Bridge health monitoring system calibration method and device based on regional loading test and storage medium

Abstract

The invention provides a bridge health monitoring system calibration method and device based on a regional loading test and a storage medium, and the calibration method comprises the steps: carrying out a regional loading test on a target real bridge based on an influence line, and obtaining monitoring data; the bridge reference state finite element model of the target real bridge is called and loaded at the same position and with the same load as that of the real bridge regional loading test, and corresponding structure response theoretical data are obtained; based on the monitoring data sequence and the structural response theoretical data sequence, respectively obtaining a first fitting relationship and a second fitting relationship; determining a target fitting relationship between the first fitting relationship and the second fitting relationship based on a first priority feature acquired by the monitoring data sequence and a preset standard threshold, and determining a fitting model corresponding to the target fitting relationship as a calibration model of the bridge health monitoring system; and the calibration model is adopted to calibrate the monitoring data. By adopting the calibration method provided by the invention, the implementation is more convenient, and the monitoring data calibration effect can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge monitoring, and particularly to a calibration method, device and storage medium for a bridge health monitoring system based on a sub-region loading test. Background Art

[0002] A bridge health monitoring system is an important technical means for real-time monitoring of the bridge structure condition. In essence, the monitoring system is to sense and obtain the bridge structure response data under the action of external loads. By comparing and analyzing the monitoring data of the structure response with the theoretical calculation data of the structure response in the reference state of the bridge, it can be used to evaluate the performance condition of the bridge.

[0003] Among them, a bridge health monitoring system (also known as a bridge structure monitoring system or simply a bridge monitoring system) is an electronic information system that connects various sensors, data acquisition and transmission, data processing and management, data analysis and application hardware devices, software modules and supporting facilities distributed at the bridge site and the monitoring center through network integration technology, and has the functions of continuously monitoring, automatically recording, data displaying, alarm and evaluation of the set parameters of the bridge, and assisting in bridge management and maintenance decision-making.

[0004] However, when the bridge structure monitoring system is installed, there may be systematic deviations in the monitoring data, and it is necessary to calibrate the initial state of each structure response monitoring sensor of the monitoring system. The bridge structure monitoring sensors may have no quality problems when leaving the factory, but after the sensors are installed, due to the influence of factors such as harsh environment, network anomalies, electromagnetic interference, installation errors, etc., the working performance of the sensors may have problems, resulting in initial errors in the monitoring data when the sensors are installed. For example, the predetermined mounting orientation of a resistance strain gauge should be consistent with the direction of the principal strain on the measured component (assuming the measuring point is in a one-dimensional stress state). If the actual mounting orientation deviates from the principal strain direction by an angle a, as Figure 1 shown, there will be an error between the measured strain value ε' and the true strain value ε, but it can be corrected using formula (1).

[0005]

[0006] In the formula, μ is the Poisson's coefficient of the material of the measured component, and a is the deviation angle.

[0007] If calibration correction is not performed, there will always be errors in the subsequent monitoring values of the sensor. The displayed value of the sensor monitoring data (i.e., the obtained monitoring value) u in the bridge health monitoring system can be expressed by formula (2). Data containing errors is difficult to reflect the true condition of the bridge structure and will also lead to inaccurate results of various analysis and evaluation algorithms based on the monitoring data. Therefore, it is very necessary to calibrate the bridge monitoring data using the theoretical calculation data of the structural response under the bridge reference state.

[0008] u = u 0 + σ 0 + σ 其他 Formula (2)

[0009] In the formula, u 0 represents the true value of the bridge structural response, σ 0 represents the instrument monitoring error caused by various factors when the sensor is installed, and σ 其他 represents the monitoring error caused by various factors during the long-term use after the sensor is installed.

[0010] In the process of implementing the present invention, the inventor found that there are at least the following problems in the prior art:

[0011] There are mainly two categories of existing monitoring data calibration methods: the monitoring data calibration method based on long-term monitoring data and the monitoring data calibration method based on measured data.

[0012] (1) The repair methods of the monitoring data calibration method based on long-term monitoring data mainly include data interpolation, data fitting, and machine learning methods.

[0013] ① The numerical interpolation method uses the existing normal data of the same bridge monitoring sensor at different time periods and adopts interpolation algorithms (such as linear interpolation, nearest neighbor interpolation) to calibrate abnormal data (such as filling in the missing time period data).

[0014] ② The data fitting method is based on the existing normal data of the same bridge monitoring sensor at different time periods. Adopting a data fitting algorithm (such as polynomial fitting), a fitting curve of the sensor monitoring data is established, and the abnormal data is calibrated using the fitting curve (such as using the polynomial fitting value to replace the abnormal data value). There is also a literature "Research on Bridge Health Monitoring System Based on Load Test Correction" that proposes to establish a fitting curve between the artificial detection data during traditional load tests and the monitoring data of the health monitoring system to calibrate the monitoring data.

[0015] ③ The machine learning method uses a neural network to train a machine learning model (including deep neural network and long short-term memory network) on the existing normal data of a certain bridge monitoring sensor at different time periods or on the normal monitoring data of other sensors related to a certain sensor, and then uses the machine learning model to calibrate the abnormal data.

[0016] Existing calibration methods for abnormal monitoring data of bridges based on data interpolation, data fitting, and machine learning are all based on the sensor monitoring data of the bridge structure monitoring system itself. The bridge monitoring data itself may contain errors. For example, when the sensor is installed, the monitoring data may have initial errors. These existing methods actually calibrate abnormal data based on the monitoring data that may contain initial errors. In short, it is difficult to calibrate the true and correct monitoring data with these methods.

[0017] (2) Monitoring data calibration method based on measured data. The literature "Research on Bridge Health Monitoring System Modified by Load Test" proposes to establish a fitting curve (mainly a linear fitting function) between the manual detection data during traditional load tests and the monitoring data of the health monitoring system to calibrate the monitoring data.

