Method, device and equipment for monitoring the state of a bridge during its construction

Abstract

A method, device, and equipment for monitoring the bridge condition during bridge construction are provided. The monitoring method includes: acquiring sensor monitoring datasets at different characteristic locations of the bridge during the current construction stage; preprocessing the sensor monitoring datasets to obtain a preprocessed dataset; extracting key feature data from the preprocessed dataset to obtain a feature dataset for the current construction stage; performing data fusion processing on the feature datasets to obtain a feature fusion dataset; inputting the fused strain data, stress data, strength data, and geometric alignment data from the feature fusion dataset into a pre-established overall bridge finite element model to obtain a first alignment dataset, wherein the first alignment dataset represents the set of alignment data at each location of the bridge during the current construction stage; obtaining an alignment matching degree set based on the first alignment dataset and a preset first alignment dataset; and determining a preset second alignment dataset for the next construction stage based on the alignment matching degree set.

Description

Technical Field

[0001] This invention relates to the field of bridge structure monitoring, and in particular to a method, device and electronic equipment for monitoring the bridge condition during bridge construction. Background Technology

[0002] Bridges overcome geographical barriers, providing a medium for expanding the scope of human activities and becoming an important channel for expanding human living space, greatly promoting social development. With the advancement of science and technology and the improvement of economic, social, and cultural levels, the scale of bridge construction is constantly expanding, and people have higher requirements for the condition of bridges.

[0003] Currently, increasing health monitoring during bridge operation and monitoring bridge safety indicators, along with implementing compensatory measures based on monitoring results, aims to improve bridge lifespan and safety. However, with increasingly stringent requirements for bridges, this approach is no longer sufficient to meet the needs of modern bridges regarding lifespan and safety. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method for monitoring the bridge condition during bridge construction, a device for monitoring the bridge condition during bridge construction, and an electronic device.

[0005] One aspect of the present invention provides a method for monitoring the state of a bridge during bridge construction, comprising: acquiring sensor monitoring datasets at different bridge feature locations during the current construction stage, wherein the sensor monitoring datasets are collected by multiple sensors installed at different bridge feature locations; performing preprocessing operations on the sensor monitoring datasets to obtain a preprocessed dataset; extracting key feature data from the preprocessed datasets to obtain a feature dataset for the current construction stage; performing data fusion processing on the feature datasets to obtain a feature fusion dataset; inputting the fused strain data, stress data, strength data, and geometric alignment data from the feature fusion datasets into a pre-established overall bridge finite element model to obtain a first alignment dataset, wherein the first alignment dataset represents a set of alignment data at each location of the bridge during the current construction stage; obtaining an alignment matching degree set based on the first alignment dataset and a preset first alignment dataset; and determining a preset second alignment dataset for the next construction stage based on the alignment matching degree set.

[0006] According to an embodiment of the present invention, the preprocessing operation on the sensor monitoring dataset to obtain a preprocessed dataset includes: inputting strain data, stress data, strength data, and geometric linearity data from the sensor monitoring dataset into a Naive Bayes classifier to obtain a maximum a posteriori probability estimate; based on the maximum a posteriori probability estimate, distinguishing between normal data and outliers in the strain data, stress data, strength data, and geometric linearity data; and removing the outliers from the sensor monitoring dataset to obtain the preprocessed dataset.

[0007] According to an embodiment of the present invention, the step of extracting key feature data from the preprocessed dataset to obtain a feature dataset includes: converting the time-domain features corresponding to strain data, stress data, strength data, and geometric linearity data in the preprocessed dataset into principal component variables through orthogonal transformation; sorting the principal component variables in descending order of variance; determining the feature information of the strain data, stress data, strength data, and geometric linearity data based on the sorted principal component variables; extracting key feature data corresponding to the feature information from the strain data, stress data, strength data, and geometric linearity data; and normalizing the extracted key feature data to obtain the feature dataset.

[0008] According to an embodiment of the present invention, the step of performing data fusion processing on the feature dataset to obtain the feature fusion dataset includes: inputting the feature dataset obtained after extracting key feature data of the current construction stage into the input gate of an LSTM model; and outputting the feature fusion dataset after fusing the current construction stage based on the feature dataset and forgotten data, wherein the forgotten data is represented as the feature fusion dataset output by the LSTM model in the previous construction stage.

[0009] According to an embodiment of the present invention, after inputting the strain data, stress data, strength data, and geometric alignment data fused from the feature fusion dataset into a pre-established overall bridge finite element model, the method further includes: obtaining a first stress dataset output by the overall bridge finite element model, wherein the first stress dataset represents a set of stress data at each location of the bridge during the current construction phase; determining whether there are stress anomalies in the first stress dataset based on the first stress dataset and the preset first stress dataset; determining the cause of the anomaly if stress anomalies exist in the first stress dataset; and performing stress compensation on the stress anomalies using a compensation strategy based on the cause of the anomaly.

[0010] According to an embodiment of the present invention, determining the preset second alignment dataset for the next construction stage based on the alignment matching degree set includes: determining the first pre-camber set for the next construction stage based on the alignment matching degree set; inputting the first pre-camber set into the overall bridge finite element model to obtain the preset alignment dataset for the next construction stage; determining whether the preset alignment dataset meets the first alignment evaluation criterion; and determining the preset alignment dataset as the preset second alignment dataset if the preset alignment dataset meets the first alignment evaluation criterion.

