A Digital Stress Control Method and System for the Demolition of PC Girder Bridges Based on Long-Term Time-Varying Factors

Abstract

This invention belongs to the field of digital stress control technology. It discloses a digital stress control method and system for the demolition of PC beam bridges based on long-term time-varying factors. The system includes: a stress change prediction module, a graded demolition optimization module, a risk probability analysis module, a multi-scale damage quantification module, and a full life-cycle digital fusion module. It establishes a stress prediction model based on historical feature vectors, and outputs predicted stress values ​​based on the feature vectors and the stress prediction model. The predicted stress values ​​are analyzed to obtain a segmented demolition plan. The segmented threshold intervals are dynamically optimized to obtain new segmented threshold intervals. Minor damage assessments are performed on the beam bridge segments, and high-risk area reports are obtained based on the assessment results. A full life-cycle digital twin is generated. Overall, this invention has significant advantages: it greatly assists in the segmented demolition of PC beam bridges, provides excellent quantification of minor damage, and offers a highly intuitive representation of the overall state of the PC beam bridge.

Description

Technical Field

[0001] This invention relates to the field of digital stress control technology, and more specifically, to a digital stress control method and system for the demolition of PC beam bridges based on long-term time-varying factors. Background Art

[0002] A beam bridge is a bridge in which the main beam, which is mainly subjected to bending, serves as the load-bearing component. The main beam can be a solid web beam or a truss beam. Solid web beams have a simple structure and are relatively convenient to manufacture, erect, and maintain, and are widely used in medium and small span bridges, but they are not economical in terms of material utilization. Truss beams have members that bear axial forces, making full use of materials, with a lighter self-weight and a large span capacity, and are often used to build long span bridges. PC beams are precast concrete beams, and as the core load-bearing component in a bridge, they have an irreplaceable importance in the use of bridges.

[0003] Bridges, as an indispensable transportation route throughout history, still exist widely in today's society. With the continuous development of society, durable concrete bridges have become the mainstay of bridge use in the world today. However, when PC beam bridges need to be demolished due to the end of their service life or regional planning, they often face challenges such as the fact that current demolition technologies mostly rely on static models, which fail to consider the dynamic impact of time-varying factors on the structural performance of PC beam bridges during long-term use. Furthermore, traditional detection technologies are unable to quantify minute damages such as internal prestressing tendon corrosion and concrete microcracks, which affects the detection of overall stress distribution. At the same time, existing demolition technologies mostly focus on the demolition stage and fail to break down the data barriers between the design, construction, and operation and maintenance stages.

[0004] In view of this, the present invention proposes a digital stress control method and system for the demolition of PC beam bridges based on long-term time-varying factors to solve the above problems. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution, including:

[0006] The demolition data acquisition module is used to collect demolition datasets, which include demolition location data, demolition time data, demolition force data, and measured stress data.

[0007] The time-varying data acquisition module is used to acquire time-varying datasets, which include shrinkage strain data, prestress relaxation data, and environmental corrosion data.

[0008] The feature vector processing module is used to preprocess the demolition dataset and the time-varying dataset to obtain feature vectors;

[0009] Furthermore, the preprocessing steps for the demolition dataset and the time-varying dataset include:

[0010] Q1: Clean the basic dataset by removing outliers and normalize all sub-data items in the basic dataset to the range of [0, 1] according to the normalization formula;

[0011] Q2: Calculate the progress characteristics based on the demolition location data and demolition time data. The specific formula for calculating the progress characteristics is as follows:

[0012] ;

[0013] Obtain progress feature data ,in, For demolition location data, Data on demolition time;

[0014] Q3: By using shrinkage strain data In time interval Dividing the change within a time interval by the change rate characteristic data yields the change rate characteristic data. ;

[0015] Q4: Data on prestress relaxation Add 1 and multiply by the demolition force data To obtain comprehensive feature data ;

[0016] Q5: Integrate progress feature data, rate of change feature data, and comprehensive feature data to obtain a feature vector;

[0017] The stress change prediction module is used to build a stress prediction model based on historical feature vectors, and output the predicted stress value based on the feature vectors and the stress prediction model.

[0018] Furthermore, the specific steps for establishing a stress prediction model based on historical eigenvectors and outputting the predicted stress values ​​based on the eigenvectors and the stress prediction model include:

[0019] Step 1: Obtain a set of historical feature vectors stored in the database, and compare them with the current time based on the timestamp. Group the comparison results from smallest to largest and label them accordingly as L1, L2, L3, ..., Ln. Use the labeled results as the sample set.

