Prefabricated pavement slab prestress intelligent tensioning construction method

Abstract

The invention relates to the technical field of building construction, and discloses a fabricated pavement slab prestress intelligent tensioning construction method which comprises the steps that an optical fiber sensing array is arranged on the surface of a pavement slab, strain data of different positions of the pavement slab are collected in real time through the optical fiber grating strain sensing technology, and according to the corresponding relation between strain and stress, the strain data of different positions of the pavement slab are obtained; calculating to obtain an actual prestress distribution condition; aiming at the detected prestressed defect position, carrying out visual representation on a defect region by adopting an image processing technology, drawing a defect contour through an edge extraction algorithm, calculating geometric parameters such as defect area and length, and quantitatively evaluating the defect severity; information such as prestress defect detection results, performance influence evaluation and safety risk analysis results is synthesized, an intelligent prestress defect detection report is generated, the prestress condition of the pavement slab is visually presented, and a basis is provided for subsequent quality control and maintenance decision making.

Description

Technical Field

[0001] The invention relates to the technical field of building construction, and in particular to a prestressed intelligent tensioning construction method for assembled road panels. Background Art

[0002] At present, there is a key technical problem in the intelligent prestressing process of prefabricated road panels, that is, how to detect prestress defects in real time and accurately. Prestress defects mainly include stress concentration and uneven prestress distribution, which will seriously affect the performance and safety of road panels. Traditional prestress detection methods usually rely on manual experience and post-inspection, and have shortcomings such as low detection efficiency and poor accuracy. Therefore, there is an urgent need for an efficient and intelligent prestress defect detection method that can monitor the prestress distribution in real time during the tensioning process and promptly detect and locate the defect position.

[0003] However, there are many technical challenges in achieving real-time intelligent detection of prestressed defects. First, the distribution of prestress is complex and is affected by many factors, such as the size of the tensioning force, the tensioning sequence, the position of the anchor, etc. The traditional point measurement method is difficult to fully reflect the characteristics of the prestressed distribution. Secondly, the structure of the pavement panel is complex, the internal prestressing mechanism is not yet clear, and there is a lack of effective prestressed defect identification models and evaluation indicators. In addition, the on-site environment is harsh, the measuring equipment is easily disturbed, and data transmission and processing also face many uncertainties. The above technical difficulties lead to low accuracy in prestressed defect detection, and it is difficult to ensure real-time and reliability, which greatly restricts the promotion and application of prefabricated pavement panels. Summary of the invention

[0004] The present application provides a prestressed intelligent tensioning construction method for assembled road panels to solve the problems in the background technology.

[0005] In order to solve the above technical problems, the present application provides a prestressed intelligent tensioning construction method for assembled road panels, comprising: step 1, prefabricating concrete road panels, and assembling the prefabricated concrete road panels into a concrete road panel structure; Step 2: According to the tensioning force, tensioning sequence, anchor position and other parameters in the prestressing intelligent tensioning process, a mathematical model of prestress distribution is established, and a theoretical prestress distribution cloud map is obtained through finite element simulation analysis as a reference for subsequent prestressing defect detection; Step 3: Arrange a fiber optic sensor array on the surface of the road panel, use fiber optic Bragg grating strain sensing technology to collect strain data at different positions of the road panel in real time, and calculate the actual prestress distribution according to the corresponding relationship between strain and stress; Step 4: tighten each concrete road panel, insert the longitudinal prestressed steel strands into the longitudinal through holes of the longitudinal ribs, and fix them; tighten each concrete road panel, insert the transverse prestressed steel strands into the transverse through holes of the transverse ribs, and fix them; Step 5: Compare and analyze the actual prestress distribution with the theoretical prestress distribution, and determine whether the prestress at each position is abnormal by setting a prestress deviation threshold. If the deviation between the actual prestress and the theoretical prestress exceeds the threshold, it is determined that there is a prestress defect at that position. Step 6: Based on the location, scope and severity of the prestressed defects, combined with the structural characteristics and material properties of the pavement panel, a correlation model between the prestressed defects and the pavement panel performance is established using a machine learning algorithm to predict the impact of the defects on the pavement panel's bearing capacity, durability and other performance indicators; Step 7: Based on the risk assessment theory, the probability and severity of accidents caused by prestressed defects are calculated to identify the potential safety hazards of road panels, determine the danger level of the defects, and propose corresponding reinforcement or repair measures based on the danger level. Step eight, integrate the prestressed defect detection results, performance impact assessment and safety risk analysis results to generate a prestressed defect intelligent detection report, which intuitively presents the prestressed condition of the road panel and provides a basis for subsequent quality control and maintenance decisions.