[0011] According to an embodiment of the present invention, the method further includes: using the stress data after centralized fusion of the feature fusion data to evaluate the bridge stress safety status at different bridge feature locations in the current construction stage; and using the geometric alignment data after centralized fusion of the feature fusion data to evaluate the bridge geometric alignment status at different bridge feature locations in the current construction stage.

[0012] According to an embodiment of the present invention, by setting up a location sensor monitoring base point on the ground, the sensor monitoring dataset is obtained based on the location of the location sensor monitoring base point and the data collected by multiple sensors.

[0013] Another aspect of the present invention provides a bridge condition monitoring device during bridge construction, characterized in that it includes: an acquisition module for acquiring sensor monitoring datasets at different bridge feature locations during the current construction stage, wherein the sensor monitoring datasets are collected by multiple sensors installed at different bridge feature locations; a first obtaining module for preprocessing the sensor monitoring datasets to obtain a preprocessed dataset; a second obtaining module for extracting key feature data from the preprocessed datasets to obtain a feature dataset for the current construction stage; a third obtaining module for performing data fusion processing on the feature datasets to obtain a feature fusion dataset; a fourth obtaining module for inputting the fused strain data, stress data, strength data, and geometric alignment data from the feature fusion datasets into a pre-established overall bridge finite element model to obtain a first alignment dataset, wherein the first alignment dataset represents a set of alignment data at each location of the bridge during the current construction stage; a fifth obtaining module for obtaining an alignment matching degree set based on the first alignment dataset and a preset first alignment dataset; and a first determining module for determining a preset second alignment dataset for the next construction stage based on the alignment matching degree set.

[0014] In another aspect, the present invention provides an electronic device comprising: one or more processors; and a memory configured to store one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the method described above.

[0015] According to embodiments of this disclosure, by setting multiple sensors at different feature locations on the bridge, a sensor monitoring dataset of the bridge at the current construction stage can be obtained. By preprocessing and extracting key feature data from the sensor monitoring dataset, outliers and noise in the transmitted data can be removed, resulting in a feature dataset with less redundant information and a smaller data transmission volume. By performing data fusion processing on the feature dataset, a feature fusion dataset with better timeliness and spatial alignment can be obtained, improving the accuracy of subsequent processing. By inputting the fused strain data, stress data, strength data, and geometric alignment data from the feature fusion dataset into a pre-established overall bridge finite element model, a first alignment dataset corresponding to the current construction stage can be obtained. An alignment matching degree set can be obtained from the first alignment dataset and the preset first alignment dataset. The alignment matching degree set can be used to determine a preset second alignment dataset, ensuring that the error between the preset second alignment dataset and the next construction alignment dataset before adjustment is within the allowable range. This compensates for the impact of data differences between the current construction stage and the preset first alignment dataset on the overall bridge alignment, ensuring the overall bridge alignment requirements, thereby guaranteeing the smooth closure of the closure section and improving the bridge's service life and safety. Attached Figure Description

[0016] The above and other objects, features and advantages of the present invention will become more apparent from the following description of embodiments of the invention with reference to the accompanying drawings, in which:

[0017] Figure 1 The illustration schematically shows an exemplary system architecture of a bridge condition monitoring method applicable to bridge construction according to an embodiment of the present invention;

[0018] Figure 2 A flowchart illustrating a method for monitoring the condition of a bridge during bridge construction according to an embodiment of the present invention is shown schematically.

[0019] Figure 3 This schematically illustrates a flowchart of preprocessing the sensor monitoring dataset according to an embodiment of the present invention to obtain a preprocessed dataset;

[0020] Figure 4 This illustration schematically shows a flowchart of extracting key feature data from the preprocessed dataset to obtain a feature dataset according to an embodiment of the present invention;

[0021] Figure 5 This schematically illustrates a flowchart of performing data fusion processing on the feature dataset according to an embodiment of the present invention to obtain the feature fusion dataset;

[0022] Figure 6 A schematic diagram of an LSTM model according to an embodiment of the present invention is shown.

[0023] Figure 7 The flowchart illustrating the present invention is shown below after the strain data, stress data, strength data, and geometric line data fused in the feature fusion dataset are input into a pre-established overall bridge finite element model.

[0024] Figure 8 This illustration schematically shows a flowchart of determining a preset second linear dataset for the next construction stage based on the linear matching degree set according to an embodiment of the present invention;

[0025] Figure 9 A flowchart illustrating the case where the preset linear dataset does not meet the first linear evaluation criterion, according to an embodiment of the present invention, is shown.

[0026] Figure 10 A block diagram schematically illustrates a bridge condition monitoring device during bridge construction according to an embodiment of the present invention; and

[0027] Figure 11 A block diagram of an electronic device for a method of monitoring the condition of a bridge during bridge construction according to an embodiment of the present invention is shown schematically. Detailed Implementation

[0028] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the invention. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the invention for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concept of the invention.

[0029] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. The terms “comprising,” “including,” etc., as used herein indicate the presence of features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0030] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0031] When using expressions such as "at least one of A, B, and C," the expression should generally be interpreted in accordance with the meaning commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, systems having A alone, having B alone, having C alone, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.). Similarly, when using expressions such as "at least one of A, B, or C," the expression should generally be interpreted in accordance with the meaning commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, or C" should include, but is not limited to, systems having A alone, having B alone, having C alone, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0032] In the process of realizing the concept of this invention, the inventors discovered at least the following problems in the related technology:

[0033] The accuracy of bridge alignment is crucial for ensuring the precision of bridge closure and the safety performance of the bridge. To achieve construction safety and a reasonable bridge alignment, real-time monitoring of the bridge alignment is essential during construction.

