CN114969934B - Stay cable damage degree identification method and model construction method - Google Patents

Stay cable damage degree identification method and model construction method Download PDF

Info

Publication number
CN114969934B
CN114969934B CN202210608594.9A CN202210608594A CN114969934B CN 114969934 B CN114969934 B CN 114969934B CN 202210608594 A CN202210608594 A CN 202210608594A CN 114969934 B CN114969934 B CN 114969934B
Authority
CN
China
Prior art keywords
cable
stay
matrix
actual
stayed bridge
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210608594.9A
Other languages
Chinese (zh)
Other versions
CN114969934A (en
Inventor
张健
董倩
陈建文
姜永滚
欧阳彬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan University of Technology
Original Assignee
Hunan University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hunan University of Technology filed Critical Hunan University of Technology
Priority to CN202210608594.9A priority Critical patent/CN114969934B/en
Publication of CN114969934A publication Critical patent/CN114969934A/en
Application granted granted Critical
Publication of CN114969934B publication Critical patent/CN114969934B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/17—Mechanical parametric or variational design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Mathematics (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Analysis (AREA)
  • Molecular Biology (AREA)
  • Structural Engineering (AREA)
  • Civil Engineering (AREA)
  • Architecture (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Bridges Or Land Bridges (AREA)

Abstract

The embodiment of the application provides a stay cable damage degree identification method and a model construction method, which are implemented by acquiring position information of each stay cable in a target cable-stayed bridge and condition data of the target cable-stayed bridge; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data; normalizing the acceleration data to generate a corresponding feature matrix; establishing an adjacent matrix according to the position information of each cable-stayed bridge; and constructing a neural network model combining the graph neural network with the gating circulation unit according to the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix. The neural network model provided by the application can fully utilize the relevance between stay cables, well reserve the information of the nodes, and realize perfect combination of the global and local.

