Bridge construction intelligent monitoring system and method based on digital twinning

Abstract

The invention belongs to the technical field of bridge construction intelligent monitoring, and discloses a bridge construction intelligent monitoring system and method based on digital twinning. The system comprises a construction stress value prediction module, an automatic optimization scheme generation module, a full-life-cycle adaptive optimization module, an extreme working condition simulation module and a distributed cloud edge backup module, obtains a stress prediction value, analyzes the stress prediction value, processes an analysis result to obtain an optimization scheme report, and sends the optimization scheme report to the cloud edge backup module. According to the method, compressive strength data and environment temperature data are analyzed, a tensioning force optimization report is obtained according to an analysis result, the environment temperature data and real-time state change data are judged, a judgment result is analyzed, and a reinforcement scheme report is obtained. The method has the remarkable advantages of being large in bridge construction assisting effect, high in coping capacity and good in operation coping effect in the severe network environment.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring of bridge construction, and more specifically, to a system and method for intelligent monitoring of bridge construction based on digital twins. Background Art

[0002] A bridge generally refers to a structure built across rivers, lakes, and seas to enable vehicles and pedestrians to pass smoothly. In order to adapt to the modern high-speed development of the transportation industry, bridges are also extended to buildings that cross mountain streams, poor geology, or meet other transportation needs to make passage more convenient. Bridges are generally composed of superstructure, substructure, supports and ancillary structures. The superstructure, also known as the span structure, is the main structure for crossing obstacles. The substructure includes abutments, piers and foundations. The supports are force transmission devices installed at the supporting places between the span structure and the piers or abutments. Ancillary structures refer to bridgehead slabs, conical slope protection, bank protection, diversion projects, etc.

[0003] The patent application publication number CN118657380B discloses an intelligent monitoring system and method for bridge steel cofferdam construction based on digital twins. Through real-time linkage of digital twin model scenarios and intelligent assessment, safety warning, and monitoring data, the digital twin model intelligently learns safety emergency response measures (personnel evacuation, reduction of pumping rate, and backflow in the cofferdam). When the safety emergency start-up standard is triggered, the emergency plan is automatically started and the emergency measures are automatically pushed to the relevant responsible persons to carry out emergency measures such as organizing personnel evacuation, broadcasting automatic announcements, and alarming. After the personnel are evacuated, the equipment is automatically controlled to carry out emergency measures such as water pumping and backflow, realizing intelligent handling of emergency plans, improving the efficiency of sudden time processing, and reducing the possibility of safety accidents.

[0004] However, the above-mentioned digital twin-based intelligent monitoring system and method for bridge steel cofferdam construction, although it has achieved intelligent assessment, safety warning and real-time linkage of monitoring data to a certain extent through the digital twin model scenario, during the bridge construction process, most of the existing intelligent monitoring systems rely on threshold alarms and lack active predictions related to construction risks. Moreover, it is difficult to realize the system's auxiliary role for workers. At the same time, because the digital twin models of existing intelligent monitoring systems are mostly static presets, they are unable to cope with sudden changes during the construction process, such as concrete strength changes with weather changes. In addition, for extreme disaster events such as typhoons or earthquakes, the existing intelligent monitoring systems also lack the ability to respond quickly.