[0006] Compared with the prior art, the present invention has the following characteristics and beneficial effects: The present invention first establishes a mathematical model of prestress distribution and performs finite element simulation to obtain a theoretical prestress distribution cloud map. Then, fiber grating strain sensing technology is used to collect road panel strain data in real time to calculate the actual prestress distribution. The location of prestress defects is determined by comparing and analyzing the actual and theoretical prestress distributions. For the detected defects, image processing technology is used for visual representation and geometric parameter calculation. Combined with machine learning algorithms, a correlation model between prestress defects and road panel performance is established to evaluate the impact of defects on performance. Based on risk assessment theory, the defect hazard level is determined and corresponding measures are proposed. Finally, a comprehensive inspection report is generated to provide a basis for quality control and maintenance decisions. The present invention realizes intelligent detection, evaluation and analysis of prestress defects in road panels, and improves the scientificity and efficiency of road panel quality control and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 is a flow chart of an embodiment of the present invention; Figure 2 is a schematic diagram of an embodiment of the present invention; Figure 3 It is another schematic diagram of an embodiment of the present invention. DETAILED DESCRIPTION

[0008] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0009] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0010] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0011] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0012] like Figure 1 As shown, according to some embodiments of the present application, the method includes: step 1, prefabricating concrete road panels, and assembling the prefabricated concrete road panels into a concrete road panel structure; Step 2: According to the tensioning force, tensioning sequence, anchor position and other parameters in the prestressing intelligent tensioning process, a mathematical model of prestress distribution is established, and a theoretical prestress distribution cloud map is obtained through finite element simulation analysis as a reference for subsequent prestressing defect detection; Step 3: Arrange a fiber optic sensor array on the surface of the road panel, use fiber optic Bragg grating strain sensing technology to collect strain data at different positions of the road panel in real time, and calculate the actual prestress distribution according to the corresponding relationship between strain and stress; Step 4: tighten the longitudinal through holes of the longitudinal ribs of each concrete road panel, insert the longitudinal prestressed steel strands and fix them; tighten the transverse through holes of the transverse ribs of each concrete road panel, insert the transverse prestressed steel strands and fix them; compare and analyze the actual prestress distribution with the theoretical prestress distribution, and determine whether the prestress at each position is abnormal by setting a prestress deviation threshold. If the deviation between the actual prestress and the theoretical prestress exceeds the threshold, it is determined that there is a prestress defect at that position; Step 5: Based on the location, scope and severity of prestressed defects, combined with the structural characteristics and material properties of the pavement panel, a correlation model between prestressed defects and pavement panel performance is established using a machine learning algorithm to predict the impact of defects on performance indicators such as the bearing capacity and durability of the pavement panel; Step 6: Based on the risk assessment theory, the probability and severity of accidents caused by prestressed defects are calculated to identify the potential safety hazards of road panels, determine the danger level of the defects, and propose corresponding reinforcement or repair measures based on the danger level. Step seven: Integrate the prestressed defect detection results, performance impact assessment, safety risk analysis results and other information to generate a prestressed defect intelligent detection report, which intuitively presents the prestressed condition of the road panel and provides a basis for subsequent quality control and maintenance decisions.

[0013] According to some embodiments of the present application, the concrete road panel is composed of a rectangular panel and a plurality of longitudinal ribs and transverse ribs intersecting vertically and horizontally at the bottom; the longitudinal ribs are provided with longitudinal through holes for inserting the longitudinal prestressed steel strands, and the transverse ribs are provided with transverse through holes for inserting the transverse prestressed steel strands; the concrete road panel is evenly distributed on the roadbed; the longitudinal prestressed steel strands are inserted into the longitudinal through holes of the longitudinal ribs of each concrete road panel; the transverse prestressed steel strands are inserted into the transverse through holes of the transverse ribs of each concrete road panel.