[0020] Step 2: Divide the sample set into 70% training set, 15% test set and 15% validation set, and establish a stress prediction model based on the sample set;

[0021] Step 3: Based on the historical feature vectors, let the historical feature vectors be three-dimensional tensors, and the specific expression formula is as follows:

[0022] ;

[0023] in, For feature vectors, For the current time, For time delay parameters, The number of historical feature vector sample groups. The number of feature data in the feature vector. For time step;

[0024] Step 4: Based on historical feature vectors, calculate the initial stress prediction value using the gradient boosting decision tree. The specific formula for calculation is as follows:

[0025] ;

[0026] Obtain the first stress prediction value ,in, For the number of decision trees, For the first The weighting factor of each tree The mean of historical eigenvectors The Mapping function for trees;

[0027] Step 5: Based on the three-dimensional tensor from Step 3 and the first stress prediction value from Step 4, substitute them into the calculation formula:

[0028] ;

[0029] The second stress prediction value was obtained. ,in, The time decay coefficient, Noise figure Let the norm of the three-dimensional tensor be... It is Gaussian noise;

[0030] Step Six: Based on the predicted second stress value, substitute it into the calculation formula:

[0031] ;

[0032] Obtain the prediction confidence value ,in, The number of folds for cross-validation. For the first The validation set of the fold. For the first Exclusion of the first sample The second stress prediction value of the validation set of the fold;

[0033] Step 7: Based on the prediction confidence value and the loss threshold, when the prediction confidence value is less than the loss threshold, the second stress prediction value is output as the stress prediction value; when the prediction confidence value is greater than or equal to the loss threshold, the average of the sums of the second stress prediction values ​​is output as the stress prediction value.

[0034] Step 8: Output the predicted stress values ​​to the graded demolition optimization module;

[0035] The tiered demolition optimization module is used to analyze the predicted stress values ​​and obtain a tiered demolition plan;

[0036] Furthermore, methods for analyzing the predicted stress values ​​include:

[0037] Based on the segmented threshold interval (R1, R2), the stress prediction value is substituted into the segmented threshold interval for comparison.

[0038] When the predicted stress value is less than or equal to R1, a large-section demolition plan is generated; when the predicted stress value is greater than R1 and less than or equal to R2, a medium-section demolition plan is generated; when the predicted stress value is greater than R2, a small-section demolition plan is generated.

[0039] The large-section demolition plan includes an explanation that the predicted stress value of the beam bridge to be demolished is low, and workers can refer to the length of the large-section segments for demolition operations.

[0040] The mid-section demolition plan includes an explanation of the predicted stress values ​​of the beam bridge to be demolished, and workers can refer to the segment lengths of the mid-section for demolition operations;

[0041] The segment demolition plan includes an explanation of the predicted high stress value of the beam bridge to be demolished, and workers can refer to the segment lengths for demolition operations.

[0042] The specific formula for calculating the segment length is as follows: The lengths of the large segment, the medium segment, and the small segment are obtained respectively. To preset the maximum segment length, The minimum segment length is preset.

[0043] By combining the large-section demolition plan, the medium-section demolition plan, and the small-section demolition plan, a segmented demolition plan is obtained.

[0044] The risk probability analysis module is used to dynamically optimize the segmented threshold intervals to obtain new segmented threshold intervals;

[0045] Furthermore, the method for dynamically optimizing the segmented threshold interval is as follows:

[0046] The absolute deviation is obtained by subtracting the absolute value of the measured stress data from the predicted stress value.

[0047] The specific formula for calculating the risk probability of a given predicted stress value and absolute deviation value is as follows:

[0048] ;

[0049] in, This is the absolute deviation value. and These are the parameters for logistic regression;

[0050] By substituting into the calculation formula: The new segmented threshold interval is obtained ( , ), and return to the hierarchical demolition optimization module to replace the segment threshold interval (R1, R2), where, For learning rate, For partial derivatives, For risk costs;

[0051] The multi-scale damage quantification module is used to assess minor damage to beam bridge segments and generate high-risk area reports based on the assessment results.

[0052] Furthermore, methods for assessing minor damage to beam bridge segments and reporting high-risk areas based on the assessment results include:

[0053] The damage index is calculated based on environmental corrosion data and predicted stress values. The specific formula for the calculation is as follows:

[0054] ;

[0055] Damage index obtained ,in, The damage impact coefficient, For environmental corrosion data, The yield stress of the material;

[0056] When the damage index is greater than the damage threshold, a high-risk area report is obtained by combining the damage index with the location data.

[0057] The full lifecycle digital fusion module is used to integrate design data, construction deviation data, and operation and maintenance loss data based on building information model to obtain a full lifecycle digital twin.

[0058] Furthermore, based on design data, construction deviation data, and operation and maintenance loss data, the methods for data integration using building information modeling include:

[0059] Building Information Modeling (BIM) tools;

[0060] Input the beam bridge BIM model from the design drawings, construction deviation data, and operation and maintenance loss data;

[0061] It should be explained that the beam bridge BIM model and construction deviation data were obtained through manual input, while the operation and maintenance loss data were obtained by accumulating damage indices;

[0062] By integrating the beam bridge BIM model and construction deviation data, an as-built baseline model is obtained.

[0063] Transform maintenance loss data into corrected material property values;

[0064] A digital twin is constructed using a physical engine built based on Building Information Modeling (BIM) tools;

[0065] By combining thermal stress cloud maps and digital twins, a full life-cycle digital twin is obtained;

[0066] The data optimization and management module is used to store system datasets, transmit segmented demolition plans and high-risk area reports, and display the entire lifecycle digital twin through a visualization panel;

[0067] Furthermore, the methods for transmitting segmented dismantling plans and high-risk area reports include:

[0068] The phased demolition plan and high-risk area reports were sent to the staff's email addresses via email, and staff were reminded to check their emails via SMS.

