A cable-stayed bridge temperature field digital modeling method fusing data and finite elements

Abstract

The present application relates to cable-stayed bridge structure health monitoring technical field, specifically to a kind of data and finite element fusion's cable-stayed bridge temperature field digital modeling method, comprising: the establishment of multiple bridge structures finite element refinement three-dimensional space model;Obtain the measured temperature data of each bridge structure;According to each measured temperature data and each finite element refinement three-dimensional space model obtains cable-stayed bridge temperature field digital model.Through first establishing the finite element refinement three-dimensional space model of multiple bridge structures, then according to each measured temperature data and each finite element refinement three-dimensional space model obtains cable-stayed bridge temperature field digital model.In this way, through cable-stayed bridge temperature field digital model can reflect the full-field characteristics of bridge structure system, get the influence of temperature on the bridge system of cable-stayed bridge, and the correlation between temperature and each bridge structure, so as to accurately damage identification and safety evaluation to cable-stayed bridge, and then realize the health monitoring of cable-stayed bridge, improve the safety of cable-stayed bridge operation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cable-stayed bridge structure health monitoring, and particularly relates to a data and finite element fused cable-stayed bridge temperature field digital modeling method. BACKGROUND

[0002] In recent years, due to the significant increase in traffic volume, the problem of overload caused by vehicles and external abnormal environment is increasingly prominent. In addition to the original design oversight, construction process defects, improper operation and maintenance, and material performance degradation, a large number of existing bridges are in a "sick work" state, and there are serious safety hazards. Various bridge collapse accidents have been heard. Among them, as a controlling project of transportation, it is of great practical significance to ensure the safe operation of the cable-stayed bridge for the regional economic development and the safety of people's lives and property.

[0003] The "beam-tower-cable" is the core bearing system of the cable-stayed bridge structure, which is extremely sensitive to changes in environmental temperature. By fine inversion of the temperature field of the bridge structure system, the health status of the cable-stayed bridge can be better monitored. The traditional method is to monitor the temperature data at a limited number of measuring points of the cable-stayed bridge through sensors, and then to evaluate the temperature field of the bridge system of the cable-stayed bridge according to the temperature data. However, such a way is difficult to reflect the full-field characteristics of the bridge structure system. At the same time, due to the damage of part of the sensors, the long-term absence of all monitoring data, the gradual drift, the over-range and other complex situations, it is difficult to restore the real sample data, and due to the discontinuity of the data in time and the finiteness of the spatial measuring points, it is impossible to accurately establish the correlation model between the temperature and the bridge response, and thus it is impossible to accurately realize damage identification and safety evaluation. SUMMARY

[0004] In view of the deficiencies in the prior art, the present application provides a data and finite element fused cable-stayed bridge temperature field digital modeling method to improve the safety of the operation of the cable-stayed bridge.

[0005] The technical scheme adopted by the present application is a data and finite element fused cable-stayed bridge temperature field digital modeling method.

[0006] In a first implementation manner, a data and finite element fused cable-stayed bridge temperature field digital modeling method comprises the following steps:

[0007] establishing a plurality of bridge structure finite element fine three-dimensional space models;

[0008] obtaining measured temperature data of each bridge structure;

[0009] obtaining a cable-stayed bridge temperature field digital model according to each measured temperature data and each finite element fine three-dimensional space model.

[0010] In combination with the first implementation manner, in the second implementation manner, the bridge structure includes a main beam, a tower and a cable-stayed cable, a fine three-dimensional space finite element model of the plurality of bridge structures is established, including:

[0011] A BIM three-dimensional space physical model of each bridge structure is established by using a building information model software.

[0012] A fine three-dimensional space finite element model of each bridge structure is established according to the BIM three-dimensional space physical model of each bridge structure.

[0013] In combination with the second implementation manner, in the third implementation manner, a BIM three-dimensional space physical model of each bridge structure is established by using a building information model software, including:

[0014] A BIM three-dimensional space physical model of each bridge structure is constructed by using a building information model software according to design parameters of each bridge structure; the design parameters include geometric dimensions and material properties.

