A bridge expansion device anchor structure detection method, system, medium and equipment

Abstract

The present invention relates to a method, system, medium, and equipment for testing the anchor structure of a bridge expansion joint. The method comprises: obtaining dynamic sensor data of a standard component under different operating conditions; training a neural network to denoise the baseline dynamic characteristics of the anchor structure of the bridge expansion joint; collecting dynamic sensor data of the anchor structure of the bridge expansion joint to be tested, obtaining dynamic characteristic data of the anchor structure of the bridge expansion joint to be tested through preprocessing and neural network analysis; calculating a coefficient of variation; and determining the dynamic characteristic state of the anchor structure of the bridge expansion joint to be tested based on the coefficient of variation. The present invention has the beneficial effect of comprehensively evaluating the operating condition of the anchor structure of the bridge expansion joint from multiple perspectives by dividing the anchor structure into representative operating condition zones and setting multiple sub-operating conditions, resulting in more accurate evaluation results.

Description

Technical Field

[0001] The present invention belongs to the field of bridge detection, and in particular relates to a method, system, medium and equipment for detecting the anchor structure of a bridge expansion device. Background Art

[0002] As a critical component of bridge structures, bridge expansion devices are the final installation step during bridge construction. Their performance and operational condition determine the safety and comfort of vehicles traveling across the bridge. These devices are installed between adjacent beam ends, between beam ends and abutments, or at hinged joints. They accommodate deformation of beam ends caused by temperature fluctuations, concrete shrinkage, various loads, and deflection during bridge service, while ensuring smooth passage of vehicles on the bridge deck.

[0003] However, the bridge expansion device is one of the weak links in the bridge structure. Under the influence of comprehensive factors such as design, manufacturing and installation, environmental climate and long-term heavy traffic loads, the problem of damage to the bridge expansion device is very prominent. It is one of the key difficulties in the current bridge operation and maintenance, and has attracted widespread attention from researchers.

[0004] The main technical approaches for research related to bridge expansion joints include: 1) Optimizing the structural and process design, production, and installation of expansion joints by studying their structure and material properties, thereby improving construction and installation efficiency. 2) Researching the performance of the concrete interface (transition zone) directly connected to the expansion joints. By improving concrete properties, the performance and durability of the transition zone of the bridge expansion joints can be enhanced, and the repair efficiency of bridge expansion joints can also be improved. 3) Technologies such as SHM (structural health monitoring) are becoming an advanced means of monitoring bridge safety and predicting fatigue life during service. SHM systems, composed of sensors and analysis modules, collect, process, and analyze data from key monitoring / inspection areas of bridges, enhancing the dimensionality of data analysis and providing data support for subsequent bridge maintenance decisions.

[0005] Although there are rich research results in the field of bridge expansion devices, there are still certain limitations:

[0006] (1) Most existing studies only focus on the expansion joint or the concrete transition zone, that is, they use a single variable model to analyze the performance of the anchorage zone of the expansion joint. However, the anchorage structure of the expansion joint should be regarded as a whole under the joint anchoring action of the expansion joint, concrete, and adjacent interfaces. Existing performance analysis methods or models are difficult to output accurate assessment results of the anchorage structure of the expansion joint, thus affecting the efficiency and accuracy of subsequent bridge maintenance decisions.

[0007] (2) Currently, most methods for assessing the status of the anchor structure of bridge expansion joints still rely on manual on-site visual inspections on a regular basis, which has the following shortcomings: First, there is a lack of in-depth detection and disease analysis of the status of the anchor area of ​​the bridge expansion joint; second, on-site inspections of bridge expansion joints often require traffic interruption, and the efficiency of manual operations and data analysis and processing is extremely low, seriously affecting the efficiency of vehicle traffic; third, regular manual inspections often have a lag, making it difficult to prevent sudden failures of the anchor structure of the bridge expansion joint.

