Steel structure digital twinborn health monitoring system and monitoring method

Abstract

The invention discloses a steel structure digital twinborn health monitoring system and method. The system comprises a data acquisition module, a data processing module, a data storage module, a model construction module, a model integration module, a user interface and visualization module, a data analysis and optimization module and an interaction and feedback module. The model construction module constructs a steel structure digital twinborn model; the model integration module integrates the steel structure digital twin model with a corresponding entity steel structure; the data analysis and optimization module comprises a data management module, a data analysis module, a data analysis module, a model management module, a model analysis module and a monitoring and early warning module. The method solves the problems that a traditional steel structure health monitoring method wastes human resources, is low in monitoring frequency and incomplete in data acquisition, and cannot efficiently acquire practical information, and although a digital twinborn technology is applied to an individual steel structure health monitoring system, a finite element simulation process is lack of detailed research, and the working efficiency is low. And application feasibility in an actual steel structure is lacked.

Description

Technical Field

[0001] The present invention belongs to the technical field of steel structure monitoring, and in particular relates to a steel structure digital twin health monitoring system and a monitoring method. Background Art

[0002] Structural health monitoring mainly uses non-destructive sensing technology to collect parameter data related to the structural health status to judge the health status of the structure, detect abnormal conditions in time and alarm, and reduce the losses caused by structural failure. Structural health monitoring can be divided into two stages: construction process and operation process. Construction phase monitoring is to ensure the smooth completion of the steel structure. Starting from the construction of the steel structure, the key parts of the key structure are monitored, the structural health status is analyzed, and the results are fed back to the construction party in time; operation phase monitoring is to monitor all key structures, analyze the health status of the structure, and predict the health trend of the structure. Traditional steel structure health monitoring methods mainly rely on manual inspections and regular inspections, which have the disadvantages of waste of human resources, low monitoring frequency, incomplete data collection, etc., lack the ability to manage, process and interpret large monitoring data sets, and therefore cannot efficiently and quickly obtain practical information. Although digital twin technology has been applied in some existing steel structure health monitoring systems, the finite element simulation process lacks detailed research and lacks the feasibility of application in actual steel structures. Summary of the invention

[0003] The purpose of the present invention is to provide a digital twin health monitoring system and monitoring method for steel structures, so as to solve the technical problems that the traditional steel structure health monitoring method mainly relies on manual inspection and regular detection, and has the disadvantages of waste of human resources, low monitoring frequency, incomplete data collection, and inability to efficiently obtain practical information, and that although digital twin technology has been applied in some existing steel structure health monitoring systems, the finite element simulation process therein lacks detailed research and lacks the feasibility of application in actual steel structures.

[0004] To achieve the above purpose, the present invention adopts the following technical solution.

[0005] A steel structure digital twin health monitoring system, comprising a data acquisition module, a data processing module, a data storage module, a model building module, a model integration module, a user interface and visualization module, a data analysis and optimization module, and an interaction and feedback module; the data acquisition module transmits the collected data to the data processing module; after receiving the original data transmitted by the data acquisition module, the data processing module repairs, cleans and integrates the original data to ensure the accuracy and integrity of the data; the data storage module is used to store the historical data collected by the data acquisition module and the real-time data after repair, cleaning and integration; the model building module builds a steel structure digital twin model according to the data collected by the data processing module; the model integration module is used to integrate the steel structure digital twin model with the corresponding physical steel structure to ensure that the steel structure digital twin model can reflect the health status of the physical steel structure in real time and simulate the behavior and response of the physical steel structure under different conditions; the data analysis and optimization module It includes a data management module, a data analysis module, a data analysis module, a model management module, a model analysis module and a monitoring and early warning module; after receiving the compiled data, the model analysis module calls the corresponding model in the model library of the model management module to perform data analysis and finite element simulation analysis, and predicts the deformation, stress and strain safety monitoring effect of key parts of the solid steel structure, and then performs a safety analysis and evaluation of the solid steel structure based on the prediction results; the monitoring and early warning module combines the early warning indicators with the threshold system to judge the early warning trigger, and issues early warnings for scenarios that trigger early warning indicators; the user interface and visualization module are used to provide a graphical display of real-time data and simulation results, and at the same time provide users with an interface for interacting with the digital twin model of the steel structure; the interaction and feedback module is used to feed back the state changes of the solid steel structure to the digital twin model of the steel structure in real time, and at the same time allow the user to provide feedback on the solid steel structure to help improve the health status of the solid steel structure.