[0014] According to some embodiments of the present application, a three-dimensional mathematical model of prestress distribution is established based on parameters such as the tensioning force size, tensioning sequence and anchor position in the prestressed intelligent tensioning process, and the model contains information such as the coordinates of the positions of each anchor, the direction and size of the tensioning force, etc.; the finite element simulation analysis method is used to import the established prestress distribution mathematical model into the finite element analysis software, and parameters such as material properties, mesh division, constraints and load conditions are set; through finite element simulation analysis, a prestress distribution cloud map of the entire prestressed structure in a theoretical state is calculated, including information such as the prestress size and distribution range in each direction; based on the theoretical prestress distribution cloud map obtained by finite element simulation analysis, each Theoretical values ​​of prestress at key positions form a database of prestress theoretical values ​​as a reference for subsequent prestress defect detection; in the actual prestressed intelligent tensioning process, the prestressed intelligent tensioning system is used to collect the measured prestress values ​​at each anchor position in real time, and the measured values ​​are compared and analyzed with the theoretical values; if the deviation between the measured prestressed value and the theoretical value exceeds the preset threshold, it is judged that there is a prestressed defect at that position, and the defect level is determined according to the deviation, and a prestressed defect distribution map is generated; the prestressed defect information obtained from the detection is fed back to the prestressed intelligent tensioning system, and by adjusting parameters such as the tensioning force and the tensioning sequence, intelligent compensation for prestressed defects is achieved to ensure the construction quality of the prestressed structure.

[0015] According to some embodiments of the present application, a fiber optic sensor array is arranged on the surface of the road panel, and fiber optic Bragg grating strain sensing technology is used to collect strain data at different positions of the road panel in real time; according to the pre-established correspondence between strain and stress, the collected strain data is converted into stress data at the corresponding position; the converted stress data is spatially interpolated to obtain continuous stress distribution data on the surface of the road panel; according to the geometric dimensions and material properties of the road panel, a finite element model is established, and the stress distribution data is loaded into the model as a boundary condition; through finite element analysis, the three-dimensional stress distribution inside the road panel is calculated and compared with the designed prestress; if the deviation between the calculated actual prestress distribution and the designed prestress distribution exceeds a preset threshold, it is judged that the prestress is abnormal, and a prestress abnormality warning message is output; if the deviation between the calculated actual prestress distribution and the designed prestress distribution does not exceed the preset threshold, it is judged that the prestress is normal, and prestress normal state information is output.

[0016] According to some embodiments of the present application, actual prestress distribution data and theoretical prestress distribution data at various positions of the structure are obtained, and the actual prestress distribution data and the theoretical prestress distribution data are aligned so that their positions correspond one to one; the deviation values ​​of the actual prestress distribution data and the theoretical prestress distribution data at each corresponding position are calculated to obtain prestress deviation distribution data; according to the statistical characteristics of the prestress deviation distribution data, such as the deviation mean and standard deviation, a prestress deviation threshold is set in combination with engineering experience; the prestress deviation distribution data are traversed, and if the prestress deviation value at a certain position exceeds the preset deviation threshold, it is determined that there is a prestress anomaly at the position; a clustering algorithm is used to perform cluster analysis on the positions where the prestress anomaly exists, and the concentrated area of ​​the abnormal position is determined according to the clustering results, and the possibility of the existence of prestress defects in the area is determined; through classification algorithms such as support vector machines, the position features and prestress deviation features are used as input to train a prestress defect recognition model to determine whether there is a prestress defect at a specific position; the information such as the prestress abnormal position, the possible area of ​​prestress defects and the prestress defect position is visualized, and a prestress defect analysis report is generated to provide a basis for subsequent prestress reinforcement and repair decisions.

[0017] According to some embodiments of the present application, based on the prestressed defect detection results, image data of the defect area is obtained, and the image data is input into the image processing module for processing; the defect image is segmented by an image segmentation algorithm, and a pixel point set of the defect area is extracted to obtain a segmented defect image; for the segmented defect image, an edge extraction algorithm is used to extract the defect contour to obtain a pixel point coordinate set of the defect contour; based on the pixel point coordinate set of the defect contour, the geometric parameters of the defect area are calculated, including parameters such as defect area and defect length; the calculated defect geometric parameters are compared with a preset defect severity threshold to determine the severity of the defect; based on the determination result of the defect severity, the defect area is visually annotated with different colors or shapes to intuitively represent the defect severity; the visually annotated defect image is fused with the original image to generate a visual representation diagram of the defect detection result, which is output and displayed to the user.

