Bridge construction intelligent monitoring system and method based on digital twinning

Abstract

The application 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 analysis results, obtains an optimization scheme report, analyzes compressive strength data and environmental temperature data, obtains a tension force optimization report according to the analysis results, judges environmental temperature data and real-time state variable data, analyzes the judgment results, and obtains a reinforcement scheme report; in general, the application has the remarkable advantages of large bridge construction construction auxiliary effect, strong response capacity and good operation response effect in a poor network environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bridge construction intelligent monitoring, more specifically, the present application relates to a bridge construction intelligent monitoring system and method based on digital twinning. BACKGROUND

[0002] A bridge generally refers to a structure erected over a river, lake, sea or the like to enable vehicles and pedestrians to pass smoothly. To adapt to the modern high-speed development of the transportation industry, a bridge is also extended to a building erected to cross a ravine, poor geology or meet other traffic needs to make travel more convenient. A bridge generally consists of an upper structure, a lower structure, a support and an accessory structure. The upper structure, also known as the bridge span structure, is the main structure that crosses obstacles. The lower structure includes abutments, piers and foundations. The support is a force transmission device provided at the support of the bridge span structure and the pier or abutment. The accessory structure refers to bridge head aprons, conical revetments, revetments, diversion works and the like.

[0003] The patent with the application publication number CN118657380B discloses a bridge steel cofferdam construction intelligent monitoring system and method based on digital twinning. Through the digital twinning model scene and intelligent evaluation, safety early warning, monitoring data real-time linkage, the digital twinning model intelligently learns safety emergency disposal measures (personnel evacuation, reduced pumping rate, cofferdam backflow), when the safety emergency start standard is triggered, the emergency plan is automatically started, and the emergency measures are automatically pushed to the relevant person in charge, and emergency measures such as organization of personnel evacuation, automatic shouting through broadcasting, and alarm bell alarm are carried out. After the personnel evacuate, the automatic control equipment carries out emergency measures such as water pump pumping and backflow, realizes intelligent disposal of emergency plans, improves the processing efficiency of unexpected time, and reduces the possibility of safety accidents.

[0004] However, the above-mentioned bridge steel cofferdam construction intelligent monitoring system and method based on digital twinning, although through the digital twinning model scene, to a certain extent, realizes intelligent evaluation, safety early warning and monitoring data real-time linkage, but in the bridge construction process, the existing intelligent monitoring system mostly relies on threshold alarm, lacks active prediction related to construction risk, and it is difficult to realize the auxiliary role of the system to the workers. At the same time, due to the fact that the digital twinning model of the existing intelligent monitoring system is mostly static preset, in the face of sudden changes in the construction process, for example, the strength of concrete changes with the weather, in addition, for extreme disaster events such as typhoon or earthquake, the existing intelligent monitoring system also lacks rapid response capability.

[0005] In view of this, the present application provides a bridge construction intelligent monitoring system and method based on digital twinning to solve the above-mentioned problems. SUMMARY

[0006] In order to overcome the above-mentioned defects of the prior art, in order to achieve the above-mentioned purpose, the present application provides the following technical scheme, which comprises:

[0007] a construction data collection module, configured to collect a construction data set, the construction data set comprising beam length data, compressive strength data, initial tension force data, and stage number data;

[0008] a stress influence data collection module, configured to collect a stress influence data set, the stress influence data set comprising environmental temperature data and real-time state variable data;

[0009] a feature data conversion module, configured to pre-process the construction data set and the stress influence data set to obtain a feature data set;

[0010] Further, the step of pre-processing the construction data set and the stress influence data set comprises:

[0011] Q1: normalizing all sub-data items in the basic data set to the range of [0, 1] based on a normalization formula;

[0012] Q2: calculating interaction feature data based on the compressive strength data and the environmental temperature data, the specific formula being:

[0013] ;

[0014] obtaining the interaction feature data , wherein is the compressive strength data, is an exponential function, is the environmental temperature data, is standard environmental temperature data;

[0015] Q3: packing the beam length data, the compressive strength data, the initial tension force data, the stage number data, the interaction feature data, and the real-time state variable data to obtain the feature data set;

[0016] a construction stress value prediction module, configured to construct a construction stress value prediction model based on a historical feature data set, and to obtain a stress prediction value based on the feature data set;

[0017] Further, the step of constructing the construction stress value prediction model based on the historical feature data set, and obtaining the stress prediction value based on the feature data set comprises:

[0018] Step one: obtaining a group of historical feature data sets stored in a database, and comparing a timestamp with a current time, grouping and marking the historical feature data sets according to the comparison results from small to large, the marking results being L1, L2, L3,..., Ln, and taking the marking results as a sample set;

[0019] Step 2: Divide the sample set into 70% training set, 15% test set and 15% validation set, and establish a stress value prediction model based on the sample set.