[0034] However, data acquired by different types of sensors differ in storage format, data units, and spatiotemporal location, which can lead to problems such as unstable monitoring, equipment failure, and large amounts of data collected.

[0035] In order to at least partially solve the technical problems existing in the related technologies, the present invention provides a method for monitoring the bridge condition during bridge construction.

[0036] According to an embodiment of the present invention, a method for monitoring the condition of a bridge during bridge construction is provided.

[0037] Figure 1 An exemplary system architecture of a bridge condition monitoring method applicable to bridge construction according to an embodiment of the present invention is illustrated.

[0038] It is important to note that Figure 1 The examples shown are merely examples of system architectures that can be applied to embodiments of the present invention, in order to help those skilled in the art understand the technical content of the present invention, but do not mean that embodiments of the present invention cannot be used in other devices, systems, environments or scenarios.

[0039] like Figure 1As shown, the system architecture 100 according to this embodiment may include a monitoring device 101, a terminal device 102, and a network 103. The network 103 serves as a medium for providing a communication link between the monitoring device 101 and the terminal device 102 of the bridge. The network 103 may include various connection types, such as wired and / or wireless communication links, etc.

[0040] Users can use terminal device 102 to interact with monitoring device 101 via network 103 to receive or send messages, etc. Monitoring device 101 and terminal device 102 can have various communication client applications installed.

[0041] The monitoring device 101 can be multiple sensors installed at different characteristic locations on the bridge, such as stress sensors, strain sensors, position sensors, and smart aggregate sensors. The monitoring device 101 can be used to collect strain data, stress data, strength data, and geometric alignment data of the bridge. The terminal device 102 can be various electronic devices with a display screen and web browsing support, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0042] Monitoring device 101 and terminal device 102 can be used in conjunction with terminal devices of various types of servers. For example, the server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. The server can also be a server for a distributed system, or a server combined with blockchain.

[0043] It should be noted that the bridge status monitoring method during bridge construction provided in this embodiment of the invention can generally be executed by the terminal device 102. Alternatively, the bridge status monitoring method during bridge construction provided in this embodiment of the invention can also be executed by a server or server cluster capable of communicating with the monitoring device 101 and the terminal device 102. Or, the bridge status monitoring method during bridge construction provided in this embodiment of the invention can also be executed by a terminal device other than the monitoring device 101 or the terminal device 102.

[0044] For example, the data to be processed can be originally stored in either monitoring device 101 or terminal device 102 (e.g., terminal device 102, but not limited thereto), or it can be stored on an external storage device and imported into terminal device 102. Then, terminal device 102 can locally execute the bridge status monitoring method during bridge construction provided in this embodiment of the invention, or send the data to be processed to other terminal devices, servers, or server clusters, and have other terminal devices, servers, or server clusters that receive the data to be processed execute the bridge status monitoring method during bridge construction provided in this embodiment of the invention.

[0045] It should be understood that Figure 1 The number of terminal devices and networks shown is merely illustrative. Depending on implementation needs, any number of terminal devices and networks can be included.

[0046] It should be noted that the sequence numbers of the operations in the following methods are for descriptive purposes only and should not be considered as indicating the execution order of the operations. Unless explicitly stated otherwise, the method does not need to be executed in the exact order shown.

[0047] Figure 2 A flowchart illustrating a method for monitoring the bridge condition during bridge construction according to an embodiment of the present invention is shown.

[0048] like Figure 2 As shown, the method 200 may include performing operations S210 to S270.

[0049] In operation S210, sensor monitoring datasets for different bridge feature locations are acquired during the current construction phase. These datasets are collected by multiple sensors positioned at different bridge feature locations.

[0050] In operation S220, the sensor monitoring dataset is preprocessed to obtain a preprocessed dataset.

[0051] In operation S230, key feature data are extracted from the preprocessed dataset to obtain the feature dataset of the current construction stage.

[0052] In operation S240, the feature dataset is fused to obtain the feature fused dataset.

[0053] In operation S250, the strain data, stress data, strength data, and geometric alignment data fused from the feature fusion dataset are input into a pre-established overall bridge finite element model to obtain the first alignment dataset. The first alignment dataset represents the collection of alignment data for each location of the bridge during the current construction phase.

[0054] In operation S260, a linear matching degree set is obtained based on the first linear dataset and the preset first linear dataset.

[0055] In operation S270, a preset second linear dataset for the next construction stage is determined based on the linear matching degree set.

[0056] According to embodiments of this disclosure, the locations of different bridge features in the current construction phase can be set based on prior experience, such as the ends of the bridge that connect to the next or previous construction phase, the middle position of the bridge, and the location where the bridge connects to the piers.

[0057] According to embodiments of this disclosure, each location in an existing bridge can be a characteristic location, and the characteristic locations of the bridge can also be a subset of all locations in an existing bridge.

[0058] According to embodiments of this disclosure, multiple sensors can be set at the same characteristic location of a bridge to obtain multiple data at that characteristic location. For example, stress sensors, strain sensors, smart aggregate sensors, and position sensors can be set at the same characteristic location to obtain stress data, strain data, strength data, and geometric shape data at the same characteristic location.