[0005] In view of this, the present invention proposes a bridge construction intelligent monitoring system and method based on digital twins to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solutions, including: A construction data collection module is used to collect construction data sets, including beam length data, compressive strength data, initial tension force data, and stage number data; Stress impact data acquisition module, used to collect stress impact data sets, which include ambient temperature data and real-time state change data; A feature data conversion module is used to pre-process the construction data set and the stress impact data set to obtain a feature data set; Furthermore, the steps of preprocessing the construction dataset and the stress impact dataset include: Q1: Normalize all sub-data items in the basic data set to the range of [0, 1] based on the normalization formula; Q2: Calculate the interactive characteristic data based on the compressive strength data and ambient temperature data. The specific calculation formula is: ; Get interactive feature data ,in, is the compressive strength data, is an exponential function, is the ambient temperature data, It is the standard ambient temperature data; Q3: Pack beam length data, compressive strength data, initial tension data, stage number data, interactive feature data, and real-time state change data to obtain a feature data set; A construction stress value prediction module is used to build a construction stress value prediction model based on the historical feature data set and obtain the stress prediction value based on the feature data set; Furthermore, the steps of constructing a construction stress value prediction model based on the historical characteristic data set and obtaining the stress prediction value according to the characteristic data set include: Step 1: Obtain a set of historical feature data sets stored in the database, compare them with the current time based on the timestamp, and group and label the historical feature data sets from small to large according to the comparison results. The labeling results are L1, L2, L3, ..., Ln, and the labeling results are used as the sample set; Step 2: Divide the sample set into a 70% training set, a 15% test set, and a 15% validation set, and establish a stress value prediction model based on the sample set; Step 3: Based on the historical feature data set in the training set, a basic stress value prediction model is constructed by substituting the historical feature data set in the training set into the calculation formula: ; Get the first Predicted foundation stress values ,in, is the number of gradient boosting trees, is the number of decision trees in a single gradient boosting tree, is the learning rate, For the The first gradient boosting tree The piecewise function of a decision tree, is the historical feature dataset in the training set, is the tree structure split point, To modify the weight factor, is the Bayesian regularization term of the historical feature dataset in the training set; Step 4: Based on the foundation stress prediction value in step 3, perform weighted fusion. The specific calculation formula for fusion is: ; Get training stress prediction value ,in, The number of basic stress value prediction models, For the Model weight factors; Step 5: Based on the training stress prediction value in step 4, calculate the absolute value of the training stress prediction value and the actual stress prediction value and multiply it by 100% to obtain the absolute deviation rate. If the absolute deviation rate is greater than or equal to 3%, return to step 3 and retrain. Step 6: Repeat steps 3 to 5 until the preset number of iterations is reached to obtain a stress value prediction model; Step 7: Based on the stress value prediction model in step 5, input the characteristic data set to obtain the stress prediction value; Step 8: Output the stress prediction value to the automatic optimization solution generation module; Automatic optimization scheme generation module is used to analyze the stress prediction value and process the analysis results to obtain the optimization scheme report; Furthermore, the stress prediction value is analyzed and the analysis results are processed in the following ways: Based on stress allowable threshold; When the stress prediction value is less than or equal to the stress allowable threshold, a safety report is generated; When the stress prediction value is greater than the stress allowable threshold, the degree of over-limit is determined; When the predicted stress value is greater than the stress allowable threshold and less than or equal to 1.2 times the stress allowable threshold, a slight overlimit report is generated; When the stress prediction value is greater than 1.2 times the stress allowable threshold, a severe over-limit report is generated; The safety report includes a statement that the predicted construction stress value is normal and that workers are requested to work according to the preset operating procedures; The slight overrun report includes a statement that the predicted construction stress value is slightly abnormal. Please ask the staff to enter Phased construction; The severe over-limit report includes a description of the severe abnormality of the predicted construction stress value. Please ask the staff to increase Tension force parameters; Package safety reports, minor over-limit reports, and major over-limit reports to obtain an optimization plan report; The full life cycle adaptive optimization module is used to analyze the compressive strength data and ambient temperature data, and obtain the tension optimization report based on the analysis results; Furthermore, the compressive strength data and the ambient temperature data are analyzed, and a method for obtaining a tension force optimization report based on the analysis results includes: When the ambient temperature data is greater than 30 degrees Celsius or less than 5 degrees Celsius, the tension force optimization report; The tension optimization report includes instructions for adjusting the initial tension data to the new initial tension data; The specific calculation formula for the new initial tension force data is: ; Get new initial tension data ,in, is the initial tension data, is the sensitivity coefficient; The extreme working condition simulation module is used to judge the ambient temperature data and real-time state change data, analyze the judgment results, and obtain a reinforcement plan report; Furthermore, the ambient temperature data and real-time state change data are judged, and the judgment results are analyzed to obtain a reinforcement plan report in the following ways: Monitor ambient temperature data and real-time state change data; When the ambient temperature data is less than 0 degrees Celsius or the real-time state change data is greater than the strain threshold, it is judged as a disaster event; When a disaster event occurs, the additional stress value is calculated. The specific calculation formula is: ; Get the additional stress value ,in, is the air density, is the drag coefficient, is the windward area of the beam, For real-time state-changing data, is the cross-sectional area of the beam; According to the additional stress value, when the sum of the additional stress value and the stress prediction value is greater than the stress allowable threshold, a reinforcement plan report is generated; The reinforcement plan report includes an explanation of the current beam's insufficient disaster resistance and requests staff to provide temporary support or reinforce the beam with steel strands as soon as possible; A distributed cloud-edge backup module is used to build a cloud-edge backup system based on feature data sets, stress prediction values, and optimization solution reports; Furthermore, based on the feature dataset, stress prediction values, and optimization solution reports, the following methods are used to build a cloud-edge backup system: Build a cloud-edge architecture, with cloud-based storage for data backup and system data sets, and edge processing for real-time data collection and calculation; The cloud-edge architecture synchronously receives system data sets based on preset time units, and edge devices can operate independently using the locally cached system data sets; Automatically back up feature datasets and stress prediction values every five minutes and send them to the cloud and edge; The data management and communication module is used to build a digital twin model of the bridge based on stress prediction values, optimization plan reports, tension optimization reports, and reinforcement plan reports, and store the system data set in the database; Furthermore, the methods for constructing a bridge digital twin model based on the stress prediction value, optimization solution report, tension force optimization report, and reinforcement solution report include: Integrate stress prediction values, optimization plan reports, tension force optimization reports, and reinforcement plan reports to build a digital twin model of the bridge; Update the stress distribution of the bridge digital twin model using the stress prediction values; Adjust the construction sequence based on the optimization plan report; Display the bridge digital twin model through a visualization panel; System data sets include construction data sets, stress impact data sets, feature data sets, stress prediction values, optimization plan reports, tension optimization reports, and reinforcement plan reports; Further, S1: collecting a construction data set, the construction data set including beam length data, compressive strength data, initial tension force data and stage number data; S2: Collect stress impact data sets, which include ambient temperature data and real-time state change data; S3: Preprocess the construction dataset and stress impact dataset to obtain a feature dataset; S4: Build a construction stress value prediction model based on the historical feature data set, and obtain the stress prediction value based on the feature data set; S5: Analyze the stress prediction value and process the analysis results to obtain an optimization solution report; S6: Analyze the compressive strength data and ambient temperature data, and obtain a tension optimization report based on the analysis results; S7: judge the ambient temperature data and real-time state change data, analyze the judgment results, and obtain a reinforcement plan report; S8: Build a cloud-edge backup system based on feature data sets, stress prediction values, and optimization solution reports; S9: Build a digital twin model of the bridge based on the stress prediction value, optimization scheme report, tension force optimization report, and reinforcement scheme report, and store the system data set in the database.