[0018] This method is mainly applicable to the structural response monitoring data in the monitoring data. The purpose of the mentioned traditional load test is to evaluate the bearing capacity of the bridge, which requires a large number of vehicle loads and high costs; moreover, the load arrangement method is relatively fixed, and the structural responses at some positions may not be obvious, and the manual detection data may have errors. The established calibration function only involves fitting algorithms, and the accuracy of the fitting algorithms may not be high. In short, the applicability of this method needs to be further improved.

[0019] Therefore, a calibration method, device, and storage medium for a bridge health monitoring system based on sub-region load tests are needed to at least partially solve the above technical problems. Summary of the Invention

[0020] In view of this, embodiments of the present invention provide a calibration method, device, and storage medium for a bridge health monitoring system based on sub-region load tests to at least solve one of the problems in the prior art.

[0021] In the first aspect, embodiments of the present invention provide a calibration method for a bridge health monitoring system based on sub-region load tests, and the calibration method includes:

[0022] Based on the influence line corresponding to the structural response to be calibrated determined in advance, conduct a measured load test at the maximum longitudinal coordinate of the influence line or its adjacent positions on the target actual bridge, obtain the structural response monitoring data through the bridge health monitoring system, and construct a monitoring data sequence;

[0023] Call and load the finite element model of the bridge reference state of the target real bridge at the same positions and with the same loads as the actual loading test of the target real bridge, obtain the corresponding theoretical data of the structural response from the finite element analysis results, and construct a sequence of theoretical data of the structural response;

[0024] Based on the sequence of the monitoring data and the sequence of the theoretical data of the structural response, perform fitting using a first fitting model that meets the requirements of a preset R-squared value to obtain a first fitting relationship;

[0025] Based on the sequence of the monitoring data and the sequence of the theoretical data of the structural response, perform fitting using a second fitting model that meets the requirements of a preset R-squared value to obtain a second fitting relationship;

[0026] Based on the sequence of the monitoring data and the sequence of the theoretical data of the structural response, obtain a first priority feature characterizing the quantity of data;

[0027] Based on the first priority feature and a preset standard threshold, determine a target fitting relationship from the first fitting relationship and the second fitting relationship; in the case where the target fitting relationship is determined, determine the fitting model corresponding to the target fitting relationship as the calibration model of the bridge health monitoring system;

[0028] Use the calibration model to calibrate the monitoring data of the bridge health monitoring system.

[0029] In a second aspect, an embodiment of the present invention further provides a calibration device for a bridge health monitoring system based on a sub-region loading test, where the calibration device includes:

[0030] A memory for storing computer-executable instructions;

[0031] A processor for, when executing the computer-executable instructions stored in the memory, implementing the calibration method of the above technical solution.

[0032] In a third aspect, an embodiment of the present invention further provides a storage medium storing computer instructions, where the computer instructions are used to cause the computer to execute the calibration method of the above technical solution.

[0033] According to the calibration method of the embodiment of the present invention, this method is not based on monitoring data that may contain errors, can improve the calibration effect of the monitoring data, and does not require manual measurement of physical quantities at the sensor positions during the load test, which can improve the convenience of this method. At the same time, the loading test in this method is carried out according to the influence line, requiring less vehicle load, and is more simple and effective than the load test. In addition, it can specifically obtain the sensor monitoring data and the theoretical data calculated by the finite element model in different regions of the bridge, and can calibrate the sensors region by region.

[0034] Additional advantages, objects, and features of the present invention will be partly set forth in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the present invention. The objectives and other advantages of the present invention may be realized and attained by the structure particularly pointed out in the specification and the drawings.

[0035] Those skilled in the art will understand that the objectives and advantages that can be achieved by the present invention are not limited to those specifically described above, and the above and other objectives that the present invention can achieve will be more clearly understood from the following detailed description. Brief Description of the Drawings

[0036] The drawings described herein are for further understanding of the present invention, form a part of this application, and do not limit the present invention. The components in the drawings are not drawn to scale, but are only for showing the principles of the present invention. For the convenience of showing and describing some parts of the present invention, the corresponding parts in the drawings may be enlarged, that is, may become larger relative to other components in the exemplary device actually manufactured according to the present invention. In the drawings:

[0037] Figure 1 is a schematic diagram of the mounting azimuth deviation of a resistance strain gauge in the prior art;

[0038] Figure 2 is a flowchart of a calibration method for a bridge health monitoring system according to an embodiment of the present invention;

[0039] Figure 3 is a flowchart of a calibration method for a bridge health monitoring system according to another embodiment of the present invention;

[0040] Figure 4 is a schematic block diagram of a calibration method for a bridge health monitoring system according to an embodiment of the present invention;

[0041] Figure 5 is a schematic diagram of a bending moment diagram and a bending moment influence line of a simply supported beam bridge in a calibration method for a bridge health monitoring system according to an embodiment of the present invention;

[0042] Figure 6 is a schematic diagram of a bending moment diagram and a bending moment influence line of another simply supported beam bridge in a calibration method for a bridge health monitoring system according to an embodiment of the present invention;

[0043] Figure 7 is a schematic diagram of a calibration device according to an embodiment of the present invention;

[0044] Figure 8 is a schematic diagram of a calibration system according to an embodiment of the present invention. Detailed Description of the Embodiments

[0045] To make the objectives, technical solutions, and advantages of the present invention more clearly understood, the present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings. Herein, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but do not limit the present invention.

[0046] Herein, it should also be noted that in order to avoid obscuring the present invention with unnecessary details, only the structures and / or processing steps closely related to the solution according to the present invention are shown in the drawings, while other details less related to the present invention are omitted.