[0006] Preferably, the data acquisition module includes a sensor; the sensor is installed on the physical steel structure to be detected to monitor and collect temperature, stress and vibration parameters of the physical steel structure; the data acquisition module transmits through a data transmission platform.

[0007] Preferably, the models in the model library include a steel structure safety analysis model and an online structure calculation model.

[0008] A monitoring method for a steel structure digital twin health monitoring system comprises the following steps.

[0009] Step 1, original data collection: obtain the structural design data, construction data, sensor data, maintenance record data and environmental data of the physical steel structure.

[0010] Step 2: After receiving the original data, the data processing module repairs, cleans and integrates the original data; After receiving the original data, the data processing module repairs, cleans and integrates the original data; The data processing module is integrated with a long short-term memory neural network model, and the data processing module repairs the original data using a structural monitoring data repair method based on the long short-term memory neural network model. The specific steps are as follows.

[0011] Step 1: According to the missing data characteristics of the steel structure data collected and whether there are multiple related adjacent measuring point data, the types of missing data are divided into single measuring point data missing and multiple measuring point data missing.

[0012] Step 2: Determine the data repair method to be an autocorrelation repair method or a spatial correlation repair method according to the type of data missing in step 1; the autocorrelation repair method is a method used for data missing at a single measuring point; the spatial correlation repair method is a method used for data missing at multiple measuring points.

[0013] Step 3, construct a data set; the existing continuous data part in the data set is used as the training set, and the missing data part is used as the test set.

[0014] Step 4: Input the training set into the constructed long short-term memory neural network model and perform model training.

[0015] Step 5: After the training is completed, the trained LSTM neural network model is saved, and the test set is input into the trained LSTM neural network model to predict the missing data.

[0016] Step 6: Analyze the error between the predicted value and the missing value, and evaluate the missing data repair performance of the long short-term memory neural network model.

[0017] Step 3: Construction of the digital twin model of the steel structure: Use the model construction module to create the digital twin model of the steel structure, and store the constructed digital twin model of the steel structure in the model library of the model management module.

[0018] Step 4: Use the model integration module to integrate the steel structure digital twin model with the corresponding physical steel structure to ensure that the steel structure digital twin model can reflect the health status of the physical steel structure in real time and simulate the behavior and response of the physical steel structure under different conditions.

[0019] Step 5. After receiving the compiled data, the model analysis module calls the corresponding steel structure digital twin model in the model library of the model management module to perform data analysis and finite element simulation analysis. At the same time, combined with the operation plan, it predicts the deformation, stress and strain safety monitoring effect of key parts of the physical steel structure.

[0020] Step six: Conduct safety analysis and evaluation of the physical steel structure based on the monitoring effect quantity prediction results.

[0021] Step seven: Based on the safety analysis and evaluation results of the physical steel structure, the early warning indicators and threshold system are combined to determine the triggering of the early warning.

[0022] Step eight: If an early warning is triggered, it will be issued, and the prediction and early warning results will be simulated on the digital twin model of the steel structure.

[0023] Step nine: Conduct risk assessment and grading of the safety analysis and evaluation results of the physical steel structure in combination with the risk indicator system and risk assessment model.

[0024] Step 10: Determine whether to activate the emergency plan.

[0025] Step 11: If the emergency plan can be activated, the steel structure plan library will be called to automatically select the optimal emergency plan based on the prediction, warning and plan results, and an application will be submitted to the superior. After approval, the plan will be executed.