[0007] The technical effects and advantages of the digital twin-based intelligent monitoring system and method for bridge construction of the present invention are as follows: The present invention collects construction data sets, which include beam length data, compressive strength data, initial tensioning force data and stage number data; collects stress influence data sets, which include ambient temperature data and real-time state change data; pre-processes the construction data sets and stress influence data sets to obtain feature data sets; constructs a construction stress value prediction model based on the historical feature data sets; obtains stress prediction values based on the feature data sets; analyzes the stress prediction values; processes the analysis results to obtain an optimization solution report; analyzes the compressive strength data and ambient temperature data; obtains a tensioning force optimization report based on the analysis results; judges the ambient temperature data and real-time state change data; analyzes the judgment results to obtain a reinforcement solution report; constructs a cloud-edge backup system based on the feature data sets, stress prediction values and optimization solution reports; constructs a bridge digital twin model based on the stress prediction values, optimization solution reports, tensioning force optimization reports and reinforcement solution reports; and stores the system data sets in a database, so that the system can accurately predict the bridge structure under the dynamic influence of environmental factors. Calculating and predicting the bridge stress values in future time periods provides an extremely important and accurate data basis for the construction of bridges. In addition, the present invention also deeply explores the stress prediction values, so that the system can assist staff in providing corresponding response measures based on the predicted changes in the bridge stress values, greatly reducing the time cost and professional cost required for construction risk response decisions. At the same time, by simulating environmental emergencies and disaster emergencies that may be encountered during the construction process, the system can provide staff with accurate and reliable response measures in the first time when an emergency occurs, greatly reducing the degree of damage to the construction process caused by low-probability natural time, thereby effectively improving the safety of bridges during the construction process. Moreover, through the establishment of a cloud-edge backup system, the system can still operate the bridge digital twin model normally when the network environment is poor, ensuring that the bridge digital twin model can continue to operate even in harsh conditions such as network disconnection. Overall, the present invention has the significant advantages of large auxiliary role in bridge construction, strong response capability and good operation response effect in harsh network environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 Schematic diagram of a digital twin-based intelligent monitoring system for bridge construction according to the present invention; Figure 2 This is a schematic diagram of an intelligent monitoring method for bridge construction based on digital twins according to the present invention. DETAILED DESCRIPTION

[0009] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0010] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "the" and "the" used in the embodiments of the present invention are also intended to include plural forms, unless the context clearly indicates otherwise, and "a plurality" generally includes at least two.

[0011] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0012] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0013] In practice, the server-side device deployed in the digital twin-based intelligent monitoring system for bridge construction may be composed of one or more devices. The aforementioned digital twin-based intelligent monitoring system for bridge construction can be implemented as a service instance, a virtual machine, or hardware devices. For example, the digital twin-based intelligent monitoring system for bridge construction can be implemented as a service instance deployed on one or more devices in a cloud node. Simply put, the digital twin-based intelligent monitoring system for bridge construction can be understood as software deployed on a cloud node, which provides the digital twin-based intelligent monitoring system for each client. Alternatively, the digital twin-based intelligent monitoring system for bridge construction can be implemented as a virtual machine deployed on one or more devices in a cloud node. Application software for managing each client is installed in the virtual machine. Alternatively, the digital twin-based intelligent monitoring system for bridge construction can be implemented as a server-side device composed of multiple hardware devices of the same or different types, with one or more hardware devices configured to provide the digital twin-based intelligent monitoring system for each client.