[0015] In combination with the second implementation manner, in the fourth implementation manner, a fine three-dimensional space finite element model of each bridge structure is established according to the BIM three-dimensional space physical model of each bridge structure, including:

[0016] A simulated temperature and a simulated structural response parameter of the bridge structure are obtained by performing a finite element analysis according to structural parameters and external environmental parameters of the bridge structure;

[0017] The simulated temperature and the simulated structural response parameter are marked into each BIM three-dimensional space physical model to obtain a BIM fine three-dimensional space finite element model.

[0018] In combination with the first implementation manner, in the fifth implementation manner, measured temperature data of each bridge structure is obtained, including:

[0019] First measured temperature data of a main beam mid-span section and second measured temperature data of each orientation surface of a tower are obtained according to a bridge health monitoring system;

[0020] An average value of the first measured temperature data and the second measured temperature data is taken as third measured temperature data of the cable-stayed cable.

[0021] In combination with the fifth implementation manner, in the sixth implementation manner, a cable-stayed bridge temperature field digital model is obtained according to each measured temperature data and each fine three-dimensional space finite element model, including:

[0022] The first measured temperature data is fused with the fine three-dimensional space finite element model of the main beam to obtain a main beam temperature three-dimensional space fusion model;

[0023] The second measured temperature data is fused with the bridge tower finite element refined three-dimensional space model to obtain a bridge tower temperature three-dimensional space fusion model;

[0024] The third measured temperature data is fused with the cable-stayed cable finite element refined three-dimensional space model to obtain a cable-stayed cable temperature field real-time deduction model;

[0025] The main beam temperature three-dimensional space fusion model, the bridge tower temperature three-dimensional space fusion model and the cable-stayed cable temperature field real-time deduction model are fused to obtain a cable-stayed bridge temperature field digital model.

[0026] In combination with the sixth implementable manner, in a seventh implementable manner, the first measured temperature data is fused with the main beam finite element refined three-dimensional space model to obtain a main beam temperature three-dimensional space fusion model, including:

[0027] The predicted temperature and the predicted structure response parameter of the main beam are obtained according to the main beam finite element refined three-dimensional space model;

[0028] The predicted temperature of the main beam is taken as the input of the neural network model, and the predicted structure response parameter of the main beam is taken as the output of the neural network model, so as to construct a main beam neural network mapping model by using a neural network algorithm;

[0029] The main beam corrected structure response parameter is obtained according to the main beam neural network mapping model;

[0030] The first measured temperature data and the main beam corrected structure response parameter are input into the main beam finite element refined three-dimensional space model to obtain the main beam temperature three-dimensional space fusion model.

[0031] In combination with the sixth implementable manner, in an eighth implementable manner, the second measured temperature data is fused with the bridge tower finite element refined three-dimensional space model to obtain a bridge tower temperature three-dimensional space fusion model, including:

[0032] The predicted temperature and the predicted structure response parameter of the bridge tower are obtained according to the bridge tower finite element refined three-dimensional space model;

[0033] The predicted temperature of the bridge tower is taken as the input of the neural network model, and the predicted structure response parameter of the bridge tower is taken as the output of the neural network model, so as to construct a bridge tower neural network mapping model by using a neural network algorithm;

[0034] The bridge tower corrected structure response parameter is obtained according to the bridge tower neural network mapping model;

[0035] The second measured temperature data and the bridge tower corrected structure response parameter are input into the bridge tower finite element refined three-dimensional space model to obtain the bridge tower temperature three-dimensional space fusion model.

[0036] In combination with the sixth implementation manner, in a ninth implementation manner, the third measured temperature data is fused with the cable finite element refined three-dimensional space model to obtain a cable temperature field real-time deduction model, including:

[0037] obtaining a predicted temperature of the cable according to the cable finite element refined three-dimensional space model;

[0038] taking an average value of the predicted temperature of the main beam and the predicted temperature of the tower as an input of the neural network model, taking the predicted temperature of the cable as an output of the neural network model, and constructing a cable neural network mapping model;

[0039] obtaining a corrected structural response parameter of the cable according to the cable neural network mapping model;

[0040] inputting the third measured temperature data and the corrected structural response parameter of the cable into the cable finite element refined three-dimensional space model to obtain the cable temperature field real-time deduction model.