[0008] (3) Although the SHM system is advanced and powerful, it is very expensive and requires very high professional skills from operators and data processors, so its popularity still needs to be improved. In addition, the SHM system is extremely dependent on data collected by sensors. The entire bridge structure is complex. Under complex environments such as vehicle loads, wind, and vibration, the data collected by the deployed sensors will contain a large amount of noise, which seriously affects the subsequent data analysis. Existing research on bridge monitoring data processing only uses specific algorithms to "fine-tune" data of specified categories, which fails to effectively remove noise and lacks applicability. Summary of the Invention

[0009] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a method, system, medium and equipment for detecting the anchor structure of a bridge expansion device.

[0010] In a first aspect, a method for detecting the anchor structure of a bridge expansion device is provided, comprising:

[0011] S1. Prefabricate the standard parts of the bridge expansion device anchor structure and obtain the dynamic sensing data of the standard parts under different working conditions;

[0012] S2. training a denoising neural network for the benchmark dynamic characteristics of the anchor structure of the bridge expansion device based on the dynamic sensing data of the standard parts under different working conditions;

[0013] S3, collecting dynamic sensor data of the anchor structure of the expansion and contraction device of the bridge to be tested, and obtaining dynamic characteristic data of the anchor structure of the expansion and contraction device of the bridge to be tested through preprocessing and neural network analysis;

[0014] S4. Calculate the difference coefficient between the dynamic characteristic data of the anchor structure of the bridge expansion device to be tested and the dynamic sensing data of the standard component under different working conditions; and determine the dynamic characteristic state of the anchor structure of the bridge expansion device to be tested based on the difference coefficient.

[0015] Preferably, S1 includes:

[0016] S101, prefabricated bridge expansion device anchoring structural standard parts, said standard parts including: bridge expansion device, concrete and bridge plate;

[0017] S102, dividing the standard parts into working condition zones, wherein the working condition zones include: a bridge expansion device working condition zone, a concrete working condition zone, a bridge expansion device and concrete interface working condition zone, and a concrete and bridge plate end interface working condition zone; the concrete working condition zone is embedded with a sensor;

[0018] S103, setting multiple sub-operating conditions for each operating zone;

[0019] S104 , collecting dynamic sensing data of the standard component in each sub-operating state through the sensor.

[0020] Preferably, in S103, the setting of multiple sub-operating conditions for each operating zone includes:

[0021] S1031, setting the bridge expansion and contraction device working condition zone to the initial intact state, intact to yield state, yield state, yield to fracture state, and fracture state;

[0022] S1032, setting the concrete working area to a concrete dense state, a first void state, a second void state, a third void state, and a fourth void state; wherein the void proportions corresponding to the first void state, the second void state, the third void state, and the fourth void state increase in sequence;

[0023] S1033, setting the bridge expansion device and concrete interface working condition zone to a fully bonded state, a first disengaged state, a second disengaged state, a third disengaged state, and a fully disengaged state; the disengagement degrees of the first disengaged state, the second disengaged state, and the third disengaged state increase in sequence;

[0024] S1034. The working condition zone of the interface between the concrete and the end of the bridge slab is set to the complete bonding state, the fourth disengagement state, the fifth disengagement state, the sixth disengagement state and the seventh disengagement state; the degree of disengagement of the fourth disengagement state, the fifth disengagement state, the sixth disengagement state and the seventh disengagement state increases in sequence.

[0025] Preferably, S2 includes:

[0026] S201, preprocessing the power sensing data of the standard component under different working conditions, wherein the preprocessing includes: adding Gaussian noise;

[0027] S202, inputting the power sensor data after adding Gaussian noise into the Transformer neural network;

[0028] S203, calculating a loss function according to the output of the Transformer neural network;

[0029] S204. Iteratively update the neural network parameters by minimizing the loss function, repeat S201-S203 until the loss error converges to a preset value, and obtain the target neural network.

[0030] Preferably, in S4, the working condition of the standard part corresponding to the minimum value of the difference coefficient is used as the dynamic characteristic state of the anchor structure of the bridge expansion device to be tested.