Description

Stay cable damage degree identification method and model construction method
Technical Field
The application relates to the field of damage identification, in particular to a stay cable damage degree identification method and a model construction method.
Background
The stay cable is a key stress component of the cable-stayed bridge, and the stay cable is rusted or fatigued due to long-term load caused by environmental factors, so that serious threat and hidden danger are formed on the operation safety and the use durability of the whole structure, and the smooth operation of national economy and the life and property safety of people are directly related. Therefore, in order to ensure that the cable-stayed bridge is safe in service and the road network is smooth, the method has important scientific research value and engineering application value for rapidly identifying the damage position and damage degree of the stayed cable. With the development of artificial intelligence technology, the machine learning and deep learning method is widely applied to the damage identification of stay cables.
Stay cable damage identification is an important modeling task, but many current researches and applications ignore the relevance among stay cables, and the existing identification model does not consider spatial relevance. Since all stay cables form a whole, the stay cables have relevance, the damage of one stay cable can also influence the vibration signal of the adjacent stay cable beside, so that the vibration signal of the adjacent cable also changes, but the change is theoretically opposite to the change trend of the damaged cable. If space factors are not considered, deviation of the recognition result is caused, the stay cable damages the inherent nonlinear characteristic of the recognition task, and a simple linear model is often insufficient to generate reliable prediction. Common nonlinear models such as artificial neural networks, recurrent neural networks, and long and short term memory networks (LSTM), none of which take into account the correlation between the different stay cables. Convolutional Neural Networks (CNNs) that perform well in many areas may rely on the location of existing stay cables as a spatial factor, whereas conventional CNNs cannot handle irregular data. Although the spacing of each stay cable on the deck is equal, but the angle to the beam varies, the graph structure determined by the stay cable position is irregular, in the topology, the distance relationship between the nodes, the characteristic relationship is different, it has more complex characteristics, and lack of translational invariance, so that it is not preferable for the CNN to process the graph data structure.
However, multiple layers of GCN (graph roll-up neural network) can cause excessive interaction of node information, and characteristics of each node tend to be consistent and cannot be distinguished obviously.
Disclosure of Invention
In view of the above, the present application has been made to provide a stay cable damage degree identification method and model construction method that overcome or at least partially solve the above problems, including:
a stay cable damage degree identification model construction method is used for constructing a stay cable damage degree identification model on a target cable-stayed bridge, and comprises the following steps:
acquiring position information of each stay cable in a target cable-stayed bridge and condition data of the target cable-stayed bridge; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data;
normalizing the acceleration data to generate a corresponding feature matrix;
establishing an adjacent matrix according to the position information of each cable-stayed bridge;
and constructing a neural network model combining the graph neural network with the gating circulation unit according to the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix.
Preferably, the step of normalizing the acceleration data to generate a corresponding feature matrix includes:
screening out the acceleration with the largest value and the acceleration with the smallest value in the acceleration data;
generating normalized acceleration of each corresponding stay cable according to the acceleration with the largest value, the acceleration with the smallest value and the acceleration data of each stay cable;
and constructing the corresponding characteristic matrix according to the normalized acceleration of each stay cable.
Preferably, the step of establishing an adjacency matrix according to the position information of each cable-stayed bridge includes:
numbering each stay cable according to the position information of each stay cable, and establishing the association strength between the stay cables according to the numbering;
and establishing the adjacency matrix according to the association strength between the stay cables.
Preferably, the step of establishing the strength of association between the stay cables according to the number includes:
setting stay cables with serial number difference values within a preset threshold as an association relation;
setting stay cables with serial number difference values not within a preset threshold value as non-association relation;
And generating the association strength between the stay cables according to the association relationship and the non-association relationship.
Preferably, the step of constructing a neural network model combining the graph neural network with the gating circulation unit according to the feature matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix includes:
setting a model parameter learning rate and a maximum iteration number, and constructing a neural network model which is combined with a graph neural network and a gating circulation unit by the feature matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacent matrix.
The application further discloses a stay cable damage degree identification method, which is used for identifying the damage degree of the stay cable on the target cable-stayed bridge and comprises the following steps:
acquiring actual position information of each stay cable in a target cable-stayed bridge and actual condition data of the target cable-stayed bridge; the actual condition data comprise actual acceleration data of each stay cable in the target cable-stayed bridge;
normalizing the actual acceleration data of the stay cable to generate an actual feature matrix;
establishing an actual adjacent matrix according to the actual position information of each stay cable;
And inputting a neural network model according to the actual characteristic matrix and the actual adjacent matrix to generate the loss degree of each stay cable of the target cable-stayed bridge.
Preferably, the neural network comprises three first neural networks connected in series, and the step of generating the damage of each stay cable according to the actual characteristic matrix and the actual adjacent matrix input neural network model comprises the following steps:
inputting the actual feature matrix and the actual adjacency matrix into the first neural network model to generate a first feature matrix;
inputting the first feature matrix and the actual adjacent matrix into the first neural network model to generate a second feature matrix;
inputting the second feature matrix and the actual adjacent matrix into the first neural network model to generate a third feature matrix;
and generating the loss degree of each stay cable of the target cable-stayed bridge according to the third characteristic matrix.
Preferably, the first neural network model includes a graph neural network and a gating loop unit, and the step of inputting the actual feature matrix and the actual adjacency matrix into the first neural network model to generate a first feature matrix includes:
inputting the actual feature matrix and the actual adjacent matrix into the graph neural network to perform feature extraction to generate hidden layer features;
And inputting the hidden layer features and the actual feature matrix into the gating circulating unit to generate the first feature matrix.
The application further comprises a stay cable damage degree identification model construction device, wherein the device is used for constructing a stay cable damage degree identification model on a target cable-stayed bridge, and comprises the following steps:
the data module is used for acquiring the position information of each stay cable in the target cable-stayed bridge and the condition data of the target cable-stayed bridge; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data;
the characteristic matrix module is used for normalizing the acceleration data to generate a corresponding characteristic matrix;
the adjacent matrix module is used for establishing an adjacent matrix according to the position information of each cable-stayed bridge;
and the neural network model module is used for constructing a neural network model which combines the graph neural network with the gating circulation unit according to the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix.
The application further comprises a stay cable damage degree identification device, wherein the device is used for identifying the damage degree of the stay cable on the target cable-stayed bridge and comprises the following components:
The actual data module is used for acquiring the actual position information of each stay cable in the target cable-stayed bridge and the actual condition data of the target cable-stayed bridge; the actual condition data comprise actual acceleration data of each stay cable in the target cable-stayed bridge;
the actual characteristic matrix module is used for normalizing the actual acceleration data of the stay cable to generate an actual characteristic matrix;
the actual adjacent matrix module is used for establishing an actual adjacent matrix according to the actual position information of each stay cable;
and the loss degree module is used for inputting a neural network model according to the actual characteristic matrix and the actual adjacent matrix to generate the loss degree of each stay cable of the target cable-stayed bridge.
The application has the following advantages:
in the embodiment of the application, the position information of each stay cable in the target cable-stayed bridge and the condition data of the target cable-stayed bridge are obtained; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data; normalizing the acceleration data to generate a corresponding feature matrix; establishing an adjacent matrix according to the position information of each cable-stayed bridge; and constructing a neural network model combining the graph neural network with the gating circulation unit according to the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix. The spatial information is extracted by constructing a neural network model combined with a graph convolution neural network and a door control circulation unit, and the problem of over-smoothing, which is the assimilation of nodes, is prevented; constructing an adjacency matrix to represent the relevance between different stay cables; and constructing a stay cable damage identification model based on the graph convolution neural network and the door control circulation unit, and realizing the whole network structure input to and output from the computer. The neural network model provided by the application can fully utilize the relevance between stay cables, well reserve the information of the nodes, and realize perfect combination of the global and local.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings that are needed in the description of the present application will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart illustrating steps of a method for identifying damage degree of a stay cable according to an embodiment of the present application;
FIG. 2 is a flowchart illustrating the overall steps of a stay cable damage degree identification method according to an embodiment of the present application;
FIG. 3 is a schematic view of a GCN-GRU module structure of a stay cable damage degree identification method according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a GCN-GRU neural network model framework for a stay cable damage degree identification method according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a three-dimensional model of a target cable-stayed bridge according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a target cable-stayed bridge structure according to a method for constructing a model for identifying the damage degree of a stayed cable according to an embodiment of the present application;
FIG. 7 is a block diagram of a stay cable damage degree identification model construction device according to an embodiment of the present application;
FIG. 8 is a schematic diagram of a target cable-stayed bridge structure according to an embodiment of the present application;
FIG. 9 is a block diagram illustrating a stay cable damage level identification device according to an embodiment of the present application;
fig. 10 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order that the manner in which the above recited objects, features and advantages of the present application are obtained will become more readily apparent, a more particular description of the application briefly described above will be rendered by reference to the appended drawings. It will be apparent that the described embodiments are some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, a step flowchart of a stay cable damage degree identification model construction method provided by an embodiment of the present application specifically includes the following steps:
s110, acquiring position information of each stay cable in a target cable-stayed bridge and condition data of the target cable-stayed bridge; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data;
S120, normalizing the acceleration data to generate a corresponding feature matrix;
s130, establishing an adjacent matrix according to the position information of each cable-stayed bridge;
and S140, constructing a neural network model combining the graph neural network with the gating circulation unit according to the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacent matrix.
Next, a stay cable damage degree identification model construction method in the present exemplary embodiment will be further described.
As described in the step S110, position information of each stay cable in the target cable-stayed bridge and condition data of the target cable-stayed bridge are obtained; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data.
In an embodiment of the present invention, the step S110 of "obtaining the position information of each stay cable in the target cable-stayed bridge and the condition data of the target cable-stayed bridge" may be further described in conjunction with the following description; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data; "specific procedure.
As an example, acquiring position information of each stay cable in a target cable-stayed bridge and condition data of the target cable-stayed bridge; wherein the condition data comprises at least 90 sets; each group of condition data comprises acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data.
As one example, the operating condition data includes operating condition type and operating condition extent. The working condition types comprise 83 damaged working conditions and healthy working conditions, and damage degree reference values of working condition degrees are 0.01, 0.02, 0.03, 0.04, 0.05, 0.1 and 0.2.
As an example, a data set is prepared, a finite element model of the cable-stayed bridge is established, and the vertical acceleration of each stay cable of the cable-stayed bridge under different working conditions is acquired. Specifically, a mode of reducing the elastic modulus is adopted to simulate the damage of the stay cable; each stay cable is provided with a plurality of acceleration acquisition points, and the positions of the nodes corresponding to different stay cables are guaranteed to be at the same height.
In a specific embodiment, the study object selection and the sensor installation are implemented, the cable-stayed bridge selected in the experiment is of a structure which is symmetrical from front to back and from left to right, 108 stay cables are all adopted for study, and only 1/4 stay cables are selected for study due to the symmetrical structure, and the total number of the stay cables is 27, as shown in a broken line frame of fig. 6. Numbering stay cables, wherein the cable close to the central shaft is number 1, and the cable far from the central shaft is number 27; the 12 acceleration sensors are arranged on each cable in a collecting mode, the sensor which is close to the bridge deck is the sensor No. 0, the sensor which is far away from the bridge deck is the sensor No. 11, and the corresponding sensors are positioned at the same horizontal position. A total of 324 sensors are mounted to collect vertical acceleration.
In one embodiment, the damage condition and the health condition are simulated and data is collected using finite element software ANSYS (a multi-purpose finite element method computer design program). The experiment simulates 83 damaged working conditions and healthy working conditions, white noise excitation is applied to the cable-stayed bridge model under each working condition, and the vertical acceleration of each node is collected. In the experiment, the elastic modulus is selected as a damage variable, stay cable damage of different degrees is simulated by carrying out different size reduction on the elastic modulus, and damage degree reference values of 0.01, 0.02, 0.03, 0.04, 0.05, 0.1 and 0.2 are selected as working condition basic conditions. And combining the collected acceleration data of all the nodes, wherein each sample characteristic in the combined data set is the vertical acceleration of 324 nodes of 27 stay cables, and the output variable is the damage degree of each stay cable.
And as described in the step S120, normalizing the acceleration data to generate a corresponding feature matrix.
In an embodiment of the present invention, the specific process of "normalizing the acceleration data to generate a corresponding feature matrix" in step S120 may be further described in conjunction with the following description.
Screening out the acceleration with the largest value and the acceleration with the smallest value in the acceleration data as follows; generating normalized acceleration of each corresponding stay cable according to the acceleration with the largest value, the acceleration with the smallest value and the acceleration data of each stay cable; and constructing the corresponding characteristic matrix according to the normalized acceleration of each stay cable.
In a specific embodiment, the acceleration data of each node of the stay cable is normalized to obtain preprocessed data, and the preprocessed data is divided into a training set and a testing set. Normalization ensures that each acceleration value falls in a certain range, and can achieve the purposes of simplifying calculation and preventing gradient explosion, and the normalization formula is as follows:
wherein x is 0 ，x 1 Values before and after normalization, a and b are the minimum and maximum values of the sample data, respectively.
As an example, the feature matrix is divided into a training feature matrix and a test feature matrix according to a preset proportion; wherein the preset ratio is 7:3.
in a specific embodiment, the normalized dataset is calculated according to 7:3 are randomly divided into a training set and a testing set, and are respectively converted into a form of characteristic matrix to form the characteristic matrix of the training set and the testing set. A total of 27 stay cables, each stay cable has 12 acceleration acquisition nodes, and the feature matrix of one sample is X= [ X ] 1 ,X 2 ,…,X i ,…,X 27 ]，
In step S130, an adjacency matrix is established according to the position information of each cable-stayed bridge.
In an embodiment of the present invention, the following description may be further described as "establishing the adjacency matrix according to the position information of each cable-stayed bridge" in step S130. "
Numbering each stay cable according to the position information of each stay cable, and establishing the association strength between the stay cables according to the numbering; and establishing the adjacency matrix according to the association strength between the stay cables.
In one embodiment of the present invention, the specific process of "establishing the strength of association between the stay cables according to the number" may be further described in conjunction with the following description.
Setting stay cables with serial number difference values within a preset threshold as an association relation; setting stay cables with serial number difference values not within a preset threshold value as non-association relation; generating the association strength between the stay cables according to the association relationship and the non-association relationship; specifically, the preset threshold is three.
