threshold, it means that the accuracy of the symmetric node stress distribution prediction result is low. At this time, a low accuracy signal is generated, and the symmetric node stress distribution prediction result under the low accuracy signal is classified as an inaccurate prediction result.

[0076] S5: For accurate prediction results, the stress distribution of the node is directly used as the reference for shear wall design; for inaccurate prediction results, the local graph structure of the symmetrical node is retrained.

[0077] For nodes with accurate prediction results, their stress distribution is highly consistent with the mechanical behavior of the actual structure, so they can be directly used as a reference for shear wall design. This means that the model's predictions of stress and deformation at these nodes are reliable, and engineers can rely on these results for structural assessment and design without additional corrections or verification. These accurately predicted nodes can serve as a stable benchmark for the entire design, ensuring that the mechanical properties of the shear wall meet the design requirements under long-term loads and complex working conditions, thereby optimizing overall safety and efficiency.

[0078] For symmetric nodes with inaccurate prediction results, the local graph structure of these nodes needs to be trained intensively because the model fails to correctly capture the stress state or creep effect of these nodes. Specifically, by extracting the local mechanical features of these nodes and their neighboring nodes, adjusting the feature input or adding symmetry constraints, the local graph is refined again. This retraining can help the model better understand the complex mechanical behavior of these nodes under long-term loads, especially capturing stress concentration problems caused by asymmetric loads, boundary conditions or material nonlinearity, thereby improving the accuracy of predictions and optimizing structural design.

[0079] S6: From the overall shear wall graph, extract each node that may accurately predict the result and its direct neighbor nodes, construct a local subgraph, and dynamically adjust the edge weights according to the abnormal degree of the accuracy of the prediction results of the stress distribution of the symmetric nodes.

[0080] Symmetric node i is a node that may accurately predict the result. This node and its direct neighbor nodes (i.e. nodes connected to i) are extracted to form a local subgraph. The node set V of the local subgraph is i Includes: V i ={i}∪{j∣(i,j)∈E}; where E is the edge set of the graph and j is the neighbor node directly connected to node i;

[0081] In the local subgraph, the initial weight of each edge (i, j) is defined according to the geometric distance or the material properties of the node. Usually, the initial weight is a fixed value, and the expression is: Among them, d(i,j) is a measure of the geometric distance or structural correlation between nodes i and j. The larger the initial weight, the closer the connection between the nodes.

[0082] If the accuracy value of the symmetric node stress distribution prediction result is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the symmetric node stress distribution prediction result generated under the medium accuracy signal is divided into possible accurate prediction results, and the accuracy values ​​of the symmetric node stress distribution prediction results generated in the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected and the corresponding data set is established, and the standard deviation of the data set is calculated as the abnormality degree of stress distribution prediction, marked as A(i); the abnormality degree A(i) of stress distribution prediction reflects the deviation of the prediction result of node i, and the larger its value, the greater the prediction deviation. According to A(i), the prediction accuracy adjustment factor α(i) of node i is defined, which is negatively correlated with A(i), and the expression is: α ( i ) =1-A ( i ) ; Among them, α(i)∈[0,1], represents the accuracy of node prediction. The closer α(i) is to 1, the more accurate the prediction is; the smaller α(i) is, the less accurate the prediction is.

[0083] In a local subgraph, the edge weights According to the dynamic adjustment of the abnormal degree of the stress distribution prediction result of the node, the edge weight is dynamically adjusted as follows by combining the prediction accuracy adjustment factor α(i) of node i and its neighbor node j: is the adjusted edge weight. The smaller the edge weight, the greater the uncertainty or error in the prediction of the node pair connected by the edge. The larger the weight, the more accurate the prediction of the connected node pair.

[0084] When the stress distribution prediction result of node i or neighboring node j is abnormal (i.e., A(i) or A(j) is large, resulting in small α(i) or α(j)), the adjusted edge weight This means that in the local graph structure, the strength of the association between the nodes is weakened, reflecting that the model does not accurately capture the mechanical interaction between these nodes, prompting the subsequent model to correct this part of the local relationship. On the contrary, if the stress distribution prediction of nodes i and j is more accurate, α(i) and α(j) are higher, and the adjusted edge weights remain high, indicating that the model can better capture the mechanical relationship between these nodes.

[0085] After dynamically adjusting the edge weights, the weight matrix Wi of the local subgraph is updated. The new weight matrix Wi(new) reflects the node association strength corrected according to the abnormality of the prediction results. The updated local subgraph is input into the graph neural network for retraining, which can further improve the stress distribution prediction accuracy of nodes that may accurately predict the results.