[0018] According to some embodiments of the present application, information such as the location, scope and severity of prestressed defects is obtained, and the defect information is quantified and standardized through image processing and data analysis technology to obtain a defect feature vector; a pavement panel performance evaluation model is established based on the structural characteristics and material properties of the pavement panel, and the model comprehensively considers factors such as the geometric size, material strength and stiffness of the pavement panel, and can calculate the stress-strain response of the pavement panel under different load conditions; a support vector machine algorithm is used to train a correlation model between prestressed defects and pavement panel performance with the defect feature vector as input and the output of the pavement panel performance evaluation model as the target; the generalization ability and prediction accuracy of the model are improved through cross-validation and parameter optimization; the trained correlation model is used to predict performance indicators such as the bearing capacity and durability of the pavement panel under given prestressed defect conditions; if If the predicted performance index is lower than the design requirement, it is judged that the prestressed defect has a serious impact on the performance of the pavement panel, and corresponding maintenance and reinforcement measures need to be taken; for prestressed defects with serious impact, the finite element analysis method is used to simulate in detail the impact of the defect on the stress distribution of the pavement panel, identify the stress concentration area, and provide a basis for formulating the optimal maintenance and reinforcement plan; according to the actual stress state and environmental conditions of the pavement panel, a performance degradation prediction model of the pavement panel is established using a neural network algorithm; through this model, the development trend of prestressed defects in the long-term service process and the impact on the durability of the pavement panel can be predicted; the prediction results of the correlation model, the finite element analysis results and the performance degradation prediction results are combined to form a prestressed defect assessment report, which provides a quantitative basis for the maintenance and repair decisions of the pavement panel and ensures that the safety, applicability and durability of the pavement panel meet the design requirements.

[0019] According to some embodiments of the present application, according to the type and degree of prestressed defects, the finite element analysis method is used to simulate the stress distribution and deformation of the road panel to obtain the degree of influence of the defects on the safety performance of the road panel; through the probability statistics method, combined with historical data and expert experience, the probability distribution of safety accidents caused by defects of different degrees is calculated, and the accidents are graded according to the severity of the consequences; a defect hazard level assessment model is established, the probability of defects causing accidents and the severity of the consequences are comprehensively considered, and the fuzzy comprehensive evaluation method is used to determine the hazard level of the defects; for defects of different hazard levels, corresponding reinforcement or maintenance measures are formulated, and emergency disposal measures are taken for defects of high hazard levels, and for defects of medium and low hazard levels, emergency disposal measures are taken. For defects with dangerous levels, regular inspection and maintenance plans are formulated; a defect dangerousness prediction model is established using machine learning algorithms, such as support vector machines or random forests, and the defect development trend and dangerousness changes are predicted by analyzing the real-time monitoring data of road panel status parameters; based on Bayesian network theory, a defect risk assessment network model is constructed, which comprehensively considers the correlation between various influencing factors, dynamically assesses the changes in defect risk levels, and provides support for road panel maintenance decisions; a road panel safety hazard management information system is established to realize the digital collection, storage and analysis of defect information, and automatically generates a bill of quantities and priority ranking for road panel reinforcement or repair based on risk assessment results, providing guidance for maintenance construction.

[0020] According to some embodiments of the present application, prestressed defect detection result data of the pavement panel is obtained, the detection result data is preprocessed, and key characteristic parameters are extracted; based on the characteristic parameters of the prestressed defect detection result, the support vector machine algorithm is used to evaluate the performance impact of the pavement panel to obtain a performance impact evaluation result; based on the characteristic parameters of the prestressed defect detection result and the performance impact evaluation result, the Bayesian network algorithm is used to analyze the safety risk of the pavement panel to obtain a safety risk analysis result; the prestressed defect detection result, the performance impact evaluation result and the safety risk analysis result and other information are integrated to construct a comprehensive evaluation index system; the hierarchical analysis method is used to calculate the weights of the comprehensive evaluation indicators, and the comprehensive score of the prestressed condition of the pavement panel is obtained by weighted summation; based on the comprehensive score of the prestressed condition, the severity of the prestressed defects of the pavement panel is judged, and corresponding quality control and maintenance decision-making suggestions are provided; a prestressed defect intelligent detection report is generated, and the report content includes a summary of the detection results, performance impact evaluation, safety risk analysis, comprehensive evaluation results, and quality control and maintenance decision-making suggestions, and is intuitively presented in the form of charts and the like.