[0069] The system dataset includes demolition dataset, time-varying dataset, feature vectors, stress prediction values, segmented demolition schemes, new segment threshold interval logs, high-risk area reports, and a full lifecycle digital twin;

[0070] Furthermore, S1: Collect the demolition dataset, which includes demolition location data, demolition time data, demolition force data, and measured stress data;

[0071] S2: Collect time-varying datasets, which include shrinkage strain data, prestress relaxation data, and environmental corrosion data;

[0072] S3: Preprocess the demolition dataset and the time-varying dataset to obtain feature vectors;

[0073] S4: Establish a stress prediction model based on historical feature vectors, and output the predicted stress value based on the feature vectors and the stress prediction model;

[0074] S5: Analyze the predicted stress values ​​to obtain a segmented demolition plan;

[0075] S6: Dynamically optimize the segmented threshold interval to obtain a new segmented threshold interval;

[0076] S7: Conduct a minor damage assessment of the beam bridge segment and report high-risk areas based on the assessment results;

[0077] S8: Based on design data, construction deviation data, and operation and maintenance loss data, data is integrated according to the building information model to obtain a digital twin of the entire life cycle;

[0078] S9: Stores system datasets, transmits segmented demolition plans and high-risk area reports, and displays the entire lifecycle digital twin through a visualization panel.

[0079] The technical effects and advantages of this invention, which relates to a digital stress control method and system for the demolition of PC beam bridges based on long-term time-varying factors, are as follows:

[0080] This invention collects a demolition dataset, including demolition location data, demolition time data, demolition force data, and measured stress data. It also collects a time-varying dataset, including shrinkage strain data, prestress relaxation data, and environmental corrosion data. The demolition dataset and the time-varying dataset are preprocessed to obtain feature vectors. A stress prediction model is established based on historical feature vectors, and stress prediction values ​​are output based on the feature vectors and the stress prediction model. The stress prediction values ​​are analyzed to obtain a segmented demolition scheme. The segmented threshold intervals are dynamically optimized to obtain new segmented threshold intervals. Minor damage assessments are performed on the beam bridge segments, and high-risk area reports are generated based on the assessment results. Finally, based on design data, construction deviation data, and operation and maintenance loss data, and using building information modeling... This invention integrates data from various models to obtain a full lifecycle digital twin. The system dataset is stored, and segmented demolition plans and high-risk area reports are transmitted. The full lifecycle digital twin is displayed through a visualization panel, enabling the system to accurately predict the stress of PC beam bridge segments under the dynamic fluctuations of time-varying datasets. This significantly reduces the error accumulation of traditional static models. Furthermore, the invention effectively assists workers in completing segmented demolition of PC beam bridges through hierarchical processing of stress prediction values, thereby effectively reducing the time and labor costs associated with segmented demolition decisions. Simultaneously, dynamic optimization of segmented threshold ranges ensures real-time updates of these ranges, further improving the accuracy of the segmented demolition plan. Moreover, through the analysis of PC... The assessment of minor damage in PC beam bridge segments can intuitively display high-risk areas, thus reducing the drawbacks of traditional detection methods that struggle to quantify minor damage. It also assists staff in intuitively obtaining information on high-risk PC beam bridge segments. Finally, by acquiring design data, construction deviation data, and operation and maintenance damage data, and using BIM tools to present the entire lifecycle of the PC beam bridge as a digital twin, the intuitiveness of the stress state distribution of the PC beam bridge can be further enhanced. Overall, this invention has significant advantages, including a large auxiliary effect on the segmental dismantling of PC beam bridges, good quantification of minor damage, and strong intuitiveness in displaying the overall state of PC beam bridges. Attached Figure Description

[0081] Figure 1 This is a schematic diagram of the digital stress control system for PC beam bridge demolition based on long-term time-varying factors according to the present invention.

[0082] Figure 2 This is a schematic diagram of the digital stress control method for the demolition of PC beam bridges based on long-term time-varying factors according to the present invention. Detailed Implementation

[0083] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0084] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” used in the embodiments of this invention are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0085] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0086] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0087] In practice, the server-side equipment deployed in the PC beam bridge demolition digital stress control system based on long-term time-varying factors may consist of one or more devices. This system can be implemented as a business instance, a virtual machine, or hardware devices. For example, it can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, it can be understood as software deployed on a cloud node to provide the PC beam bridge demolition digital stress control system based on long-term time-varying factors to various user terminals. Alternatively, it can be implemented as a virtual machine deployed on one or more devices in a cloud node, with application software installed to manage various user terminals. Or, it can also be implemented as a server-side equipment composed of numerous identical or different types of hardware devices, with one or more devices configured to provide the PC beam bridge demolition digital stress control system based on long-term time-varying factors to various user terminals.