In a specific embodiment, the adjacency matrix A is constructed to reflect the relationship between the different stay cables. An excellent adjacent structure can filter training consumption among nodes with little association, and can extract the relation among the nodes with strong association, so that the training of a model is facilitated. The strength of the association between the stay cables is mainly reduced with the increase of the distance, and a threshold value is set on the assumption that one stay cable is taken as the center, and the stay cables within the threshold value from the stay cable are regarded as having a dependency relationship with the center stay cable. Since the intersections of the stay cables and the bridge deck are equidistantly distributed on a straight line and numbered according to the geographical position sequence, the distance between the stay cables can be reflected by the number difference of the stay cables. The graph structure determined by taking the stay cable number difference as a threshold is shown in the following formula:
Wherein d i,j For the difference value of the serial numbers of the stay cables i and j, dis is the threshold value of the serial number difference value of the stay cables, a i,j Indicating the dependency relationship between two stay cables, a i,j The value of which depends on the stay cable number difference d i,j And compared with the threshold value Dis, the value of 1 indicates that the two stay cables have a dependency relationship, and the value of 0 indicates that the two stay cables have no dependency relationship and have no mutual influence. By filtering the stay cables, each stay cable can integrate stay cable information related to the stay cable, rather than only considering self factors.
In one embodiment, a 27X 27-dimensional adjacency matrix is constructed based on the connection between stay cables, using a i,j Indicating whether the stay cables i and j are related, if 1, indicating that the cable is closedIf the value is 0, the association is not performed. In the experiment, the association is established only between the stay cables with no more than 3, if the serial number difference of the stay cables is no more than 3, the corresponding value in the matrix is 1, otherwise, the value is 0, and the established adjacent matrix A is shown as follows
In one embodiment, a target cable-stayed bridge outputs an abutment matrix of integral stay cables.
And step S140, constructing a neural network model combining the graph neural network with the gating circulation unit according to the feature matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix.
In an embodiment of the present invention, the specific process of "constructing a neural network model combining a graph neural network with a gating cycle unit according to the feature matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data, and the adjacency matrix" in step S140 may be further described in conjunction with the following description.
Setting a model parameter learning rate and a maximum iteration number, and constructing a neural network model combining a graph neural network and a gating circulation unit by using the feature matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacent matrix.
In an embodiment of the present invention, the specific process of setting the model parameter learning rate and the maximum iteration number, and constructing the neural network model by combining the feature matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data, and the adjacent matrix into the graph neural network and the gating loop unit may be further described in conjunction with the following description.
Constructing a feature extraction model according to the combination of the graph convolution neural network and the gating circulating unit; setting three feature extraction models and connecting the feature extraction models in series, and setting a full connection layer at the last feature extraction model so as to generate a neural network to be trained; the training feature matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix are input into the neural network model to be trained to train so as to generate a trained neural network; and inputting the test feature matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix into the trained neural network model to generate the neural network.
As an example, setting a model parameter learning rate and a maximum iteration number, and constructing a first neural network model by combining the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacent matrix into a graph neural network and a gating cycle unit; and setting three first neural network models to be connected in series, and setting a full connection layer at the last first neural network, so as to generate the neural network.
In a specific embodiment, a feature extraction module (GCN-GRU) is constructed that combines a graph convolutional neural network and a gated loop unit. Firstly, extracting spatial features of a graph by adopting a graph convolutional neural network, so that each node contains information of other nodes, and adding a GRU structure to strengthen the information of the node. The GCN network layer can enable the central node to aggregate information of adjacent nodes, but the problem of excessive smoothness easily occurs after multiple graph convolutions, namely, the nodes are similar in characteristics and cannot be distinguished. In order to solve the problem, the invention adopts GRU to strengthen the information of the node itself, and prevents over-smoothing, as shown in the following formula:
X (l+1) ＝GRU(GCN(X (l) ,A；θ (l) ),X (l) )
for the GCN-GRU network layer of the first layer, one GCN layer is used for outputting X to the upper layer (l) Convolving if it is the firstA GCN-GRU network layer convolves the original characteristic X, takes the result of GCN convolution as a hidden layer state of GRU input unit, and the input characteristic of GRU of the current layer is still X (l) Thus, the information of the current node is ensured, and the information of the adjacent nodes is fused. The structure of a GCN-GRU module is shown in FIG. 3.
As an example, a GCN-GRU neural network model is built, 3 GCN-GRU network layers are connected in series to perform feature extraction, and then the result of each node is output through a full connection layer, and the specific structure is shown in fig. 4. And selecting the mean square error as a loss function, and selecting an Adam algorithm to optimize model parameters.
As an example, a GCN-GRU neural network model is built, 3 GCN-GRU network layers are connected in series to perform feature extraction, and then the result of each node is output through a full connection layer, and the specific structure is shown in fig. 3. And selecting the mean square error as a loss function, and selecting an Adam algorithm to optimize model parameters.
Training a GCN-GRU neural network model, setting a model parameter learning rate, and setting the maximum iteration times and iteration termination conditions. And continuously updating the model parameters until the training stopping condition is met, and obtaining the trained stay cable damage identification model. The training process is as follows:
TABLE 1 GCN-GRU model training process table
And inputting the test data and the adjacency matrix into a trained model to obtain a result of the model on the test set, and judging the model effect.
It should be noted that GCN is a neural network of a study graph, which essentially functions as CNN, and is a feature extractor, except that its object is graph data. The GCN subtly devised a method of extracting features from the graph data, so that we can use these features to classify and predict the nodes of the graph data, and also can get an embedded representation of the graph by the way. The core idea of the graph convolution neural network is to infer information of nodes to be predicted by using information of other nodes, and the graph convolution neural network is a characteristic propagation process in each node.
The training process of the graph convolution neural network needs to use the arrival matrix and the adjacent matrix to describe the propagation process of the graph structure, and multi-layer aggregation is performed by using the information of the edges existing in the matrix, so that the final characteristic matrix which tends to be stable is generated. The degree matrix represents the number of nodes that each node is connected to, with only the diagonal having values, and the other positions being zero. The connection matrix represents the entire graph structure, from which it can be seen which nodes were previously associated, the two nodes being connected with a value of 1 and the other being 0. Finally, a Laplacian matrix fused with two matrix information can be obtained through connecting the matrix and the degree matrix, and the calculation process is shown in the following formula:
In the formula, D represents a degree matrix, and A represents an adjacency matrix. F is a Laplace matrix, and the advantage of the Laplace matrix is that the Laplace matrix is a symmetric matrix and can be used for characteristic decomposition.
The graph convolution neural network has the advantages that unnecessary training processes among points can be reduced through graph structure information, finally, all relevant nodes are continuously and iteratively integrated in a weighted mode, finally, a characteristic matrix which tends to be stable is trained, information among all nodes is contained in the matrix, and finally, a predicted value can be obtained through extracting characteristics through a full-connection layer. The propagation computation process between the levels in the GCN is shown in the following formula:
in the formula, D represents a matrix, A represents an adjacent matrix, H is a characteristic matrix of each layer, if the characteristic matrix is the first layer, the characteristic matrix is the input X of the graph convolution neural network, W is a parameter matrix of the first layer, and ReLU is a nonlinear activation function.
GRU (Gate Recurrent Unit) is one of the recurrent neural networks (Recurrent Neural Network, RNN). As with LSTM (Long-Short Term Memory), it has also been proposed to address the problems of Long-term memory and gradients in counter-propagation.
In a specific embodiment, a GCN-GRU stay cable damage identification model is designed, and the GCN-GRU neural network model designed in the step is connected with a full connection layer after 3 GCN-GRU modules are connected in series. The specific GCN-GRU module extracts the spatial characteristics of the stay cable by a convolutional neural network, and inputs the result after characteristic extraction into the GRU structure as a hidden state, wherein the input characteristics of the GRU are still the input characteristics of the GCN network of the layer.