[0059] According to embodiments of this disclosure, the sensor monitoring dataset may include all monitoring data collected by each sensor located at a key location on the bridge, or it may include all monitoring data collected by each sensor located at other locations on the bridge besides the key locations. The sensor monitoring dataset may also be monitoring data collected by one or more sensors as needed; for example, it may be stress data, strain data, strength data, and geometric data collected by stress sensors, strain sensors, smart aggregate sensors, and position sensors. Sensor monitoring data of different types and at different key points can be transmitted via wireless communication (ZigBee) technology to monitoring device 101 or terminal device 102 for storage and processing. Through smart aggregate sensors, concrete strength at different ages can be collected, forming strength-age curves, providing time-varying material parameters for subsequent overall bridge finite element model analysis.

[0060] According to embodiments of this disclosure, the preprocessing operation may be an operation for identifying and removing outliers and noise from the sensor monitoring dataset.

[0061] According to embodiments of this disclosure, the preprocessed dataset can be a collection of data remaining after removing outliers and noise from a sensor monitoring dataset.

[0062] According to embodiments of this disclosure, extracting key feature data from a preprocessed dataset can involve transforming a large number of relevant variables in the preprocessed dataset into fewer irrelevant variables while preserving as much information as possible from the original dataset. The key feature data can be characterized as the irrelevant variables and the information from the preserved original dataset.

[0063] According to embodiments of this disclosure, the feature dataset can be a collection of data after extracting key feature data from a preprocessed dataset. Compared with the preprocessed dataset, the feature dataset can have the characteristics of less redundant feature information and reduced data transmission volume.

[0064] According to embodiments of this disclosure, data fusion processing can be a process of fusing multiple data and related information from a preprocessed dataset to obtain a more stable fusion result. For example, data fusion processing can involve fusing stress datasets, strain data, and strength data corresponding to a certain preprocessed geometric line data to obtain stress information, strain information, and strength information at the corresponding location of the geometric line data. The data after data fusion processing can have better timeliness and spatial alignment. The feature fusion dataset can be a dataset obtained by processing feature datasets through data fusion processing.

[0065] According to embodiments of this disclosure, the pre-established overall bridge finite element model can be a pre-established finite element model of an overall bridge that meets the design alignment and stress requirements. The overall bridge finite element model can be divided into multiple sub-models corresponding to different construction stages according to the construction plan. Based on the actual data of the bridge after the completion of the current construction stage, by changing some data in the overall bridge finite element model corresponding to the current construction stage's sub-model, each data point in the overall bridge finite element model corresponding to the current construction stage can be updated. By changing some data in the overall bridge finite element model corresponding to the current construction stage's sub-model, the data of each sub-model in the overall bridge finite element model can be updated.

[0066] According to embodiments of this disclosure, the first linear dataset can be obtained by changing some linear data in the sub-model corresponding to the current construction stage in the overall bridge finite element model, and then updating the overall bridge finite element model, resulting in linear data at each location in the bridge during the current construction stage. Alternatively, it can be represented as linear data at each location in the sub-model corresponding to the current construction stage.

[0067] According to embodiments of this disclosure, the preset first linear dataset can be a collection of linear data at each location in the sub-model corresponding to the current construction stage before the strain data, stress data, strength data, and geometric linear data fused from the feature fusion dataset are input into the pre-established overall bridge finite element model. The linear data at each location in the sub-model can be set according to the design and construction plan.

[0068] According to embodiments of this disclosure, the linear matching degree set can be a set of data difference values ​​between a first linear dataset and a corresponding first linear dataset after the strain data, stress data, strength data, and geometric linear data of the feature fusion dataset are input into a pre-established overall bridge finite element model.

[0069] According to embodiments of this disclosure, the preset second alignment dataset can be a dataset obtained after adjusting the next construction alignment dataset within the allowable adjustment range of the alignment, for example, 5 mm, based on the alignment matching degree set. The next construction alignment dataset can be characterized as the data in the sub-model corresponding to the next construction stage in the overall bridge finite element model before the strain data, stress data, strength data, and geometric alignment data fused from the feature fusion dataset are input into the pre-established overall bridge finite element model. By adjusting the next construction alignment dataset to obtain the preset second alignment dataset, the error between the preset second alignment dataset and the unadjusted next construction alignment dataset can be kept within the allowable range, compensating for the impact of the data difference between the current construction stage and the preset first alignment dataset on the overall alignment of the bridge.

[0070] According to embodiments of this disclosure, by setting multiple sensors at different feature locations on the bridge, a sensor monitoring dataset of the bridge at the current construction stage can be obtained. By preprocessing and extracting key feature data from the sensor monitoring dataset, outliers and noise in the transmitted data can be removed, resulting in a feature dataset with less redundant information and a smaller data transmission volume. By performing data fusion processing on the feature dataset, a feature fusion dataset with better timeliness and spatial alignment can be obtained, improving the accuracy of subsequent processing. By inputting the fused strain data, stress data, strength data, and geometric alignment data from the feature fusion dataset into a pre-established overall bridge finite element model, a first alignment dataset corresponding to the current construction stage can be obtained. An alignment matching degree set can be obtained from the first alignment dataset and the preset first alignment dataset. The alignment matching degree set can be used to determine a preset second alignment dataset, ensuring that the error between the preset second alignment dataset and the next construction alignment dataset before adjustment is within the allowable range. This compensates for the impact of data differences between the current construction stage and the preset first alignment dataset on the overall bridge alignment, ensuring the overall bridge alignment requirements, thereby guaranteeing the smooth closure of the closure section and improving the bridge's service life and safety.

[0071] Figure 3 The flowchart illustrating the preprocessing operation of a sensor monitoring dataset according to an embodiment of the present invention is shown.