[0088] In terms of implementation, the digital stress control system for PC beam bridge demolition based on long-term time-varying factors and the user terminal are mutually compatible. That is, if the digital stress control system for PC beam bridge demolition based on long-term time-varying factors is implemented as an application installed on a cloud service platform, then the user terminal is a client that establishes a communication connection with the application; or if the digital stress control system for PC beam bridge demolition based on long-term time-varying factors is implemented as a website, then the user terminal is implemented as a webpage; or if the digital stress control system for PC beam bridge demolition based on long-term time-varying factors is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0089] like Figure 1 The figure shown is a system architecture diagram of a digital stress control system for the demolition of PC beam bridges based on long-term time-varying factors, provided by an embodiment of the present invention.

[0090] The digital stress control system for PC beam bridge demolition based on long-term time-varying factors described in this invention can be set up in a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed in the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed into a website. Depending on the functions implemented, the digital stress control system for PC beam bridge demolition based on long-term time-varying factors may include a demolition data acquisition module, a time-varying data acquisition module, a feature vector processing module, a stress change prediction module, a graded demolition optimization module, a risk probability analysis module, a multi-scale damage quantification module, a full life-cycle digital fusion module, and a data optimization management module. The modules described in this invention can also be called units, referring to a series of computer program segments that can be executed by an electronic device's processor and perform a fixed function, stored in the electronic device's memory.

[0091] In this embodiment of the invention, in the digital stress control system for PC beam bridge demolition based on long-term time-varying factors, each of the above modules can be implemented independently and can be called by other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. For example, the sharing and evaluation module can call the same information acquisition module to obtain the information collected by that module. Based on the above characteristics, in the digital stress control system for PC beam bridge demolition based on long-term time-varying factors provided in this embodiment of the invention, without modifying the program code, the applicable scope of the architecture of the digital stress control system for PC beam bridge demolition based on long-term time-varying factors can be adjusted by adding modules and directly calling them, achieving cluster-based horizontal expansion to achieve the purpose of quickly and flexibly expanding the digital stress control system for PC beam bridge demolition based on long-term time-varying factors. In practical applications, the above modules can be set in the same device or different devices, or they can be set in a virtual device, such as a service instance in a cloud server.

[0092] Example 1, please refer to Figure 1 As shown in this embodiment, the digital stress control system for the demolition of PC beam bridges based on long-term time-varying factors includes:

[0093] The demolition data acquisition module is used to collect demolition datasets, which include demolition location data, demolition time data, demolition force data, and measured stress data.

[0094] It needs to be explained that the following steps are taken: A GNSS positioning device is used to collect the three-dimensional coordinates of the designated demolition equipment, which are then converted into a bridge segment number to obtain demolition location data; an IoT terminal device is used to collect the timestamp record of the demolition action triggered by the designated demolition equipment to obtain demolition time data; a hydraulic pressure sensor is used to collect the pressure value of the hydraulic oil circuit of the designated demolition equipment, and the oil pressure is multiplied by the effective area of ​​the hydraulic cylinder to obtain demolition force data; a fiber optic grating sensor is used to collect the strain value of the key section of the designated bridge segment, and the strain value is multiplied by the strain sensitivity coefficient to obtain the wavelength offset, which is then multiplied by the elastic modulus of concrete to obtain the measured stress data.

[0095] The time-varying data acquisition module is used to acquire time-varying datasets, which include shrinkage strain data, prestress relaxation data, and environmental corrosion data.

[0096] It should be explained that, by using a vibrating wire strain gauge, the vibration frequency inside a specified beam bridge segment is collected, the rate of change of the vibration frequency is calculated and multiplied by the instrument calibration value to obtain shrinkage strain data; by using an intelligent anchor cable gauge, the prestress relaxation rate of the prestressed tendon anchorage of a specified beam bridge segment is collected to obtain prestress relaxation data; and by using a linear polarized resistance sensor, the corrosion depth of the concrete layer of a specified beam bridge segment is collected to obtain environmental corrosion data.

[0097] The feature vector processing module is used to preprocess the demolition dataset and the time-varying dataset to obtain feature vectors;

[0098] Further steps for preprocessing the demolition dataset and the time-varying dataset include:

[0099] Q1: Clean the basic dataset by removing outliers and normalize all sub-data items in the basic dataset to the range of [0, 1] according to the normalization formula;

[0100] It should be explained that removing outliers refers to, for example, negative demolition force data; the base dataset includes the demolition dataset and the time-varying dataset; the specific expression of the normalization formula is as follows: ,in Normalized value Any sub-data item of the basic data, This represents the historical maximum value of any given sub-data item. This represents the historical minimum value of the arbitrary sub-data item;

[0101] Q2: Calculate the progress characteristics based on the demolition location data and demolition time data. The specific formula for calculating the progress characteristics is as follows:

[0102] ;

[0103] Obtain progress feature data ,in, For demolition location data, Data on demolition time;

[0104] Q3: By using shrinkage strain data In time interval Dividing the change within a time interval by the change rate characteristic data yields the change rate characteristic data. ;

[0105] Q4: Data on prestress relaxation Add 1 and multiply by the demolition force data To obtain comprehensive feature data ;

[0106] Q5: Integrate progress feature data, rate of change feature data, and comprehensive feature data to obtain a feature vector;

[0107] The stress change prediction module is used to establish a stress prediction model based on historical feature vectors, and output the stress prediction value based on the feature vectors and the stress prediction model.