[0020] Step 3: Based on the historical feature dataset in the training set, construct a basic stress value prediction model by substituting the historical feature dataset from the training set into the calculation formula:

[0021] ;

[0022] Get the first One predicted basic stress value ,in, To increase the number of gradient boosting trees, The number of decision trees in a single gradient boosting tree. For learning rate, For the first The first gradient boosting tree Piecewise function of a decision tree For the historical feature dataset in the training set, This is a tree structure split point. To adjust the weighting factors, To provide the Bayesian regularization term for the historical feature dataset in the training set;

[0023] Step 4: Based on the predicted basic stress values ​​from Step 3, perform weighted fusion. The specific calculation formula for fusion is as follows:

[0024] ;

[0025] Obtain training stress prediction values ,in, The number of basic stress value prediction models, For the first Each model weight factor;

[0026] 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. When the absolute deviation rate is greater than or equal to 3%, return to Step 3 to retrain.

[0027] Step 6: Repeat steps 3 to 5 until the preset number of iterations is reached to obtain the stress value prediction model;

[0028] Step 7: Based on the stress prediction model in Step 5, input the feature dataset to obtain the predicted stress values;

[0029] Step 8: Output the predicted stress values ​​to the automatic optimization scheme generation module;

[0030] An automatic optimization scheme generation module is configured to analyze the stress prediction value and process the analysis result to obtain an optimization scheme report.

[0031] Further, the analysis of the stress prediction value and the processing of the analysis result include:

[0032] based on the stress allowance threshold value;

[0033] When the stress prediction value is less than or equal to the stress allowance threshold value, a safety report is generated.

[0034] When the stress prediction value is greater than the stress allowance threshold value, the degree of overrun is determined.

[0035] When the stress prediction value is greater than the stress allowance threshold value and less than or equal to 1.2 times the stress allowance threshold value, a mild overrun report is generated.

[0036] When the stress prediction value is greater than 1.2 times the stress allowance threshold value, a severe overrun report is generated.

[0037] The safety report includes an explanation that the predicted construction stress value is normal, and the staff should work according to the preset work procedure.

[0038] The mild overrun report includes an explanation that the predicted construction stress value is mildly abnormal, and the staff should enter the stage construction;

[0039] The severe overrun report includes an explanation that the predicted construction stress value is severely abnormal, and the staff should increase the tension force parameter;

[0040] The safety report, the mild overrun report and the severe overrun report are packaged to obtain the optimization scheme report.

[0041] A full life cycle adaptive optimization module is configured to analyze the compressive strength data and the environmental temperature data, and to obtain a tension force optimization report according to the analysis result.

[0042] Further, the analysis of the compressive strength data and the environmental temperature data and the obtaining of the tension force optimization report according to the analysis result include:

[0043] When the environmental temperature data is greater than 30 degrees Celsius or less than 5 degrees Celsius, a tension force optimization report is generated.

[0044] The tension force optimization report includes an explanation that the initial tension force data needs to be adjusted to new initial tension force data.

[0045] The specific calculation formula of the new initial tension force data is:

[0046] ;

[0047] obtain new initial tension data wherein, is initial tension data, is a sensitivity coefficient;

[0048] an extreme working condition simulation module, configured to judge the environmental temperature data and the real-time state variable data, and analyze the judgment result to obtain a reinforcement scheme report;

[0049] Further, the way of judging the environmental temperature data and the real-time state variable data, and analyzing the judgment result to obtain a reinforcement scheme report includes:

[0050] monitoring the environmental temperature data and the real-time state variable data;

[0051] when the environmental temperature data is less than 0 degrees Celsius or the real-time state variable data is greater than a strain threshold value, judging as a disaster event;

[0052] when there is a disaster event, calculating an additional stress value, and the specific formula is:

[0053] ;

[0054] obtaining the additional stress value wherein, is air density, is a drag coefficient, is a beam windward area, is real-time state variable data, is a beam cross-sectional area;

[0055] according to the additional stress value, when the sum of the additional stress value and the stress prediction value is greater than a stress allowed threshold value, generating a reinforcement scheme report;

[0056] the reinforcement scheme report includes that the current beam disaster resistance performance is insufficient, and the staff is requested to provide temporary support or reinforcement steel for the beam as soon as possible;

[0057] a distributed cloud edge backup module, configured to construct a cloud edge backup system based on the feature data set, the stress prediction value and the optimization scheme report;