[0021] In summary, the present invention relates to the field of building construction technology, and discloses a prestressed intelligent tensioning construction method for assembled road panels, comprising: laying a fiber optic sensor array on the surface of the road panel, using fiber optic Bragg grating strain sensing technology to collect strain data at different positions of the road panel in real time, and calculating the actual prestress distribution according to the corresponding relationship between strain and stress; for the detected prestressed defect position, using image processing technology to visualize the defect area, outlining the defect contour through an edge extraction algorithm, and calculating geometric parameters such as the defect area and length, and quantitatively evaluating the severity of the defect; integrating information such as prestressed defect detection results, performance impact assessment, and safety risk analysis results to generate a prestressed defect intelligent detection report, intuitively presenting the prestressed condition of the road panel, and providing a basis for subsequent quality control and maintenance decisions.

[0022] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention. These improvements and substitutions should also be regarded as the scope of protection of the present invention.

Claims

1. A prestressed intelligent tensioning construction method for assembled road panels, characterized in that: include: Step 1: prefabricate concrete road panels and assemble the prefabricated concrete road panels into a concrete road panel structure; Step 2: According to the tensioning force, tensioning sequence, anchor position and other parameters in the prestressing intelligent tensioning process, a mathematical model of prestress distribution is established, and a theoretical prestress distribution cloud map is obtained through finite element simulation analysis as a reference for subsequent prestressing defect detection; Step 3: Arrange a fiber optic sensor array on the surface of the road panel, use fiber optic Bragg grating strain sensing technology to collect strain data at different positions of the road panel in real time, and calculate the actual prestress distribution according to the corresponding relationship between strain and stress; Step 4: tighten the longitudinal through holes of the longitudinal ribs of each concrete road panel, insert the longitudinal prestressed steel strands and fix them; tighten the transverse through holes of the transverse ribs of each concrete road panel, insert the transverse prestressed steel strands and fix them; compare and analyze the actual prestress distribution with the theoretical prestress distribution, and determine whether the prestress at each position is abnormal by setting a prestress deviation threshold. If the deviation between the actual prestress and the theoretical prestress exceeds the threshold, it is determined that there is a prestress defect at that position; Step 5: Based on the location, scope and severity of prestressed defects, combined with the structural characteristics and material properties of the pavement panel, a correlation model between prestressed defects and pavement panel performance is established using a machine learning algorithm to predict the impact of defects on performance indicators such as the bearing capacity and durability of the pavement panel; Step 6: Based on the risk assessment theory, the probability and severity of accidents caused by prestressed defects are calculated to identify the potential safety hazards of road panels, determine the danger level of the defects, and propose corresponding reinforcement or repair measures based on the danger level. Step seven: Integrate the prestressed defect detection results, performance impact assessment, safety risk analysis results and other information to generate a prestressed defect intelligent detection report, which intuitively presents the prestressed condition of the road panel and provides a basis for subsequent quality control and maintenance decisions.

2. The method for prestressed intelligent tensioning of assembled road panels according to claim 1 is characterized in that: The concrete road panel is composed of a rectangular panel and a plurality of longitudinal ribs and transverse ribs intersecting vertically and horizontally at the bottom; the longitudinal ribs are provided with longitudinal through holes for inserting longitudinal prestressed steel strands, and the transverse ribs are provided with transverse through holes for inserting transverse prestressed steel strands; the concrete road panels are evenly distributed on the roadbed; the longitudinal prestressed steel strands are inserted into the longitudinal through holes of the longitudinal ribs of each concrete road panel; the transverse prestressed steel strands are inserted into the transverse through holes of the transverse ribs of each concrete road panel.