[0108] Furthermore, the specific steps for establishing a stress prediction model based on historical eigenvectors and outputting the predicted stress values ​​based on the eigenvectors and the stress prediction model include:

[0109] Step 1: Obtain a set of historical feature vectors stored in the database, and compare them with the current time based on the timestamp. Group the comparison results from smallest to largest and label them accordingly as L1, L2, L3, ..., Ln. Use the labeled results as the sample set.

[0110] Step 2: Divide the sample set into 70% training set, 15% test set and 15% validation set, and establish a stress prediction model based on the sample set;

[0111] Step 3: Based on the historical feature vectors, let the historical feature vectors be three-dimensional tensors, and the specific expression formula is as follows:

[0112] ;

[0113] in, For feature vectors, For the current time, For time delay parameters, The number of historical feature vector sample groups. The number of feature data in the feature vector. For time step;

[0114] Step 4: Based on historical feature vectors, calculate the initial stress prediction value using the gradient boosting decision tree. The specific formula for calculation is as follows:

[0115] ;

[0116] Obtain the first stress prediction value ,in, For the number of decision trees, For the first The weighting factor of each tree The mean of historical eigenvectors The Mapping function for trees;

[0117] Step 5: Based on the three-dimensional tensor from Step 3 and the first stress prediction value from Step 4, substitute them into the calculation formula:

[0118] ;

[0119] The second stress prediction value was obtained. ,in, The time decay coefficient, Noise figure Let the norm of the three-dimensional tensor be... It is Gaussian noise;

[0120] It should be explained that the norm is the square root of the sum of the squares of the elements;

[0121] Step Six: Based on the predicted second stress value, substitute it into the calculation formula:

[0122] ;

[0123] Obtain the prediction confidence value ,in, The number of folds for cross-validation. For the first The validation set of the fold. For the first Exclusion of the first sample The second stress prediction value of the validation set of the fold;

[0124] It should be explained that the number of folds in cross-validation refers to dividing the training set into 5 mutually exclusive subsets, which is called a fold;

[0125] Step 7: Based on the prediction confidence value and the loss threshold, when the prediction confidence value is less than the loss threshold, the second stress prediction value is output as the stress prediction value; when the prediction confidence value is greater than or equal to the loss threshold, the average of the sums of the second stress prediction values ​​is output as the stress prediction value.

[0126] It should be explained that the loss threshold was determined and entered manually;

[0127] Step 8: Output the predicted stress values ​​to the graded demolition optimization module;

[0128] The graded demolition optimization module is used to analyze the predicted stress values ​​and obtain a segmented demolition plan.

[0129] Furthermore, methods for analyzing predicted stress values ​​include:

[0130] Based on the segmented threshold interval (R1, R2), the stress prediction value is substituted into the segmented threshold interval for comparison.

[0131] When the predicted stress value is less than or equal to R1, a large-section demolition plan is generated; when the predicted stress value is greater than R1 and less than or equal to R2, a medium-section demolition plan is generated; when the predicted stress value is greater than R2, a small-section demolition plan is generated.

[0132] The large-section demolition plan includes an explanation that the predicted stress value of the beam bridge to be demolished is low, and workers can refer to the length of the large-section segments for demolition operations.

[0133] The mid-section demolition plan includes an explanation of the predicted stress values ​​of the beam bridge to be demolished, and workers can refer to the segment lengths of the mid-section for demolition operations;

[0134] The segment demolition plan includes an explanation of the predicted high stress value of the beam bridge to be demolished, and workers can refer to the segment lengths for demolition operations.

[0135] The specific formula for calculating the segment length is as follows: The lengths of the large segment, the medium segment, and the small segment are obtained respectively. To preset the maximum segment length, The minimum segment length is preset.

[0136] By combining the large-section demolition plan, the medium-section demolition plan, and the small-section demolition plan, a segmented demolition plan is obtained.

[0137] The risk probability analysis module is used to dynamically optimize the segmented threshold interval to obtain a new segmented threshold interval.

[0138] Furthermore, the method for dynamically optimizing the segmented threshold interval is as follows:

[0139] The absolute deviation is obtained by subtracting the absolute value of the measured stress data from the predicted stress value.

[0140] The specific formula for calculating the risk probability of a given predicted stress value and absolute deviation value is as follows:

[0141] ;

[0142] in, This is the absolute deviation value. and These are the parameters for logistic regression;

[0143] By substituting into the calculation formula: The new segmented threshold interval is obtained ( , ), and return to the hierarchical demolition optimization module to replace the segment threshold interval (R1, R2), where, For learning rate, For partial derivatives, For risk costs;

[0144] The multi-scale damage quantification module is used to assess minor damage to beam bridge segments and generate high-risk area reports based on the assessment results.