[0072] like Figure 3 As shown, the method 300 may include performing operations S310 to S340.

[0073] When operating S310, the strain data, stress data, strength data, and geometric shape data from the sensor monitoring dataset are input into the Naive Bayes classifier to obtain Bayesian data.

[0074] In operation S320, obtain the maximum posterior probability estimate of the sensor monitoring dataset.

[0075] In operating S330, based on maximum a posteriori probability estimation and Bayesian data, normal data and outliers are distinguished in strain data, stress data, strength data, and geometric linearity data.

[0076] In operation S340, outliers are removed from the sensor monitoring dataset to obtain a preprocessed dataset.

[0077] According to embodiments of this disclosure, based on maximum a posteriori probability estimation, Bayesian rules can be used to determine sensor monitoring datasets and Bayesian data, thereby distinguishing normal data from outliers in the sensor monitoring dataset and achieving the effect of removing outliers and noise from the sensor monitoring dataset.

[0078] Figure 4 The flowchart illustrating the extraction of key feature data from a preprocessed dataset to obtain a feature dataset according to an embodiment of the present invention is shown.

[0079] like Figure 4 As shown, the method 400 may include execution operations S410 to S450.

[0080] In operation S410, the time-domain features corresponding to strain data, stress data, strength data, and geometric linearity data in the preprocessed dataset are transformed into principal component variables through orthogonal transformation.

[0081] In operation S420, the principal component variables are sorted from largest to smallest according to their variance.

[0082] In operation S430, characteristic information of strain data, stress data, strength data, and geometric shape data is determined based on the sorted principal component variables.

[0083] In operation S440, extract key feature data corresponding to feature information from strain data, stress data, strength data, and geometric shape data.

[0084] In operation S450, the extracted key feature data is normalized to obtain the feature dataset.

[0085] According to embodiments of this disclosure, by converting the time-domain features corresponding to strain data, stress data, strength data, and geometric linearity data in the preprocessed dataset into principal component variables through orthogonal transformation, the feature information of strain data, stress data, strength data, and geometric linearity data can be determined using the principal component variables. Then, key feature data corresponding to the feature information can be extracted from the strain data, stress data, strength data, and geometric linearity data. After normalizing the extracted key feature data, a compressed feature dataset can be obtained, which can reduce the amount of data transmitted and improve transmission efficiency.

[0086] Figure 5 The flowchart illustrating the process of performing data fusion processing on a feature dataset according to an embodiment of the present invention to obtain a feature fusion dataset is shown.

[0087] Figure 6 A schematic diagram of an LSTM model according to an embodiment of the present invention is shown.

[0088] like Figure 5 As shown, the method 500 may include execution operations S510 to S520.

[0089] When operating S510, the feature dataset obtained after extracting key feature data in the current construction stage is input into the input gate of the LSTM model.

[0090] In operation with S520, based on the feature dataset and forgotten data, the output gate of the LSTM model outputs the fused feature dataset of the current construction stage. The forgotten data is represented as the feature fused dataset output by the LSTM model in the previous construction stage.

[0091] like Figure 6 As shown, by fusing the features output by the LSTM model from the previous construction stage into the dataset h t-1 and the feature dataset x of the current construction phase t The data can be input as arrays [,] into the forget gate, input gate, and output gate respectively. The forget gate is based on the feature fusion dataset h output by the LSTM model in the previous construction stage. t-1 and the feature dataset x of the current construction phase t The forget gate weight matrix W is updated using the sigmoid function σ. xf Forget gate bias term b f Obtain the output data f of the forget gate t The input gate is based on the feature fusion dataset h output by the LSTM model from the previous construction stage. t-1 and the feature dataset x of the current construction phase t The first weight matrix W of the input gate is updated using the sigmoid function σ. xi Input gate first bias term bi Obtain the first output data i of the input gate t The input gate is based on the feature fusion dataset h output by the LSTM model from the previous construction stage. t-1 and the feature dataset x of the current construction phase t The second weight matrix W of the input gate is updated using the hyperbolic tangent function tanh. xl Input gate second bias term b l Obtain the second output data l of the input gate t The forget gate is based on the feature fusion dataset h output by the LSTM model from the previous construction phase. t-1 and the feature dataset x of the current construction phase t The first weight matrix W of the output gate is updated using the sigmoid function σ. xo Output gate first bias term b o Obtain the first output data o from the input gate t The forget gate is based on the unit state c of the previous construction phase. t-1 The first output data i of the input gate t The output data f of the forget gate t The second output data of the input gate l t Output the unit state c of the current construction stage. t The output gate is based on the first output data of the input gate. t The second output data of the input gate l t The first output data i of the input gate t Unit state c of the previous construction phase t-1 The initial feature fusion dataset h for the current construction stage is obtained by using the hyperbolic tangent function tanh. t The output gate is based on the initial feature fusion dataset h. t The second weight matrix W of the output gate is updated using the sigmoid function σ. hy Output gate second bias term b hy Obtain the feature fusion dataset y for the current construction phase. t .

[0092] Figure 7 The flowchart illustrates, according to an embodiment of the present invention, the process of inputting strain data, stress data, strength data, and geometric line data after the feature fusion dataset is centrally fused into a pre-established overall bridge finite element model.

[0093] like Figure 7 As shown, the method 700 may include execution operations S710 to S740.

[0094] Using the S710, the first stress dataset output from the overall bridge finite element model is obtained. The first stress dataset represents the collection of stress data at each location of the bridge during the current construction phase.