[0026] Preferably, in step one, the structural design data includes drawings, dimensions, material specifications and connection methods; the construction data includes actual measurement data and construction records during the construction process; the sensor data is obtained by arranging sensors on the physical steel structure to be monitored on site, and the sensors collect the temperature, stress and vibration in the physical steel structure; the maintenance record data is obtained from historical maintenance and repair records; and the environmental data is obtained from geological survey reports, basic data of buildings and structures, and environmental and meteorological data.

[0027] Preferably, in step 3, when the type of data missing is multi-point data missing, a correlation analysis method is used to analyze the correlation between the adjacent multiple measuring points and the missing measuring point; the measuring point data with the largest correlation is selected as the repair model data set; the existing continuous data part in the repair model data set is used as the training set, and the missing data part is used as the test set; When the data of a single measuring point is missing, a data set containing the missing data is constructed, and the existing continuous data part of the data set with missing data is used as the training set, and the missing data part is used as the test set.

[0028] Preferably, if no warning is triggered in step seven, the operation plan is adjusted and steps five to six are repeated.

[0029] Preferably, if the decision in step ten does not support the initiation of the emergency plan, the physical steel structure is treated on site.

[0030] Compared with the prior art, the present invention has the following characteristics and beneficial effects.

[0031] 1. The present invention deeply combines the Internet of Things monitoring platform system with the digital twin technology, converts the collected sensor data into a digital twin model of the steel structure, introduces the ABAQUS finite element analysis software into the digital twin model of the steel structure, simulates and analyzes real scenes on the digital twin model of the steel structure, establishes a mapping relationship between the digital twin model of the steel structure and the actual structure, optimizes the actual monitoring system, and realizes real-time monitoring, real-time early warning and health assessment of the steel structure.

[0032] 2. Existing methods for monitoring the health of steel structures suffer from waste of human resources, low monitoring frequency, incomplete data collection, and lack of the ability to manage, process, and interpret large monitoring data sets. This platform deeply combines the Internet of Things monitoring platform system with digital twin technology to establish methods and technologies that run through various links such as detection and monitoring, status and safety assessment, maintenance, and management, to achieve intelligent structural detection and management; at the same time, the present invention can efficiently and quickly process large-scale monitoring data to ensure the safety and stability of steel structure construction and operation.

[0033] 3. For the monitoring system, most sensors and monitoring equipment are in poor service conditions, resulting in frequent abnormal monitoring data, which directly makes it difficult to carry out data analysis and structural safety assessment. The present invention adopts a structural response recovery method based on a long short-term memory neural network model. By studying the autocorrelation of data and the spatial correlation of multiple measuring points, it can effectively restore the missing data, so that the data repair accuracy is higher than that of traditional methods, and the evaluation of the health status of the physical steel structure is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a flow chart of the method for repairing structural monitoring data based on long short-term memory neural network in step 2 of the present invention. DETAILED DESCRIPTION

[0035] The digital twin health monitoring system for steel structures includes a data acquisition module, a data processing module, a data storage module, a model building module, a model integration module, a user interface and visualization module, a data analysis and optimization module, and an interaction and feedback module; the data acquisition module collects structural design data, construction data, sensor data, maintenance record data, and environmental data of the physical steel structure, and transmits the collected data to the data processing module; after receiving the original data transmitted by the data acquisition module, the data processing module repairs, cleans, and integrates the original data to ensure the accuracy and integrity of the data; the data storage module is used to store the historical data collected by the data acquisition module and the real-time data after repair, cleaning, and integration; the model building module constructs a digital twin model of the steel structure according to the data collected by the data processing module; the model integration module is used to integrate the digital twin model of the steel structure with the corresponding physical steel structure to ensure that the digital twin model of the steel structure can reflect the health status of the physical steel structure in real time, and simulate the physical steel structure under different conditions The behavior and response under the condition; the data analysis and optimization module includes a data management module, a data analysis module, a data analysis module, a model management module, a model analysis module and a monitoring and early warning module; after receiving the compiled data, the model analysis module calls the corresponding model in the model library of the model management module to perform data analysis and finite element simulation analysis, and predicts the deformation, stress and strain safety monitoring effect of key parts of the solid steel structure, and then performs a safety analysis and evaluation of the solid steel structure based on the prediction results; the monitoring and early warning module combines the early warning indicators with the threshold system to judge the early warning trigger, and issues an early warning for the scenario that triggers the early warning indicators; the user interface and visualization module are used to provide a graphical display of real-time data and simulation results, and at the same time provide users with an interface for interacting with the digital twin model of the steel structure; the interaction and feedback module is used to feed back the state changes of the solid steel structure to the digital twin model of the steel structure in real time, and at the same time allow the user to provide feedback on the solid steel structure to help improve the health status of the solid steel structure.