[0145] Furthermore, methods for assessing minor damage to beam bridge segments and reporting high-risk areas based on the assessment results include:

[0146] The damage index is calculated based on environmental corrosion data and predicted stress values. The specific formula for the calculation is as follows:

[0147] ;

[0148] Damage index obtained ,in, The damage impact coefficient, For environmental corrosion data, The yield stress of the material;

[0149] When the damage index is greater than the damage threshold, a high-risk area report is obtained by combining the damage index with the location data.

[0150] It should be explained that the damage threshold is manually set and entered.

[0151] The full lifecycle digital fusion module is used to integrate design data, construction deviation data, and operation and maintenance loss data based on the building information model to obtain a full lifecycle digital twin.

[0152] Furthermore, based on design data, construction deviation data, and operation and maintenance loss data, the methods for data integration using building information modeling include:

[0153] Building Information Modeling (BIM) tools;

[0154] Input the beam bridge BIM model from the design drawings, construction deviation data, and operation and maintenance loss data;

[0155] It should be explained that the beam bridge BIM model and construction deviation data were obtained through manual input, while the operation and maintenance loss data were obtained by accumulating damage indices;

[0156] By integrating the beam bridge BIM model and construction deviation data, an as-built baseline model is obtained.

[0157] Transform maintenance loss data into corrected material property values;

[0158] A digital twin is constructed using a physical engine built based on Building Information Modeling (BIM) tools;

[0159] By combining thermal stress cloud maps and digital twins, a full life-cycle digital twin is obtained;

[0160] The data optimization and management module is used to store the system dataset, transmit the segmented demolition plan and high-risk area reports, and display the full life cycle digital twin through a visualization panel;

[0161] Furthermore, the transmission segmentation and dismantling scheme and the methods for reporting high-risk areas include:

[0162] The phased demolition plan and high-risk area reports were sent to the staff's email addresses via email, and staff were reminded to check their emails via SMS.

[0163] The system dataset includes demolition dataset, time-varying dataset, feature vectors, stress prediction values, segmented demolition schemes, new segment threshold interval logs, high-risk area reports, and a full lifecycle digital twin;

[0164] It should be explained that the new segment threshold interval log is a set of timestamps for the new segment threshold interval and the transmission of the new segment threshold interval to the hierarchical demolition optimization module;

[0165] In this embodiment, the beneficial effects are achieved by collecting a demolition dataset, including demolition location data, demolition time data, demolition force data, and measured stress data; and a time-varying dataset, including shrinkage strain data, prestress relaxation data, and environmental corrosion data. The demolition dataset and the time-varying dataset are preprocessed to obtain feature vectors. A stress prediction model is established based on historical feature vectors, and stress prediction values ​​are output based on the feature vectors and the stress prediction model. The stress prediction values ​​are analyzed to obtain a segmented demolition plan. The segmented threshold intervals are dynamically optimized to obtain new segmented threshold intervals. Minor damage assessments are performed on the beam bridge segments, and high-risk area reports are generated based on the assessment results. Based on design data, construction deviation data, and operation and maintenance loss data, and according to the building... The information model integrates data to obtain a full lifecycle digital twin. The system dataset is stored, and segmented demolition plans and high-risk area reports are transmitted. The full lifecycle digital twin is displayed through a visualization panel, enabling the system to accurately predict the stress of PC beam bridge segments under the dynamic fluctuations of time-varying datasets. This significantly reduces the error accumulation of traditional static models. Furthermore, this invention effectively assists workers in completing segmented demolition of PC beam bridges through hierarchical processing of stress prediction values, thereby effectively reducing the time and labor costs of segmented demolition judgment. Simultaneously, dynamic optimization of the segmented threshold range ensures real-time updates of the segmented threshold range, further improving the accuracy of the segmented demolition plan. Moreover, through the PC... The assessment of minor damage in PC beam bridge segments can intuitively display high-risk areas, thus reducing the drawbacks of traditional detection methods that struggle to quantify minor damage. It also assists staff in intuitively obtaining information on high-risk PC beam bridge segments. Finally, by acquiring design data, construction deviation data, and operation and maintenance damage data, and using BIM tools to present the entire lifecycle of the PC beam bridge as a digital twin, the intuitiveness of the stress state distribution of the PC beam bridge can be further enhanced. Overall, this invention has significant advantages, including a large auxiliary effect on the segmental dismantling of PC beam bridges, good quantification of minor damage, and strong intuitiveness in displaying the overall state of PC beam bridges.

[0166] Example 2, please refer to Figure 2 As shown, the parts not described in detail in this embodiment are described in Embodiment 1. A digital stress control method for the demolition of PC beam bridges based on long-term time-varying factors is provided. The method includes: S1: collecting a demolition dataset, which includes demolition location data, demolition time data, demolition force data and measured stress data;

[0167] S2: Collect time-varying datasets, which include shrinkage strain data, prestress relaxation data, and environmental corrosion data;

[0168] S3: Preprocess the demolition dataset and the time-varying dataset to obtain feature vectors;

[0169] S4: Establish a stress prediction model based on historical feature vectors, and output the predicted stress value based on the feature vectors and the stress prediction model;

[0170] S5: Analyze the predicted stress values ​​to obtain a segmented demolition plan;

[0171] S6: Dynamically optimize the segmented threshold interval to obtain a new segmented threshold interval;

[0172] S7: Conduct a minor damage assessment of the beam bridge segment and report high-risk areas based on the assessment results;

[0173] S8: Based on design data, construction deviation data, and operation and maintenance loss data, data is integrated according to the building information model to obtain a digital twin of the entire life cycle;

[0174] S9: Stores system datasets, transmits segmented demolition plans and high-risk area reports, and displays the entire lifecycle digital twin through a visualization panel.