[0041] In combination with the seventh or eighth implementation manner, in a tenth implementation manner, the method further includes:

[0042] obtaining a bridge measured structural response parameter according to the bridge health monitoring system;

[0043] verifying a predicted structural response parameter of a neural network mapping model corresponding to the bridge structure according to the bridge measured structural response parameter.

[0044] According to the above technical solution, the present application has the following beneficial technical effects:

[0045] 1. By establishing a plurality of finite element refined three-dimensional space models of bridge structures, and then obtaining a cable-stayed bridge temperature field digital model according to each measured temperature data and each finite element refined three-dimensional space model, the full-field characteristics of the bridge structural system can be reflected through the cable-stayed bridge temperature field digital model, the influence of temperature on the bridge system of the cable-stayed bridge can be obtained, and the correlation between temperature and each bridge structure can be obtained, so that the cable-stayed bridge can be accurately damaged and safety evaluated, and the health of the cable-stayed bridge can be monitored, and the safety of the cable-stayed bridge operation can be improved.

[0046] 2. By decomposing the complex whole cable-stayed bridge temperature field digital model into a plurality of finite element refined three-dimensional space models of bridge structures, the calculation amount is greatly reduced.

[0047] 3. The measured temperature data of each bridge structure is fused into the finite element refined three-dimensional space model of each bridge structure, and finally the cable-stayed bridge temperature field digital model is obtained, which is closer to the real data of the cable-stayed bridge, and the accuracy of the cable-stayed bridge temperature field digital model is improved. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the description of the embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference signs. In the drawings, the elements or parts are not necessarily drawn according to the actual proportions.

[0049] Figure 1 A schematic diagram of a data and finite element fusion cable-stayed bridge temperature field digital modeling method provided by the embodiment of the present application. EMBODIMENT

[0050] The embodiments of the technical solutions of the present application will be described in detail below with reference to the drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present application, and therefore only serve as examples, and cannot limit the protection scope of the present application.

[0051] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in the present application should be understood as the usual meanings understood by the skilled person in the field to which the present application belongs.

[0052] In combination with Figure 1 As shown in the drawings, the embodiment provides a data and finite element fusion cable-stayed bridge temperature field digital modeling method, comprising:

[0053] Step S01, establishing a plurality of bridge structure finite element refined three-dimensional space models;

[0054] Step S02, obtaining measured temperature data of each bridge structure;

[0055] Step S03, obtaining a cable-stayed bridge temperature field digital model according to each measured temperature data and each bridge structure finite element refined three-dimensional space model.

[0056] By first establishing a plurality of bridge structure finite element refined three-dimensional space models, and then obtaining a cable-stayed bridge temperature field digital model according to each measured temperature data and each bridge structure finite element refined three-dimensional space model. In this way, the cable-stayed bridge temperature field digital model can reflect the full-field characteristics of the bridge structure system, obtain the influence of temperature on the bridge system of the cable-stayed bridge, and the correlation between temperature and each bridge structure, so as to accurately identify the damage of the cable-stayed bridge and evaluate the safety, and then realize the health monitoring of the cable-stayed bridge, and improve the safety of the operation of the cable-stayed bridge. At the same time, the complex entire cable-stayed bridge temperature field digital model is decomposed into a plurality of bridge structure finite element refined three-dimensional space models, which greatly reduces the calculation amount. The measured temperature data of each bridge structure is integrated into each bridge structure finite element refined three-dimensional space model, and finally the cable-stayed bridge temperature field digital model is obtained, which is closer to the real data of the cable-stayed bridge, and improves the accuracy of the cable-stayed bridge temperature field digital model.

[0057] Optionally, the bridge structure comprises a main beam, a tower and a cable-stayed cable, a finite element refined three-dimensional space model of the plurality of bridge structures is established, comprising: a BIM (Building Information Modeling) three-dimensional space physical model of each bridge structure is respectively established by using a building information modeling software; and a finite element refined three-dimensional space model of each bridge structure is established according to the BIM three-dimensional space physical model of each bridge structure.

[0058] Optionally, the BIM three-dimensional space physical model of each bridge structure is respectively established by using the building information modeling software, comprising: the BIM three-dimensional space physical model of each bridge structure is constructed according to design parameters of each bridge structure by using the building information modeling software; and the design parameters comprise geometric dimensions and material properties.