[0058] Further, the way of constructing the cloud edge backup system based on the feature data set, the stress prediction value and the optimization scheme report includes:

[0059] constructing a cloud edge architecture, the cloud end stores data backup and system data set, and the edge processes real-time data acquisition and data calculation;

[0060] the cloud edge architecture synchronously receives the system data set according to a preset time unit, and the edge device can use the local cache system data set to run independently;

[0061] The characteristic data set and stress prediction value are automatically backed up every five minutes and sent to the cloud and edge;

[0062] The data management communication module is used to construct a bridge digital twin model according to the stress prediction value, optimization scheme report, tension force optimization report and reinforcement scheme report, and store the system data set in the database;

[0063] Further, the way of constructing the bridge digital twin model according to the stress prediction value, optimization scheme report, tension force optimization report and reinforcement scheme report comprises:

[0064] Integrating the stress prediction value, optimization scheme report, tension force optimization report and reinforcement scheme report, the bridge digital twin model is constructed;

[0065] The stress distribution of the bridge digital twin model is updated using the stress prediction value;

[0066] The construction sequence is adjusted based on the optimization scheme report;

[0067] The bridge digital twin model is displayed through a visual panel;

[0068] The system data set comprises a construction data set, a stress influence data set, a characteristic data set, a stress prediction value, an optimization scheme report, a tension force optimization report and a reinforcement scheme report;

[0069] Further, S1: a construction data set is collected, and the construction data set comprises beam length data, compressive strength data, initial tension force data and stage number data;

[0070] S2: a stress influence data set is collected, and the stress influence data set comprises environmental temperature data and real-time state variable data;

[0071] S3: the construction data set and the stress influence data set are preprocessed to obtain a characteristic data set;

[0072] S4: a construction stress value prediction model is constructed based on a historical characteristic data set, and a stress prediction value is obtained according to the characteristic data set;

[0073] S5: the stress prediction value is analyzed, and an optimization scheme report is obtained by processing the analysis result;

[0074] S6: the compressive strength data and the environmental temperature data are analyzed, and a tension force optimization report is obtained according to the analysis result;

[0075] S7: the environmental temperature data and the real-time state variable data are judged, and a reinforcement scheme report is obtained by analyzing the judgment result;

[0076] S8: constructing a cloud-edge backup system based on the feature data set, the stress prediction value and the optimization scheme report;

[0077] S9: constructing a bridge digital twin model according to the stress prediction value, the optimization scheme report, the tension force optimization report and the reinforcement scheme report, and storing the system data set in a database.

[0078] The bridge construction intelligent monitoring system and method based on digital twin have the following technical effects and advantages:

[0079] The bridge construction intelligent monitoring system and method based on digital twin have the following technical effects and advantages: BRIEF DESCRIPTION OF DRAWINGS

[0080] Figure 1A bridge construction intelligent monitoring system based on digital twinning according to the present application;

[0081] Figure 2 A bridge construction intelligent monitoring method based on digital twinning according to the present application. DETAILED DESCRIPTION

[0082] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0083] The terms used in the embodiments of the present application are merely for the purpose of describing the specific embodiments, and are not intended to limit the present application. The singular forms "a", "an" and "the" used in the embodiments of the present application are also intended to include the plural forms, unless the context clearly indicates otherwise. "Plural" generally includes at least two.

[0084] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if determined" or "if detecting (a stated condition or event)" can be interpreted to mean "when determined" or "in response to determining" or "when detecting (a stated condition or event)" or "in response to detecting (a stated condition or event)".

[0085] In addition, the step sequence in each of the following method embodiments is only an example, and is not strictly limited.

[0086] In fact, the server equipment deployed by the bridge construction intelligent monitoring system based on digital twinning may be composed of one or more devices. The bridge construction intelligent monitoring system based on digital twinning can be realized as a business instance, a virtual machine, and a hardware device. For example, the bridge construction intelligent monitoring system based on digital twinning can be realized as a business instance deployed on one or more devices in a cloud node. In short, the bridge construction intelligent monitoring system based on digital twinning can be understood as a software deployed on a cloud node, which is used to provide a bridge construction intelligent monitoring system based on digital twinning for each user end. Alternatively, the bridge construction intelligent monitoring system based on digital twinning can also be realized as a virtual machine deployed on one or more devices in a cloud node. The virtual machine has application software for managing each user end. Alternatively, the bridge construction intelligent monitoring system based on digital twinning can also be realized as a server composed of a plurality of same or different types of hardware devices, and one or more hardware devices are set to provide a bridge construction intelligent monitoring system based on digital twinning for each user end.