[0047] It should be emphasized that the term "comprising / including" when used herein refers to the presence of features, elements, steps, or components, but does not exclude the presence or addition of one or more other features, elements, steps, or components.

[0048] Herein, it should also be noted that if not otherwise specified, the term "connection" herein can refer not only to direct connection but also to indirect connection with an intermediate.

[0049] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0050] First, reference will be made to Figure 2 describe a calibration method 100 for a bridge health monitoring system based on a sub-region loading test according to an embodiment of the present application. As Figure 2 shown, the calibration method 100 may include steps S110 to S170, which are specifically as follows:

[0051] In step S110, based on the influence line corresponding to the structure response to be calibrated determined in advance, a measured loading test is carried out on the target actual bridge at the maximum longitudinal coordinate of the influence line or its adjacent position, structural response monitoring data is obtained through the bridge health monitoring system, and a monitoring data sequence is constructed.

[0052] In step S120, the finite element model of the bridge reference state of the target actual bridge is called and loaded with the same position and the same load as the measured loading test of the target actual bridge, and the corresponding structural response theoretical data is obtained from the finite element analysis results, and a structural response theoretical data sequence is constructed.

[0053] In step S130, based on the monitoring data sequence and the structural response theoretical data sequence, a first fitting model that meets the preset R-square value requirement is used for fitting to obtain a first fitting relationship.

[0054] In step S140, based on the monitoring data sequence and the structural response theoretical data sequence, a second fitting model that meets the preset R-square value requirement is used for fitting to obtain a second fitting relationship.

[0055] In step S150, a first priority feature representing the number of data is obtained based on the monitored data sequence and the structural response theoretical data sequence.

[0056] In step S160, based on the first priority feature and a preset standard threshold, a target fitting relationship is determined between the first fitting relationship and the second fitting relationship; when the target fitting relationship is determined, the fitting model corresponding to the target fitting relationship is determined as the calibration model of the bridge health monitoring system.

[0057] In step S170, the monitored data of the bridge health monitoring system is calibrated using the calibration model.

[0058] In the embodiment of the present application, first, a duration loading test of loads such as vehicles is carried out on the actual bridge according to the influence line, the sensors of the bridge health monitoring system are used to obtain the monitored data of the structural response, and at the same time, according to the finite element model established when the bridge structure is in the reference state, the same load is applied at the corresponding position of the finite element model, and the theoretical calculation data of the structural response is calculated; then, the first fitting model or the second fitting model is respectively used to establish the fitting relationship (calibration function) between the monitored data and the finite element theoretical calculation data, and then according to the first priority feature and the preset standard threshold situation, the first fitting relationship or the second fitting relationship is determined as the target fitting relationship, so as to determine the calibration model, and finally the calibration model is used to calibrate the bridge monitoring data.

[0059] From the description of the above process, it can be seen that according to the calibration method 100 of the embodiment of the present application, calibration is not based on the monitored data that may contain errors, but on the theoretical calculation values through the finite element model, which can improve the calibration effect of the monitored data; at the same time, the loading test in it is carried out according to the influence line, the required load is less, the bridge health monitoring system can obtain larger and stable monitored data of the structural response, which is simpler and more effective than the load test. In addition, it can be targeted according to the situation of the monitored data sequence and the structural response theoretical data sequence. On the basis of ensuring the calibration accuracy, the first fitting model or the second fitting model is respectively used for calibration according to the situation, and the flexibility and applicability are relatively high.

[0060] Among them, in Figure 2 Steps S110 to S170 are shown to be arranged in sequence one after another, which is only an example. It can be understood that the order of steps S130, S140 and S160 may not be limited.

[0061] See Figure 3 , and the content of each step of the calibration method 200 according to the embodiment of the present application will be specifically described below.

[0062] In an embodiment of the present application, in step S201, a field loading test is carried out at the maximum ordinate of the influence line or its adjacent position on the target actual bridge based on the influence line corresponding to the structure response to be calibrated determined in advance. The structural response monitoring data is obtained through the bridge health monitoring system, and a monitoring data sequence is constructed.

[0063] It should be noted that referring to Figure 4 , the structure response to be calibrated in this embodiment may include response structure displacement, strain, cable force, rotation angle, vibration acceleration, etc. For example, the strain and vertical displacement of the main girder are not specifically limited. In addition, the calibration method of this embodiment is applicable to the calibration and correction of various types of monitoring data of various bridge structures (not limited to structural response type monitoring data, but also including environmental and load type monitoring data), with a wide range of applications, and can also be applied to various structures and construction projects.

[0064] Before performing step S201, it is necessary to determine in advance the influence line corresponding to the structure response to be calibrated. Generally, for a certain structural response monitoring sensor that needs to be calibrated, the influence line of the internal force of the cross-section at the position of the sensor (such as the bending moment influence line) can be established by the static method or the kinematic method. For the calibration of structural response monitoring data, the present invention considers assisting in the manual measurement of structural response data through a simple loading test based on the influence line rather than necessarily a load test, and the loading test is simple and efficient.

[0065] Specifically, on the target actual bridge, for example, the vehicle load or other loads can be loaded at the maximum ordinate of the influence line or its adjacent position, so that the bridge health monitoring system can obtain larger and stable structural response monitoring data through the monitoring sensors corresponding to the structural response. And a monitoring data sequence is further constructed.

[0066] For example, referring to Figure 5 , for the Figure 5 simply supported beam bridge, displacement sensors ①②③④⑤⑥ in the bridge health monitoring system are respectively arranged in regions C and E to monitor the deflection at different positions of the main girder. When the load (such as vehicle load) is loaded at section c, the main girder at sensors ①②③ will have a large displacement, and the bridge health monitoring system can obtain the monitoring data of sensors ①②③; at the same time, in the bridge finite element model, the displacement calculation values at sensors ①②③ under the corresponding loading mode can be extracted. Similarly, when the load (such as vehicle load) is loaded at section e, the bridge health monitoring system can obtain the monitoring data of sensors ④⑤⑥, and the displacement calculation values at sensors ④⑤⑥ can be extracted from the bridge finite element analysis results.