[0095] During operation S720, based on the first stress dataset and the preset first stress dataset, it is determined whether there are stress anomaly points in the first stress dataset.

[0096] In operation S730, if there are stress anomalies in the first stress dataset, determine the cause of the anomaly.

[0097] When operating the S740, stress compensation is performed on stress anomaly points using a compensation strategy based on the cause of the anomaly.

[0098] According to embodiments of this disclosure, the first stress dataset can be obtained by changing some stress data in the sub-model corresponding to the current construction stage in the overall bridge finite element model, and then updating the overall bridge finite element model, resulting in stress data at each location in the bridge during the current construction stage. Alternatively, it can be characterized as stress data at each location in the sub-model corresponding to the current construction stage.

[0099] According to embodiments of this disclosure, the preset first stress dataset can be a set of allowable stress values ​​at each location in the sub-model corresponding to the current construction stage before the strain data, stress data, strength data, and geometric alignment data fused from the feature fusion dataset are input into the pre-established overall bridge finite element model.

[0100] According to an embodiment of this disclosure, a stress anomaly point can be a location where, after the strain data, stress data, strength data, and geometric line data of the feature fusion dataset are centrally fused into a pre-established overall bridge finite element model, the difference between the first stress dataset and the corresponding preset first stress dataset exceeds the allowable range of stress difference.

[0101] According to embodiments of this disclosure, the cause of an anomaly at an abnormal point may be the appearance of localized cracks, localized tensile stress in the prestressed concrete anchorage zone, etc. Compensation strategies may include bonding stress plates, increasing the length of the anchorage zone, or modifying the bending angle of the prestressed steel bars. For example, if the anomaly at an abnormal point is caused by localized tensile stress in the prestressed concrete anchorage zone, the compensation strategy may be to increase the length of the anchorage zone or modify the bending angle of the prestressed steel bars.

[0102] Figure 8 The flowchart illustrating the process of determining a preset second linear dataset for the next construction stage based on a linear matching degree set according to an embodiment of the present invention is shown.

[0103] like Figure 8 As shown, the method 800 may include execution operations S810 to S840.

[0104] In operation S810, the first precamber set for the next construction stage is determined based on the linear matching degree set.

[0105] When operating the S820, the first pre-camber set is input into the overall bridge finite element model to obtain the preset alignment dataset for the next construction stage.

[0106] In operation S830, it is determined whether the preset linear dataset meets the first linear evaluation criterion.

[0107] In operation S840, if the preset linear dataset meets the first linear evaluation criterion, the preset linear dataset is determined to be the preset second linear dataset.

[0108] Figure 9 The flowchart illustrating the present invention is shown in the case where a preset linear dataset does not meet the first linear evaluation criterion.

[0109] like Figure 9 As shown, the method 900 may include repeatedly performing operations S910 to S930 until the preset linear dataset meets the first linear evaluation criterion.

[0110] During operation of S910, the first pre-camber set is adjusted based on the adjustment strategy.

[0111] When operating the S920, the adjusted first precamber set is input into the finite element bridge model to obtain the preset alignment dataset for the next construction stage.

[0112] In operation S930, the preset linear dataset is determined to be the preset second linear dataset.

[0113] According to embodiments of this disclosure, the first precamber set before adjustment can be a collection of precamber data from various construction stages during the initial design.

[0114] According to embodiments of this disclosure, the adjustment strategy may be to adjust the precamber data in the first precamber set so that the preset alignment in the next construction stage meets the first alignment evaluation criteria.

[0115] According to an embodiment of this disclosure, the first alignment evaluation criterion may be to determine the difference between the alignment data in the preset alignment dataset of the next construction stage and the alignment data of the initial design of the next construction stage within the allowable adjustment range of the alignment, for example, the allowable adjustment range of the alignment is -5mm to +5mm.

[0116] According to embodiments of this disclosure, the pre-camber of the bridge in the next construction stage can be repeatedly adjusted using an adjustment strategy. Based on the first alignment evaluation standard, the difference between the preset alignment dataset (i.e., the preset second alignment dataset) and the alignment data of the initial design in the next construction stage can be controlled within the allowable adjustment range of the alignment. This ensures that the alignment of each construction stage meets the design alignment requirements, makes the elevation deviation of the closure section meet the requirements, and thus enables the overall bridge alignment to meet the design alignment requirements.

[0117] According to embodiments of this disclosure, the monitoring method further includes: evaluating the bridge stress safety status at different bridge feature locations during the current construction phase using the stress data centrally fused from the feature fusion dataset; and evaluating the bridge geometric alignment status at different bridge feature locations during the current construction phase using the geometric alignment data centrally fused from the feature fusion dataset.

[0118] According to embodiments of this disclosure, the stress safety status of bridges at different bridge feature locations during the current construction stage can be evaluated by determining whether the stress data after centralized fusion of the feature fusion dataset is less than the allowable stress value [σ]. For example, if the stress data after centralized fusion of the feature fusion dataset is less than the allowable stress value [σ], the stress state at that bridge location can be determined to be safe; otherwise, the stress state at that bridge location is considered abnormal.

[0119] According to embodiments of this disclosure, the geometric alignment status of bridges at different bridge feature locations during the current construction stage can be evaluated by determining whether the difference between the geometric alignment data fused in the feature fusion dataset and the design data of the alignment during bridge design is less than the allowable alignment deviation value X. For example, if the difference between the geometric alignment data fused in the feature fusion dataset and the design data of the alignment during bridge design is less than the allowable alignment deviation value X, it can be determined that the alignment at that bridge location is reasonable; otherwise, the alignment is off.