3. The method for prestressed intelligent tensioning of assembled road panels according to claim 1 is characterized in that: The method includes: establishing a three-dimensional mathematical model of prestress distribution according to parameters such as the tensioning force, tensioning sequence and anchor position in the prestressing intelligent tensioning process, wherein the model contains information such as the position coordinates of each anchor, the direction and magnitude of the tensioning force, etc.; using a finite element simulation analysis method, importing the established mathematical model of prestress distribution into finite element analysis software, and setting parameters such as material properties, mesh division, constraint conditions and load conditions, etc.; Through finite element simulation analysis, the prestress distribution cloud diagram of the entire prestressed structure in the theoretical state is calculated, including information such as the prestress size and distribution range in each direction; According to the theoretical prestress distribution cloud map obtained by finite element simulation analysis, the theoretical prestress values ​​at each key position are extracted to form a prestress theoretical value database as a reference benchmark for subsequent prestress defect detection; in the actual prestressed intelligent tensioning process, the prestressed intelligent tensioning system is used to collect the measured prestress values ​​at each anchor position in real time, and the measured values ​​are compared and analyzed with the theoretical values; if the deviation between the measured prestressed value and the theoretical value exceeds the preset threshold, it is judged that there is a prestressed defect at that position, and the defect level is determined according to the deviation size, and a prestressed defect distribution map is generated; the prestressed defect information obtained by the detection is fed back to the prestressed intelligent tensioning system, and by adjusting parameters such as the tensioning force and the tensioning sequence, intelligent compensation for prestressed defects is achieved to ensure the construction quality of the prestressed structure.

4. The method for prestressed intelligent tensioning of assembled road panels according to claim 1 is characterized in that: It includes: laying out a fiber optic sensor array on the surface of the road panel, and using fiber optic Bragg grating strain sensing technology to collect strain data at different positions of the road panel in real time; converting the collected strain data into stress data at the corresponding position according to the pre-established correspondence between strain and stress; performing spatial interpolation processing on the converted stress data to obtain continuous stress distribution data on the surface of the road panel; establishing a finite element model according to the geometric dimensions and material properties of the road panel, and loading the stress distribution data into the model as boundary conditions; calculating the three-dimensional stress distribution inside the road panel through finite element analysis, and comparing it with the designed prestress; if the deviation between the calculated actual prestress distribution and the designed prestress distribution exceeds a preset threshold, it is judged as prestress abnormality, and a prestress abnormality warning message is output; If the deviation between the calculated actual prestress distribution and the designed prestress distribution does not exceed the preset threshold, the prestress is judged to be normal, and the prestress normal state information is output.

5. The method for prestressed intelligent tensioning of assembled road panels according to claim 1 is characterized in that: The method includes: obtaining the actual prestress distribution data and theoretical prestress distribution data at each position of the structure, aligning the actual prestress distribution data with the theoretical prestress distribution data so that their positions correspond one to one; calculating the deviation values ​​between the actual prestress distribution data and the theoretical prestress distribution data at each corresponding position to obtain the prestress deviation distribution data; setting the prestress deviation threshold according to the statistical characteristics of the prestress deviation distribution data, such as the deviation mean and standard deviation, combined with engineering experience; traversing the prestress deviation distribution data, if the prestress deviation value at a certain position exceeds the preset deviation threshold, it is determined that there is a prestress anomaly at that position; using a clustering algorithm to perform cluster analysis on the positions where prestress anomalies exist, determining the concentrated area of ​​the abnormal positions according to the clustering results, and judging the possibility of the existence of prestress defects in the area; using classification algorithms such as support vector machines, taking position features and prestress deviation features as input, training a prestress defect recognition model to determine whether there are prestress defects at a specific position; visually displaying information such as the prestress abnormal position, possible prestress defect area, and prestress defect position, and generating a prestress defect analysis report to provide a basis for subsequent prestress reinforcement and repair decisions.

6. The method for prestressed intelligent tensioning of assembled road panels according to claim 1 is characterized in that: The method includes: obtaining image data of the defect area according to the prestressed defect detection result, and inputting the image data into the image processing module for processing; segmenting the defect image by using the image segmentation algorithm, extracting the pixel point set of the defect area, and obtaining the segmented defect image; extracting the defect contour by using the edge extraction algorithm for the segmented defect image, and obtaining the pixel point coordinate set of the defect contour; calculating the geometric parameters of the defect area according to the pixel point coordinate set of the defect contour, including parameters such as defect area and defect length; comparing the calculated defect geometric parameters with the preset defect severity threshold value to determine the severity of the defect; According to the judgment results of the severity of the defect, the defect area is visually annotated with different colors or shapes to intuitively represent the severity of the defect; the defect image after visual annotation is fused with the original image to generate a visual representation of the defect detection results, which is output and displayed to the user.