[0059] Optionally, the finite element refined three-dimensional space model of each bridge structure is established according to the BIM three-dimensional space physical model of each bridge structure, comprising: a simulated temperature and a simulated structural response parameter of the bridge structure are obtained by performing finite element analysis according to structural parameters and external environment parameters of the bridge structure; and the simulated temperature and the simulated structural response parameter are marked into the BIM three-dimensional space physical model to obtain a BIM finite element refined three-dimensional space model.

[0060] In some embodiments, the simulated structural response comprises stress, strain, displacement, etc.

[0061] In some embodiments, when the bridge structure is a main beam, a BIM three-dimensional space physical model of the main beam is constructed according to design parameters such as geometric dimensions and material properties of the main beam by using a general building information modeling software such as revit. Then, a simulated temperature and a simulated structural response parameter of the main beam are obtained by performing finite element analysis according to structural parameters such as geometric dimensions and load design parameters of the main beam and external environment parameters. Finally, the simulated temperature and the simulated structural response of the main beam are marked into the BIM three-dimensional space physical model of the main beam, so as to obtain a BIM finite element refined three-dimensional space model of the main beam.

[0062] In some embodiments, when the bridge structure is a tower, a BIM three-dimensional space physical model of the tower is constructed according to design parameters such as geometric dimensions and material properties of the tower by using a general building information modeling software such as revit. Then, a simulated temperature and a simulated structural response parameter of the tower are obtained by performing finite element analysis according to structural parameters such as geometric dimensions and load design parameters of the tower and external environment parameters. Finally, the simulated temperature and the simulated structural response parameter of the tower are marked into the BIM three-dimensional space physical model of the tower, so as to obtain a BIM finite element refined three-dimensional space model of the tower.

[0063] In some embodiments, when the bridge structure is a cable-stayed cable, a general building information model software such as Revit is used to construct a BIM three-dimensional space physical model of the cable-stayed cable according to design parameters such as the geometric size and material properties of the cable-stayed cable. Then, according to the structural parameters such as the geometric size and load design parameters of the cable-stayed cable, and the external environmental parameters, the simulated temperature of the cable-stayed cable is obtained through finite element analysis method. Finally, the simulated temperature of the cable-stayed cable is marked to the BIM three-dimensional space physical model of the cable-stayed cable, so as to obtain a BIM finite element refined three-dimensional space model of the cable-stayed cable.

[0064] Optionally, the finite element analysis method is a method of replacing a complex problem with a simpler problem and then solving it, which is widely used in the field of bridge structures, and the specific steps refer to the prior art. It regards the solution domain as being composed of many small interconnected sub-domains called finite elements, assumes a suitable relatively simpler approximate solution for each element, and then derives a solution that satisfies the conditions of the entire domain, such as the balance conditions of the structure, to obtain the solution of the problem. Because the actual problem is replaced by a simpler problem, the solution is not an accurate solution, but an approximate solution. The finite element analysis method has the advantages of convenience, practicality and effectiveness.

[0065] Optionally, the measured temperature data of each bridge structure is obtained by: obtaining first measured temperature data of the main girder mid-span section and second measured temperature data of each orientation surface of the tower from the bridge health monitoring system respectively; and taking the average of the first measured temperature data and the second measured temperature data as third measured temperature data of the cable-stayed cable.

[0066] In some embodiments, temperature sensors are arranged at the bridge mid-span section, and the first measured temperature data of the main girder mid-span section is obtained by the sensor subsystem, the data acquisition and transmission subsystem, and the data management subsystem of the bridge structure health monitoring system.

[0067] In some embodiments, temperature sensors are arranged at each orientation surface of the tower, and the second measured temperature data of each orientation surface of the tower is obtained by the sensor subsystem, the data acquisition and transmission subsystem, and the data management subsystem of the bridge structure health monitoring system.

[0068] In some embodiments, temperature sensors are arranged at the bridge mid-span section and each orientation surface of the tower. The first measured temperature data of the main girder mid-span section and the second measured temperature data of each orientation surface of the tower are obtained by the sensor subsystem, the data acquisition and transmission subsystem, and the data management subsystem of the bridge structure health monitoring system. The average of the first measured temperature data and the second measured temperature data, i.e. the third measured temperature data of the cable-stayed cable, is calculated by mathematical statistics method.