And inputting the training feature matrix and the adjacent matrix into a GCN-GRU stay cable damage identification model for training. And continuously updating the model parameters until the training stopping condition is met, and obtaining the trained traffic flow prediction model. The mean square error MSE is selected as the loss function and the Adam algorithm is selected as the parametric optimizer.
And inputting the test feature matrix and the adjacent matrix into the trained GCN-GRU, predicting the GCN-GRU through a network model to obtain the loss degree of the stay cable, and selecting three error functions of average absolute error, average absolute percentage error and root mean square error as indexes for evaluating the prediction effect of the model.
In one embodiment, referring to FIG. 2, the present application provides a stay cable damage identification method (GCN-GRU) with a graph convolutional neural network and a gated loop unit. The GCN is adopted to extract space characteristics of the stay cable, the result of GCN extraction is input to the GRU as a hidden state, the input of the GRU is still characteristics without GCN extraction, and the effective extraction of global information of the stay cable can be realized through a plurality of GCN-GRU modules, and meanwhile, local information of the stay cable is reserved.
The application can realize the identification of the damage degree of all the stay cables by utilizing the damage working condition data of part of typical stay cables. Because the damage condition of the stay cable is very many, the stay cable can be a single cable or a plurality of cables, the combination condition of different cables is very many, the damage degree of each cable is also different, and the difficulty of collecting all damage conditions is very great.
The application can utilize the relevance between stay cables, because the cable-stayed bridge is a whole, when one cable is damaged, the adjacent cables can be affected to a certain extent.
The application needs to effectively combine global information and local information of the stay cables, and each stay cable is related, but the relation is emphasized excessively, so that different stay cables can be assimilated, and the characteristics of the stay cables cannot be ignored while the related information of other stay cables is fused.
Referring to fig. 8, a step flowchart of a stay cable damage degree identification method according to an embodiment of the present application is shown, and specifically includes the following steps:
s810, acquiring actual position information of each stay cable in a target cable-stayed bridge and actual condition data of the target cable-stayed bridge; the actual condition data comprise actual acceleration data of each stay cable in the target cable-stayed bridge;
s820, normalizing the actual acceleration data of the stay cable to generate an actual feature matrix;
s830, establishing an actual adjacent matrix according to the actual position information of each stay cable;
s840, inputting a neural network model according to the actual characteristic matrix and the actual adjacent matrix to generate the loss degree of each stay cable of the target cable-stayed bridge.
As described in the step S810, obtaining actual position information of each stay cable in the target cable-stayed bridge and actual condition data of the target cable-stayed bridge; the actual condition data comprise actual acceleration data of each stay cable in the target cable-stayed bridge.
In an embodiment of the present invention, the step S810 of "obtaining the actual position information of each stay cable in the target cable-stayed bridge and the actual condition data of the target cable-stayed bridge" may be further described in conjunction with the following description; the actual condition data comprise actual acceleration data of each stay cable in the target cable-stayed bridge. "specific procedure.
In a specific embodiment, the study object selection and the sensor installation are implemented, the cable-stayed bridge selected in the experiment is of a structure which is symmetrical from front to back and from left to right, 108 stay cables are all adopted for study, and only 1/4 stay cables are selected for study due to the symmetrical structure, and the total number of the stay cables is 27, as shown in a broken line frame of fig. 6. Numbering stay cables, wherein the cable close to the central shaft is number 1, and the cable far from the central shaft is number 27; the 12 acceleration sensors are arranged on each cable in a collecting mode, the sensor which is close to the bridge deck is the sensor No. 0, the sensor which is far away from the bridge deck is the sensor No. 11, and the corresponding sensors are positioned at the same horizontal position. A total of 324 sensors are mounted to collect vertical acceleration.
And as described in the step S820, normalizing the actual acceleration data of the stay cable to generate an actual feature matrix.
In an embodiment of the present invention, the specific process of "normalizing the actual acceleration data of the suspension cable to generate the actual feature matrix" in step S820 may be further described in conjunction with the following description.
Screening out the actual acceleration with the largest value and the actual acceleration with the smallest value in the actual acceleration data as follows; generating an actual normalized acceleration of each corresponding stay cable according to the actual acceleration with the maximum value, the actual acceleration with the minimum value and the actual acceleration data of each stay cable; and constructing the corresponding actual characteristic matrix according to the actual normalized acceleration of each stay cable.
In a specific embodiment, the acceleration data of each node of the stay cable is normalized to obtain preprocessed data, and the preprocessed data is divided into a training set and a testing set. Normalization ensures that each acceleration value falls in a certain range, and can achieve the purposes of simplifying calculation and preventing gradient explosion, and the normalization formula is as follows:
wherein x is 0 ，x 1 Values before and after normalization, respectively, a and b are the minimum of the sample data, respectively Values and maximum values.
As described in the above step S830, an actual adjacency matrix is established according to the actual position information of each cable-stayed bridge.
In an embodiment of the present invention, the step S830 of "establishing an actual adjacency matrix according to the actual position information of each cable-stayed bridge" may be further described in conjunction with the following description. "
Numbering each stay cable according to the actual position information of each stay cable, and establishing the actual association strength between the stay cables according to the numbers; and establishing the actual adjacent matrix according to the actual association strength between the stay cables.
In one embodiment of the present invention, the specific process of "establishing the actual strength of association between the stay cables according to the number" may be further described in conjunction with the following description.
Setting the stay cables with serial number difference values within a preset threshold as actual association relations; setting the stay cables with the serial number difference values not within a preset threshold value as actual non-association relations; and generating the actual association strength between the stay cables according to the actual association relationship and the actual non-association relationship.
In a specific embodiment, a 27X 27-dimensional actual adjacency matrix is constructed according to the connection relation between stay cables, a i,j Indicating whether the stay cables i and j are related, if 1, the stay cables i and j are related, and if 0, the stay cables j are not related. In the experiment, the association is established only between the stay cables with no more than 3, if the serial number difference of the stay cables is no more than 3, the corresponding value in the matrix is 1, otherwise, the value is 0, and the established actual adjacent matrix A is shown as follows
And as described in the above step S840, the degree of loss of each stay cable of the target cable-stayed bridge is generated according to the actual feature matrix and the actual adjacent matrix input neural network model.
In an embodiment of the present invention, the specific process of "generating the loss degree of each stay cable of the target cable-stayed bridge according to the actual feature matrix and the actual adjacent matrix input neural network model" in step S840 may be further described in conjunction with the following description.
The neural network comprises three first neural networks connected in series, and the actual feature matrix and the actual adjacent matrix are input into the first neural network model to generate a first feature matrix; inputting the first feature matrix and the actual adjacent matrix into the first neural network model to generate a second feature matrix; inputting the second feature matrix and the actual adjacent matrix into the first neural network model to generate a third feature matrix; and generating the loss degree of each stay cable of the target cable-stayed bridge according to the third characteristic matrix.
In an embodiment of the present application, the step of inputting the actual feature matrix and the actual adjacency matrix into the first neural network model to generate a first feature matrix may be further described in conjunction with the following description.
Inputting the actual feature matrix and the actual adjacent matrix into the graph neural network for feature extraction to generate hidden layer features; and inputting the hidden layer features and the actual feature matrix into the gating circulating unit to generate the first feature matrix.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
Referring to fig. 7, an apparatus for constructing a model for identifying damage degree of stay cable according to an embodiment of the present application is shown, which specifically includes the following modules,
data module 710: the method comprises the steps of acquiring position information of each stay cable in a target cable-stayed bridge and condition data of the target cable-stayed bridge; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data;