[0120] According to embodiments of this disclosure, by setting up location sensor monitoring base points on the ground, a sensor monitoring dataset is obtained based on the location of the location sensor monitoring base points and data collected by multiple sensors.

[0121] According to embodiments of this disclosure, outliers can be removed through preprocessing. Then, using an LSTM model, by continuously updating the weight matrix and bias terms, a more accurate feature fusion dataset can be obtained for calculating the overall bridge finite element model. Based on this feature fusion dataset, the first stress dataset and first alignment dataset of the bridge at the current construction stage can be calculated and analyzed using the overall bridge finite element model. This allows for real-time and accurate assessment of the bridge alignment's rationality and structural safety. Furthermore, by adjusting the bridge's pre-camber in the next construction stage, the overall bridge alignment can be ensured to meet design requirements, improving bridge accuracy and construction safety, reducing construction costs, and enhancing the accuracy of bridge alignment and safety status assessment during construction.

[0122] Figure 10 A block diagram illustrating a bridge condition monitoring device during bridge construction according to an embodiment of the present invention is shown.

[0123] like Figure 10 As shown, the bridge status monitoring device 1000 during bridge construction may include an acquisition module 1010, a first acquisition module 1020, a second acquisition module 1030, a third acquisition module 1040, a fourth acquisition module 1050, a fifth acquisition module 1060, and a determination module 1070.

[0124] The acquisition module 1010 is used to acquire sensor monitoring datasets at different bridge feature locations during the current construction phase. These datasets are collected by multiple sensors positioned at different bridge feature locations.

[0125] The first module 1020 is used to perform preprocessing operations on the sensor monitoring dataset to obtain a preprocessed dataset.

[0126] The second module 1030 is used to extract key feature data from the preprocessed dataset to obtain the feature dataset of the current construction stage.

[0127] The third module 1040 is used to perform data fusion processing on the feature dataset to obtain the feature fusion dataset.

[0128] The fourth module 1050 is used to input the strain data, stress data, strength data, and geometric alignment data obtained by centrally fusing the feature fusion dataset into a pre-established overall bridge finite element model to obtain the first alignment dataset. The first alignment dataset represents the collection of alignment data for each location of the bridge during the current construction phase.

[0129] The fifth module 1060 is used to obtain a linear matching degree set based on the first linear dataset and the preset first linear dataset.

[0130] The determination module 1070 is used to determine the preset second linear dataset for the next construction stage based on the linear matching degree set.

[0131] Figure 11 A block diagram of an electronic device for a method of monitoring the condition of a bridge during bridge construction according to an embodiment of the present invention is shown schematically. Figure 11 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0132] like Figure 11 As shown, an electronic device 1100 according to an embodiment of the present invention includes a processor 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage portion 1108 into a random access memory (RAM) 1103. The processor 1101 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1101 may also include onboard memory for caching purposes. The processor 1101 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0133] RAM 1103 stores various programs and data required for the operation of electronic device 1100. Processor 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. Processor 1101 executes various operations of the method flow according to embodiments of the present invention by executing programs in ROM 1102 and / or RAM 1103. It should be noted that programs may also be stored in one or more memories other than ROM 1102 and RAM 1103. Processor 1101 may also execute various operations of the method flow according to embodiments of the present invention by executing programs stored in one or more memories.

[0134] According to an embodiment of the present invention, the electronic device 1100 may further include an input / output (I / O) interface 1105, which is also connected to the bus 1104. The electronic device 1100 may also include one or more of the following components connected to the I / O interface 1105: an input section 1106 including a keyboard, mouse, etc.; an output section 1107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. A removable medium 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1110 as needed so that computer programs read from it can be installed into the storage section 1108 as needed.

[0135] According to embodiments of the present invention, the method flow according to embodiments of the present invention can be implemented as a computer software program. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1109, and / or installed from removable medium 1111. When the computer program is executed by processor 1101, it performs the functions defined in the system of the embodiments of the present invention. According to embodiments of the present invention, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0136] The present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present invention.

[0137] According to embodiments of the present invention, a computer-readable storage medium may be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0138] For example, according to embodiments of the present invention, a computer-readable storage medium may include the ROM 1102 and / or RAM 1103 described above and / or one or more memories other than ROM 1102 and RAM 1103.

[0139] Embodiments of the present invention also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of the present invention. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the methods provided in the embodiments of the present invention.

[0140] When the computer program is executed by the processor 1101, it performs the functions defined in the system / apparatus of this embodiment of the invention. According to embodiments of the invention, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0141] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 1109, and / or installed from the removable medium 1111. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0142] According to embodiments of the present invention, program code for executing the computer programs provided in the embodiments of the present invention can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0143] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features recited in the various embodiments and / or claims of the present invention can be combined and / or combined in various ways, even if such combinations or combinations are not expressly stated in the present invention. In particular, the features described in the various embodiments and / or claims of this invention can be combined and / or combined in various ways without departing from the spirit and teachings of this invention. All such combinations and / or combinations fall within the scope of this invention.

[0144] The embodiments of the present invention have been described above. However, these embodiments are merely illustrative and not intended to limit the scope of the invention. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of the invention is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of the invention, and all such substitutions and modifications should fall within the scope of the invention.