[0031] In a second aspect, a bridge expansion device anchor structure detection system is provided, which is configured to execute any of the methods described in the first aspect, including:

[0032] An acquisition module is used to prefabricate standard parts of anchor structures for bridge expansion devices and obtain dynamic sensing data of standard parts under different working conditions;

[0033] A training module for training a denoising neural network for the benchmark dynamic characteristics of the anchor structure of the bridge expansion device based on the dynamic sensing data of the standard parts under different working conditions;

[0034] The acquisition module is used to collect the dynamic sensing data of the anchor structure of the bridge expansion device to be detected, and obtain the dynamic characteristic data of the anchor structure of the bridge expansion device to be detected through preprocessing and neural network analysis.

[0035] A calculation module is used to calculate the difference coefficient between the dynamic characteristic data of the anchor structure of the bridge expansion device to be tested and the dynamic sensing data of the standard part under different working conditions; and determine the dynamic characteristic state of the anchor structure of the bridge expansion device to be tested based on the difference coefficient.

[0036] According to a third aspect, a computer storage medium is provided, wherein a computer program is stored in the computer storage medium; when the computer program is executed on a computer, the computer executes any one of the methods described in the first aspect.

[0037] In a fourth aspect, an electronic device is provided, including:

[0038] Memory, used to store computer programs;

[0039] A processor is used to execute the computer program to implement any method as described in the first aspect.

[0040] The beneficial effects of the present invention are:

[0041] 1. This invention prefabricates standard components (scalable to appropriate sizes) based on the construction process, structure, and construction characteristics of newly constructed bridge expansion device anchor structures. These components are divided into representative operating zones, and sensors are simultaneously installed on both the standard components and the newly constructed bridge expansion device anchor structures. This ensures that real-time detection data can be collected from the newly constructed structures during their service life. This detection data can also be compared with the different sub-operating conditions set for each operating zone of the standard components. This enables real-time status detection of the bridge expansion device anchor structures during their service life, providing timely feedback on the service status without interrupting traffic.

[0042] 2. Compared with current research that mostly focuses on the study of bridge expansion devices or concrete transition zones, this proposal divides representative working conditions into zones and sets multiple sub-working conditions to comprehensively evaluate the working conditions of the anchor structure of the bridge expansion device from multiple aspects, resulting in more accurate evaluation results.

[0043] 3. Currently, there is very little research on the application of deep learning technology to evaluate the service condition of bridge expansion joint anchor structures. This paper proposes a denoising neural network for the benchmark dynamic characteristics of bridge expansion joint anchor structures. During the training process, the network learns the deep characteristics of dynamic data for each operating zone and each sub-operating condition, enabling it to parse input data to obtain the corresponding bridge expansion joint anchor structure characteristic data. Secondly, the denoising network training technique introduces real noise data, training the network to generate data with the same characteristics. After receiving actual test data, the trained denoising network generates noise data. Then, through denoising calculations, noise-free bridge expansion joint anchor structure status data is obtained. This significantly reduces the analytical difficulty of bridge facility maintenance decision-making and solves the problem that existing data refinement technologies easily disturb the original data and have poor denoising effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A flow chart of a method for detecting the anchoring structure of a bridge expansion device provided by the present invention;

[0045] Figure 2 A schematic diagram of the structure of the standard anchoring structure of the bridge expansion device provided by the present invention;

[0046] Figure 3 A schematic diagram of the working area division of the standard anchor structure component of the bridge expansion device provided by the present invention;

[0047] Figure 4 A schematic diagram of another working area division of the standard anchoring structure component of the bridge expansion device provided by the present invention;

[0048] Figure 5 A schematic structural diagram of a bridge expansion device anchorage structure detection system provided by the present invention;

[0049] Explanation of the accompanying symbols: bridge slab 1, concrete 2, bridge expansion device 3, bridge expansion device working area A, concrete working area B, bridge expansion device and concrete interface working area C, concrete and bridge slab end interface working area D. DETAILED DESCRIPTION

[0050] The present invention will be further described below with reference to the following examples. The following examples are provided only to facilitate understanding of the present invention. It should be noted that, without departing from the principles of the present invention, it is possible for a person skilled in the art to make various modifications to the present invention, and such improvements and modifications fall within the scope of the claims of the present invention.