[0014] In terms of implementation, the digital twin-based intelligent monitoring system for bridge construction and the user end are mutually compatible. Specifically, if the digital twin-based intelligent monitoring system for bridge construction is an application installed on a cloud service platform, the user end is the client that establishes a communication connection with the application. Alternatively, if the digital twin-based intelligent monitoring system for bridge construction is implemented as a website, the user end is implemented as a webpage. Alternatively, if the digital twin-based intelligent monitoring system for bridge construction is implemented as a cloud service platform, the user end is implemented as a mini-program within an instant messaging application.

[0015] like Figure 1 , which is a system architecture diagram of a digital twin-based intelligent monitoring system for bridge construction provided in one embodiment of the present invention.

[0016] The digital twin-based intelligent monitoring system for bridge construction described in the present invention can be set in a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed on the cloud (such as a mobile service operator's server, server cluster, etc.), or it can be developed as a website. According to the functions implemented, the digital twin-based intelligent monitoring system for bridge construction can include a construction data acquisition module, a stress impact data acquisition module, a feature data conversion module, a construction stress value prediction module, an automatic optimization solution generation module, a full life cycle adaptive optimization module, an extreme working condition simulation module, a distributed cloud edge backup module and a data management and communication module. The module described in the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0017] In an embodiment of the present invention, in the intelligent monitoring system for bridge construction based on digital twins, each of the above modules can be implemented independently and called with other modules. The call here can be understood as a module that can connect to multiple modules of another type and provide corresponding services to the multiple modules connected to it. For example, the sharing evaluation module can call the same information acquisition module to obtain the information collected by the information acquisition module. Based on the above characteristics, in the intelligent monitoring system for bridge construction based on digital twins provided by an embodiment of the present invention, the scope of application of the intelligent monitoring system for bridge construction based on digital twins can be adjusted by adding modules and directly calling them without modifying the program code, thereby realizing cluster-type horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the intelligent monitoring system for bridge construction based on digital twins. In actual applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in cloud servers.