[0069] Optionally, the cable-stayed bridge temperature field digital model is obtained according to the respective measured temperature data and the respective finite element refined three-dimensional space models, and the cable-stayed bridge temperature field digital model comprises: fusing the first measured temperature data with the main beam finite element refined three-dimensional space model to obtain a main beam temperature three-dimensional space fusion model; fusing the second measured temperature data with the bridge tower finite element refined three-dimensional space model to obtain a bridge tower temperature three-dimensional space fusion model; fusing the third measured temperature data with the cable-stayed cable finite element refined three-dimensional space model to obtain a cable-stayed cable temperature field real-time deduction model; and fusing the main beam temperature three-dimensional space fusion model, the bridge tower temperature three-dimensional space fusion model and the cable-stayed cable temperature field real-time deduction model to obtain the cable-stayed bridge temperature field digital model.

[0070] Optionally, the first measured temperature data is fused with the main beam finite element refined three-dimensional space model to obtain the main beam temperature three-dimensional space fusion model, and the method comprises: obtaining a predicted temperature and a predicted structural response parameter of the main beam according to the main beam finite element refined three-dimensional space model; constructing a main beam neural network mapping model by taking the predicted temperature of the main beam as input of the neural network model and taking the predicted structural response parameter of the main beam as output of the neural network model by using a neural network algorithm; obtaining a main beam corrected structural response parameter according to the main beam neural network mapping model; and inputting the first measured temperature data and the main beam corrected structural response parameter into the main beam finite element refined three-dimensional space model to obtain the main beam temperature three-dimensional space fusion model.

[0071] In some embodiments, the predicted temperature and the predicted structural response parameter of the main beam mid-span cross section are obtained by the main beam BIM finite element refined three-dimensional space model. The predicted temperature is taken as input training data set, and the predicted structural response parameter is taken as output training data set. A neural network algorithm in machine learning is used to machine learn the training data set, a linear regression model is constructed, and a neural network mapping model of temperature-structural response of the main beam unit is obtained.

[0072] In some embodiments, the first measured temperature data obtained by the health monitoring system is input into the neural network mapping model of temperature-structural response of the main beam unit, and main beam corrected structural response parameters are obtained. The first measured temperature data and the main beam corrected structural response parameters are input into the main beam BIM finite element refined three-dimensional space model, so that the fusion of data and finite elements is realized, and the accuracy of the obtained main beam temperature three-dimensional space fusion model is higher.

[0073] Optionally, the second measured temperature data is fused with the bridge tower finite element refined three-dimensional space model to obtain a bridge tower temperature three-dimensional space fusion model, including: obtaining a predicted temperature and a predicted structure response parameter of the bridge tower according to the bridge tower finite element refined three-dimensional space model; using a neural network algorithm, taking the predicted temperature of the bridge tower as the input of the neural network model and the predicted structure response parameter of the bridge tower as the output of the neural network model, a bridge tower neural network mapping model is constructed; obtaining a corrected structure response parameter of the bridge tower according to the bridge tower neural network mapping model; inputting the second measured temperature data and the corrected structure response parameter of the bridge tower into the bridge tower finite element refined three-dimensional space model to obtain the bridge tower temperature three-dimensional space fusion model.

[0074] In some embodiments, the bridge tower is simulated by the bridge tower BIM finite element refined three-dimensional space model to obtain a predicted temperature and a predicted structure response parameter of each orientation surface of the bridge tower. The predicted temperature of the bridge tower is taken as the input training data set, the predicted structure response parameter of the bridge tower is taken as the output training data set, a neural network algorithm in machine learning is used, machine learning is performed according to the training data set, a linear regression model is constructed, and thus a neural network mapping model of the temperature-structure response of the bridge tower unit is obtained.

[0075] In some embodiments, the second measured temperature data obtained by the bridge structure health monitoring system is input into the neural network mapping model of the temperature-structure response of the bridge tower unit to obtain a corrected structure response parameter of the bridge tower. The second measured temperature data and the corrected structure response parameter of the bridge tower are input into the bridge tower BIM finite element refined three-dimensional space model, the fusion of data and finite elements is realized, and the accuracy of the obtained bridge tower temperature three-dimensional space fusion model is higher.