[0067] In an embodiment of the present application, in step S203, the finite element model of the bridge structure of the target actual bridge is called and loaded with the same position and the same load as the actual measurement loading test of the target actual bridge, the corresponding structural response theoretical data is obtained from the finite element analysis result, and a structural response theoretical data sequence is constructed.

[0068] Of course, before performing step S203, it is necessary to first construct a finite element model of the bridge benchmark state of the target actual bridge.

[0069] In terms of the selection of the bridge benchmark state, when calculating the theoretical value of the structural response, the bridge benchmark state is preferably selected as the state before the bridge is opened to traffic. After the bridge has been in operation for a long time, various damages may occur, such as concrete cracking, steel bar corrosion, etc. If the bridge state during the long-term operation period is selected as the benchmark state for finite element modeling and calculation, it is difficult to truly simulate various damages, and it is also difficult to obtain the true structural response. For a newly built bridge, the bridge performance is in good condition, and the performance parameters of the bridge are basically the same as the design state. For a small number of performance parameters that are inconsistent with the design caused by construction, they can be obtained through actual measurement, so as to establish a finite element model that is consistent with the true performance of the bridge. Generally, the monitoring system is gradually implemented during the bridge construction process, and the monitoring system also needs to be accepted during the bridge completion acceptance. In addition, for extremely large and complex bridges, a load test is also required during the completion acceptance to test the bearing capacity of the bridge. Therefore, when calibrating the bridge health monitoring system, a finite element model of the bridge benchmark state is established with the bridge completion acceptance as the benchmark state to calculate the theoretical value of the structural response, that is, a bridge finite element model is established with the bridge state before opening to traffic as the benchmark state. This finite element model can more accurately reflect the true performance of the bridge compared to the finite element model of the bridge during the operation period.

[0070] Specifically, after determining the finite element model of the bridge benchmark state of the target actual bridge, and at the same position as the actual bridge loading test, the same load is applied to the finite element model, and the corresponding structural response theoretical data is extracted from the finite element analysis result. For details, reference can be made to Figure 5 and the relevant descriptions in the above text.

[0071] In an embodiment of the present application, in step S205, based on the monitoring data sequence and the structural response theoretical data sequence, a first fitting model that meets the preset R-squared value requirement is used for fitting to obtain a first fitting relationship.

[0072] The first fitting model uses a regression model (such as a linear regression model, a polynomial regression model, etc.).

[0073] Specifically, after the sensors in the bridge health monitoring system obtain the monitoring data sequence X = (x1, x2, …, xn) and the finite element theoretical calculation value sequence Y = (y1, y2, …, yn) (i.e., the structural response theoretical data sequence), a regression model (such as a linear regression model, a polynomial regression model, etc.) is used to determine the functional relationship f between X and Y, such as y = f(x).

[0074] With the help of mathematical analysis tool software, multiple fitting functions (known functions) including polynomial functions, linear functions, and logarithmic functions are used to fit the obtained structural response monitoring data and structural response theoretical data one by one, and the R-squared value used to measure the fitting degree of the model to the data is calculated.

[0075] When the R-squared value reaches a preset value, for example, the R-squared value reaches 0.95, the fitting function at this time is determined as the first fitting model that meets the requirements, and the fitting function at this time is the first fitting relationship.

[0076] Among them, the calculation of the R-squared value used to measure the fitting degree of the model to the data is specifically shown in formula (3).

[0077]

[0078] In the formula, y i represents the i-th structural response theoretical data, m represents the average value of n structural response theoretical data, and p i represents the fitting value corresponding to the i-th structural response monitoring data calculated according to a certain fitting function.

[0079] For example, referring to Figure 6 , assume that a simply supported beam bridge is installed with a bridge health monitoring system, and sensors are installed at three positions a, b, and c of the cross-section to monitor the vertical displacement of the main beam. The sensor layout is as Figure 6 shown. Figure 6The influence lines of the bending moments at three cross-section positions calculated by the static method are also given. It can be seen from the Ma bending moment influence line that when the load F is applied at position ③ and its adjacent positions, a relatively large vertical displacement will occur at the cross-section a of the main girder, while when the load F is applied at position ⑨, the vertical displacement generated at the cross-section a of the main girder is relatively small. Therefore, in order to calibrate the displacement sensor at the cross-section a, the load F can be applied at positions ① to ⑥ respectively, so as to obtain 6 relatively large and stable vertical displacement monitoring values. At the same time, in the finite element model, loads of the same weight are applied to 6 positions (each loading position is regarded as a working condition) that are the same as the loading positions of the actual bridge, and the theoretical calculated values of the vertical displacements at the cross-section a under 6 working conditions are extracted from the finite element analysis results. The regression analysis is carried out on these 6 theoretical calculated values and 6 monitoring data (see Table 1). When using a polynomial function to fit the relationship between the theoretical calculated data and the monitoring data, the R-squared value is 0.9806, and the corresponding polynomial function is as follows:

[0080] y = 0.6719x 2 -3.5672x + 7.8275 Formula (4)

[0081] Therefore, the function represented by Formula (4) can be used as the calibration function (i.e., the first fitting relationship) for calibrating the displacement monitoring data at the cross-section a of the main girder. After that, using this calibration function, the displacement monitoring data at the cross-section a can be corrected. For example, when the displacement monitoring value at the cross-section a is 4.1, it can be corrected to 4.5 (retaining 1 significant digit after the decimal point) according to the correction function.