[0051] Example 1:

[0052] In order to solve the problems of the prior art, the embodiment 1 of the present application provides a method for detecting the anchor structure of a bridge expansion device, so as to realize real-time detection of the anchor structure state of the bridge expansion device without interrupting traffic. Specifically, Figure 1 As shown, the method includes:

[0053] S1. Anchor structural standard parts of prefabricated bridge expansion devices and obtain dynamic sensing data of standard parts under different working conditions.

[0054] S1 includes:

[0055] S101, prefabricated bridge expansion device anchor structure standard parts, according to the structure style and process of the expansion device anchor structure of the bridge to be tested. Figure 2 As shown, the standard parts include: bridge expansion device 3, concrete 2 and bridge plate 1.

[0056] S102, dividing the standard parts into working condition areas, such as Figure 3 and Figure 4 As shown, the working zones include: bridge expansion device working zone A, concrete working zone B, bridge expansion device and concrete interface working zone C, and concrete and bridge slab end interface working zone D. Sensors are embedded in concrete working zone B. These sensors can be paired fiber optic sensors.

[0057] S103. Set multiple sub-operating conditions for each operating zone.

[0058] For example, the sub-operating state of the operating zone is recorded as A {a} 、B {b} 、C {c} 、D {d}, representing respectively: fatigue state of bridge expansion device in working condition zone A, concrete void defect state in working condition zone B, detachment state of interface between bridge expansion device and concrete in working condition zone C, detachment state of interface between bridge expansion device and concrete, and detachment state of interface between concrete and end of bridge slab in working condition zone D.

[0059] Specifically, in S103, the setting of multiple sub-operating conditions for each operating zone includes:

[0060] S1031. Set the bridge expansion device working condition zone A to the initial intact state, intact to yield state, yield state, yield to fracture state and fracture state.

[0061] For example, the fatigue state of the bridge expansion device {a}∈{0, 0.25, 0.5, 0.75, 1} represents the initial intact state, intact to yield state, yield state, yield to fracture state, and fracture state of the bridge expansion device, respectively.

[0062] S1032. Set the concrete dense state, the first void state, the second void state, the third void state and the fourth void state for the concrete working area B; the void proportions corresponding to the first void state, the second void state, the third void state and the fourth void state increase in sequence.

[0063] For example, the concrete void defect state {b}∈{0, 0.15, 0.25, 0.35, 0.5} represents the concrete dense state, void 15% state, void 25% state, void 35% state, and void 50% state, respectively.

[0064] S1033. The working condition zone C between the bridge expansion device and the concrete interface is set to a fully bonded state, a first disengaged state, a second disengaged state, a third disengaged state, and a fully disengaged state; the disengagement degrees of the first disengaged state, the second disengaged state, and the third disengaged state are increased in sequence.

[0065] For example, the disengagement state between the bridge expansion device and the concrete interface {c}∈{0, 0.25, 0.5, 0.75, 1} respectively represents the state of complete bonding between the bridge expansion device and the concrete interface, the state of 25% disengagement, the state of 50% disengagement, the state of 75% disengagement, and the state of complete disengagement.

[0066] S1034. The working condition zone D of the interface between the concrete and the end of the bridge slab is set to the complete bonding state, the fourth disengagement state, the fifth disengagement state, the sixth disengagement state and the seventh disengagement state; the degree of disengagement of the fourth disengagement state, the fifth disengagement state, the sixth disengagement state and the seventh disengagement state increases in sequence.

[0067] For example, the interface detachment state between concrete and the end of the bridge slab {d}∈{0, 0.15, 0.25, 0.35, 0.5} represents the complete bonding state, 15% detachment state, 25% detachment state, 35% detachment state, and 50% detachment state between the interface between concrete and the end of the bridge slab, respectively.

[0068] In S103, the standard parts are arranged and combined according to the set working conditions and the corresponding working conditions. Therefore, there are 5 standard parts in this embodiment. 4 (four working conditions, each working condition has 5 states), the serial number of a single standard part is recorded as i, then i∈[1, 2, 3......5 4 ].