Claims

1. A method for monitoring the condition of a bridge during bridge construction, characterized in that, include: Obtain sensor monitoring datasets at different bridge feature locations during the current construction phase, wherein the sensor monitoring datasets are collected by multiple sensors installed at different bridge feature locations; The strain data, stress data, strength data, and geometric linearity data from the sensor monitoring dataset are input into a Naive Bayes classifier to obtain Bayesian data. Obtain the maximum posterior probability estimate of the sensor monitoring dataset; Based on the maximum a posteriori probability estimate and the Bayesian data, distinguish normal data from outliers in the strain data, stress data, strength data, and geometric linearity data; The outliers are removed from the sensor monitoring dataset to obtain a preprocessed dataset; The time-domain features corresponding to strain data, stress data, strength data, and geometric linearity data in the preprocessed dataset are respectively transformed into principal component variables through orthogonal transformation; Sort the principal component variables in descending order of variance; Based on the sorted principal component variables, the characteristic information of the strain data, stress data, strength data, and geometric shape data is determined; Extract key feature data corresponding to the feature information from the strain data, stress data, strength data, and geometric shape data; The extracted key feature data is then normalized to obtain a feature dataset. The feature dataset obtained after extracting key feature data in the current construction phase is input into the input gate of the LSTM model; Based on the feature dataset and forgotten data, the output gate of the LSTM model outputs the feature fusion dataset after the current construction stage, wherein the forgotten data is represented as the feature fusion dataset output by the LSTM model in the previous construction stage; The strain data, stress data, strength data, and geometric alignment data of the feature fusion dataset are input into the pre-established overall bridge finite element model to obtain the first alignment dataset, wherein the first alignment dataset represents the collection of alignment data at each location of the bridge in the current construction stage. Based on the first linear dataset and the preset first linear dataset, a linear matching degree set is obtained; The preset second linear dataset for the next construction stage is determined based on the linear matching degree set.

2. The monitoring method according to claim 1, characterized in that, After inputting the strain data, stress data, strength data, and geometric shape data obtained by centrally fusing the feature fusion dataset into the pre-established overall bridge finite element model, the following steps are also included: Obtain the first stress dataset output by the overall bridge finite element model, wherein the first stress dataset is characterized as a set of stress data at each location of the bridge during the current construction phase; Based on the first stress dataset and the preset first stress dataset, determine whether there are stress anomaly points in the first stress dataset; If stress anomalies exist in the first stress dataset, determine the cause of the anomaly. Based on the aforementioned causes of the anomaly, a compensation strategy is used to compensate for the stress anomaly points.

3. The monitoring method according to claim 1, characterized in that, The preset second linear dataset for determining the next construction stage based on the linear matching degree set includes: The first pre-camber set for the next construction stage is determined based on the linear matching degree set. The first precamber set is input into the overall bridge finite element model to obtain the preset alignment dataset for the next construction stage; Determine whether the preset linear dataset meets the first linear evaluation criterion; If the preset linear dataset meets the first linear evaluation criterion, the preset linear dataset is determined to be the preset second linear dataset.

4. The monitoring method according to claim 1, characterized in that, Also includes: Using the stress data centrally fused from the aforementioned feature fusion dataset, the stress safety status of the bridge at different bridge feature locations during the current construction phase is evaluated: The geometric alignment data of the bridge at different bridge feature locations is evaluated using the geometric alignment data fused from the feature fusion dataset.

5. The monitoring method according to claim 1, characterized in that, By setting up location sensor monitoring base points on the ground, and based on the location of the location sensor monitoring base points and the data collected by multiple sensors, the sensor monitoring dataset is obtained.

6. A monitoring device for the condition of a bridge during bridge construction, characterized in that, include: The acquisition module is used to acquire sensor monitoring datasets at different bridge feature locations during the current construction phase, wherein the sensor monitoring datasets are collected by multiple sensors set at different bridge feature locations; The first obtaining module is used to input strain data, stress data, strength data, and geometric line data from the sensor monitoring dataset into a Naive Bayes classifier to obtain Bayesian data; obtain the maximum a posteriori probability estimate of the sensor monitoring dataset; based on the maximum a posteriori probability estimate and the Bayesian data, distinguish between normal data and outliers in the strain data, stress data, strength data, and geometric line data; and remove the outliers from the sensor monitoring dataset to obtain a preprocessed dataset. The second obtaining module is used to convert the time-domain features corresponding to strain data, stress data, strength data, and geometric linearity data in the preprocessed dataset into principal component variables through orthogonal transformation; sort the principal component variables in descending order of variance; determine the feature information of the strain data, stress data, strength data, and geometric linearity data based on the sorted principal component variables; extract key feature data corresponding to the feature information from the strain data, stress data, strength data, and geometric linearity data; and normalize the extracted key feature data to obtain a feature dataset. The third module is used to input the feature dataset obtained after extracting key feature data in the current construction stage into the input gate of the LSTM model; based on the feature dataset and forgotten data, the output gate of the LSTM model outputs the feature fusion dataset after the current construction stage, wherein the forgotten data is represented as the feature fusion dataset output by the LSTM model in the previous construction stage; The fourth module is used to input the strain data, stress data, strength data and geometric alignment data after central fusion of the feature fusion dataset into a pre-established overall bridge finite element model to obtain a first alignment dataset, wherein the first alignment dataset represents a set of alignment data for each location of the bridge in the current construction stage. The fifth module is used to obtain a linear matching degree set based on the first linear dataset and the preset first linear dataset; The determination module is used to determine the preset second linear dataset for the next construction stage based on the linear matching degree set.

7. An electronic device, characterized in that, include: One or more processors; as well as The memory is configured to store one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1 to 5.

Images