[0018] Example 1 See also Figure 1 As shown, the bridge construction intelligent monitoring system based on digital twin described in this embodiment includes: The construction data acquisition module is used to collect construction data sets, which include beam length data, compressive strength data, initial tension force data and stage number data; It should be explained that the laser rangefinder is used to collect the distance between the two ends of a specified beam to obtain the beam length data; the on-site rebound tester is used to collect the compressive resistance value of the specified beam to obtain the compressive strength data; the hydraulic jack pressure sensor is used to collect the oil pressure gauge value of the specified beam and multiply it by the piston area to obtain the initial tension force data; the construction BIM tool is used to collect the number value of the current construction stage to obtain the stage number data; The stress impact data acquisition module is used to acquire a stress impact data set, which includes ambient temperature data and real-time state change data; It should be explained that the wireless temperature sensor collects the temperature value in the specified area to obtain the ambient temperature data; the vibrating wire strain gauge collects the strain value of the specified beam to obtain the real-time state change data; The characteristic data conversion module is used to pre-process the construction data set and the stress impact data set to obtain a characteristic data set; Furthermore, the steps of preprocessing the construction dataset and the stress impact dataset include: Q1: Normalize all sub-data items in the basic data set to the range of [0, 1] based on the normalization formula; It should be explained that the basic data set includes the construction data set and the stress impact data set; the specific expression formula of the normalization formula is: ,in is the normalized value, Any sub-data item of the basic data, is the historical maximum value of any sub-data item, is the historical minimum value of any sub-data item; Q2: Calculate the interactive characteristic data based on the compressive strength data and ambient temperature data. The specific calculation formula is: ; Get interactive feature data ,in, is the compressive strength data, is an exponential function, is the ambient temperature data, It is the standard ambient temperature data; It should be explained that the exponential function is used to represent the base of natural logarithms. The power of Q3: Pack beam length data, compressive strength data, initial tension data, stage number data, interactive feature data, and real-time state change data to obtain a feature data set; It should be explained that the beam length data, initial tension data, stage number data and interactive feature data in the feature data set are normalized data values, while the compressive strength data and real-time state change data are original data values; The construction stress value prediction module is used to build a construction stress value prediction model based on the historical feature data set and obtain the stress prediction value according to the feature data set; Furthermore, the steps of constructing a construction stress value prediction model based on the historical characteristic data set and obtaining the stress prediction value according to the characteristic data set include: Step 1: Obtain a set of historical feature data sets stored in the database, compare them with the current time based on the timestamp, and group and label the historical feature data sets from small to large according to the comparison results. The labeling results are L1, L2, L3, ..., Ln, and the labeling results are used as the sample set; Step 2: Divide the sample set into a 70% training set, a 15% test set, and a 15% validation set, and establish a stress value prediction model based on the sample set; Step 3: Based on the historical feature data set in the training set, a basic stress value prediction model is constructed by substituting the historical feature data set in the training set into the calculation formula: ; Get the first Predicted foundation stress values ,in, is the number of gradient boosting trees, is the number of decision trees in a single gradient boosting tree, is the learning rate, For the The first gradient boosting tree The piecewise function of a decision tree, is the historical feature dataset in the training set, is the tree structure split point, To modify the weight factor, is the Bayesian regularization term of the historical feature dataset in the training set; It needs to be explained that the piecewise function is the computational unit of the gradient boosting tree; Step 4: Based on the foundation stress prediction value in step 3, perform weighted fusion. The specific calculation formula for fusion is: ; Get training stress prediction value ,in, The number of basic stress value prediction models, For the Model weight factors; Step 5: Based on the training stress prediction value in step 4, calculate the absolute value of the training stress prediction value and the actual stress prediction value and multiply it by 100% to obtain the absolute deviation rate. If the absolute deviation rate is greater than or equal to 3%, return to step 3 and retrain. Step 6: Repeat steps 3 to 5 until the preset number of iterations is reached to obtain a stress value prediction model; Step 7: Based on the stress value prediction model in step 5, input the characteristic data set to obtain the stress prediction value; Step 8: Output the stress prediction value to the automatic optimization solution generation module; The automatic optimization solution generation module is used to analyze the stress prediction value and process the analysis results to obtain an optimization solution report; Furthermore, the stress prediction values are analyzed and the analysis results are processed in the following ways: Based on stress allowable threshold; It should be explained that the stress allowable threshold is usually a preset multiple of the compressive strength data. For example, 0.6 times the compressive strength data is taken as the stress allowable threshold; When the stress prediction value is less than or equal to the stress allowable threshold, a safety report is generated; When the stress prediction value is greater than the stress allowable threshold, the degree of over-limit is determined; When the predicted stress value is greater than the stress allowable threshold and less than or equal to 1.2 times the stress allowable threshold, a slight overlimit report is generated; When the stress prediction value is greater than 1.2 times the stress allowable threshold, a severe over-limit report is generated; The safety report includes a statement that the predicted construction stress value is normal and that workers are requested to work according to the preset operating procedures; The slight overrun report includes a statement that the predicted construction stress value is slightly abnormal. Please ask the staff to enter Phased construction; What needs to be explained is that is the stage number data, The required skip stage data is obtained by calculating the difference between the stress prediction value and the stress allowable threshold and dividing it by 0.1 times the stress allowable threshold; The severe over-limit report includes a description of the severe abnormality