7. The method for prestressed intelligent tensioning of assembled road panels according to claim 1 is characterized in that: The method includes: obtaining information such as the location, scope and severity of prestressed defects, quantifying and standardizing the defect information through image processing and data analysis technology, and obtaining defect feature vectors; establishing a pavement panel performance evaluation model based on the structural characteristics and material properties of the pavement panel, which comprehensively considers factors such as the geometric dimensions, material strength and stiffness of the pavement panel, and can calculate the stress-strain response of the pavement panel under different load conditions; using the support vector machine algorithm, with the defect feature vector as input and the output of the pavement panel performance evaluation model as the target, training the association model between prestressed defects and pavement panel performance; improving the generalization ability and prediction accuracy of the model through cross-validation and parameter optimization; using the trained association model to predict performance indicators such as the bearing capacity and durability of the pavement panel under given prestressed defect conditions; if the predicted performance indicators are low, According to the design requirements, it is judged that the prestressed defects have a serious impact on the performance of the pavement panel, and corresponding maintenance and reinforcement measures need to be taken; for prestressed defects with serious impact, the finite element analysis method is used to simulate in detail the impact of defects on the stress distribution of the pavement panel, identify stress concentration areas, and provide a basis for formulating the optimal maintenance and reinforcement plan; according to the actual stress state and environmental conditions of the pavement panel, a performance degradation prediction model for the pavement panel is established using a neural network algorithm; through this model, the development trend of prestressed defects in the long-term service process and the impact on the durability of the pavement panel can be predicted; the prediction results of the comprehensive correlation model, the finite element analysis results and the performance degradation prediction results are formed to form a prestressed defect assessment report, which provides a quantitative basis for the maintenance and repair decisions of the pavement panel and ensures that the safety, applicability and durability of the pavement panel meet the design requirements.

8. The method for prestressed intelligent tensioning of assembled road panels according to claim 1 is characterized in that: Including: According to the type and degree of prestressed defects, the finite element analysis method is used to simulate the stress distribution and deformation of the road panel to obtain the degree of influence of the defects on the safety performance of the road panel; through the probability statistics method, combined with historical data and expert experience, the probability distribution of safety accidents caused by defects of different degrees is calculated, and the accidents are graded according to the severity of the consequences; a defect hazard level assessment model is established, the probability of defects causing accidents and the severity of the consequences are comprehensively considered, and the fuzzy comprehensive evaluation method is used to determine the hazard level of the defects; for defects of different hazard levels, corresponding reinforcement or maintenance measures are formulated, emergency disposal measures are taken for defects of high hazard levels, and regular inspection and maintenance plans are formulated for defects of medium and low hazard levels; Using machine learning algorithms, such as support vector machines or random forests, a defect hazard prediction model is established. By analyzing the real-time monitoring data of road panel status parameters, the defect development trend and hazard changes are predicted. Based on Bayesian network theory, a defect risk assessment network model is constructed to comprehensively consider the correlation between various influencing factors, dynamically assess the changes in defect risk levels, and provide support for road panel maintenance decisions. A road panel safety hazard management information system is established to realize the digital collection, storage and analysis of defect information. According to the risk assessment results, a bill of quantities and priority ranking for road panel reinforcement or repair are automatically generated to provide guidance for maintenance construction.

9. The method for prestressed intelligent tensioning of assembled road panels according to claim 1 is characterized in that: Including: obtaining the prestressed defect detection result data of the road panel, preprocessing the detection result data, and extracting key characteristic parameters; using the support vector machine algorithm to evaluate the performance impact of the road panel based on the characteristic parameters of the prestressed defect detection result, and obtaining the performance impact evaluation result; using the Bayesian network algorithm to analyze the safety risk of the road panel based on the characteristic parameters of the prestressed defect detection result and the performance impact evaluation result, and obtaining the safety risk analysis result; The prestressed concrete defect detection results, performance impact assessment results, and safety risk analysis results are integrated to construct a comprehensive evaluation index system. The analytic hierarchy process is used to calculate the weights of the comprehensive evaluation indicators, and the comprehensive score of the prestressed concrete slab condition is obtained by weighted summation. Based on the comprehensive score of the prestressed concrete slab condition, the severity of the prestressed concrete slab defect is determined, and corresponding quality control and maintenance decision-making recommendations are provided. Generates intelligent detection report of prestressed defects, which includes summary of detection results, performance impact assessment, safety risk analysis, comprehensive evaluation results, and quality control and maintenance decision recommendations, and is presented intuitively in the form of charts, etc.

Images