[0175] Example 3 It will be apparent to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0176] Therefore, the embodiments should be regarded as exemplary and non-limiting in all respects, and the scope of the invention is not limited by the foregoing description. Thus, all changes falling within the meaning and scope of equivalents are intended to be included within the invention.

[0177] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0178] Furthermore, it is clear that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in the system can also be implemented by a single unit or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0179] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A digital stress control system for the demolition of PC beam bridges based on long-term time-varying factors, characterized in that, The system includes: a demolition data acquisition module, a time-varying data acquisition module, a feature vector processing module, a data optimization and management module, a stress change prediction module, a graded demolition optimization module, a risk probability analysis module, a multi-scale damage quantification module, and a full life-cycle digital fusion module, wherein: The demolition data acquisition module is used to collect demolition datasets, which include demolition location data, demolition time data, demolition force data, and measured stress data. The time-varying data acquisition module is used to acquire time-varying datasets, which include shrinkage strain data, prestress relaxation data, and environmental corrosion data. The feature vector processing module is used to preprocess the demolition dataset and the time-varying dataset to obtain feature vectors; The stress change prediction module is used to establish a stress prediction model based on historical feature vectors, and output the stress prediction value based on the feature vectors and the stress prediction model. The graded demolition optimization module is used to analyze the predicted stress values ​​and obtain a segmented demolition plan. The risk probability analysis module is used to dynamically optimize the segmented threshold interval to obtain a new segmented threshold interval. The multi-scale damage quantification module is used to assess minor damage to beam bridge segments and generate high-risk area reports based on the assessment results. The full lifecycle digital fusion module is used to integrate design data, construction deviation data, and operation and maintenance loss data based on the building information model to obtain a full lifecycle digital twin. The data optimization and management module is used to store system datasets, transmit segmented demolition plans and high-risk area reports, and display the entire lifecycle digital twin through a visualization panel.

2. The digital stress control system for PC beam bridge demolition based on long-term time-varying factors as described in claim 1, characterized in that, The preprocessing steps for the demolition dataset and the time-varying dataset include: Q1: Clean the basic dataset by removing outliers and normalize all sub-data items in the basic dataset to the range of [0, 1] according to the normalization formula; Q2: Calculate the progress characteristics based on the demolition location data and demolition time data. The specific formula for calculating the progress characteristics is as follows: ； Obtain progress feature data ,in, For demolition location data, Data on demolition time; Q3: By using shrinkage strain data In time interval Dividing the change within a time interval by the change rate characteristic data yields the change rate characteristic data. ; Q4: Data on prestress relaxation Add 1 and multiply by the demolition force data To obtain comprehensive feature data ; Q5: Integrate progress feature data, rate of change feature data, and comprehensive feature data to obtain a feature vector.

3. The digital stress control system for PC beam bridge demolition based on long-term time-varying factors as described in claim 1, characterized in that, The specific steps for establishing a stress prediction model based on historical eigenvectors and outputting the predicted stress value based on the eigenvectors and the stress prediction model include: Step 1: Obtain a set of historical feature vectors stored in the database, and compare them with the current time based on the timestamp. Group the comparison results from smallest to largest and label them accordingly as L1, L2, L3, ..., Ln. Use the labeled 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 prediction model based on the sample set; Step 3: Based on the historical feature vectors, let the historical feature vectors be three-dimensional tensors, and the specific expression formula is as follows: ； in, For feature vectors, For the current time, For time delay parameters, The number of historical feature vector sample groups. The number of feature data in the feature vector. For time step; Step 4: Based on historical feature vectors, calculate the initial stress prediction value using the gradient boosting decision tree. The specific formula for calculation is as follows: ； Obtain the first stress prediction value ,in, For the number of decision trees, For the first The weighting factor of each tree The mean of historical eigenvectors The Mapping function for trees; Step 5: Based on the three-dimensional tensor from Step 3 and the first stress prediction value from Step 4, substitute them into the calculation formula: ； The second stress prediction value was obtained. ,in, The time decay coefficient, Noise figure Let the norm of the three-dimensional tensor be... It is Gaussian noise; Step Six: Based on the predicted second stress value, substitute it into the calculation formula: ； Obtain the prediction confidence value ,in, The number of folds for cross-validation. For the first The validation set of the fold. For the first Exclusion of the first sample The second stress prediction value of the validation set of the fold; Step 7: Based on the prediction confidence value and the loss threshold, when the prediction confidence value is less than the loss threshold, the second stress prediction value is output as the stress prediction value; when the prediction confidence value is greater than or equal to the loss threshold, the average of the sums of the second stress prediction values ​​is output as the stress prediction value. Step 8: Output the predicted stress values ​​to the graded demolition optimization module.