[0036] In this embodiment, the data acquisition module includes a sensor; the sensor is installed on the physical steel structure to be detected to monitor and collect temperature, stress and vibration parameters of the physical steel structure; the data acquisition module transmits data through a data transmission platform.

[0037] In this embodiment, the models in the model library include a steel structure safety analysis model and an online structure calculation model.

[0038] In this embodiment, the data processing module includes a data cleaning module and a data integration module, which are used to clean, filter and process the collected data to ensure the accuracy and integrity of the data.

[0039] In this embodiment, the data storage module is such as a database, a data warehouse, or a cloud storage.

[0040] In this embodiment, the data processing module adopts a server, and the data transmission platform is a signal base station or a local area network or 5G.

[0041] In this embodiment, the model construction module includes a physical model construction module, a simulation model construction module and a data-driven model construction module; the physical model construction module is used to create a mathematical model of the physical steel structure to describe its behavior and characteristics; the simulation model construction module is used to simulate based on the physical model and predict the behavior of the physical steel structure under different conditions; the data-driven model construction module uses machine learning and artificial intelligence technology to establish a prediction model through historical data.

[0042] In this embodiment, the model integration module includes system integration and interfaces and protocols; wherein the system integration is used to integrate the steel structure digital twin model with the physical steel structure to ensure that the virtual model can reflect the state of the physical object in real time. Interfaces and protocols enable data exchange and collaboration between different modules. In this embodiment, the user interface and visualization module include a data visualization module and an interactive interface; the data visualization module provides a graphical display of real-time data and simulation results, such as dashboards, charts, 3D views, etc.; the interactive interface is an interface for users to interact with the digital twin model of the steel structure, supporting monitoring, control and analysis.

[0043] In this embodiment, the data analysis and optimization module includes a data analysis module and an optimization algorithm module; wherein the data analysis module performs in-depth analysis on the collected data to identify patterns, trends and abnormal situations; the optimization algorithm module is used to make optimization suggestions for the analysis results and improve the performance of the physical object or system.

[0044] In this embodiment, the steel structure digital twin health monitoring system also includes a maintenance and update module; the maintenance and update module includes a model update module and a fault diagnosis module; wherein the model update module is used to regularly update the steel structure digital twin model to reflect changes and upgrades in the actual system; the model update module is used to identify and diagnose faults in the system and provide repair suggestions and solutions.

[0045] In this embodiment, the interaction and feedback module is used to feed back the state changes of the physical steel structure to the digital twin model of the steel structure in real time, while allowing users to provide feedback on the system to help improve the model and system functions.

[0046] In this embodiment, the data acquisition module, data processing module, data storage module, model building module, model integration module, user interface and visualization module, data analysis and optimization module, maintenance and update module, and interaction and feedback module work together on a comprehensive integration platform, which is usually designed as a complete system to integrate different systems and components. They support data flow, information exchange and collaboration between systems, and cover the entire process from data acquisition to user interaction; common integration platforms include middleware, service bus (ESB) and API management system.

[0047] The monitoring method of the steel structure digital twin health monitoring system includes the following steps.