[0076] Optionally, the third measured temperature data is fused with the cable finite element refined three-dimensional space model to obtain a cable temperature field real-time deduction model, including: obtaining a predicted temperature of the cable according to the cable finite element refined three-dimensional space model; using a neural network algorithm, taking the average of the predicted temperature of the main beam and the predicted temperature of the bridge tower as the input of the neural network model and the predicted temperature of the cable as the output of the neural network model, a cable neural network mapping model is constructed; obtaining a corrected structure response parameter of the cable according to the cable neural network mapping model; inputting the third measured temperature data and the corrected structure response parameter of the cable into the cable finite element refined three-dimensional space model to obtain the cable temperature field real-time deduction model.

[0077] In some embodiments, the main girder predicted temperature is obtained according to the main girder BIM finite element refinement model, the tower predicted temperature is obtained according to the tower BIM finite element refinement model, and the cable-stayed cable predicted temperature is obtained according to the finite element refinement three-dimensional space model. The average value of the main girder predicted temperature and the tower predicted temperature is taken as the input training data set, the cable-stayed cable predicted temperature is taken as the output training data set, a neural network algorithm in machine learning is adopted, machine learning is performed according to the training data set, and a linear regression model is constructed, so as to obtain the neural network mapping model of the average temperature-temperature field of the cable-stayed cable unit.

[0078] In some embodiments, the third measured temperature data obtained by the bridge structure health monitoring system is input into the neural network mapping model of the average temperature-temperature field of the cable-stayed cable unit to obtain the cable-stayed cable corrected structural response parameter, and the third measured temperature data and the cable-stayed cable corrected structural response parameter are input into the cable-stayed cable finite element refinement three-dimensional space model, so that the data and the finite element are fused, and the accuracy of the cable-stayed cable temperature field real-time deduction model obtained is higher. At the same time, it is verified that the cable-stayed cable temperature estimation value generated by the cable-stayed cable temperature field real-time deduction model approximates to the measured value.

[0079] In this way, based on the cable-stayed cable BIM finite element refinement three-dimensional space model, the neural network algorithm is adopted to generate the neural network mapping model of the average temperature-temperature field of the cable-stayed cable unit, then the cable-stayed cable corrected structural response parameter is obtained according to the neural network mapping model of the average temperature-temperature field of the cable-stayed cable unit, and the third measured temperature data and the cable-stayed cable corrected structural response parameter are input into the cable-stayed cable finite element refinement three-dimensional space model, so that the cable-stayed cable temperature field real-time deduction model can generate a predicted temperature approximating to the real cable-stayed cable temperature, and the accuracy of the model is improved.

[0080] Optionally, the main girder temperature three-dimensional space fusion model, the tower temperature three-dimensional space fusion model and the cable-stayed cable temperature field real-time deduction model are fused to obtain a cable-stayed bridge temperature field digital model. Through the cable-stayed bridge temperature field digital model, the monitoring and evaluation of the bridge appearance deformation, carrying capacity, operation safety and durability performance and other indicators are strengthened, the real state of the bridge and the mechanical properties thereof under complex environment are accurately grasped, and the major needs of the bridge structure health monitoring and safety evaluation are met.

[0081] Optionally, a hierarchical modeling method is adopted, the revit software constructed by the building information model platform models the main girder, the tower and the cable-stayed cable as different modules, respectively obtains the main girder temperature three-dimensional space fusion model, the tower temperature three-dimensional space fusion model and the cable-stayed cable temperature field real-time deduction model, and then fuses the main girder temperature three-dimensional space fusion model, the tower temperature three-dimensional space fusion model and the cable-stayed cable temperature field real-time deduction model to obtain a temperature field digital model of the beam-tower-cable system of the cable-stayed bridge based on the BIM platform.

[0082] Optionally, the hierarchical modeling method can derive the BIM model of the bridge structure corresponding to the measuring point where the current data anomaly occurs, and obtain the corresponding finite element refinement model. The model integrates relevant material information and structural information.

[0083] Optionally, the cable-stayed bridge temperature field digital modeling method combining data and finite elements further includes: obtaining bridge measured structural response parameters according to a bridge health monitoring system; and verifying predicted structural response parameters of a neural network mapping model corresponding to the bridge structure according to the bridge measured structural response parameters.