[0082] Table 1 Theoretical calculated data and monitoring data of the vertical displacement at the cross-section a (unit: mm)

[0083] Theoretical calculation data Y 3.4 3.5 4.2 3.9 3.8 3.2 Monitoring data X 3.3 3.4 3.9 3.8 3.7 3.1

[0084] It should be noted that when the load is applied at positions ⑦, ⑧, and ⑨, the displacement generated at the cross-section a is relatively small. Therefore, the vertical displacement values at the cross-section a calculated by the finite element model when the load is applied at positions ⑦, ⑧, and ⑨ are not used to calibrate and correct the monitoring data of the displacement sensor at the cross-section a, but the vertical displacement values at the cross-section c calculated by the finite element model when the load is applied at positions ⑦, ⑧, and ⑨ can be used to calibrate and correct the monitoring data of the displacement sensor at the cross-section c.

[0085] In the embodiment of the present application, in step S207, based on the monitoring data sequence and the structural response theoretical data sequence, a second fitting model that meets the preset R-squared value requirement is used for fitting to obtain a second fitting relationship.

[0086] The second fitting model adopts a neural network model (such as a deep neural network, a long short-term memory network, etc.).

[0087] Similarly, after the sensor in the bridge health monitoring system obtains the monitoring data sequence X = (x1, x2, …, xn) and the finite element theoretical calculation value sequence Y = (y1, y2, …, yn) (i.e., the structural response theoretical data sequence), a neural network model (such as a deep neural network, a long short-term memory network, etc.) is used to determine the functional relationship f between X and Y.

[0088] Specifically, first, a neural network model that meets the preset R-squared value requirement needs to be obtained. The specific process is as follows:

[0089] The obtained monitoring data sequence and the structural response theoretical data sequence are combined into a data set, which is divided into mutually exclusive training set and validation set according to a certain ratio. For example, the data set is divided into mutually exclusive training set and validation set according to the ratio of 8:2. Among them, the monitoring data sequence X is used as the input layer, and the corresponding structural response theoretical data sequence Y is used as the output layer.

[0090] Then, a common and more suitable neural network model is selected, and the number of network layers, the number of neurons, the learning rate, and the loss function parameters of the second fitting model are preset. The training set is used to train the model, and the R-squared value is calculated as an index to evaluate the performance of the model. Among them, the calculation method of the R-squared value can refer to formula (3) in the above text and will not be elaborated here.

[0091] If the R-squared value reaches the preset value, the second fitting model at this time is determined as the second fitting model that meets the requirements, and the relationship between the monitoring data sequence and the structural response theoretical data sequence determined by the second fitting model at this time is the second fitting relationship.

[0092] If the R-squared value does not reach the preset value, continue to adjust the model parameters and iterate the above steps until the R-squared value reaches the preset value.

[0093] It can be understood that when the neural network model selected for the first time always fails to meet the requirements, it can be replaced with another more suitable known neural network model, and the same steps as above are used for processing until the R-squared value reaches the preset value.

[0094] For example, for Figure 6For a simply supported beam bridge installed with a health monitoring system, it is assumed that a vehicle moves slowly and loads near and at section a. 500 pieces of theoretical calculation data and monitoring data of the vertical displacement at section a are obtained. This dataset is divided into mutually exclusive training set and validation set according to the ratio of 8:2. A deep neural network with 2 hidden layers and 7 neurons in each layer is adopted, and the activation function is the Sigmoid function. It is trained on the training set, and various hyperparameters are tuned on the validation set. Finally, a deep learning model with an R-squared value of 0.98 is obtained. After that, using this deep learning model, the displacement monitoring data at section a can be corrected. For example, when the monitored value of the displacement at section a is 4.2, its corrected value is 4.6 (retaining 1 significant digit after the decimal point).

[0095] In the embodiment of the present application, in step S209, a first priority feature representing the number of data is obtained based on the monitored data sequence and the structural response theoretical data sequence.

[0096] Specifically, the first priority feature refers to the total number of data in the monitored data sequence and the structural response theoretical data sequence. For example, if the number of data in both the monitored data sequence and the structural response theoretical data sequence is 500, then the first priority feature is 1000.

[0097] In the embodiment of the present application, in step S211, the first priority feature is compared with a preset standard threshold to determine whether the first priority feature reaches the preset standard threshold. For example, if the first priority feature is 800 and the preset standard threshold is set to 1000, then the first priority feature does not reach the preset standard threshold.

[0098] In the embodiment of the present application, in step S213, when the first priority feature does not reach the preset standard threshold, the first fitting relationship is determined as the target fitting relationship; in the case where the target fitting relationship is determined, the first fitting model corresponding to the first fitting relationship is determined as the calibration model of the bridge health monitoring system.

[0099] In the embodiment of the present application, in step S215, when calibrating the monitoring data obtained by the bridge health monitoring system using the first fitting model, a second priority feature representing the fitting error rate of the fitting result is obtained.

[0100] Specifically, when the first fitting relationship is determined as the target fitting relationship and the first fitting model corresponding to the first fitting relationship is determined as the calibration model, the monitoring data obtained by the bridge health monitoring system is calibrated by the first fitting model. For example, by obtaining the fitting result after calibrating the monitoring data obtained by the bridge health monitoring system by the first fitting model within a set time period, the second priority feature representing the fitting error rate can be obtained based on the fitting result, and the fitting error value within this time period can be obtained based on the second priority feature.

[0101] In the embodiment of the present application, in step S217, the fitting error value obtained according to the second priority feature is compared with a preset error threshold to determine whether the fitting error value obtained according to the second priority feature reaches the preset error threshold. For example, the second priority feature (fitting error rate) obtained within a certain time period is 15%, then the fitting error value obtained according to the second priority feature is 0.15, and the preset error threshold is set to 0.05, so the fitting error value obtained according to the second priority feature is greater than the preset error threshold. If the fitting error value obtained according to the second priority feature is less than the preset error threshold, the first fitting model continues to be determined as the calibration model of the bridge health monitoring system.