[0048] Step 1: Original data collection: obtain the structural design data, construction data, sensor data, maintenance record data and environmental data of the physical steel structure; Step 2: The raw data collected in step 1 is transmitted to the data storage module through the local area network, signal base station or 5G network, and stored in the database of the data storage module; at the same time, the data collected in step 1 is transmitted to the data processing module through the local area network, signal base station or 5G network, and the data processing module repairs, cleans and integrates the raw data after receiving the raw data; the data processing module repairs, cleans and integrates the raw data after receiving the raw data; the data processing module integrates a long short-term memory neural network model, and the data processing module repairs the raw data using a structural monitoring data repair method based on a long short-term memory (LSTM) neural network model, and the specific steps are as follows: Step 1: According to the missing data characteristics of the steel structure data collected and whether there are multiple related adjacent measuring point data, the types of missing data are divided into single measuring point data missing and multiple measuring point data missing.

[0049] Step 2: Determine the data repair method to be an autocorrelation repair method or a spatial correlation repair method according to the type of data missing in step 1; the autocorrelation repair method is a method used for data missing at a single measuring point; the spatial correlation repair method is a method used for data missing at multiple measuring points.

[0050] Step 3, construct a data set; the existing continuous data part in the data set is used as the training set, and the missing data part is used as the test set.

[0051] Step 4: Input the training set into the constructed long short-term memory neural network model and perform model training.

[0052] Step 5: After the training is completed, the trained LSTM neural network model is saved, and the test set is input into the trained LSTM neural network model to predict the missing data.

[0053] Step 6: Analyze the error between the predicted value and the missing value, and evaluate the missing data repair performance of the long short-term memory neural network model.

[0054] Step 3: Construction of the digital twin model of the steel structure: Use the model building module to create the digital twin model of the steel structure by acquiring the structural design data, construction data, sensor data, maintenance record data and environmental data of the physical steel structure.

[0055] Step 4: Use the model integration module to integrate the steel structure digital twin model with the corresponding physical steel structure to ensure that the steel structure digital twin model can reflect the health status of the physical steel structure in real time and simulate the behavior and response of the physical steel structure under different conditions.

[0056] Step 5. After receiving the compiled data, the model analysis module calls the corresponding steel structure digital twin model in the model library of the model management module to perform data analysis and finite element simulation analysis. At the same time, combined with the operation plan, it predicts the deformation, stress and strain safety monitoring effect of key parts of the physical steel structure.

[0057] Step six: Conduct safety analysis and evaluation of the physical steel structure based on the monitoring effect quantity prediction results.

[0058] Step seven: Based on the safety analysis and evaluation results of the physical steel structure, the early warning indicators and threshold system are combined to determine the triggering of the early warning.

[0059] Step eight: If an early warning is triggered, it will be issued, and the prediction and early warning results will be simulated on the digital twin model of the steel structure.

[0060] Step nine: Conduct risk assessment and grading of the steel structure safety analysis and evaluation results in combination with the risk indicator system and risk assessment model; Step 10: Determine whether to activate the emergency plan.

[0061] Step 11: If the emergency plan can be activated, the steel structure plan library will be called to automatically select the optimal emergency plan based on the prediction, warning and plan results, and an application will be submitted to the superior. After approval, the plan will be executed.

[0062] In this embodiment, the data acquisition module includes a sensor; the sensor is arranged on the physical steel structure to collect real-time data from the physical steel structure, and the data transmission platform is used to transmit the sensor data to the data storage module and the data processing module for data exchange with the digital twin model of the steel structure in the later stage. Then, the digital twin model of the steel structure is created by using the model construction module, and the physical steel structure is integrated with the digital twin model of the steel structure by using the model integration module, and the digital twin model of the steel structure is analyzed and analyzed by the model analysis module. The data in the digital twin model of the steel structure is exchanged with the finite element simulation analysis data and the data of the physical steel structure through the data transmission platform, and feedback monitoring is performed at the same time; the user obtains the graphical display of real-time data and simulation results through the user interface and visualization module, and the interface for interacting with the digital twin model of the steel structure supports monitoring, control and analysis and evaluation, and then the analysis and evaluation results are risk evaluated and graded, and optimization suggestions are put forward.