[0084] Optionally, the neural network mapping model is a temperature data set T={T i ,i=1,2,…,n} and a structural response data set R={R i ,i=1,2,…,n}. The correspondence between the two data models is established by a neural network algorithm

[0085] Optionally, the measured structural response parameters of the main girder are obtained according to the bridge health monitoring system, and the predicted structural response parameters of the neural network mapping model of the main girder are verified according to the measured structural response parameters of the main girder, including: arranging the required corresponding type of sensors at the corresponding structural response positions of the main girder, and obtaining the measured structural response data of the main girder by the sensor subsystem, the data acquisition and transmission subsystem, and the data management subsystem of the bridge structure health monitoring system. In the case where the difference between the measured structural response data of the main girder and the predicted structural response parameters of the neural network mapping model of the main girder is within the preset error range, it is verified that the measured structural response data of the main girder is close to the predicted structural response data of the temperature-structural response neural network mapping model of the main girder unit.

[0086] Since the temperature-structural response mapping relationship of the main girder unit established by the neural network algorithm in machine learning in the main girder BIM finite element refinement three-dimensional space model is similar to the relationship between the temperature-structural response measured data obtained by the structural health monitoring system, the accuracy of the main girder BIM finite element refinement three-dimensional space model can be verified.

[0087] Optionally, the bridge tower measured structure response parameters are acquired according to the bridge health monitoring system, and the predicted structure response parameters of the bridge tower neural network mapping model are verified according to the bridge tower measured structure response parameters, including: arranging the required type of sensors at the corresponding structure response positions of the bridge tower, and obtaining the bridge tower measured structure response data by the sensor subsystem, data acquisition and transmission subsystem and data management subsystem in the bridge structure health monitoring system. In the case where the difference between the bridge tower measured structure response data and the predicted structure response parameters of the bridge tower neural network mapping model is within the preset error range, it is verified that the bridge tower measured structure response data is close to the predicted structure response parameters of the bridge tower neural network mapping model.

[0088] Since the bridge tower measured structure response data is close to the predicted structure response data of the temperature-structure response neural network mapping model of the bridge tower unit, the temperature-structure response mapping relationship of the bridge tower unit established by the neural network algorithm of the bridge tower unit BIM finite element refinement simulation model is similar to the temperature-structure response measured data relationship obtained by the structure health monitoring system, and the accuracy of the bridge tower BIM finite element refinement three-dimensional space model can be verified.

[0089] By verifying the main girder structure response, the bridge tower structure response and the cable temperature field, it can be known that the predicted parameters of each model are consistent with the measured data in trend and close in value, so that the method of modeling based on the fusion of monitoring data and finite elements can be verified, and an accurate long-term simulation temperature field of the whole bridge can be established. Therefore, the modeling method provided by the embodiment can make the predicted data of the model consistent with the measured structure response data in trend and close in value, and can establish an accurate long-term simulation temperature field of the whole bridge. At the same time, a digital fusion solution is proposed for the spatial dimension limitation of existing monitoring point data and the cable measured estimation, and a long-term complete measured temperature field of the whole bridge is reconstructed. And it can reflect the full-field characteristics of the bridge structure system, provide effective suggestions for the long-term health status evaluation of the bridge, and make up for the blank of the prior art.

[0090] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should be covered in the scope of the claims and description of the present application.