[0102] In the embodiment of the present application, in step S219, when the first priority feature bit reaches the preset standard threshold, the second fitting relationship is determined as the target fitting relationship; and when the fitting error value obtained according to the second priority feature is greater than the preset error threshold, the second fitting relationship is determined as the target fitting relationship. In the case where the target fitting relationship is determined, the second fitting model corresponding to the second fitting relationship is determined as the calibration model of the bridge health monitoring system.

[0103] In the embodiment of the present application, in step S221, the monitoring data of the bridge health monitoring system is calibrated by using the calibration model. That is, after determining the first fitting model or the second fitting model as the calibration model of the bridge health monitoring system according to steps S217 and S219, the subsequent monitoring data of the bridge health monitoring system is calibrated by using the first fitting model or the second fitting model.

[0104] For example, according to the determined calibration function, the monitoring data x0 of a certain (or some) sensor to be calibrated is obtained, and y0 = f(x0) is calculated using the calibration function y = f(x), and x0 is replaced with y0. If the calibration function is established using a neural network model, x0 is input into the trained neural network model, and the neural network model can output the calibration value y0 of the monitoring value x0.

[0105] Based on the above description, according to the calibration method of the embodiments of the present application, a calibration function relationship between the theoretical calculation data based on the finite element analysis theory of the theoretical loading test and the monitoring data in the bridge health monitoring system is established, and the monitoring data is calibrated using the calibration function relationship. This calibration method uses the finite element analysis theoretical calculation value instead of the monitoring data itself. Compared with calibrating the monitoring data based on the monitoring data that may contain initial errors, it can correct the monitoring data more accurately. Moreover, in the embodiments of the present invention, the bridge finite element model is established with the bridge state before opening to traffic as the reference state. This finite element model can reflect the true performance status of the bridge more accurately than the bridge finite element model during the operation period. At the same time, the loading test in it is carried out according to the influence line, requiring less load. The bridge health monitoring system can obtain larger and stable structural response monitoring data, which is simpler and more effective than the load test, and there is no need to manually measure the physical quantities at the sensor positions during the load test, which can improve the implementation convenience of this method. It can also specifically obtain the sensor monitoring data in different regions and the theoretical data calculated by the finite element model, and can calibrate the sensors regionally. In addition, according to the situation of the monitoring data sequence and the structural response theoretical data sequence, the first fitting model or the second fitting model is respectively used for calibration on the basis of ensuring the calibration accuracy, with higher flexibility and applicability.

[0106] Moreover, the calibration method of the embodiments of the present invention is different from "Research on Bridge Health Monitoring System Modified Based on Load Test" in that:

[0107] ① In terms of the loading method, in the present invention, a vehicle load of a certain fixed weight G1 is directly loaded onto the bridge position c according to the influence line, and is continuously loaded for a period of time so that the structural response monitoring sensors arranged near the position c can collect larger and stable monitoring values. Then, the vehicle load is slowly moved to the bridge position e and continuously loaded for a period of time so that the structural response monitoring sensors arranged near the position e can collect larger and stable monitoring values. The method in "Research on Bridge Health Monitoring System Modified Based on Load Test" is based on the traditional load test implemented to evaluate the bridge bearing capacity. In this load test, at a fixed position of the bridge, the vehicle load is gradually loaded to a certain fixed weight G2 (G2 > G1). The vehicle load required in the embodiments of the present invention is lower, and the implementation cost is lower.

[0108] ② In terms of the calibration data, the present invention uses the structural response data calculated by the finite analysis of the bridge structure in the loading test to calibrate the monitoring data. The method in "Research on Bridge Health Monitoring System Modified Based on Load Test" is to use the structural response data manually measured during the load test to calibrate the monitoring data.

[0109] ③In terms of the calibration function, the present invention proposes that statistical regression and neural networks can be used to establish a correction function between the monitoring data and the finite element theoretical calculation data. The method in "Research on Bridge Health Monitoring System Based on Load Test Correction" only uses the regression fitting method to establish the correction function. The regression fitting method sometimes has difficulty achieving good results. The neural network model adopted by the present invention can theoretically fit any functional relationship. Therefore, the present invention has a wider range of applications and stronger applicability.

[0110] Reference Figure 7 , the calibration device 300 for implementing the calibration method according to the embodiment of the present application includes a processor 310 and a memory 320. The calibration device 300 may include one or more processors 310 and one or more memories 320. The memory 320 stores an executable program run by the processor 310. When the executable program is run by the processor 310, the processor 310 is caused to execute the calibration method 200 according to the embodiment of the present application described above.

[0111] The processor 310 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities.

[0112] The memory 320 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 310 may run the program instructions to implement the client functions (implemented by the processor) in the embodiment of the present application described herein and / or other desired functions. Various application programs and various data may also be stored in the computer-readable storage medium, such as various data used and / or generated by the application programs, etc.

[0113] The calibration device 300 may further include an input device and an output device, and these components are interconnected through a bus system and / or other forms of connection mechanisms. It should be noted that Figure 7 The components and structure of the calibration device 300 shown are exemplary and not restrictive. According to needs, the calibration device 300 may also have other components and structures.

[0114] The input device may be a device used by a user to input instructions and may include one or more of a keyboard, a mouse, a microphone, and a touch screen, etc. In addition, the input device may also be any interface for receiving information.

[0115] The output device can output various information (such as images or sounds) to the outside (such as a user), and may include one or more of a display, a speaker, etc. In addition, the output device may also be any other device with an output function.

[0116] Exemplarily, the exemplary calibration device 300 for implementing the calibration method 200 according to the embodiments of the present application can be applied to electronic devices such as terminal devices (such as mobile phones), tablet computers, laptop computers, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smart watches, smart glasses, or smart helmets, etc.), augmented reality (AR), virtual reality (VR) devices, smart home devices, in-vehicle computers, etc. The embodiments of the present application do not impose any restrictions on this.