[0063] In this embodiment, a steel structure plan library is provided in the monitoring and early warning module, and the finite element simulation analysis is performed using ABAQUS finite element analysis software.

[0064] In this embodiment, in step 3, when the type of data missing is multi-point data missing, the correlation analysis method is used to analyze the correlation between the adjacent multiple points and the missing points; the point data with the largest correlation is selected as the repair model data set; the existing continuous data part in the repair model data set is used as the training set, and the missing data part is used as the test set; When the data of a single measuring point is missing, a data set containing the missing data is constructed, and the existing continuous data part of the data set with missing data is used as the training set, and the missing data part is used as the test set.

[0065] In this embodiment, if the warning is not triggered in step seven, the operation plan is adjusted and steps five to six are repeated.

[0066] In this embodiment, if the decision in step ten does not support the initiation of the emergency plan, the physical steel structure is processed on site.

[0067] The above embodiments are not exhaustive of specific implementation methods, and there may be other embodiments. The above embodiments are intended to illustrate the present invention rather than to limit the protection scope of the present invention. All applications derived from simple variations of the present invention fall within the protection scope of the present invention.

Claims

1. A digital twin health monitoring system for steel structures, characterized in that: It includes data acquisition module, data processing module, data storage module, model building module, model integration module, user interface and visualization module, data analysis and optimization module, and interaction and feedback module; The data acquisition module collects structural design data, construction data, sensor data, maintenance record data and environmental data of the physical steel structure, and transmits the collected data to the data processing module; After receiving the raw data transmitted by the data acquisition module, the data processing module repairs, cleans and integrates the raw data to ensure the accuracy and integrity of the data; The data storage module is used to store the historical data collected by the data acquisition module and the real-time data after repair, cleaning and integration; The model building module builds a digital twin model of the steel structure according to the data collected by the data processing module; the model integration module is used to integrate the digital twin model of the steel structure with the corresponding physical steel structure to ensure that the digital twin model of the steel structure can reflect the health status of the physical steel structure in real time and simulate the behavior and response of the physical steel structure under different conditions; the data analysis and optimization module includes a data management module, a data analysis module, a data analysis module, a model management module, a model analysis module and a monitoring and early warning module; After receiving the compiled data, the model analysis module calls the corresponding model in the model library of the model management module to perform data analysis and finite element simulation analysis, and predicts the deformation, stress and strain safety monitoring effect of key parts of the solid steel structure. Then, based on the prediction results, the solid steel structure safety analysis and evaluation are carried out; the monitoring and early warning module combines the early warning indicators with the threshold system to judge the early warning trigger, and issues early warnings for the scenarios that trigger the early warning indicators; The user interface and visualization module are used to provide a graphical display of real-time data and simulation results, and provide users with an interface for interacting with the digital twin model of the steel structure; the interaction and feedback module is used to feed back the state changes of the physical steel structure to the digital twin model of the steel structure in real time, and allow users to provide feedback on the physical steel structure to help improve the health status of the physical steel structure.

2. The steel structure digital twin health monitoring system according to claim 1, characterized in that: The data acquisition module includes a sensor; the sensor is installed on the physical steel structure to be detected, and is used to monitor and collect the temperature, stress and vibration parameters of the physical steel structure; The data acquisition module transmits data through the data transmission platform.

3. The steel structure digital twin health monitoring system according to claim 1, characterized in that: The models in the model library include steel structure safety analysis models and online structural calculation models.