[0069] S104 , collecting dynamic sensing data of the standard component in each sub-operating state through the sensor.

[0070] Specifically, a pair of sensors are set up when making standard parts, one of which is used to generate a pulse signal of a specific frequency. The pulse energy is transmitted inside the standard part, and the other sensor collects the signal, that is, data collection. What is collected is the dynamic sensing data of the standard part of the anchor structure of the bridge expansion device. It should be noted that the dynamic sensing data collected by the sensor is the first-order natural frequency of the anchor structure of the bridge expansion device. The first-order natural frequency is an inherent property of the rigid object as a whole; the first-order natural frequency changes with the rigidity and constraint conditions (boundary conditions) of the object itself. The anchor structure of the bridge expansion device should be regarded as a whole under the joint anchoring action of the expansion device, concrete and adjacent interfaces. Combined with the example Figure 4 Considering the actual installation and construction methods of the structure, the sensor actually collects the first-order natural frequency data for concrete working area B. Changes in the working conditions of any working area will also cause corresponding changes in the collected data (changes in A, C, or D, i.e., changes in the constraints of B, will cause changes in B's natural frequency data; changes in voids or damage within B, i.e., changes in B's rigidity, will cause changes in B's natural frequency data). The sub-working conditions set by the present invention exhaustively enumerate all possible permutations and combinations, thus including data for each sub-working condition when it is effective independently and when it is effective in conjunction with each other.

[0071] The power sensor data collected by each standard component is recorded as: i [A {a} 、B {b} 、C {c} 、D {d} ].

[0072] Specifically, the dynamic sensing data of the first standard part is recorded as: x1[A {0} 、B {0} 、C {0} 、D {0}], representing the dynamic sensing data of the standard anchor structure components of the bridge expansion device in the initial intact state, the dense concrete state, the complete bonding state between the bridge expansion device and the concrete interface, and the complete bonding state between the concrete and the end of the bridge plate; ... By analogy, the dynamic sensing data of the last component is recorded as: x 625 [A {1} 、B {0.5} 、C {01} 、D {0.5} ], which represents the dynamic sensing data of the standard parts of the anchor structure of the bridge expansion device in the broken state, 50% concrete void state, complete detachment state between the bridge expansion device and the concrete interface, and 50% detachment state between the concrete and the end of the bridge plate.

[0073] Specifically, the power sensor data collected by the i-th standard component is X i , i∈[1,2,3......5 4 ]; all X i The set is the benchmark dynamic characteristic data; in this example, the standard part 5 is made 4 indivual.

[0074] S2. Based on the dynamic sensing data of the standard parts under different working conditions, a denoising neural network of the benchmark dynamic characteristics of the anchor structure of the bridge expansion device is trained.

[0075] S3. Collect dynamic sensing data of the anchor structure of the expansion and contraction device of the bridge to be detected, and obtain dynamic characteristic data of the anchor structure of the expansion and contraction device of the bridge to be detected through preprocessing and neural network analysis.

[0076] S4. Calculate the difference coefficient between the dynamic characteristic data of the anchor structure of the bridge expansion device to be tested and the dynamic sensing data of the standard component under different working conditions; and determine the dynamic characteristic state of the anchor structure of the bridge expansion device to be tested based on the difference coefficient.

[0077] Example 2:

[0078] Based on Example 1, Example 2 of the present application provides a more specific method for detecting the anchor structure of a bridge expansion device, including:

[0079] S1. Anchor structural standard parts of prefabricated bridge expansion devices and obtain dynamic sensing data of standard parts under different working conditions.

[0080] S2. Based on the dynamic sensing data of the standard parts under different working conditions, a denoising neural network of the benchmark dynamic characteristics of the anchor structure of the bridge expansion device is trained.

[0081] S2 includes:

[0082] S201 , preprocessing the dynamic sensing data (denoted as X0) of the standard component under different working conditions, wherein the preprocessing includes adding Gaussian noise.