of the predicted construction stress value. Please ask the staff to increase Tension force parameters; What needs to be explained is that To adjust the tension data, the specific calculation formula is: ,in is the proportionality coefficient, is the initial tension data, is the stress prediction value, is the stress allowable threshold; Package safety reports, minor over-limit reports, and major over-limit reports to obtain an optimization plan report; The full life cycle adaptive optimization module is used to analyze the compressive strength data and the ambient temperature data, and obtain a tension optimization report based on the analysis results; Furthermore, the compressive strength data and the ambient temperature data are analyzed, and based on the analysis results, a method for obtaining a tension force optimization report includes: When the ambient temperature data is greater than 30 degrees Celsius or less than 5 degrees Celsius, the tension force optimization report; The tension optimization report includes instructions for adjusting the initial tension data to the new initial tension data; The specific calculation formula for the new initial tension force data is: ; Get new initial tension data ,in, is the initial tension data, is the sensitivity coefficient; The extreme working condition simulation module is used to judge the ambient temperature data and real-time state change data, and analyze the judgment results to obtain a reinforcement plan report; Furthermore, the ambient temperature data and real-time state change data are judged, and the judgment results are analyzed to obtain a reinforcement plan report in the following ways: Monitor ambient temperature data and real-time state change data; When the ambient temperature data is less than 0 degrees Celsius or the real-time state change data is greater than the strain threshold, it is judged as a disaster event; It should be explained that the strain threshold is manually selected and input into the system; When a disaster event occurs, the additional stress value is calculated. The specific calculation formula is: ; Get the additional stress value ,in, is the air density, is the drag coefficient, is the windward area of the beam, For real-time state-changing data, is the cross-sectional area of the beam; According to the additional stress value, when the sum of the additional stress value and the stress prediction value is greater than the stress allowable threshold, a reinforcement plan report is generated; The reinforcement plan report includes an explanation of the current beam's insufficient disaster resistance and requests staff to provide temporary support or reinforce the steel strands as soon as possible. The distributed cloud-edge backup module is used to build a cloud-edge backup system based on the feature data set, stress prediction value and optimization solution report; Furthermore, based on the feature data set, stress prediction values, and optimization solution reports, the following methods are used to build a cloud-edge backup system: Build a cloud-edge architecture, with cloud-based storage for data backup and system data sets, and edge processing for real-time data collection and calculation; The cloud-edge architecture synchronously receives system data sets based on preset time units, and edge devices can operate independently using the locally cached system data sets; Automatically back up feature datasets and stress prediction values every five minutes and send them to the cloud and edge; The data management and communication module is used to build a digital twin model of the bridge based on the stress prediction value, optimization solution report, tension optimization report and reinforcement solution report, and store the system data set in the database; Furthermore, the methods for constructing a bridge digital twin model based on the stress prediction value, optimization solution report, tension force optimization report, and reinforcement solution report include: Integrate stress prediction values, optimization plan reports, tension force optimization reports, and reinforcement plan reports to build a digital twin model of the bridge; Update the stress distribution of the bridge digital twin model using the stress prediction values; Adjust the construction sequence based on the optimization plan report; Display the bridge digital twin model through a visualization panel; System data sets include construction data sets, stress impact data sets, feature data sets, stress prediction values, optimization plan reports, tension optimization reports, and reinforcement plan reports; This embodiment has the beneficial effects of collecting construction data sets, which include beam length data, compressive strength data, initial tensioning force data and stage number data; collecting stress influence data sets, which include ambient temperature data and real-time state change data; pre-processing the construction data sets and stress influence data sets to obtain feature data sets; building a construction stress value prediction model based on the historical feature data sets; and obtaining stress prediction values based on the feature data sets; analyzing the stress prediction values and processing the analysis results to obtain an optimization plan report; analyzing the compressive strength data and ambient temperature data, and obtaining a tensioning force optimization report based on the analysis results; judging the ambient temperature data and real-time state change data, and analyzing the judgment results to obtain a reinforcement plan report; building a cloud-edge backup system based on the feature data sets, stress prediction values and optimization plan reports; building a bridge digital twin model based on the stress prediction values, optimization plan reports, tensioning force optimization reports and reinforcement plan reports; and storing the system data sets in a database, so that the system can be dynamically affected by environmental factors. The system can accurately calculate and predict the bridge stress values in future time periods, providing an extremely important and accurate data basis for the construction of bridges. In addition, the present invention also deeply explores the stress prediction values, so that the system can assist staff in providing corresponding response measures based on the predicted changes in the bridge stress values, greatly reducing the time cost and professional cost required for construction risk response decisions. At the same time, by simulating environmental emergencies and disaster emergencies that may be encountered during the construction process, the system can provide staff with accurate and reliable response measures in the first time when an emergency occurs, greatly reducing the degree of damage to the construction process caused by low-probability natural time, thereby effectively improving the safety of bridges during the construction process. Moreover, through the establishment of a cloud-edge backup system, the system can still operate the bridge digital twin model normally when the network environment is poor, ensuring that the bridge digital twin model can continue to operate even in harsh conditions such as network disconnection. Overall, the present invention has the significant advantages of large auxiliary role in bridge construction, strong response capability and good operation response effect in harsh network environments.