4. A monitoring method for a steel structure digital twin health monitoring system according to any one of claims 1 to 3, characterized in that: The steps include: Step 1: Original data collection: obtain the structural design data, construction data, sensor data, maintenance record data and environmental data of the physical steel structure; Step 2: After receiving the raw data, the data processing module repairs, cleans and integrates the raw data; the data processing module integrates a long short-term memory neural network model, and the data processing module repairs the raw data using a structural monitoring data repair method based on the long short-term memory neural network model. The specific steps are as follows: Step 1: According to the missing data characteristics of the steel structure data, and whether there are multiple related adjacent measuring point data, the missing data types are divided into single measuring point data missing and multiple measuring point data missing; Step 2: Determine the data repair method to be an autocorrelation repair method or a spatial correlation repair method according to the type of data missing in step 1; the autocorrelation repair method is a method used for data missing at a single measuring point; the spatial correlation repair method is a method used for data missing at multiple measuring points; Step 3, constructing a data set; wherein the existing continuous data part of the data set is used as a training set, and the missing data part is used as a test set; Step 4, input the training set into the constructed long short-term memory neural network model and perform model training; Step 5: After the training is completed, the trained LSTM neural network model is saved, and the test set is input into the trained LSTM neural network model to predict the missing data. Step 6, analyzing the error between the predicted value and the missing value, and evaluating the missing data repair performance of the long short-term memory neural network model; Step 3: Construction of the digital twin model of the steel structure: Use the model construction module to create the digital twin model of the steel structure, and store the constructed digital twin model of the steel structure in the model library of the model management module; Step 4: Use the model integration module to integrate the steel structure digital twin model with the corresponding physical steel structure to ensure that the steel structure digital twin model can reflect the health status of the physical steel structure in real time and simulate the behavior and response of the physical steel structure under different conditions; Step 5: After receiving the compiled data, the model analysis module calls the corresponding steel structure digital twin model in the model library of the model management module to perform data analysis and finite element simulation analysis. At the same time, combined with the operation plan, the deformation, stress and strain safety monitoring effect of key parts of the physical steel structure are predicted; Step 6: Conduct safety analysis and evaluation of the physical steel structure based on the monitoring effect prediction results; Step 7: Based on the safety analysis and evaluation results of the physical steel structure, the early warning indicators and threshold system are combined to determine the triggering of the early warning; Step 8: If an early warning is triggered, it will be issued, and the prediction and early warning results will be simulated on the digital twin model of the steel structure; Step nine, combining the risk indicator system and risk assessment model to conduct risk assessment and grading of the safety analysis and assessment results of the physical steel structure; Step 10, determine whether to activate the emergency plan; Step 11: If the emergency plan can be activated, the steel structure plan library will be called to automatically select the optimal emergency plan based on the prediction, warning and plan results, and an application will be submitted to the superior. After approval, the plan will be executed.

5. The monitoring method of the steel structure digital twin health monitoring system according to claim 4, characterized in that: In step one, the structural design data includes drawings, dimensions, material specifications and connection methods; the construction data includes actual measurement data and construction records during the construction process; the sensor data is obtained by arranging sensors on the physical steel structure to be monitored on site, and the sensors collect the temperature, stress and vibration in the physical steel structure; the maintenance record data is obtained from historical maintenance and repair records; the environmental data is obtained from geological survey reports, basic data of buildings and structures, and environmental and meteorological data.

6. The monitoring method of the steel structure digital twin health monitoring system according to claim 4, characterized in that: In step 3, when the type of data missing is multiple measurement point data missing, the correlation analysis method is used to analyze the correlation between multiple adjacent measurement points and the missing measurement point; the measurement point data with the largest correlation is selected as the repair model data set; the existing continuous data part in the repair model data set is used as the training set, and the missing data part is used as the test set; When the data of a single measuring point is missing, a data set containing the missing data is constructed, and the existing continuous data part of the data set with missing data is used as the training set, and the missing data part is used as the test set.

7. The monitoring method of the steel structure digital twin health monitoring system according to claim 4, characterized in that: If no warning is triggered in step seven, adjust the operation plan and repeat steps five to six.

8. The monitoring method of the steel structure digital twin health monitoring system according to claim 4, characterized in that: If the decision in step ten does not support the initiation of the emergency plan, the physical steel structure is treated on site.

Images