[0087] In an implementation form, the bridge construction intelligent monitoring system based on digital twinning and the user end are mutually adapted. That is, the bridge construction intelligent monitoring system based on digital twinning is an application installed on a cloud service platform, and the user end is a client that establishes a communication connection with the application; or the bridge construction intelligent monitoring system based on digital twinning is realized as a website, and the user end is realized as a webpage; or the bridge construction intelligent monitoring system based on digital twinning is realized as a cloud service platform, and the user end is realized as an applet in an instant messaging application.

[0088] As shown in Figure 1 FIG. 1 is a system architecture diagram of a bridge construction intelligent monitoring system based on digital twinning provided by an embodiment of the present application.

[0089] The bridge construction intelligent monitoring system based on digital twinning can be set in a cloud server, and in an implementation form, can be one or more service devices, or can be an application installed on a cloud (such as a server of a mobile service operator, a server cluster, etc.), or can be developed as a website. According to the functions realized, the bridge construction intelligent monitoring system based on digital twinning can include a construction data acquisition module, a stress influence data acquisition module, a feature data conversion module, 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, a distributed cloud edge backup module, and a data management and transmission module. The modules of the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, and are stored in the memory of the electronic device.

[0090] In the embodiment of the present application, each of the above modules can be independently implemented and called by other modules in the bridge construction intelligent monitoring system based on digital twinning. The calling here can be understood as that a module can connect multiple modules of another type and provide corresponding services for the connected multiple modules. For example, the sharing evaluation module can call the same information collection module to obtain the information collected by the information collection module. Based on the above characteristics, the bridge construction intelligent monitoring system based on digital twinning provided by the embodiment of the present application can adjust the application scope of the bridge construction intelligent monitoring system architecture based on digital twinning by increasing modules and directly calling without modifying program codes, realize cluster horizontal expansion, and achieve the purpose of quickly and flexibly expanding the bridge construction intelligent monitoring system based on digital twinning. In actual application, the above modules can be arranged in the same device or different devices, or in a virtual device, such as a service instance in a cloud server.

[0091] Embodiment 1, please refer to Figure 1 The bridge construction intelligent monitoring system based on digital twinning described in the embodiment comprises:

[0092] The construction data collection module is configured to collect a construction data set, wherein the construction data set comprises beam length data, compressive strength data, initial tension force data and stage number data.

[0093] It should be explained that the beam length data is obtained by collecting the distance values of the two ends of a specified beam body by a laser range finder; the compressive strength data is obtained by collecting the compressive values of the specified beam body by a field rebounder; the initial tension force data is obtained by collecting the detection oil pressure gauge values of the specified beam body by a hydraulic jack pressure sensor and multiplying the piston area; and the stage number data is obtained by collecting the number values of the current construction stage by a construction BIM tool.

[0094] The stress influence data collection module is configured to collect a stress influence data set, wherein the stress influence data set comprises environmental temperature data and real-time state change data.

[0095] It should be explained that the environmental temperature data is obtained by collecting the temperature values in a specified area by a wireless temperature sensor; and the real-time state change data is obtained by collecting the strain values of a specified beam body by a vibrating wire strain gauge.

[0096] The feature data conversion module is configured to pre-process the construction data set and the stress influence data set to obtain a feature data set.

[0097] Further, the step of pre-processing the construction data set and the stress influence data set comprises:

[0098] Q1: normalize all sub-data items in the basic data set to the range of [0, 1] based on the normalization formula;

[0099] It needs to be explained that the basic data set includes the construction data set and the stress influence data set; the specific expression formula of the normalization formula is: , wherein is the normalized value, is any sub-data item of the basic data, is the historical maximum value of the sub-data item, is the historical minimum value of the sub-data item;

[0100] Q2: calculate the interaction feature data based on the compressive strength data and the environmental temperature data, and the specific formula for calculation is:

[0101] ;

[0102] get the interaction feature data , wherein is the compressive strength data, is the exponential function, is the environmental temperature data, is the standard environmental temperature data;

[0103] It needs to be explained that the exponential function is used to represent the power of the base of natural logarithm ;

[0104] Q3: pack the beam length data, the compressive strength data, the initial tension force data, the stage number data, the interaction feature data and the real-time state variable data to get the feature data set;

[0105] It needs to be explained that the beam length data, the initial tension force data, the stage number data and the interaction feature data in the feature data set are normalized data values, and the compressive strength data and the real-time state variable data are original data values;

[0106] The construction stress value prediction module is configured to construct a construction stress value prediction model based on the historical feature data set, and obtain a stress prediction value according to the feature data set;

[0107] Further, the step of constructing a construction stress value prediction model based on the historical feature data set and obtaining a stress prediction value according to the feature data set includes:

[0108] Step 1: obtain a group of historical feature data sets stored in the database, and compare the time stamp with the current time, and mark the historical feature data sets according to the comparison results from small to large, and the marking results are L1, L2, L3,..., Ln, and the marking results are used as a sample set;

[0109] Step two: 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 according to the sample set;

[0110] Step three: based on the historical feature data set in the training set, a basic stress value prediction model is constructed, and the historical feature data set in the training set is substituted into the calculation formula:

[0111] ;

[0112] the first basic stress prediction value , wherein, is the number of gradient boosting trees, is the number of decision trees in a single gradient boosting tree, is the learning rate, is the segment function of the i-th decision tree of the j-th gradient boosting tree, is the historical feature data set in the training set, is the tree structure split point, is the correction weight factor, is the Bayesian regularization term of the historical feature data set in the training set; It needs to be explained that the segment function is the calculation unit of the gradient boosting tree; Step four: based on the basic stress prediction value in step three, weighted fusion is performed, and the specific calculation formula for fusion is:

[0113]

[0114] ;

[0115] ;

[0116] the training stress prediction value , wherein, is the number of basic stress value prediction models, is the i-th model weight factor; Step five: based on the training stress prediction value in step four, the absolute value of the training stress prediction value and the actual stress prediction value is calculated and multiplied by 100% to obtain the absolute deviation rate. When the absolute deviation rate is greater than or equal to 3%, return to step three to retrain;

[0117] Step six: repeat steps three to five until a preset iteration number is reached to obtain a stress value prediction model;

[0118] Step seven: based on the stress value prediction model in step five, input the feature data set to obtain a stress prediction value;

[0119]

[0120] ​​​Step eight: output the stress prediction value to the automatic optimization scheme generation module;

[0121] The automatic optimization scheme generation module is configured to analyze the stress prediction value and process the analysis result to obtain an optimization scheme report.

[0122] Further, the analysis of the stress prediction value and the processing of the analysis result include:

[0123] based on the stress allowable threshold value;

[0124] It should be explained that the stress allowable threshold value is usually a preset multiple of the compressive strength data, for example, taking 0.6 times the compressive strength data as the stress allowable threshold value;

[0125] When the stress prediction value is less than or equal to the stress allowable threshold value, a safety report is generated;

[0126] When the stress prediction value is greater than the stress allowable threshold value, the degree of overrun is determined;

[0127] When the stress prediction value is greater than the stress allowable threshold value and less than or equal to 1.2 times the stress allowable threshold value, a mild overrun report is generated;

[0128] When the stress prediction value is greater than 1.2 times the stress allowable threshold value, a severe overrun report is generated;

[0129] The safety report includes an explanation that the predicted construction stress value is normal, and the staff should work according to the preset work procedure;

[0130] The mild overrun report includes an explanation that the predicted construction stress value has a mild abnormality, and the staff should enter the stage construction;

[0131] It should be explained that is the stage number data, is the required skipped stage data, which is obtained by calculating the difference between the stress prediction value and the stress allowable threshold value and dividing it by 0.1 times the stress allowable threshold value;

[0132] The severe overrun report includes an explanation that the predicted construction stress value has a severe abnormality, and the staff should increase the tension force parameter;

[0133] It should be explained that is the adjusted tension force data, and the specific calculation formula is:

[0134] wherein is a proportionality coefficient, is the initial tension force data, is the stress prediction value, a stress allowable threshold value;

[0135] packaging safety reports, mild overrun reports and severe overrun reports, and obtain an optimized solution report;

[0136] The full-life-cycle adaptive optimization module is configured to analyze the compressive strength data and the environmental temperature data, and obtain a tension force optimization report based on the analysis result.

[0137] Further, the compressive strength data and the environmental temperature data are analyzed, and the tension force optimization report is obtained based on the analysis result.

[0138] When the environmental temperature data is greater than 30 degrees Celsius or less than 5 degrees Celsius, a tension force optimization report is generated.

[0139] The tension force optimization report includes instructions to adjust the initial tension force data to new initial tension force data.

[0140] The specific calculation formula of the new initial tension force data is:

[0141] ;

[0142] Obtain new initial tension force data wherein, is the initial tension force data, is the sensitivity coefficient.

[0143] The extreme working condition simulation module is configured to judge the environmental temperature data and the real-time state variable data, analyze the judgment result, and obtain a reinforcement scheme report.

[0144] Further, the environmental temperature data and the real-time state variable data are judged, and the judgment result is analyzed to obtain a reinforcement scheme report.

[0145] Monitor the environmental temperature data and the real-time state variable data.