Feature matrix module 720: the method comprises the steps of normalizing the acceleration data to generate a corresponding feature matrix;
the adjacency matrix module 730: the method comprises the steps of establishing an adjacency matrix according to the position information of each cable-stayed bridge;
neural network model module 740: and the neural network model is used for constructing a graph neural network and a neural network combined with a gating circulation unit according to the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacent matrix.
In one embodiment of the present invention, the feature matrix module 720 includes:
acceleration submodule: the method comprises the steps of screening out acceleration with the largest value and acceleration with the smallest value in the acceleration data;
and (5) normalizing the acceleration submodule: the system is used for generating normalized acceleration of each corresponding stay cable according to the acceleration with the largest numerical value, the acceleration with the smallest numerical value and the acceleration data of each stay cable;
and a characteristic matrix submodule: and the corresponding characteristic matrix is constructed according to the normalized acceleration of each stay cable.
In one embodiment of the present invention, the adjacency matrix module 730 includes:
correlation strength sub-module: the method comprises the steps of numbering each stay cable according to the position information of each stay cable, and establishing the association strength between each stay cable and each stay cable according to the numbering;
Adjacent matrix submodules: and the adjacent matrix is established according to the association strength between the stay cables.
In an embodiment of the present application, the association strength submodule includes:
and (3) an association sub-module: the stay cables are used for setting the serial number difference value between the stay cables within a preset threshold value as an association relation;
unassociated sub-modules: the stay cables are used for setting the number difference value between the stay cables not within a preset threshold value as an unassociated relation;
the association strength generation sub-module: and the method is used for generating the association strength between the stay cables according to the association relationship and the non-association relationship.
In one embodiment of the present application, the neural network model module 740 includes:
neural network model submodule: and the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacent matrix are used for setting the model parameter learning rate and the maximum iteration number, and a neural network model combined with a gate control loop unit is constructed by the graph neural network.
Referring to fig. 9, there is shown a stay cable damage degree recognition device according to an embodiment of the present application, which specifically includes the following modules,
Actual data module 910: the method comprises the steps of acquiring actual position information of each stay cable in a target cable-stayed bridge and actual condition data of the target cable-stayed bridge; the actual condition data comprise actual acceleration data of each stay cable in the target cable-stayed bridge;
the actual feature matrix module 920: the method comprises the steps of normalizing actual acceleration data of the stay cable to generate an actual feature matrix;
the actual adjacency matrix module 930: the method comprises the steps of establishing an actual adjacent matrix according to actual position information of each stay cable;
the loss degree module 940: and the system is used for inputting a neural network model according to the actual characteristic matrix and the actual adjacent matrix to generate the loss degree of each stay cable of the target cable-stayed bridge.
In one embodiment of the present invention, the loss degree module 940 includes:
a first feature matrix sub-module: the method comprises the steps of inputting the actual feature matrix and the actual adjacency matrix into the first neural network model to generate a first feature matrix;
and a second feature matrix submodule: the first feature matrix and the actual adjacency matrix are input into the first neural network model to generate a second feature matrix;
and a third feature matrix submodule: the third feature matrix is generated by inputting the second feature matrix and the actual adjacent matrix into the first neural network model;
Loss degree submodule: and the loss degree of each stay cable of the target cable-stayed bridge is generated according to the third characteristic matrix.
In an embodiment of the present invention, the first feature matrix submodule includes:
hidden layer feature sub-module: the method comprises the steps of inputting the actual feature matrix and the actual adjacent matrix into the graph neural network for feature extraction to generate hidden layer features;
a first feature matrix generation sub-module: and the hidden layer feature and the actual feature matrix are input into the gating circulating unit to generate the first feature matrix.
It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.
In this embodiment and the above embodiments, repeated operation steps are provided, and this embodiment is only described briefly, and the rest of the solutions only need to be described with reference to the above embodiments.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
The application also includes an electronic device comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, which when executed by the processor, implements the steps of the stay cable damage degree identification method as described.
The application also includes a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the stay cable damage degree identification method as described.
Referring to fig. 10, a computer device illustrating a stay cable damage degree recognition method of the present application may specifically include the following:
the computer device 12 described above is embodied in the form of a general purpose computing device, and the components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, a memory 28, and a bus 18 that connects the various system components, including the memory 28 and the processing unit 16.
Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Computer device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory 30 and/or cache memory 32. The computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (commonly referred to as a "hard disk drive"). Although not shown in fig. 10, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk such as a CD-ROM, DVD-ROM, or other optical media may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, the program modules 42 being configured to carry out the functions of embodiments of the application.
A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, a memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.
The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, camera, etc.), one or more devices that enable an operator to interact with the computer device 12, and/or any devices (e.g., network card, modem, etc.) that enable the computer device 12 to communicate with one or more other computing devices. Such communication may occur through the I/O interface 22. Moreover, computer device 12 may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet, through network adapter 20. As shown in fig. 10, the network adapter 20 communicates with other modules of the computer device 12 via the bus 18. It should be appreciated that although not shown in fig. 10, other hardware and/or software modules may be used in connection with computer device 12, including, but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, data backup storage systems 34, and the like.
The processing unit 16 executes programs stored in the memory 28 to perform various functional applications and data processing, for example, to implement a stay cable damage degree identification method according to an embodiment of the present application.
That is, the processing unit 16 realizes when executing the program: acquiring position information of each stay cable in a target cable-stayed bridge and condition data of the target cable-stayed bridge; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data; normalizing the acceleration data to generate a corresponding feature matrix; establishing an adjacent matrix according to the position information of each cable-stayed bridge; and constructing a neural network model combining the graph neural network with the gating circulation unit according to the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix.
In an embodiment of the present application, the present application further provides a computer readable storage medium having a computer program stored thereon, which when executed by a processor implements a stay cable damage degree identifying method as provided in all embodiments of the present application.
That is, the program is implemented when executed by a processor: acquiring position information of each stay cable in a target cable-stayed bridge and condition data of the target cable-stayed bridge; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data; normalizing the acceleration data to generate a corresponding feature matrix; establishing an adjacent matrix according to the position information of each cable-stayed bridge; and constructing a neural network model combining the graph neural network with the gating circulation unit according to the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix.
Any combination of one or more computer readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Computer program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the operator's computer, partly on the operator's computer, as a stand-alone software package, partly on the operator's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the operator computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (e.g., connected through the internet using an internet service provider). In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the application.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The stay cable damage degree identification method and the model construction method provided by the application are described in detail, and specific examples are applied to illustrate the principle and the implementation mode of the application, and the description of the examples is only used for helping to understand the method and the core idea of the application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Claims (8)