[0083] Specifically, add t-times Gaussian noise to X0 to get data X t , the formula is as follows:

[0084] , formula (1);

[0085] In formula (1): X t Represents the data obtained by adding Gaussian noise to X0 t times; t is a random positive integer, t∈(1, 2, 3...T], T is a large positive integer; e is a random sampling noise value that obeys the standard normal distribution N(0, 1); set the weight coefficient: 0.99≤α t ≤0.99999; .

[0086] S202: Input the power sensor data after adding Gaussian noise into the Transformer neural network.

[0087] Specifically, (X t , t) is input to the Transformer neural network, and the neural network outputs ε θ (X t , t). The role of the neural network is to receive the data of the actual component to be tested in the subsequent S3, and then generate data with certain distribution characteristics (the network has been trained to have this ability).

[0088] S203. Calculate a loss function based on the output of the Transformer neural network.

[0089] The loss function is expressed as:

[0090] loss=||e-ε θ (X t , t)|| 2

[0091] In the formula, e is the true value, ε θ (X t , t) as the predicted value.

[0092] S204. Iteratively update the neural network parameters by minimizing the loss function, repeat S201-S203 until the loss error converges to a preset value, and obtain the target neural network.

[0093] Among them, the target neural network is the benchmark dynamic characteristic denoising neural network N of the anchor structure of the bridge expansion device.

[0094] Specifically, the preset value can be set to a small positive number, which in this example is set to 0.0000001.

[0095] Specifically, a standard part data is trained to obtain a benchmark denoising network, denoted as N i , i∈[1,2,3......5 4 ]; Therefore, in this example, the training results are 5 4 A denoising network.

[0096] Specifically, train a single denoising network N i When training a denoising network N, the noise e is added to the original data X0 t times. Each added noise is randomly sampled and obeys the standard normal distribution. i When the number of samples is 1, 2, 3, ..., T], an integer t is generated, and then t different noises e are sampled, and t different α items are generated at the same time (0.99≤α t ≤0.99999); each N in training i T can be fixed or set independently. In this example, T is set to 2000 for ease of calculation.

[0097] Specifically, according to formula (1) of S201, X0 is used as the initial data. After the first noise e1 and weight coefficient α1 are added for the first time (t1), the data X1 is obtained, which is expressed as Similarly, X2 is added with the second noise e2 and weight coefficient α2 for the second time (t2) to obtain X3, which is expressed as ; ... and so on, the data X obtained for the tth time t , is the data X of the previous time (t-1) t-1 Add the tth noise data e t And the corresponding weight coefficient α t When the number of times t that noise is added is large enough, the data X t Obey the standard normal distribution.

[0098] S3. Collect dynamic sensing data of the anchor structure of the expansion and contraction device of the bridge to be detected, and obtain dynamic characteristic data of the anchor structure of the expansion and contraction device of the bridge to be detected through preprocessing and neural network analysis.

[0099] For example, the dynamic sensing data of the anchor structure of the bridge expansion device to be tested is recorded as G, and the dynamic characteristic data of the anchor structure of the bridge expansion device to be tested is recorded as H. S3 includes:

[0100] S301, pre-process the power sensor data G, the initial data G is recorded as G0, and the processed data is recorded as G t , the preprocessing method is as follows:

[0101] , formula (2);

[0102] According to the method described in S2, the number t, the weight coefficient term β, the random noise value E that obeys the standard normal distribution N (0, 1), and the calculated G t .

[0103] S302, against G t Perform i rounds of denoising analysis;

[0104] Specifically, the i-th round uses the i-th denoising network N i To G t Perform denoising analysis, single N i The data obtained by analysis is recorded as H i ;

[0105] Remember, G t H0 is the initial data of the parsing process; specifically, the parsing steps of each round are: input H0 into the denoising network N i , N i The output data is E θ (H t , t), θ represents the neural network parameters; the number t and the weight coefficient β are determined by step S31, and then H is calculated as follows: t-1 :

[0106] , formula (3);

[0107] H t-1 Enter N again i , calculate t times according to formula (3) to get H t . Then a single N i The data obtained by analysis is H t,i , denoted as H i , all H i The set of is H.