[0117] Those skilled in the art can understand the specific operations of the calibration device 300 for implementing the calibration method 200 according to the embodiments of the present application in combination with the content described above. For the sake of brevity, the specific details are not described here, and only some main operations of the processor 310 are described.

[0118] In one embodiment of the present application, when the executable program is run by the processor 310, the processor 310 is caused to perform the following steps: Based on the influence line corresponding to the structure response to be calibrated determined in advance, perform a measured loading test at the maximum longitudinal coordinate of the influence line or its adjacent position on the target actual bridge, obtain structure response monitoring data through the bridge health monitoring system, and construct a monitoring data sequence; Call and perform loading on the finite element model of the bridge structure of the target actual bridge at the same position and with the same load as the measured loading test of the target actual bridge, obtain the corresponding structure response theoretical data from the finite element analysis results, and construct a structure response theoretical data sequence; Based on the monitoring data sequence and the structure response theoretical data sequence, perform fitting using a first fitting model that meets the preset R-squared value requirement to obtain a first fitting relationship; Based on the monitoring data sequence and the structure response theoretical data sequence, perform fitting using a second fitting model that meets the preset R-squared value requirement to obtain a second fitting relationship; Obtain a first priority feature characterizing the number of data based on the monitoring data sequence and the structure response theoretical data sequence; Compare the first priority feature with a preset standard threshold to determine whether the first priority feature reaches the preset standard threshold; When the first priority feature does not reach the preset standard threshold, the first fitting relationship is determined as the target fitting relationship, and the first fitting model is determined as the calibration model; In the case of calibrating the monitoring data obtained by the bridge health monitoring system using the first fitting model, obtain a second priority feature characterizing the fitting error rate corresponding to the fitting result; Compare the fitting error value obtained based on the second priority feature with a preset error threshold to determine whether the error value obtained based on the second priority feature reaches the preset error threshold; When the first priority feature reaches the preset standard threshold and the fitting error value obtained based on the second priority feature is greater than the preset error threshold, the second fitting relationship is determined as the target fitting relationship, and the second fitting model is determined as the calibration model; Use the calibration model to calibrate the subsequent monitoring data of the bridge health monitoring system.

[0119] The calibration method 200 according to the embodiments of the present application is exemplarily shown above. Next, in combination with Figure 8 describe the calibration system 400 provided in another aspect of the embodiments of the present application.

[0120] Refer to Figure 8 to describe an exemplary calibration system 400 for implementing the calibration method of the embodiments of the present application. The calibration system 400 may include a first construction module 402, a second construction module 404, a first fitting relationship acquisition module 406, a second fitting relationship acquisition module 408, a first priority feature acquisition module 410, a first judgment module 412, a first determination module 414, a second priority feature acquisition module 416, a second judgment module 418, a second determination module 420, and a calibration module 422. Wherein:

[0121] The first construction module 402 is configured to: conduct a measured loading test on the target real bridge at the maximum longitudinal coordinate of the influence line or at a position near it based on the influence line corresponding to the structure response to be calibrated determined in advance, obtain the structure response monitoring data through the bridge health monitoring system, and construct a monitoring data sequence.

[0122] The second construction module 404 is configured to: call and perform loading on the finite element model of the bridge structure of the target real bridge at the same position and with the same load as the measured loading test on the target real bridge, obtain the corresponding structure response theoretical data from the finite element analysis results, and construct a structure response theoretical data sequence.

[0123] The first fitting relationship obtaining module 406 is configured to: based on the monitoring data sequence and the structure response theoretical data sequence, perform fitting using a first fitting model that meets the preset R-squared value requirement to obtain a first fitting relationship.

[0124] The second fitting relationship obtaining module 408 is configured to: based on the monitoring data sequence and the structure response theoretical data sequence, perform fitting using a second fitting model that meets the preset R-squared value requirement to obtain a second fitting relationship.

[0125] The first priority feature obtaining module 410 is configured to: obtain a first priority feature characterizing the data quantity based on the monitoring data sequence and the structure response theoretical data sequence.

[0126] The first judgment module 412 is configured to: compare the first priority feature with a preset standard threshold to determine whether the first priority feature reaches the preset standard threshold.

[0127] The first determination module 414 is configured to: when the first priority feature does not reach the preset standard threshold, determine the first fitting relationship as the target fitting relationship and the first fitting model as the calibration model.

[0128] The second priority feature obtaining module 416 is configured to: in the case of calibrating the monitoring data obtained by the bridge health monitoring system using the first fitting model, obtain a second priority feature characterizing the fitting error rate of the fitting result.

[0129] The second judgment module 418 is configured to: compare the fitting error value obtained based on the second priority feature with a preset error threshold to determine whether the error value obtained based on the second priority feature reaches the preset error threshold.

[0130] The second determination module 420 is configured to: when the first priority feature reaches the preset standard threshold and the error value obtained based on the second priority feature is greater than the preset error threshold, determine the second fitting relationship as the target fitting relationship and the second fitting model as the calibration model.

[0131] A calibration module 422, configured to: calibrate the monitoring data of the bridge health monitoring system by using the calibration model.

[0132] The calibration system 400 provided by the embodiment of the present invention calculates the theoretical value through the finite element analysis instead of the monitoring data itself. Compared with calibrating the monitoring data based on the monitoring data that may contain initial errors, it can correct the monitoring data more accurately. At the same time, the loading test in it is carried out according to the influence line, and the required load is less. The bridge health monitoring system can obtain larger and stable structural response monitoring data, which is simpler and more effective than the load test. In addition, according to the situation of the monitoring data sequence and the structural response theoretical data sequence, the first fitting model or the second fitting model is respectively used for calibration on the basis of ensuring the calibration accuracy rate, with high flexibility and applicability.