[0146] When the environmental temperature data is less than 0 degrees Celsius or the real-time state variable data is greater than the strain threshold value, it is judged as a disaster event.

[0147] It should be explained that the strain threshold value is manually selected and input into the system.

[0148] When there is a disaster event, calculate the additional stress value, and the specific formula is:

[0149] ;

[0150] Obtain the additional stress value wherein, is the air density, is the drag coefficient. is the windward area of the beam body, is the real-time state variable data, is the cross-sectional area of the beam body;

[0151] According to the additional stress value, when the sum of the additional stress value and the stress prediction value is greater than the stress allowed threshold value, a reinforcement scheme report is generated;

[0152] The reinforcement scheme report includes an explanation that the current beam body disaster resistance performance is insufficient, and the staff is requested to provide temporary support or reinforcement steel for the beam body as soon as possible;

[0153] The distributed cloud edge backup module is configured to construct a cloud-edge backup system based on the feature data set, the stress prediction value, and the optimization scheme report;

[0154] Further, the cloud-edge backup system is constructed based on the feature data set, the stress prediction value, and the optimization scheme report, and the manner includes:

[0155] The cloud-edge architecture is constructed, the cloud stores data backup and system data set, and the edge processes real-time data acquisition and data calculation;

[0156] The cloud-edge architecture synchronously receives the system data set according to a preset time unit, and the edge device can use the local cache system data set to run independently;

[0157] The feature data set and the stress prediction value are automatically backed up every five minutes and sent to the cloud and the edge;

[0158] The data management and communication module is configured to construct a bridge digital twin model based on the stress prediction value, the optimization scheme report, the tension force optimization report, and the reinforcement scheme report, and store the system data set in a database;

[0159] Further, the bridge digital twin model is constructed based on the stress prediction value, the optimization scheme report, the tension force optimization report, and the reinforcement scheme report, and the manner includes:

[0160] The stress prediction value, the optimization scheme report, the tension force optimization report, and the reinforcement scheme report are integrated to construct the bridge digital twin model;

[0161] The stress prediction value is used to update the stress distribution of the bridge digital twin model;

[0162] The construction sequence is adjusted based on the optimization scheme report;

[0163] The bridge digital twin model is displayed through a visual panel;

[0164] The system data set includes a construction data set, a stress influence data set, a feature data set, a stress prediction value, an optimization scheme report, a tension force optimization report, and a reinforcement scheme report;

[0165] The embodiment has the beneficial effects that by collecting a construction data set including beam body length data, compressive strength data, initial tension force data and stage number data, collecting a stress influence data set including environmental temperature data and real-time state variable data, preprocessing the construction data set and the stress influence data set to obtain a feature data set, constructing a construction stress value prediction model based on a historical feature data set, obtaining a stress prediction value based on the feature data set, analyzing the stress prediction value, processing the analysis result to obtain an optimization scheme report, analyzing the compressive strength data and the environmental temperature data, and obtaining a tension force optimization report based on the analysis result, judging the environmental temperature data and the real-time state variable data, and analyzing the judgment result to obtain a reinforcement scheme report, constructing a cloud-edge backup system based on the feature data set, the stress prediction value and the optimization scheme report, constructing a bridge digital twin model based on the stress prediction value, the optimization scheme report, the tension force optimization report and the reinforcement scheme report, and storing the system data set in the database, the system can accurately calculate the bridge stress value in the future period under the dynamic influence of environmental factors, which provides an extremely important and accurate data basis for the construction of the bridge. In addition, the system can assist the staff to provide corresponding measures according to the predicted change of the bridge stress value by deep mining of the stress prediction value, greatly reducing the time cost and professional cost required for construction risk response decision-making. At the same time, by simulating the environmental emergency and disaster emergency that may occur in the construction process, the system can provide accurate and reliable response measures for the staff at the first time when the emergency comes, greatly reducing the damage degree of small probability natural time to the construction process, thereby effectively improving the bridge safety of the construction process. Moreover, through the establishment of the cloud-edge backup system, the system can still normally run the bridge digital twin model when the network environment is poor, ensuring that the bridge digital twin model can still run continuously even in the case of network interruption and other adverse conditions. Overall, the present application has the remarkable advantages of large bridge construction assistance, strong response capability and good adverse network environment operation response effect.