[0108] S4. Calculate the difference coefficient between the dynamic characteristic data of the anchor structure of the bridge expansion device to be tested and the dynamic sensing data of the standard component under different working conditions; and determine the dynamic characteristic state of the anchor structure of the bridge expansion device to be tested based on the difference coefficient.

[0109] In S4, the actual dynamic characteristic data H is calculated. i Compared with the benchmark dynamic characteristic data X i The dynamic characteristic state of the anchor structure of the actual bridge expansion device to be tested is obtained based on the difference analysis.

[0110] Specifically, S4 includes:

[0111] S401. Calculate the difference according to the following formula (4) to obtain i difference coefficients:

[0112] , formula (4);

[0113] In the formula, the coefficient of difference K i Represents the i-th actual dynamic characteristic data H i and the i-th benchmark dynamic characteristic data X i The difference between P(X i ) and Q (H i ) represent the benchmark dynamic characteristic data X i and the dynamic characteristic data H of the actual detection of the anchor structure of the bridge expansion device i data distribution.

[0114] S402, calculate min{K i}, that is, the minimum value of the i-th difference coefficient, and the corresponding i-th group of standard parts working conditions are the actual working conditions for actually testing the anchoring structure of the bridge expansion device.

[0115] For example: when the minimum value of the difference coefficient is calculated, the serial number i corresponds to the first group of working conditions of the standard part, then [A {0} 、B {0} 、C {0} 、D {0} ], that is, the anchoring structure of the bridge expansion device: the bridge expansion device is in intact condition, the concrete area is in a dense state, the interface between the bridge expansion device and the concrete is completely bonded, and the interface between the concrete and the end of the bridge plate is completely bonded.

[0116] It should be noted that the parts in this embodiment that are the same or similar to those in Example 1 can be referenced to each other and will not be described in detail in this application.

[0117] Example 3:

[0118] Based on Example 2, Example 3 of the present application provides a bridge expansion device anchor structure detection system, including:

[0119] The acquisition module is used to prefabricate standard parts of the anchor structure of the bridge expansion device and obtain the dynamic sensing data of the standard parts under different working conditions.

[0120] Specifically, in this solution, prefabricated standard components are equipped with fiber optic sensors. During deployment, the sensor body resides within the specimen, with transmission lines extending to the outside of the specimen for connection to an external data acquisition module. Similarly, the present invention applies to newly constructed bridge expansion device anchor structures. During installation and construction, sensors are deployed according to the present invention's solution at the appropriate locations. During service, the sensor leads can be connected to the data acquisition module of the present invention system.

[0121] A training module is used to train a denoising neural network of the benchmark dynamic characteristics of the anchor structure of the bridge expansion device based on the dynamic sensing data of the standard parts under different working conditions.

[0122] The acquisition module is used to collect the dynamic sensing data of the anchor structure of the bridge expansion device to be detected, and obtain the dynamic characteristic data of the anchor structure of the bridge expansion device to be detected through preprocessing and neural network analysis.

[0123] A calculation module is used to calculate the difference coefficient between the dynamic characteristic data of the anchor structure of the bridge expansion device to be tested and the dynamic sensing data of the standard part under different working conditions; and determine the dynamic characteristic state of the anchor structure of the bridge expansion device to be tested based on the difference coefficient.

[0124] It should be noted that the system provided in this embodiment is a system corresponding to the method provided in Example 2. Therefore, the parts in this embodiment that are the same or similar to those in Example 2 can be referenced to each other and will not be repeated in this application.