1. The method for constructing the stay cable damage degree identification model on the target cable-stayed bridge is characterized by comprising the following steps of:
acquiring position information of each stay cable in a target cable-stayed bridge and condition data of the target cable-stayed bridge; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data, and particularly, the working condition data comprise working condition types and working condition degrees;
normalizing the acceleration data to generate a corresponding feature matrix;
Establishing an adjacent matrix according to the position information of each cable-stayed bridge;
specifically, the step of establishing an adjacency matrix according to the position information of each cable-stayed bridge includes: numbering each stay cable according to the position information of each stay cable, and establishing the association strength between the stay cables according to the numbering; establishing the adjacency matrix according to the association strength between the stay cables;
specifically, the step of establishing the association strength between the stay cables according to the numbers comprises the following steps: setting stay cables with serial number difference values within a preset threshold as an association relation; setting stay cables with serial number difference values not within a preset threshold value as non-association relation; generating the association strength between the stay cables according to the association relationship and the non-association relationship;
and constructing a neural network model combining the graph neural network with the gating circulation unit according to the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix.
2. The method for constructing a model for identifying the damage degree of a stay cable according to claim 1, wherein the step of normalizing the acceleration data to generate a corresponding feature matrix comprises the steps of:
Screening out the acceleration with the largest value and the acceleration with the smallest value in the acceleration data;
generating normalized acceleration of each corresponding stay cable according to the acceleration with the largest value, the acceleration with the smallest value and the acceleration data of each stay cable;
and constructing the corresponding characteristic matrix according to the normalized acceleration of each stay cable.
3. The method for constructing a model for identifying the damage degree of a stayed cable according to claim 1, wherein the constructing a neural network model of combining a graph neural network with a door control circulation unit according to the feature matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacent matrix comprises:
setting a model parameter learning rate and a maximum iteration number, and constructing a neural network model which is combined with a graph neural network and a gating circulation unit by the feature matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacent matrix.
4. A method for identifying the damage degree of a stayed cable, which is used for identifying the damage degree of the stayed cable on a target cable-stayed bridge, and is characterized by adopting an identification model obtained by the construction method of the stayed cable damage degree identification model as claimed in any one of claims 1-3, and comprising the following steps:
Acquiring actual position information of each stay cable in a target cable-stayed bridge and actual condition data of the target cable-stayed bridge; the actual condition data comprise actual acceleration data of each stay cable in the target cable-stayed bridge;
normalizing the actual acceleration data of the stay cable to generate an actual feature matrix;
establishing an actual adjacent matrix according to the actual position information of each stay cable;
and inputting a neural network model according to the actual characteristic matrix and the actual adjacent matrix to generate the loss degree of each stay cable of the target cable-stayed bridge.
5. The method for recognizing damage degree of stay cables according to claim 4, wherein the neural network comprises three first neural networks connected in series, and the step of generating damage of each stay cable according to the actual feature matrix and the actual adjacent matrix input neural network model comprises the steps of:
inputting the actual feature matrix and the actual adjacency matrix into the first neural network model to generate a first feature matrix;
inputting the first feature matrix and the actual adjacent matrix into the first neural network model to generate a second feature matrix;
inputting the second feature matrix and the actual adjacent matrix into the first neural network model to generate a third feature matrix;
And generating the loss degree of each stay cable of the target cable-stayed bridge according to the third characteristic matrix.
6. The method of claim 5, wherein the first neural network model includes a graph neural network and a gating loop unit, and the step of inputting the actual feature matrix and the actual adjacency matrix into the first neural network model generates a first feature matrix includes:
inputting the actual feature matrix and the actual adjacent matrix into the graph neural network to perform feature extraction to generate hidden layer features;
and inputting the hidden layer features and the actual feature matrix into the gating circulating unit to generate the first feature matrix.
7. The utility model provides a stay cable damage degree discernment model construction device, the device is used for constructing the damage degree discernment model of stay cable on the target cable-stayed bridge, its characterized in that includes:
the data module is used for acquiring the position information of each stay cable in the target cable-stayed bridge and the condition data of the target cable-stayed bridge; the condition data comprise acceleration data of each stay cable in the target cable-stayed bridge and working condition data of the target cable-stayed bridge corresponding to the acceleration data, and particularly, the working condition data comprise working condition types and working condition degrees;
The characteristic matrix module is used for normalizing the acceleration data to generate a corresponding characteristic matrix;
the adjacent matrix module is used for establishing an adjacent matrix according to the position information of each cable-stayed bridge;
specifically, the step of establishing an adjacency matrix according to the position information of each cable-stayed bridge includes: numbering each stay cable according to the position information of each stay cable, and establishing the association strength between the stay cables according to the numbering; establishing the adjacency matrix according to the association strength between the stay cables;
specifically, the step of establishing the association strength between the stay cables according to the numbers comprises the following steps: setting stay cables with serial number difference values within a preset threshold as an association relation; setting stay cables with serial number difference values not within a preset threshold value as non-association relation; generating the association strength between the stay cables according to the association relationship and the non-association relationship;
and the neural network model module is used for constructing a neural network model which combines the graph neural network with the gating circulation unit according to the characteristic matrix, the working condition data of the target cable-stayed bridge corresponding to the acceleration data and the adjacency matrix.
8. A stay cable damage degree identification device for identifying the damage degree of a stay cable on a target cable-stayed bridge, the stay cable damage degree identification device adopting the identification model obtained by the stay cable damage degree identification model construction device according to claim 7, comprising:
the actual data module is used for acquiring the actual position information of each stay cable in the target cable-stayed bridge and the actual condition data of the target cable-stayed bridge; the actual condition data comprise actual acceleration data of each stay cable in the target cable-stayed bridge;
the actual characteristic matrix module is used for normalizing the actual acceleration data of the stay cable to generate an actual characteristic matrix;
the actual adjacent matrix module is used for establishing an actual adjacent matrix according to the actual position information of each stay cable;
and the loss degree module is used for inputting a neural network model according to the actual characteristic matrix and the actual adjacent matrix to generate the loss degree of each stay cable of the target cable-stayed bridge.
CN202210608594.9A 2022-05-31 2022-05-31 Stay cable damage degree identification method and model construction method Active CN114969934B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210608594.9A CN114969934B (en) 2022-05-31 2022-05-31 Stay cable damage degree identification method and model construction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210608594.9A CN114969934B (en) 2022-05-31 2022-05-31 Stay cable damage degree identification method and model construction method