[0086] In this embodiment, symmetrical node pairs in the shear wall structure are identified by comparing geometric coordinates and connection relationships, and these nodes are marked in the graph structure. Next, the shear response data of the symmetrical nodes under horizontal loads and the material creep data caused by stress differences under long-term loads are obtained, and these data are converted into feature vectors and input into the machine learning model for training to determine the accuracy of the stress distribution prediction of the symmetrical nodes. Then, the nodes are classified according to the accuracy of the prediction results, and are divided into accurate, possibly accurate, and inaccurate prediction results. For accurate prediction results, the stress distribution of the node is directly used for shear wall design, and for nodes with inaccurate prediction results, their local graph structure is extracted and retrained. For nodes that may be accurate, these nodes and their neighboring nodes are extracted from the overall shear wall graph, a local subgraph is constructed, and the edge weights are dynamically adjusted according to the degree of abnormality of the prediction results to optimize the model prediction.

[0087] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0088] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0089] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A shear wall design method based on graph node classification graph neural network, characterized by: The steps include: S1: Determine whether the node pairs in the shear wall structure are symmetrical by comparing the geometric coordinates and the connection relationship, mark the symmetrical node pairs identified in the shear wall structure, and construct the graph structure of the shear wall to keep the symmetrical node pairs in the same graph; S2: After identifying the symmetrical nodes, obtain the horizontal shear response data of the symmetrical nodes of the wall under horizontal loads, as well as the material creep data generated based on the stress difference of the symmetrical nodes under long-term loads; S3: convert the acquired horizontal shear response data and material creep data into feature vectors, use the feature vectors as inputs of the machine learning model, train the machine learning model, and determine the accuracy of the prediction results of the symmetrical node stress distribution according to the model output results; S4: classifying the accuracy of the prediction results of the stress distribution of the symmetric nodes into different levels, namely, accurate prediction results, possibly accurate prediction results and inaccurate prediction results; S5: For accurate prediction results, the stress distribution of the node is directly used as the reference for shear wall design; for inaccurate prediction results, the local graph structure of the symmetrical node is retrained; S6: From the overall shear wall diagram, extract each node that may accurately predict the result and its direct neighbor nodes, construct a local subgraph, and dynamically adjust the edge weights according to the abnormal degree of the accuracy of the prediction results of the stress distribution of the symmetric nodes.

2. A shear wall design method based on graph node classification graph neural network according to claim 1, characterized in that: In S2, a shear response anomaly index is generated according to the shear force data at the extracted symmetric nodes, wherein the shear response deviation index is obtained by: Extract the shear response data of all symmetrical nodes in the shear wall and construct a feature matrix. The feature matrix of the shear response data of each symmetrical node i is as follows: the shear response τ of node i in the horizontal shear direction i,xy and the shear response τ of node i in the vertical shear direction i,xz , the shear response eigenvector f of each node i i is: f i =[τ i,xy ,τ i,xz ]; For N nodes, form a feature matrix X, X = [ f1,f2,…,f N] T ; Where X is an N×d-dimensional matrix, d is the dimension of the feature, T is the matrix transpose, and it is standardized. For the standardized feature matrix X′, its covariance matrix C is calculated, and the expression is: Among them, C is a d×d dimensional matrix, which represents the covariance between the shear response characteristics. The covariance matrix C is subjected to eigenvalue decomposition to obtain the eigenvalues ​​λ1,λ2,…,λ d and the corresponding eigenvectors v1,v2,…,v d ; The eigenvalue represents the variance contribution in the direction of each principal component, while the eigenvector represents the direction of the principal component. The expression is: Cv i =λ i v i ; Among them, the eigenvalue λ i represents the importance of the i-th principal component, v i is the corresponding eigenvector, and the principal components v1, v2, …, v corresponding to the first g largest eigenvalues ​​are selected. g To reduce the dimension, the original feature vector f i Project it into the principal component space, and reconstruct the approximate value Sf of the original eigenvector through the principal component vector. i , calculate the difference between the original eigenvector and the reconstructed eigenvector, that is, calculate the shear response deviation index, the expression is: HK = || f i -Sf i ||2; where HK is the shear response deviation index.