[0019] Example 2 See also Figure 2 As shown, for parts not described in detail in this embodiment, please refer to the description of Example 1. A method for intelligent monitoring of bridge construction based on digital twins is provided, the method comprising: S1: collecting a construction data set, the construction data set comprising beam length data, compressive strength data, initial tension force data, and stage number data; S2: Collect stress impact data sets, which include ambient temperature data and real-time state change data; S3: Preprocess the construction dataset and stress impact dataset to obtain a feature dataset; S4: Build a construction stress value prediction model based on the historical feature data set, and obtain the stress prediction value based on the feature data set; S5: Analyze the stress prediction value and process the analysis results to obtain an optimization solution report; S6: Analyze the compressive strength data and ambient temperature data, and obtain a tension optimization report based on the analysis results; S7: judge the ambient temperature data and real-time state change data, analyze the judgment results, and obtain a reinforcement plan report; S8: Build a cloud-edge backup system based on feature data sets, stress prediction values, and optimization solution reports; S9: Build a digital twin model of the bridge based on the stress prediction value, optimization scheme report, tension force optimization report, and reinforcement scheme report, and store the system data set in the database.

[0020] Example 3 It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0021] Therefore, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is not limited to the above description. Therefore, it is intended that all changes that fall within the meaning and range of equivalent elements are included in the present invention.

[0022] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0023] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in a system may also be implemented by a single unit or device through software or hardware. Terms such as first and second are used to indicate names and do not imply any particular order.

[0024] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent monitoring system for bridge construction based on digital twins, characterized by: The system includes: a construction stress value prediction module, an automatic optimization solution generation module, a full life cycle adaptive optimization module, an extreme working condition simulation module and a distributed cloud-edge backup module, wherein: The construction stress value prediction module is used to build a construction stress value prediction model based on the historical feature data set and obtain the stress prediction value according to the feature data set; The automatic optimization solution generation module is used to analyze the stress prediction value and process the analysis results to obtain an optimization solution report; The full life cycle adaptive optimization module is used to analyze the compressive strength data and the ambient temperature data, and obtain a tension optimization report based on the analysis results; The extreme working condition simulation module is used to judge the ambient temperature data and real-time state change data, and analyze the judgment results to obtain a reinforcement plan report; The distributed cloud-edge backup module is used to build a cloud-edge backup system based on feature data sets, stress prediction values and optimization solution reports.

2. The bridge construction intelligent monitoring system based on digital twin according to claim 1 is characterized in that: The system further comprises: a construction data acquisition module, a stress impact data acquisition module, a feature data conversion module and a data management and communication module, wherein: The construction data acquisition module is used to collect construction data sets, which include beam length data, compressive strength data, initial tension force data and stage number data; The stress impact data acquisition module is used to acquire a stress impact data set, which includes ambient temperature data and real-time state change data; The characteristic data conversion module is used to pre-process the construction data set and the stress impact data set to obtain a characteristic data set; The data management and communication module is used to build a digital twin model of the bridge based on the stress prediction value, optimization scheme report, tensioning force optimization report and reinforcement scheme report, and store the system data set in the database.

3. The bridge construction intelligent monitoring system based on digital twin according to claim 2 is characterized in that: The steps for preprocessing the construction dataset and stress impact dataset include: Q1: Normalize all sub-data items in the basic data set to the range of [0, 1] based on the normalization formula; Q2: Calculate the interactive characteristic data based on the compressive strength data and ambient temperature data. The specific calculation formula is: ； Get interactive feature data ,in, is the compressive strength data, is an exponential function, is the ambient temperature data, is the standard ambient temperature data; Q3: Package the beam length data, compressive strength data, initial tension force data, stage number data, interactive feature data and real-time state change data to obtain a feature data set.

4. The bridge construction intelligent monitoring system based on digital twin according to claim 1 is characterized in that: The steps of constructing a construction stress value prediction model based on the historical characteristic data set and obtaining the stress prediction value based on the characteristic data set include: Step 1: Obtain a set of historical feature data sets stored in the database, compare them with the current time based on the timestamp, and group and label the historical feature data sets from small to large according to the comparison results. The labeling results are L1, L2, L3, ..., Ln, and the labeling results are used as the sample set; Step 2: Divide the sample set into a 70% training set, a 15% test set, and a 15% validation set, and establish a stress value prediction model based on the sample set; Step 3: Based on the historical feature data set in the training set, a basic stress value prediction model is constructed by substituting the historical feature data set in the training set into the calculation formula: ； Get the first Predicted foundation stress values ,in, is the number of gradient boosting trees, is the number of decision trees in a single gradient boosting tree, is the learning rate, For the The first gradient boosting tree The piecewise function of a decision tree, is the historical feature dataset in the training set, is the tree structure split point, To modify the weight factor, is the Bayesian regularization term of the historical feature dataset in the training set; Step 4: Based on the foundation stress prediction value in step 3, perform weighted fusion. The specific calculation formula for fusion is: ； Get training stress prediction value ,in, The number of basic stress value prediction models, For the Model weight factors; Step 5: Based on the training stress prediction value in step 4, calculate the absolute value of the training stress prediction value and the actual stress prediction value and multiply it by 100% to obtain the absolute deviation rate. If the absolute deviation rate is greater than or equal to 3%, return to step 3 and retrain. Step 6: Repeat steps 3 to 5 until the preset number of iterations is reached to obtain a stress value prediction model; Step 7: Based on the stress value prediction model in step 5, input the characteristic data set to obtain the stress prediction value; Step 8: Output the stress prediction value to the automatic optimization solution generation module.