[0133] In addition, according to the embodiments of the present application, the present application also provides a storage medium, on which a computer program is stored, and when the computer program is run by a processor, it is used to execute the corresponding steps of the calibration method 200 of the embodiments of the present application. The storage medium may include, for example, a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a portable compact disc read-only memory (CD-ROM), a USB memory, or any combination of the above storage media. The computer-readable storage medium may be any combination of one or more computer-readable storage media.

[0134] In addition, according to the embodiments of the present application, the present application also provides a computer program product, including computer instructions, and when the computer instructions are executed by a processor, the steps of the calibration method 200 of the embodiments of the present application are implemented.

[0135] Although example embodiments have been described herein with reference to the drawings, it should be understood that the above example embodiments are merely exemplary and are not intended to limit the scope of the present application thereto. Those of ordinary skill in the art can make various changes and modifications therein without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as claimed by the appended claims.

[0136] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0137] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0138] In addition, those skilled in the art can understand that although some embodiments described herein include certain features included in other embodiments rather than other features, the combination of features of different embodiments means that it is within the scope of the present application and forms different embodiments. For example, in the claims, any one of the claimed embodiments can be used in any combination.

[0139] It should be noted that the above embodiments illustrate the present application rather than limit the present application, and those skilled in the art can design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in the claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented by means of hardware including several different elements and by means of a suitably programmed computer. In a unit claim listing several devices, several of these devices can be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not denote any order. These words can be interpreted as names.

[0140] As described above, this is only the specific implementation manner or the description of the specific implementation manner of the present application, and the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present application, and all of them should be covered by the protection scope of the present application. The protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A bridge health monitoring system calibration method based on regional loading test, characterized in that: The calibration method comprises: Based on the predetermined influence line corresponding to the structural response to be calibrated, a measured loading test is performed on the target real bridge at the maximum ordinate of the influence line or its adjacent position, the structural response monitoring data is obtained through the bridge health monitoring system, and a monitoring data sequence is constructed; Call and load the finite element model of the bridge benchmark state of the target real bridge at the same position and with the same load as the measured loading test of the target real bridge, obtain the corresponding structural response theory data from the finite element analysis results, and construct a structural response theory data sequence; Based on the monitoring data sequence and the structural response theory data sequence, a first fitting model that meets a preset R-square value requirement is used for fitting to obtain a first fitting relationship; Based on the monitoring data sequence and the structural response theory data sequence, a second fitting model that meets a preset R-square value requirement is used for fitting to obtain a second fitting relationship; Acquire a first priority feature characterizing the quantity of data based on the monitoring data sequence and the structural response theory data sequence; Based on the first priority feature and the preset standard threshold, determining a target fitting relationship in the first fitting relationship and the second fitting relationship; when the target fitting relationship is determined, determining a fitting model corresponding to the target fitting relationship as a calibration model of the bridge health monitoring system; The calibration model is used to calibrate the monitoring data of the bridge health monitoring system.

2. The calibration method according to claim 1, characterized in that: The calibration method further comprises: When the first fitting model is used to calibrate the monitoring data obtained by the bridge health monitoring system, a second priority feature characterizing the fitting error rate corresponding to the fitting result is obtained. If the second priority feature is greater than a preset error threshold, the second fitting model is determined as the calibration model.

3. The calibration method according to claim 1, characterized in that: The first fitting model is used for fitting to obtain a first fitting relationship, which specifically includes: With the help of mathematical analysis tool software, multiple fitting functions including polynomial function, linear function and logarithmic function are used to fit the acquired structural response monitoring data and structural response theory data one by one, and the R square value used to measure the degree of fit of the model to the data is calculated; When the R-squared value reaches a preset value, the fitting function at this time is determined as the first fitting model that meets the requirements, and the fitting function at this time is the first fitting relationship.

4. The calibration method according to claim 3, characterized in that: The calculation is used to measure the R-squared value of the model's fit to the data, specifically: In the formula, y i represents the i-th structural response theory data, m represents the average value of n structural response theory data, and p i It means that the fitting value corresponding to the i-th structural response monitoring data is calculated according to a certain fitting function.

5. The calibration method according to claim 1, characterized in that: The second fitting model is used for fitting to obtain a second fitting relationship, which specifically includes: The acquired monitoring data sequence and structural response theory data sequence are divided into mutually exclusive training set and validation set according to a certain ratio, wherein the monitoring data sequence is used as the input layer and the corresponding structural response theory data sequence is used as the output layer; The number of network layers, number of neurons, learning rate and loss function parameters of the second fitting model are preset, the model is trained using the training set, and the R-squared value is calculated as an indicator for evaluating the performance of the model; If the R-squared value reaches the preset value, the second fitting model at this time is determined as the second fitting model that meets the requirements, and the relationship between the monitoring data sequence and the structural response theory data sequence determined by the second fitting model at this time is the second fitting relationship; If the R-squared value does not reach the preset value, continue to adjust the model parameters and iterate the above steps until the R-squared value reaches the preset value.

6. The calibration method according to claim 1, characterized in that: The first fitting model is a regression model.

7. The calibration method according to claim 1, characterized in that: The second fitting model is a neural network model.

8. The calibration method according to claim 1, characterized in that: The first priority feature refers to the total data quantity of the monitoring data sequence and the structural response theory data sequence; The satisfying the preset R-squared value requirement means that the R-squared value is at least 0.

95.

9. A bridge health monitoring system calibration device based on regional loading test, characterized in that: The calibration device comprises: A memory for storing computer executable instructions; A processor, configured to implement the calibration method according to any one of claims 1 to 8 when executing the computer executable instructions stored in the memory.

10. A storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the calibration method according to any one of claims 1 to 8.

Images