[0166] Embodiment 2 Please refer to Figure 2 The embodiment does not describe some parts in detail, see the description of embodiment 1, and provides a bridge construction intelligent monitoring method based on digital twin, which comprises the following steps: S1: collecting a construction data set, the construction data set comprising beam body length data, compressive strength data, initial tension force data and stage number data;

[0167] S2: collecting a stress influence data set, the stress influence data set comprising environmental temperature data and real-time state variable data;

[0168] S3: preprocessing the construction data set and the stress influence data set to obtain a feature data set;

[0169] S4: constructing a construction stress value prediction model based on the historical feature data set, and obtaining a stress prediction value according to the feature data set;

[0170] S5: analyzing the stress prediction value, and processing the analysis result to obtain an optimization scheme report;

[0171] S6: analyzing the compressive strength data and the environmental temperature data, and obtaining a tension force optimization report according to the analysis result;

[0172] S7: judging the environmental temperature data and the real-time state variable data, and analyzing the judgment result to obtain a reinforcement scheme report;

[0173] S8: constructing a cloud-edge backup system based on the feature data set, the stress prediction value and the optimization scheme report;

[0174] S9: constructing a bridge digital twin model according to the stress prediction value, the optimization scheme report, the tension force optimization report and the reinforcement scheme report, and storing the system data set in a database.

[0175] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0176] Therefore, the embodiments should all be regarded as exemplary and non-limiting, and the scope of the present application is not limited by the above description, and all changes falling within the meaning and scope of the equivalent elements are intended to be included in the present application.

[0177] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (Artificial Intelligence, AI) is to use digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0178] In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. The plurality of units or devices stated in the system can also be realized by one unit or device through software or hardware. The words first, second, etc. are used to represent names, and do not represent any specific order.

[0179] Finally, it should be noted that the above examples are merely intended to illustrate the technical solutions of the present application and not to limit the present application. Although the present application 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 application can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A bridge construction intelligent monitoring system based on digital twins, characterized in that, The system includes: a construction stress value prediction module, an automatic optimization scheme generation module, a full lifecycle 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 historical feature datasets, and obtain the stress prediction value based on the feature datasets. The automatic optimization scheme generation module is used to analyze the stress prediction values ​​and process the analysis results to obtain an optimization scheme report. The full life cycle adaptive optimization module is used to analyze compressive strength data and ambient temperature data, and generate a tension optimization report based on the analysis results. The methods for analyzing compressive strength data and ambient temperature data, and obtaining a tension 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, a tension optimization report is generated; The tension optimization report includes an explanation of the need to adjust the initial tension data to the new initial tension data; The specific formula for calculating the new initial tension data is as follows: ； Obtain new initial tension data ,in, For initial tension data, Sensitivity coefficient For ambient temperature data, Standard ambient temperature data; 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 scheme report. The methods for obtaining a reinforcement scheme report include: judging environmental temperature data and real-time dynamic change data, and analyzing the judgment results. 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 using the following formula: ； Obtain the additional stress value ,in, air density, The drag coefficient, The windward area of ​​the beam. For real-time dynamic data, The cross-sectional area of ​​the beam; Based on the additional stress value, when the sum of the additional stress value and the predicted stress value is greater than the allowable stress threshold, a reinforcement scheme report is generated; The reinforcement plan report includes an explanation of the current insufficient disaster resistance of the beam structure, and requests that staff provide temporary support or reinforced steel strands for the beam structure as soon as possible; The distributed cloud-edge backup module is used to build a cloud-edge backup system based on feature datasets, stress prediction values, and optimization scheme reports.

2. The intelligent monitoring system for bridge construction based on digital twins according to claim 1, characterized in that, The system also includes: a construction data acquisition module, a stress influence data acquisition module, a feature data conversion module, and a data management and transmission module, wherein: The construction data acquisition module is used to collect construction datasets, which include beam length data, compressive strength data, initial tension force data, and stage number data. The stress influence data acquisition module is used to acquire stress influence datasets, which include ambient temperature data and real-time state change data. The feature data conversion module is used to preprocess the construction dataset and stress influence dataset to obtain the feature dataset; The data management and communication module is used to construct a digital twin model of the bridge based on the stress prediction value, optimization plan report, tension optimization report and reinforcement plan report, and to store the system dataset in the database.