Claims

1. A method for digital modeling of temperature field of a cable-stayed bridge with data and finite elements fusion, characterized in that, The application relates to a method for establishing a temperature field digital model of a cable-stayed bridge. The method comprises the following steps: establishing a finite element refined three-dimensional space model of a plurality of bridge structures; obtaining measured temperature data of each bridge structure; obtaining a temperature field digital model of a cable-stayed bridge according to each measured temperature data and each finite element refined three-dimensional space model; obtaining measured temperature data of each bridge structure comprises: obtaining first measured temperature data of a main beam cross-section and second measured temperature data of each orientation surface of a bridge tower through a bridge health monitoring system respectively; taking the average value of the first measured temperature data and the second measured temperature data as third measured temperature data of a stay cable; obtaining a temperature field digital model of a cable-stayed bridge according to each measured temperature data and each finite element refined three-dimensional space model comprises: fusing the first measured temperature data with the finite element refined three-dimensional space model of the main beam to obtain a main beam temperature three-dimensional space fusion model; fusing the second measured temperature data with the finite element refined three-dimensional space model of the bridge tower to obtain a bridge tower temperature three-dimensional space fusion model; fusing the third measured temperature data with the finite element refined three-dimensional space model of the stay cable to obtain a stay cable temperature field real-time deduction model; 2. The method of claim 1, wherein, fusing the main beam temperature three-dimensional space fusion model, the bridge tower temperature three-dimensional space fusion model and the stay cable temperature field real-time deduction model to obtain a temperature field digital model of a cable-stayed bridge. The bridge structure comprises a main beam, a bridge tower and a stay cable, and the finite element refined three-dimensional space model of a plurality of bridge structures comprises: establishing a BIM three-dimensional space physical model of each bridge structure by using a building information model software; 3. The method of claim 2, wherein, establishing a finite element refined three-dimensional space model of each bridge structure according to the BIM three-dimensional space physical model of each bridge structure. The BIM three-dimensional space physical model of each bridge structure is established by using a building information model software, and the method comprises the following steps:

4. The method of claim 2, wherein, adopting the building information model software, constructing the BIM three-dimensional space physical model of each bridge structure according to the design parameters of each bridge structure; the design parameters comprise geometric dimensions and material characteristics. The finite element refined three-dimensional space model of each bridge structure is established according to the BIM three-dimensional space physical model of each bridge structure, and the method comprises the following steps: performing finite element analysis according to the structural parameters and external environmental parameters of the bridge structure to obtain simulated temperature and simulated structural response parameters of the bridge structure; 5. The method of claim 1, wherein, marking the simulated temperature and the simulated structural response parameters into each BIM three-dimensional space physical model to obtain a BIM finite element refined three-dimensional space model. The first measured temperature data is fused with the finite element refined three-dimensional space model of the main beam to obtain a main beam temperature three-dimensional space fusion model, and the method comprises the following steps: obtaining predicted temperature and predicted structural response parameters of the main beam according to the finite element refined three-dimensional space model of the main beam; adopting a neural network algorithm, taking the predicted temperature of the main beam as the input of a neural network model and taking the predicted structural response parameters of the main beam as the output of the neural network model to construct a main beam neural network mapping model; obtaining corrected structural response parameters of the main beam according to the main beam neural network mapping model; The first measured temperature data and the girder correction structure response parameter are input into a girder finite element refined three-dimensional space model to obtain a girder temperature three-dimensional space fusion model.

6. The method of claim 1, wherein, The second measured temperature data is fused with a bridge tower finite element refined three-dimensional space model to obtain a bridge tower temperature three-dimensional space fusion model, including: The predicted temperature and the predicted structure response parameter of the bridge tower are obtained according to the bridge tower finite element refined three-dimensional space model; The predicted temperature of the bridge tower is taken as the input of the neural network model, and the predicted structure response parameter of the bridge tower is taken as the output of the neural network model to construct a bridge tower neural network mapping model by using a neural network algorithm; The bridge tower correction structure response parameter is obtained according to the bridge tower neural network mapping model; The second measured temperature data and the bridge tower correction structure response parameter are input into the bridge tower finite element refined three-dimensional space model to obtain the bridge tower temperature three-dimensional space fusion model.

7. The method of claim 1, wherein, The third measured temperature data is fused with a cable finite element refined three-dimensional space model to obtain a cable temperature field real-time deduction model, including: The predicted temperature of the cable is obtained according to the cable finite element refined three-dimensional space model; The average value of the predicted temperature of the girder and the predicted temperature of the bridge tower is taken as the input of the neural network model, and the predicted temperature of the cable is taken as the output of the neural network model to construct a cable neural network mapping model; The cable correction structure response parameter is obtained according to the cable neural network mapping model; The third measured temperature data and the cable correction structure response parameter are input into the cable finite element refined three-dimensional space model to obtain the cable temperature field real-time deduction model.

8. The method according to claim 5 or 6, characterized in that, Further comprising: The bridge measured structure response parameter is obtained according to the bridge health monitoring system; The predicted structure response parameter of the corresponding neural network mapping model of the bridge structure is verified according to the bridge measured structure response parameter.

Images