Claims

1. A method for detecting the anchor structure of a bridge expansion device, characterized in that: include: S1. Prefabricate the standard parts of the bridge expansion device anchor structure and obtain the dynamic sensing data of the standard parts under different working conditions; S1 includes: S101, prefabricated bridge expansion device anchoring structural standard parts, said standard parts including: bridge expansion device, concrete and bridge plate; S102, dividing the standard parts into working condition zones, wherein the working condition zones include: a bridge expansion device working condition zone, a concrete working condition zone, a bridge expansion device and concrete interface working condition zone, and a concrete and bridge plate end interface working condition zone; the concrete working condition zone is embedded with a sensor; S103, setting multiple sub-operating conditions for each operating zone; S104, collecting dynamic sensing data of the standard component in each sub-operating state through the sensor; S2. training a denoising neural network for the benchmark dynamic characteristics of the anchor structure of the bridge expansion device based on the dynamic sensing data of the standard parts under different working conditions; S3, collecting dynamic sensor data of the anchor structure of the expansion and contraction device of the bridge to be tested, and obtaining dynamic characteristic data of the anchor structure of the expansion and contraction device of the bridge to be tested through preprocessing and neural network analysis; S4. Calculate the difference coefficient between the dynamic characteristic data of the anchor structure of the bridge expansion device to be tested and the dynamic sensing data of the standard component under different working conditions; and determine the dynamic characteristic state of the anchor structure of the bridge expansion device to be tested based on the difference coefficient.

2. The method for detecting the anchoring structure of a bridge expansion device according to claim 1, characterized in that: In S103, the setting of multiple sub-operating conditions for each operating zone includes: S1031, setting the bridge expansion and contraction device working condition zone to the initial intact state, intact to yield state, yield state, yield to fracture state, and fracture state; S1032, setting the concrete working area to a concrete dense state, a first void state, a second void state, a third void state, and a fourth void state; wherein the void proportions corresponding to the first void state, the second void state, the third void state, and the fourth void state increase in sequence; S1033, setting the bridge expansion device and concrete interface working condition zone to a fully bonded state, a first disengaged state, a second disengaged state, a third disengaged state, and a fully disengaged state; the disengagement degrees of the first disengaged state, the second disengaged state, and the third disengaged state increase in sequence; S1034. The working condition zone of the interface between the concrete and the end of the bridge slab is set to the complete bonding state, the fourth disengagement state, the fifth disengagement state, the sixth disengagement state and the seventh disengagement state; the degree of disengagement of the fourth disengagement state, the fifth disengagement state, the sixth disengagement state and the seventh disengagement state increases in sequence.

3. The method for detecting the anchoring structure of a bridge expansion device according to claim 2, characterized in that: S2 includes: S201, preprocessing the power sensing data of the standard component under different working conditions, wherein the preprocessing includes: adding Gaussian noise; S202, inputting the power sensor data after adding Gaussian noise into the Transformer neural network; S203, calculating a loss function according to the output of the Transformer neural network; S204. Iteratively update the neural network parameters by minimizing the loss function, repeat S201-S203 until the loss error converges to a preset value, and obtain the target neural network.

4. The method for detecting the anchoring structure of a bridge expansion device according to claim 3, characterized in that: In S4, the working condition of the standard component corresponding to the minimum value of the difference coefficient is used as the dynamic characteristic state of the anchor structure of the bridge expansion device to be tested.

5. A bridge expansion device anchor structure detection system, characterized in that: The method for executing any one of claims 1 to 4 comprises: An acquisition module is used to prefabricate standard parts of anchor structures for bridge expansion devices and obtain dynamic sensing data of standard parts under different working conditions; A training module for training a denoising neural network for the benchmark dynamic characteristics of the anchor structure of the bridge expansion device based on the dynamic sensing data of the standard parts under different working conditions; An acquisition module is used to collect dynamic sensor data of the anchor structure of the bridge expansion device to be tested, and obtain dynamic characteristic data of the anchor structure of the bridge expansion device to be tested through preprocessing and neural network analysis; A calculation module is used to calculate the difference coefficient between the dynamic characteristic data of the anchor structure of the bridge expansion device to be tested and the dynamic sensing data of the standard part under different working conditions; and determine the dynamic characteristic state of the anchor structure of the bridge expansion device to be tested based on the difference coefficient.

6. A computer storage medium, characterized in that The computer storage medium stores a computer program; when the computer program is run on a computer, the computer executes the method according to any one of claims 1 to 4.

7. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the method according to any one of claims 1 to 4.

Images