3. The shear wall design method based on graph node classification graph neural network according to claim 2 is characterized by: After analyzing the creep rate of each node under long-term load, the creep rate anomaly index is generated. The method for obtaining the creep rate anomaly index is as follows: Construct the creep rate feature vector of each node. For each node, its creep rate vector Q i Contains creep rates at multiple times: in: Node i at time t n The creep rate of n is the number of time points. For N nodes, an N×n creep rate matrix Y is constructed. The Euclidean distance between each node is calculated. For node i and node j, the Euclidean distance d(i, j) is: Where d(i,j) represents the Euclidean distance between the creep rate feature vectors of nodes i and j. For each node i, a parameter k is selected to represent the number of nearest neighbor nodes to be considered. The k-distance d of node i is k (i refers to the distance from node i to its kth nearest neighbor node: Among them, N i Represents the k nearest neighbor nodes of node i, d(i,j) is the Euclidean distance from node i to node j, and calculates the reach-dist of node i to node j k (i,j), the expression is: Reach-dist k (i,j)=max{d k (j), d(i, j)}; Calculate the local reachability density. The local reachability density of node i is the average LRD of the reciprocal of its reachability distance to its nearest neighbor node. k (i) The creep rate anomaly index is calculated based on the average value of the inverse of the calculated reachable distance, and the expression is: Where, LRD k (j) is the local reachability density of node j, LRD k (i) is the local reachability density of node i, and KM is the creep rate anomaly index.

4. The shear wall design method based on graph node classification graph neural network according to claim 3 is characterized by: In S3, the acquired horizontal shear response data and material creep data are converted into feature vectors, and the feature vectors are used as inputs of the machine learning model to train the machine learning model. The accuracy of the prediction results of the symmetric node stress distribution is determined according to the model output results, specifically: The shear response deviation index and the creep rate anomaly index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses the accuracy value label of the symmetric node stress distribution prediction result predicted by each group of first eigenvectors as the prediction target, and minimizes the sum of the prediction errors of the accuracy value labels of all symmetric node stress distribution prediction results as the training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The accuracy value of the symmetric node stress distribution prediction result is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

5. The shear wall design method based on graph node classification graph neural network according to claim 4 is characterized by: In S4, the accuracy of the prediction results of the stress distribution of the symmetric nodes is divided into different levels, namely, accurate prediction results, possibly accurate prediction results and inaccurate prediction results, specifically: The obtained accuracy value of the symmetric node stress distribution prediction result is compared with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the accuracy value of the symmetric node stress distribution prediction result is compared with the first standard threshold and the second standard threshold respectively; If the accuracy value of the symmetric node stress distribution prediction result is greater than the second standard threshold, it means that the accuracy of the symmetric node stress distribution prediction result is high, and a high accuracy signal is generated at this time, and the symmetric node stress distribution prediction result under which the high accuracy signal is generated is classified as an accurate prediction result; If the accuracy value of the symmetric node stress distribution prediction result is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the accuracy of the symmetric node stress distribution prediction result is general, and a medium accuracy signal is generated at this time, and the symmetric node stress distribution prediction result under the medium accuracy signal is classified as a possible accurate prediction result; If the accuracy value of the symmetric node stress distribution prediction result is less than the first standard threshold, it means that the accuracy of the symmetric node stress distribution prediction result is low. At this time, a low accuracy signal is generated, and the symmetric node stress distribution prediction result under the low accuracy signal is classified as an inaccurate prediction result.

6. The shear wall design method based on graph node classification graph neural network according to claim 1 is characterized by: In S6, each node that may accurately predict the result and its direct neighbor nodes are extracted from the overall shear wall diagram to construct a local subgraph. According to the abnormal degree of the accuracy of the prediction results of the stress distribution of the symmetric nodes, the edge weights are dynamically adjusted, specifically: Symmetric node i is a node that may accurately predict the result. The node and its direct neighbor nodes are extracted to form a local subgraph. The node set V of the local subgraph is i Includes: V i ={i}∪{j∣(i,j)∈E}; where E is the edge set of the graph and j is the neighbor node directly connected to node i; In the local subgraph, the initial weight of each edge (i, j) is defined according to the geometric distance. is a fixed value, and the expression is: Where d(i,j) is the measure of the geometric distance between nodes i and j; If the accuracy value of the symmetric node stress distribution prediction result is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the symmetric node stress distribution prediction result under the generated medium accuracy signal is divided into possible accurate prediction results, and the accuracy values ​​of the symmetric node stress distribution prediction results generated in the subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected and the corresponding data set is established, and the standard deviation of the data set is calculated as the abnormality degree of stress distribution prediction, marked as A(i); the prediction accuracy adjustment factor α(i) of node i is defined according to A(i), which is negatively correlated with A(i), and the expression is: α ( i ) =1-A ( i ) ; Among them, α(i)∈[0,1], represents the accuracy of node prediction.

7. The shear wall design method based on graph node classification graph neural network according to claim 6 is characterized by: In a local subgraph, edge weights According to the dynamic adjustment of the abnormal degree of the stress distribution prediction result of the node, the edge weight is dynamically adjusted as follows by combining the prediction accuracy adjustment factor α(i) of node i and its neighbor node j: is the adjusted edge weight; after dynamically adjusting the edge weight, the weight matrix of the local subgraph is updated.

Images