4. The digital stress control system for PC beam bridge demolition based on long-term time-varying factors according to claim 1, characterized in that, Methods for analyzing predicted stress values ​​include: Based on the segmented threshold interval (R1, R2), the stress prediction value is substituted into the segmented threshold interval for comparison. When the predicted stress value is less than or equal to R1, a large-section demolition plan is generated; when the predicted stress value is greater than R1 and less than or equal to R2, a medium-section demolition plan is generated; when the predicted stress value is greater than R2, a small-section demolition plan is generated. The large-section demolition plan includes an explanation that the predicted stress value of the beam bridge to be demolished is low, and workers can refer to the length of the large-section segments for demolition operations. The mid-section demolition plan includes an explanation of the predicted stress values ​​of the beam bridge to be demolished, and workers can refer to the segment lengths of the mid-section for demolition operations; The segment demolition plan includes an explanation of the predicted high stress value of the beam bridge to be demolished, and workers can refer to the segment lengths for demolition operations. The specific formula for calculating the segment length is as follows: The lengths of the large segment, the medium segment, and the small segment are obtained respectively. To preset the maximum segment length, The minimum segment length is preset. By combining the large-section demolition plan, the medium-section demolition plan, and the small-section demolition plan, a segmented demolition plan is obtained.

5. The digital stress control system for PC beam bridge demolition based on long-term time-varying factors according to claim 1, characterized in that, The method for dynamically optimizing the segmented threshold interval is as follows: The absolute deviation is obtained by subtracting the absolute value of the measured stress data from the predicted stress value. The specific formula for calculating the risk probability of a given predicted stress value and absolute deviation value is as follows: ； in, This is the absolute deviation value. and These are the parameters for logistic regression; By substituting into the calculation formula: The new segmented threshold interval is obtained ( , ), and return to the hierarchical demolition optimization module to replace the segment threshold interval (R1, R2), where, For learning rate, For partial derivatives, For risk costs.

6. The digital stress control system for PC beam bridge demolition based on long-term time-varying factors according to claim 1, characterized in that, Methods for assessing minor damage to beam bridge segments and reporting high-risk areas based on the assessment results include: The damage index is calculated based on environmental corrosion data and predicted stress values. The specific formula for the calculation is as follows: ； Damage index obtained ,in, The damage impact coefficient, For environmental corrosion data, The yield stress of the material; When the damage index is greater than the damage threshold, the damage index and the location data are combined to obtain a high-risk area report.

7. The digital stress control system for PC beam bridge demolition based on long-term time-varying factors according to claim 1, characterized in that, Based on design data, construction deviation data, and operation and maintenance loss data, the methods for data integration using Building Information Modeling (BIM) include: Building Information Modeling (BIM) tools; Input the beam bridge BIM model from the design drawings, construction deviation data, and operation and maintenance loss data; It should be explained that the beam bridge BIM model and construction deviation data were obtained through manual input, while the operation and maintenance loss data were obtained by accumulating damage indices; By integrating the beam bridge BIM model and construction deviation data, an as-built baseline model is obtained. Transform maintenance loss data into corrected material property values; A digital twin is constructed using a physical engine built based on Building Information Modeling (BIM) tools; By combining thermal stress cloud maps and digital twins, a full lifecycle digital twin is obtained.

8. The digital stress control system for PC beam bridge demolition based on long-term time-varying factors according to claim 1, characterized in that, Transmission segmentation and dismantling schemes and high-risk area reporting methods include: The phased demolition plan and high-risk area reports were sent to the staff's email addresses via email, and staff were reminded to check their emails via SMS. The system dataset includes demolition dataset, time-varying dataset, feature vector, stress prediction value, segmented demolition scheme, new segment threshold interval log, high-risk area report, and full life cycle digital twin.

9. A digital stress control method for the demolition of PC beam bridges based on long-term time-varying factors, implemented according to any one of claims 1-8, characterized in that, The work includes the following steps: S1: Collect demolition dataset, which includes demolition location data, demolition time data, demolition force data, and measured stress data; S2: Collect time-varying datasets, which include shrinkage strain data, prestress relaxation data, and environmental corrosion data; S3: Preprocess the demolition dataset and the time-varying dataset to obtain feature vectors; S4: Establish a stress prediction model based on historical feature vectors, and output the predicted stress value based on the feature vectors and the stress prediction model; S5: Analyze the predicted stress values ​​to obtain a segmented demolition plan; S6: Dynamically optimize the segmented threshold interval to obtain a new segmented threshold interval; S7: Conduct a minor damage assessment of the beam bridge segment and report high-risk areas based on the assessment results; S8: Based on design data, construction deviation data, and operation and maintenance loss data, data is integrated according to the building information model to obtain a digital twin of the entire life cycle; S9: Stores system datasets, transmits segmented demolition plans and high-risk area reports, and displays the entire lifecycle digital twin through a visualization panel.

Images