3. The intelligent monitoring system for bridge construction based on digital twins according to claim 1, characterized in that, The steps for constructing a construction stress prediction model based on historical feature datasets and obtaining predicted stress values ​​based on the feature datasets include: Step 1: Obtain a set of historical feature datasets stored in the database, and compare them with the current time based on the timestamp. Group the historical feature datasets into corresponding groups according to the comparison results from smallest to largest, and label the labels as L1, L2, L3, ..., Ln. Use the labeling results as the sample set. Step 2: Divide the sample set into 70% training set, 15% test set and 15% validation set, and establish a stress value prediction model based on the sample set. Step 3: Based on the historical feature dataset in the training set, construct a basic stress value prediction model by substituting the historical feature dataset from the training set into the calculation formula: ； Get the first One predicted basic stress value ,in, To increase the number of gradient boosting trees, The number of decision trees in a single gradient boosting tree. For learning rate, For the first The first gradient boosting tree Piecewise function of a decision tree For the historical feature dataset in the training set, This is a tree structure split point. To adjust the weighting factor, To provide the Bayesian regularization term for the historical feature dataset in the training set; Step 4: Based on the predicted basic stress values ​​from Step 3, perform weighted fusion. The specific calculation formula for fusion is as follows: ； Obtain training stress prediction values ,in, The number of basic stress value prediction models, For the first Each model weight factor; 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. When the absolute deviation rate is greater than or equal to 3%, return to Step 3 to retrain. Step 6: Repeat steps 3 to 5 until the preset number of iterations is reached to obtain the stress value prediction model; Step 7: Based on the stress prediction model in Step 5, input the feature dataset to obtain the predicted stress values; Step 8: Output the predicted stress values ​​to the automatic optimization scheme generation module.

4. The intelligent monitoring system for bridge construction based on digital twins according to claim 1, characterized in that, The methods for analyzing predicted stress values ​​and processing the analysis results include: Based on the allowable stress threshold; A safety report is generated when the predicted stress value is less than or equal to the allowable stress threshold. When the predicted stress value exceeds the allowable stress threshold, the degree of exceeding the limit is determined. A minor over-limit report is generated when the predicted stress value is greater than the allowable stress threshold but less than or equal to 1.2 times the allowable stress threshold. A severe over-limit report is generated when the predicted stress value is greater than 1.2 times the allowable stress threshold. The safety report should state that the predicted construction stress value is normal and that staff should follow the pre-set work procedures. The report for minor over-limit conditions includes an explanation that the predicted construction stress value is slightly abnormal, and requests that staff enter the area. Phased construction, For stage number data, The required skip stage data is obtained by calculating the difference between the predicted stress value and the allowable stress threshold and dividing it by 0.1 times the allowable stress threshold; The severe exceedance report includes a description of severe anomalies in the predicted construction stress values, requesting staff to add... Tension parameters; The packaging safety report, minor over-limit report, and major over-limit report are used to obtain an optimization plan report.

5. The intelligent monitoring system for bridge construction based on digital twins according to claim 1, characterized in that, The methods for building a cloud-edge backup system based on feature datasets, stress predictions, and optimization reports include: Build a cloud-edge architecture, with cloud storage for data backup and system datasets, and edge processing for real-time data acquisition and computation; The cloud-edge architecture synchronously receives system datasets based on a preset time unit, and edge devices can run independently using locally cached system datasets. Every five minutes, the feature dataset and stress prediction values ​​are automatically backed up and sent to the cloud and edge.

6. The intelligent monitoring system for bridge construction based on digital twins according to claim 2, characterized in that, The methods for constructing a digital twin model of a bridge based on predicted stress values, optimization reports, tension optimization reports, and reinforcement reports include: By integrating stress prediction values, optimization plan reports, tension force optimization reports, and reinforcement plan reports, a digital twin model of the bridge is constructed. The stress distribution of the bridge's digital twin model is updated using predicted stress values; The construction sequence was adjusted based on the optimized plan report; The digital twin model of the bridge is displayed through a visualization panel; The system dataset includes construction dataset, stress influence dataset, feature dataset, stress prediction values, optimization scheme report, tension optimization report, and reinforcement scheme report.

7. A method for intelligent monitoring of bridge construction based on digital twins, implemented according to any one of claims 1-6, characterized in that, The work includes the following steps: S1: Collect construction datasets, which include beam length data, compressive strength data, initial tension force data, and stage number data; S2: Collect stress impact dataset, which includes ambient temperature data and real-time state change data; S3: Preprocess the construction dataset and stress influence dataset to obtain the feature dataset; S4: Construct a construction stress value prediction model based on historical feature datasets, and obtain the stress prediction value based on the feature datasets; S5: Analyze the predicted stress values ​​and process the analysis results to obtain an optimization report; S6: Analyze the compressive strength data and ambient temperature data, and based on the analysis results, obtain a tension optimization report; S7: Judge the ambient temperature data and real-time dynamic change data, analyze the judgment results, and obtain a reinforcement scheme report; S8: Based on feature datasets, stress prediction values, and optimization scheme reports, construct a cloud-edge backup system; S9: Construct a digital twin model of the bridge based on the predicted stress values, optimization plan report, tension optimization report, and reinforcement plan report, and store the system dataset in the database.

Images