5. The bridge construction intelligent monitoring system based on digital twin according to claim 1 is characterized in that: Methods for analyzing stress prediction values and processing analysis results include: Based on stress allowable threshold; When the stress prediction value is less than or equal to the stress allowable threshold, a safety report is generated; When the stress prediction value is greater than the stress allowable threshold, the degree of over-limit is determined; When the predicted stress value is greater than the stress allowable threshold and less than or equal to 1.2 times the stress allowable threshold, a slight overlimit report is generated; When the stress prediction value is greater than 1.2 times the stress allowable threshold, a severe over-limit report is generated; The safety report includes a statement that the predicted construction stress value is normal and that workers are requested to work according to the preset operating procedures; The slight overrun report includes a statement that the predicted construction stress value is slightly abnormal. Please ask the staff to enter Phased construction; The severe over-limit report includes a description of the severe abnormality of the predicted construction stress value. Please ask the staff to increase Tension force parameters; Package the safety report, minor over-limit report and major over-limit report to obtain the optimization plan report.

6. The bridge construction intelligent monitoring system based on digital twin according to claim 1 is characterized in that: Methods for analyzing compressive strength data and ambient temperature data and obtaining a tension force optimization report based on the analysis results include: When the ambient temperature data is greater than 30 degrees Celsius or less than 5 degrees Celsius, the tension force optimization report; The tension optimization report includes instructions for adjusting the initial tension data to the new initial tension data; The specific calculation formula for the new initial tension force data is: ； Get new initial tension data ,in, is the initial tension data, is the sensitivity coefficient.

7. The bridge construction intelligent monitoring system based on digital twin according to claim 1 is characterized in that: Methods for judging ambient temperature data and real-time state change data, analyzing the judgment results, and obtaining a reinforcement plan report include: Monitor ambient temperature data and real-time state change data; When the ambient temperature data is less than 0 degrees Celsius or the real-time state change data is greater than the strain threshold, it is judged as a disaster event; When a disaster event occurs, the additional stress value is calculated. The specific calculation formula is: ； Get the additional stress value ,in, is the air density, is the drag coefficient, is the windward area of the beam, For real-time state-changing data, is the cross-sectional area of the beam; According to the additional stress value, when the sum of the additional stress value and the stress prediction value is greater than the stress allowable threshold, a reinforcement plan report is generated; The reinforcement plan report includes an explanation of the current beam's insufficient disaster resistance performance, and staff are requested to provide temporary support or reinforce steel bundles for the beam as soon as possible.

8. The bridge construction intelligent monitoring system based on digital twin according to claim 1 is characterized in that: Based on the feature dataset, stress prediction values, and optimization solution reports, methods for building a cloud-edge backup system include: Build a cloud-edge architecture, with cloud-based storage for data backup and system data sets, and edge processing for real-time data collection and calculation; The cloud-edge architecture synchronously receives system data sets based on preset time units, and edge devices can operate independently using the locally cached system data sets; The feature dataset and stress prediction values are automatically backed up every five minutes and sent to the cloud and edge.

9. The bridge construction intelligent monitoring system based on digital twin according to claim 2 is characterized in that: Methods for constructing a bridge digital twin model based on stress prediction values, optimization solution reports, tension force optimization reports, and reinforcement solution reports include: Integrate stress prediction values, optimization plan reports, tension force optimization reports, and reinforcement plan reports to build a digital twin model of the bridge; Update the stress distribution of the bridge digital twin model using the stress prediction values; Adjust the construction sequence based on the optimization plan report; Display the bridge digital twin model through a visualization panel; The system data sets include construction data sets, stress impact data sets, feature data sets, stress prediction values, optimization scheme reports, tension optimization reports and reinforcement scheme reports.

10. A bridge construction intelligent monitoring method based on digital twins, implemented according to a bridge construction intelligent monitoring system based on digital twins according to any one of claims 1 to 9, characterized in that: The following steps are included: S1: Collect construction data sets, including beam length data, compressive strength data, initial tension force data, and stage number data; S2: Collect stress impact data sets, which include ambient temperature data and real-time state change data; S3: Preprocess the construction dataset and stress impact dataset to obtain a feature dataset; S4: Build a construction stress value prediction model based on the historical feature data set, and obtain the stress prediction value based on the feature data set; S5: Analyze the stress prediction value and process the analysis results to obtain an optimization solution report; S6: Analyze the compressive strength data and ambient temperature data, and obtain a tension force optimization report based on the analysis results; S7: judge the ambient temperature data and real-time state change data, analyze the judgment results, and obtain a reinforcement plan report; S8: Build a cloud-edge backup system based on feature data sets, stress prediction values, and optimization solution reports; S9: Build a digital twin model of the bridge based on the stress prediction value, optimization scheme report, tension force optimization report, and reinforcement scheme report, and store the system data set in the database.

Images