Publications (2)

Publication Number Publication Date
CN114969934A CN114969934A (en) 2022-08-30
CN114969934B true CN114969934B (en) 2023-09-05

Family

ID=82957192

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210608594.9A Active CN114969934B (en) 2022-05-31 2022-05-31 Stay cable damage degree identification method and model construction method

Country Status (1)

Country Link
CN (1) CN114969934B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108090295A (en) * 2017-12-27 2018-05-29 武汉光谷北斗控股集团有限公司 A kind of long-span cablestayed bridges Damages in Stay Cables recognition methods
CN111783212A (en) * 2020-07-09 2020-10-16 长沙理工大学 Typical damage identification method for cable-stayed bridge
CN112733933A (en) * 2021-01-08 2021-04-30 北京邮电大学 Data classification method and device based on unified optimization target frame graph neural network
CN112890827A (en) * 2021-01-14 2021-06-04 重庆兆琨智医科技有限公司 Electroencephalogram identification method and system based on graph convolution and gate control circulation unit
CN114169374A (en) * 2021-12-10 2022-03-11 湖南工商大学 Cable-stayed bridge stay cable damage identification method and electronic equipment

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220101103A1 (en) * 2020-09-25 2022-03-31 Royal Bank Of Canada System and method for structure learning for graph neural networks

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108090295A (en) * 2017-12-27 2018-05-29 武汉光谷北斗控股集团有限公司 A kind of long-span cablestayed bridges Damages in Stay Cables recognition methods
CN111783212A (en) * 2020-07-09 2020-10-16 长沙理工大学 Typical damage identification method for cable-stayed bridge
CN112733933A (en) * 2021-01-08 2021-04-30 北京邮电大学 Data classification method and device based on unified optimization target frame graph neural network
CN112890827A (en) * 2021-01-14 2021-06-04 重庆兆琨智医科技有限公司 Electroencephalogram identification method and system based on graph convolution and gate control circulation unit
CN114169374A (en) * 2021-12-10 2022-03-11 湖南工商大学 Cable-stayed bridge stay cable damage identification method and electronic equipment

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
杨杰 ; 李爱群 ; 缪长青 ; .BP神经网络在大跨斜拉桥的斜拉索损伤识别中的应用.土木工程学报.2006,(05),第72-77页. *

Also Published As

Publication number Publication date
CN114969934A (en) 2022-08-30

Similar Documents

Publication Publication Date Title
CN109117987B (en) Personalized traffic accident risk prediction recommendation method based on deep learning
Sun et al. Understanding architecture age and style through deep learning
CN113779675B (en) Physical-data driven intelligent shear wall building structure design method and device
Zou et al. Multicategory damage detection and safety assessment of post‐earthquake reinforced concrete structures using deep learning
CN111325319B (en) Neural network model detection method, device, equipment and storage medium
CN111369299A (en) Method, device and equipment for identification and computer readable storage medium
CN113761250A (en) Model training method, merchant classification method and device
CN113011895A (en) Associated account sample screening method, device and equipment and computer storage medium
Liao et al. Deep transfer learning and time-frequency characteristics-based identification method for structural seismic response
CN114037478A (en) Advertisement abnormal flow detection method and system, electronic equipment and readable storage medium
Zheng et al. An automatic data process line identification method for dam safety monitoring data outlier detection
CN113553356A (en) Drilling parameter prediction method and system
Shi et al. A novel unsupervised real‐time damage detection method for structural health monitoring using machine learning
CN111783716A (en) Pedestrian detection method, system and device based on attitude information
CN112988851B (en) Counterfactual prediction model data processing method, device, equipment and storage medium
CN114219701A (en) Dunhuang fresco artistic style conversion method, system, computer equipment and storage medium
CN114969934B (en) Stay cable damage degree identification method and model construction method
CN117540136A (en) Time sequence signal prediction method, device, equipment and storage medium
CN117217779A (en) Training method and device of prediction model and information prediction method and device
Chen et al. Research on object detection algorithm based on multilayer information fusion
CN117235633A (en) Mechanism classification method, mechanism classification device, computer equipment and storage medium
CN116976491A (en) Information prediction method, device, equipment, storage medium and program product
CN116541507A (en) Visual question-answering method and system based on dynamic semantic graph neural network
CN114036829B (en) Geological profile generation method, system, equipment and storage medium
Sun et al. Automatic building age prediction from street view images

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant