Intelligent monitoring method and system based on AI suspended pouring bridge

Abstract

The invention provides an intelligent monitoring method and system based on an AI suspended pouring bridge, and relates to the technical field of bridge construction.The intelligent monitoring method comprises the steps that the experimental environment temperature and experimental image data are obtained; performing linear analysis on the experimental image data to obtain an experimental elevation and an experimental axis; obtaining a first experiment downwarping trend according to the experiment elevation and a preset experiment formwork erection elevation; according to the experimental environment temperature, the experimental elevation and the experimental axis, trend prediction is carried out through the constructed down-warping trend prediction model, and a predicted down-warping trend is obtained; comparing the first experiment down-warping trend with the predicted down-warping trend to generate a hanging basket construction adjustment strategy so as to optimize and adjust hanging basket construction; and performing concrete pouring construction management through the predicted formwork erecting elevation corresponding to the optimized and adjusted second experiment downwarping trend. According to the monitoring method and system provided by the invention, the accuracy of formwork erecting elevation can be ensured, the linear effective control of the suspended pouring bridge construction is realized, and the construction precision and efficiency are improved.

Description

Technical Field

[0001] This invention relates to the field of bridge construction technology, and in particular to an intelligent monitoring method and system for cantilever bridges based on AI. Background Technology

[0002] During the construction of a cantilever bridge using formwork, the linear control of the bridge is a key aspect to ensure construction quality, while accurate monitoring of elevation and axis is the foundation of linear control.

[0003] In the existing construction process of cantilever bridges using formwork, contact measuring instruments are often used to determine the elevation. This method is not only inefficient, but also its accuracy is affected by environmental factors and the construction of the formwork. It is difficult to accurately predict the bridge's deflection trend, which in turn leads to lag and error in setting the formwork elevation, affecting the linear quality of the bridge. Summary of the Invention

[0004] This invention provides an intelligent monitoring method and system for cantilever bridges based on AI, which solves the technical problems of low efficiency in elevation measurement in existing technologies, and the measurement accuracy being affected by the environment and the construction of hanging baskets, making it difficult to accurately predict the bridge deflection trend, resulting in lag and error in the setting of the formwork elevation, which affects the linear quality of the bridge.

[0005] To achieve the above and other related objectives, this invention provides an intelligent monitoring method for cantilever bridges based on AI, comprising: acquiring experimental image data of the experimental environment temperature and bridge construction characteristics as the experimental load increases during the bridge hanging basket test phase; performing linear analysis on the experimental image data to obtain the experimental elevation and experimental axis corresponding to different experimental loads; obtaining the first experimental deflection trend corresponding to different experimental loads based on the experimental elevation and the preset experimental formwork elevation; predicting the trend based on the experimental environment temperature, experimental elevation, and experimental axis using a constructed deflection trend prediction model to obtain the predicted deflection trend; comparing the first experimental deflection trend with the predicted deflection trend to generate a hanging basket construction adjustment strategy for optimizing the hanging basket construction; and managing concrete pouring construction based on the predicted formwork elevation corresponding to the optimized second experimental deflection trend.

[0006] In one embodiment of the present invention, linear analysis is performed on experimental image data to obtain experimental elevations and experimental axes corresponding to different experimental loads. This includes: feature recognition and bounding selection of preset bridge construction features in the experimental image data to obtain feature categories and feature frames; rotation processing of the preset bridge construction feature model corresponding to the feature category to adjust the view angle of the preset bridge construction feature model to be consistent with the feature frame; comparison of each first linear dimension of the preset bridge construction feature model under the corresponding view angle with the corresponding second linear dimension in the feature frame to obtain the size ratio; identification of elevation markers and axis markers corresponding to the experimental image data to obtain image elevation dimensions and axis spatial data; scaling conversion of the image elevation dimensions according to the size ratio to obtain the experimental elevation; and linear analysis of the axis spatial data according to the view angle adjustment to obtain the experimental axis.

[0007] In one embodiment of the present invention, the deflection trend prediction model is constructed as follows: historical image data of bridge construction characteristics corresponding to different historical construction loads at different historical construction stages of the bridge hanging basket under different historical environmental temperatures are acquired; the bridge construction characteristics in the historical image data are identified and analyzed to obtain the corresponding historical elevations and historical axes; based on the historical elevations and historical axes corresponding to different historical construction loads at each historical environmental temperature, the historical deflection dataset corresponding to each historical environmental temperature is obtained; based on the historical deflection dataset, the historical deflection trend of the deflection data changing with the historical construction load is obtained; the model is trained by using the historical elevations, historical axes, and historical deflection trends obtained under different historical environmental temperatures and different construction loads to obtain the deflection trend prediction model.

[0008] In one embodiment of the present invention, the first experimental deflection trend corresponding to different experimental loads is obtained based on the experimental elevation and the preset experimental model elevation, including: calculating the experimental deflection data corresponding to different experimental loads based on the experimental elevation and the preset experimental model elevation; and plotting the trend based on the experimental deflection data corresponding to different experimental loads to obtain the first experimental deflection trend of the bridge.

[0009] In one embodiment of the present invention, a first experimental deflection trend is compared with a predicted deflection trend to generate a hanging basket construction adjustment strategy for optimizing the hanging basket construction. This includes: calculating the difference between the first experimental deflection trend and the predicted deflection trend to obtain a difference dataset. , This represents the first experimental deflection data corresponding to each experimental load. This represents the predicted deflection data corresponding to each experimental load; for the difference dataset Numerical detection is performed on each first difference data point in the dataset; when the difference dataset... If some of the first difference data points are greater than the difference threshold, then the difference dataset is used as a reference. For each first difference data point, the difference change trend is obtained. The difference change trend includes the first change trend corresponding to the first difference data being greater than the difference threshold and the second change trend corresponding to the first difference data being less than the difference threshold. Each benchmark change trend in the benchmark change trend library is compared with the difference change trend to obtain the target benchmark change trend that is closest to the difference change trend. The hanging basket construction adjustment strategy corresponding to the target benchmark change trend is found to optimize and adjust the hanging basket construction.

[0010] In one embodiment of the present invention, comparing each benchmark trend in the benchmark trend library with the difference trend to obtain a target benchmark trend that is closest to the difference trend includes: comparing the similarity of a first trend with each benchmark trend in the benchmark trend library to obtain a first similarity value; extracting the benchmark trend corresponding to the first similarity value that is greater than a first similarity threshold; comparing a second trend with the benchmark trend to obtain a second similarity value; and obtaining a similarity index based on the first similarity value, a first weight corresponding to the first similarity value, a second similarity value, and a second weight corresponding to the second similarity value. The calculation formula for the similarity index is as follows: , This represents the first similarity value. Indicates the first weight. This represents the second similarity value. This represents the second weight; the benchmark change trend corresponding to the largest similarity index is selected as the target benchmark change trend that is closest to the difference change trend.

[0011] In one embodiment of the present invention, concrete pouring construction management is carried out by using the predicted formwork elevation corresponding to the optimized and adjusted second experimental deflection trend. This includes: searching for deflection data in the second experimental deflection trend using a preset full load to obtain the predicted experimental deflection data corresponding to the preset full load, wherein the second difference data between the second experimental deflection trend and the predicted deflection trend is less than a difference threshold; and obtaining the predicted formwork elevation for concrete pouring construction management based on the predicted experimental deflection data and the design elevation. The calculation formula for the predicted formwork elevation is: ,in, Indicates the design elevation. This represents the predicted deflection data from the experiment.

[0012] In one embodiment of the present invention, the predicted formwork elevation is obtained based on the predicted experimental deflection data and the design elevation for concrete pouring construction management. This includes: during the construction of the bridge formwork, acquiring real-time image data of the bridge construction characteristics as the real-time concrete load increases at the predicted formwork elevation; performing linear analysis on the real-time image data to obtain the real-time elevation and real-time axis corresponding to different real-time concrete loads; calculating the real-time deflection trend of the bridge based on the real-time elevation and the predicted formwork elevation; and performing optimization analysis on the predicted formwork elevation based on the second experimental deflection trend and the real-time deflection trend to obtain a formwork elevation compensation value, so as to dynamically fine-tune the predicted formwork elevation before concrete curing.

[0013] In one embodiment of the present invention, the predicted formwork elevation is optimized and analyzed based on the second experimental deflection trend and the real-time deflection trend to obtain a formwork elevation compensation value, so as to dynamically fine-tune the predicted formwork elevation before concrete curing. This includes: predicting the full load corresponding to the full load volume of the corresponding beam segment based on the real-time concrete load and the loading volume, to obtain the full load of the concrete; calculating the deflection difference between the second experimental deflection trend and the real-time deflection trend corresponding to the current real-time concrete load, to obtain a first deflection difference trend; predicting the deflection difference trend between the current real-time concrete load and the full load of the concrete based on the first deflection difference trend, to obtain a second deflection difference trend; fusing the second deflection difference trend and the second experimental deflection trend to obtain a deflection compensation trend; searching for corresponding deflection data in the deflection compensation trend using the full load of the concrete to obtain full load compensation deflection data; and obtaining the formwork elevation compensation value based on the full load compensation deflection data and the design elevation, so as to dynamically fine-tune the predicted formwork elevation before concrete curing.

[0014] To achieve the above and other related objectives, the present invention also provides an intelligent monitoring system for cantilever bridges based on AI, comprising: an acquisition unit for acquiring experimental image data of the experimental environment temperature and bridge construction characteristics as the experimental load increases during the bridge hanging basket test phase; an analysis unit for performing linear analysis on the experimental image data to obtain the experimental elevation and experimental axis corresponding to different experimental loads; an experimental trend analysis unit for obtaining the first experimental deflection trend corresponding to different experimental loads based on the experimental elevation and the preset experimental formwork elevation; a prediction trend analysis unit for predicting the trend based on the experimental environment temperature, experimental elevation, and experimental axis using a constructed deflection trend prediction model to obtain the predicted deflection trend; a trend comparison unit for comparing the first experimental deflection trend with the predicted deflection trend to generate a hanging basket construction adjustment strategy for optimizing the hanging basket construction; and a construction management unit for managing concrete pouring construction based on the predicted formwork elevation corresponding to the optimized second experimental deflection trend.

[0015] The beneficial effects of this invention are as follows: This invention proposes an intelligent monitoring method and system for cantilever bridges based on AI. By utilizing the experimental environment temperature during the experimental phase after the cantilever bridge's suspended platform is installed and the experimental image data obtained under different experimental loads, and after analyzing the experimental elevation and axis in the experimental image data, the experimental deflection trend can be plotted. Then, the experimental deflection trend is compared with the predicted deflection trend obtained under the corresponding conditions through a deflection trend prediction model. This allows it to determine whether there are problems in the cantilever bridge suspended platform construction under the current experimental load, and accurately identify the corresponding adjustment strategy for the suspended platform construction. This facilitates timely optimization and adjustment of the cantilever bridge suspended platform construction. Furthermore, by using the second experimental deflection trend obtained from the adjusted experimental load tests, the pre-set full-load formwork elevation can be predicted more accurately, ensuring that the predicted formwork elevation can more precisely match the concrete pouring construction, making the setting of the formwork elevation more scientific and reasonable. Furthermore, to ensure the accuracy of the predicted formwork elevation, real-time elevation and axis measurements can be performed using real-time image data corresponding to different real-time concrete loads during concrete pouring. This allows for the determination of the bridge's real-time deflection trend. Based on the comparison between the second experimental deflection trend and the real-time deflection trend, a real-time formwork elevation compensation value can be generated. This ensures the linearity of the corresponding beam segment during the construction of the cantilever bridge, improves construction accuracy and efficiency, ensures that the bridge construction quality meets design standards, reduces subsequent finishing work, and lowers construction costs. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0017] In the attached diagram: Figure 1 This is a flowchart illustrating the intelligent monitoring method for AI-based cantilever bridges provided in an embodiment of the present invention.

[0018] Figure 2 The diagram shown is a structural block diagram of an AI-based intelligent monitoring system for cantilever bridges provided in an embodiment of the present invention.

[0019] Figure 3 The diagram shown is a structural schematic of an electronic device according to an embodiment of the present invention.

[0020] The attached figures are labeled as follows: Electronic device 1; AI-based intelligent monitoring system for cantilever bridges 11; memory 12; processor 13; acquisition unit 111; parsing unit 112; experimental trend analysis unit 113; predictive trend analysis unit 114; trend comparison unit 115; construction management unit 116. Detailed Implementation

[0021] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0022] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. The drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0023] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0024] This invention provides an AI-based intelligent monitoring method for cantilever bridges. By utilizing the experimental environment temperature during the experimental phase after the cantilever bridge's suspended platform is installed, and experimental image data obtained under different experimental loads, the method analyzes the experimental elevation and axis from the experimental image data to plot the experimental deflection trend. This experimental deflection trend is then compared with the predicted deflection trend obtained under the corresponding conditions using a deflection trend prediction model. This allows the method to determine if there are any problems with the cantilever bridge's suspended platform construction under the current experimental load and to accurately identify adjustment strategies for the suspended platform construction. Furthermore, by using the newly obtained second experimental deflection trend from different experimental load tests after adjustments, the method can more accurately predict the formwork elevation under a preset full load, ensuring that the predicted formwork elevation more precisely matches the concrete pouring construction and making the setting of the formwork elevation more scientific and reasonable. Furthermore, to ensure the accuracy of the predicted formwork elevation, real-time elevation and axis measurements can be performed using real-time image data corresponding to different real-time concrete loads during concrete pouring. This allows for the determination of the bridge's real-time deflection trend. Based on the comparison between the second experimental deflection trend and the real-time deflection trend, a real-time formwork elevation compensation value is generated to ensure the linearity of the corresponding beam segment during the construction of the cantilever bridge. This ensures that the bridge construction quality meets design standards, reduces subsequent repair work, and lowers construction costs.

[0025] Figure 1 A flowchart illustrating an exemplary embodiment of this application shows a method for intelligent monitoring of AI-based cantilever bridges, applied to an intelligent monitoring system for AI-based cantilever bridges, including steps S10-S60. The following will be combined with... Figure 1 The technical solution of this application will be described in detail below.

[0026] First, step S10 is executed to obtain experimental image data of the experimental environment temperature during the bridge hanging basket test phase and the bridge construction characteristics as the experimental load increases.

[0027] High-precision, non-contact mechanical vision measurement equipment is deployed at the cantilever bridge formwork and key bridge components. This equipment may include a high-definition industrial camera, a light source, a temperature sensor, and a laser detector for measuring the concrete pouring height within the formwork. By supplementing the construction site with illumination from the light source, the high-definition industrial camera can collect experimental image data of the bridge construction characteristics during the cantilever bridge formwork experimental phase, real-time image data of the bridge construction characteristics during the cantilever bridge formwork pouring phase, or historical image data from the historical construction process. This data is then uploaded to the intelligent monitoring system of this invention. Alternatively, the intelligent monitoring system can actively collect experimental, real-time, and historical image data captured by the high-definition industrial camera. Furthermore, during construction, the corresponding experimental, real-time, and historical ambient temperatures for the experimental, real-time, and historical image data can be acquired by temperature sensors and uploaded to the intelligent monitoring system. Alternatively, the intelligent monitoring system can collect relevant ambient temperatures from the temperature sensors.

[0028] Next, step S20 is executed to perform linear analysis on the experimental image data to obtain the experimental elevation and experimental axis corresponding to different experimental loads.

[0029] After acquiring experimental image data through the intelligent monitoring system, the experimental elevation and experimental axis in the experimental image data are further identified and their dimensions are analyzed to obtain the experimental elevation and experimental axis corresponding to different experimental loads. Based on the experimental elevation and experimental axis, the corresponding first experimental deflection trend can be determined. By comparing it with the predicted deflection trend obtained from the deflection trend prediction model, the elevation of the formwork under the preset full load can be predicted more accurately. This ensures that the predicted elevation of the formwork can be more accurately matched with the concrete pouring construction, making the setting of the formwork elevation more scientific and reasonable.

[0030] In step S20, linear analysis is performed on the experimental image data to obtain the experimental elevation and experimental axis corresponding to different experimental loads, which may further include: Pre-defined bridge construction features in the experimental image data are identified and bounded to obtain feature categories and feature bounding boxes. The preset bridge construction feature model corresponding to the feature category is rotated to adjust the view angle of the preset bridge construction feature model to match the feature frame. The size ratio is obtained by comparing the first linear dimensions of the preset bridge construction feature model under the corresponding view angle with the corresponding second linear dimensions in the feature frame. The elevation and axis markers corresponding to the experimental image data are identified to obtain the image elevation dimensions and axis spatial data. The image elevation dimensions are proportionally converted according to the size ratio to obtain the experimental elevation. Linear analysis of the spatial data of the axis was performed based on the view angle adjustment to obtain the experimental axis.

[0031] In the process of linear analysis of experimental image data, feature recognition can be performed on the preset bridge construction features in the acquired experimental image data to find the feature category of each preset bridge construction feature, and feature bounding boxes can be selected to obtain feature frames. These preset bridge construction features may include features of the cantilevered bridge formwork, features of key bridge components, and of course, other construction features. Then, the preset bridge construction feature model corresponding to the feature category is retrieved, and the view angle of the preset bridge construction feature model is switched to correspond to the perspective of the feature frame, and the model size is switched to correspond to the size of the feature frame, thereby determining the shooting angle (view angle) of the experimental image data and the size ratio between the experimental image data and the preset bridge construction feature model. Alternatively, after switching the view angle of the preset bridge construction feature model, the first linear dimension of each feature line can be compared with the second linear dimension of the corresponding feature line in the feature frame to obtain the size ratio between the experimental image data and the preset bridge construction feature model. Furthermore, by querying the experimental image data based on the corresponding markers used for measuring elevation and axis in the preset bridge construction feature model, the corresponding elevation and axis markers in the experimental image data can be found. This allows for the determination of the corresponding image elevation dimensions and axis spatial data. Finally, by scaling the image elevation dimensions using a size ratio, the corresponding experimental elevation can be obtained. Linear analysis of the axis spatial data can then be performed based on the view angle adjustment; that is, by combining the linear relationship between the axis markers and the view angle of the preset bridge construction feature model, the corresponding experimental axis can be determined.

[0032] Next, step S30 is executed to obtain the first experimental deflection trend corresponding to different experimental loads based on the experimental elevation and the preset experimental model elevation.

[0033] The preset experimental formwork elevation can be obtained before conducting the bridge cantilever basket test. This is achieved by using a deflection trend prediction model combined with environmental temperature and a preset full-load load to predict the corresponding full-load deflection data. Then, this data is added to the design elevation required for the cantilever bridge design to obtain the preset experimental formwork elevation. In this invention, the design elevation refers to the pre-set elevation that the bridge will ultimately form after deflection. Therefore, after the experimental elevation is analyzed by the intelligent monitoring system, the preset experimental formwork elevation can be used to calculate the corresponding experimental deflection data under different experimental loads. This experimental deflection data is then used to construct a first experimental deflection trend, which is compared and analyzed with the predicted deflection trend. This allows for timely adjustments when problems arise in the first experimental deflection trend.

[0034] In step S30, based on the experimental elevation and the preset experimental model elevation, the first experimental deflection trend corresponding to different experimental loads is obtained, including: Based on the experimental elevation and the preset experimental model elevation, the experimental deflection data corresponding to different experimental loads were calculated. Trends were plotted based on the experimental deflection data corresponding to different experimental loads to obtain the first experimental deflection trend of the bridge.

[0035] After obtaining the experimental elevation, the difference can be calculated by combining it with the preset experimental formwork elevation required for construction, thus determining the bridge's deflection. After obtaining the experimental deflection data corresponding to different experimental loads, a curve graph of the experimental load and experimental deflection data can be constructed as the bridge's first real-time deflection trend. This curve represents the bridge's deflection change trend during the experiment, allowing for comparison and analysis with the predicted deflection trend, thereby optimizing and adjusting the formwork construction.

[0036] Next, step S40 is executed, and the downward deflection trend is predicted by using the constructed downward deflection trend prediction model based on the experimental ambient temperature, experimental elevation and experimental axis.

[0037] To compare the first real-time deflection trend with the predicted deflection trend, it is also necessary to use the pre-constructed deflection trend prediction model, combined with the experimental ambient temperature, experimental elevation extracted from the experimental image data, and experimental axis during the experiment, to achieve the prediction of the deflection trend corresponding to different construction loads.

[0038] The downward trend prediction model can be constructed as follows: Acquire historical image data of bridge construction characteristics corresponding to different historical construction loads during different historical environmental temperatures and bridge formwork construction stages. By identifying and analyzing the bridge construction features in historical image data, the corresponding historical elevations and historical axes are obtained. Based on the historical elevation and historical axis corresponding to each historical ambient temperature under different historical construction loads, the historical deflection dataset corresponding to each historical ambient temperature is obtained. Based on the historical deflection dataset, the historical deflection trend of deflection data as a function of historical construction loads is obtained; By training the model using historical elevations, historical axes, and historical deflection trends obtained under different historical environmental temperatures and construction loads, a deflection trend prediction model is obtained.

[0039] When constructing the deflection trend prediction model, historical image data of bridge construction characteristics under different historical ambient temperatures and construction loads during the historical construction stages of the bridge formwork can be used. The same processing method as for experimental image data can be employed to determine the corresponding historical elevations and axes. Then, based on the historical elevations, axes, and deflection trends under different historical ambient temperatures and construction loads, using these as training sets and the historical deflection trend as the label, a deflection trend prediction model is constructed through model training. This allows for the rapid generation of predicted deflection trends based on corresponding historical ambient temperatures, enabling timely adjustments to the formwork elevation during different load experiments or real-time construction, ensuring the rationality of the formwork elevation setting.

[0040] Next, step S50 is executed to compare the first experimental deflection trend with the predicted deflection trend and generate a hanging basket construction adjustment strategy to optimize and adjust the hanging basket construction.

[0041] After obtaining the first experimental deflection trend and the predicted deflection trend through the intelligent monitoring system, the problems in the first experimental deflection trend can be found by comparing the first experimental deflection trend with the predicted deflection trend. If there are problems in the first experimental deflection trend, the hanging basket construction adjustment strategy can be adjusted accordingly to optimize the hanging basket construction in a timely manner, so as to make the setting of the formwork elevation more scientific and reasonable.

[0042] In step S50, the first experimental deflection trend is compared with the predicted deflection trend to generate a hanging basket construction adjustment strategy for optimizing the hanging basket construction, including: The difference between the first experimental downward deflection trend and the predicted downward deflection trend is calculated to obtain the difference dataset. , This represents the first experimental deflection data corresponding to each experimental load. This represents the predicted deflection data corresponding to each experimental load; For difference datasets Numerical detection is performed on each first difference data point in the dataset; When the difference dataset If some of the first difference data points are greater than the difference threshold, then the difference dataset is used as a reference. For each first difference data point, the difference change trend is obtained. The difference change trend includes a first change trend corresponding to the first difference data being greater than the difference threshold and a second change trend corresponding to the first difference data being less than the difference threshold. Each benchmark change trend in the benchmark change trend library is compared with the difference change trend to obtain the target benchmark change trend that is closest to the difference change trend. Identify the corresponding adjustment strategies for the hanging basket construction based on the changing trend of the target benchmark, in order to optimize and adjust the hanging basket construction.

[0043] In comparing the first experimental downward deflection trend with the predicted downward deflection trend, the difference between the two trends can be calculated to obtain the difference dataset. Then, for the difference dataset The corresponding first difference data is numerically checked. If some first difference data are greater than the difference threshold, it indicates that there is a problem with the hanging basket construction design corresponding to the current first experimental deflection trend. Then, the difference change trend corresponding to the first difference data can be split into a first change trend corresponding to the first difference data being greater than the difference threshold and a second change trend corresponding to the first difference data being less than the difference threshold. Then, the first change trend and the second change trend are compared with each benchmark change trend in the benchmark change trend library to determine the target benchmark change trend that is closest to the difference change trend in the benchmark change trend library. The hanging basket construction adjustment strategy corresponding to the target benchmark change trend is then used to optimize and adjust the hanging basket construction to ensure that the setting of the formwork elevation is more scientific and reasonable.

[0044] This process involves comparing each benchmark change trend in the benchmark change trend library with the difference change trend to obtain the target benchmark change trend that is closest to the difference change trend. This may further include: The first trend of change is compared with each benchmark trend of change in the benchmark trend of change library to obtain the first similarity value; Extract the baseline change trend corresponding to the first similarity value that is greater than the first similarity threshold; The second trend of change is compared with the baseline trend of change to obtain the second similarity value; Based on the first similarity value, the first weight corresponding to the first similarity value, the second similarity value, and the second weight corresponding to the second similarity value, the similarity index is obtained. The formula for calculating the similarity index is as follows: , This represents the first similarity value. Indicates the first weight. This represents the second similarity value. Indicates the second weight; The benchmark change trend corresponding to the largest similarity index is selected as the target benchmark change trend that is closest to the difference change trend.

[0045] In comparing each benchmark trend in the benchmark trend library with the difference trend, the process can begin by comparing the first trend with each benchmark trend in the library to obtain a first similarity value. Then, benchmark trends with first similarity values ​​greater than the first similarity threshold are extracted and further compared with second trends to determine the second similarity value between each selected benchmark trend and the second trend. After obtaining the first and second similarity values, by combining the first and second weights pre-set manually for each similarity, a formula can be used to calculate the second similarity value. The similarity index corresponding to each selected benchmark trend is calculated. Then, by using the similarity index derived from the fusion of the first and second trend comparisons, the target benchmark trend that best matches the difference trend can be accurately determined, ensuring the accuracy of the found hanging basket construction adjustment strategy. The benchmark trend database pre-stores hanging basket construction adjustment strategies and corresponding adjustment strategies for each strategy.

[0046] Next, step S60 is executed, and the concrete pouring construction management is carried out by using the predicted formwork elevation corresponding to the optimized and adjusted second experimental deflection trend.

[0047] After adjusting the formwork construction using the formwork construction adjustment strategy, the predicted formwork elevation can be obtained by continuing to test the deflection trend in the second experiment. This allows for further optimization of the formwork elevation during the concrete pouring process, ensuring that the formwork elevation maintains a dynamic match with the concrete pouring construction. This effectively controls the linearity of the bridge and ensures that the bridge construction quality meets the design standards.

[0048] In step S60, concrete pouring construction management is carried out using the predicted formwork elevation corresponding to the optimized and adjusted second experimental deflection trend, including: By searching for deflection data in the second experimental deflection trend under a preset full load, the predicted experimental deflection data corresponding to the preset full load is obtained. The second difference data between the second experimental deflection trend and the predicted deflection trend are all less than the difference threshold. Based on the predicted deflection data from the experiment and the design elevation, the predicted formwork elevation is obtained for concrete pouring construction management. The formula for calculating the predicted formwork elevation is as follows: ,in, Indicates the design elevation. This represents the predicted deflection data from the experiment.

[0049] In the process of calculating the predicted formwork elevation, one can first search for deflection data in the second experimental deflection trend using a preset full load, thereby finding the predicted experimental deflection data corresponding to the preset full load. Then, the predicted experimental deflection data is summed with the design elevation to obtain the predicted formwork elevation for concrete pouring. Concrete pouring is then carried out using this predicted formwork elevation, allowing for further compensation of the predicted formwork elevation during the concrete pouring process, thus ensuring the accuracy of the formwork elevation and improving the precision of the bridge's linearity.

[0050] Following this, based on the predicted deflection data from the experimental setup and the design elevation, the predicted formwork elevation is obtained for concrete pouring construction management, which may further include: During the construction of the bridge formwork, real-time image data of the bridge construction characteristics are obtained as the real-time concrete load increases below the predicted formwork elevation. Linear analysis of real-time image data yields real-time elevations and real-time axes corresponding to different real-time concrete loads; The real-time deflection trend of the bridge is calculated based on the real-time elevation and the predicted elevation of the formwork. Based on the deflection trend of the second experiment and the real-time deflection trend, the predicted formwork elevation is optimized and analyzed to obtain the formwork elevation compensation value, so as to dynamically fine-tune the predicted formwork elevation before concrete curing.

[0051] In the process of concrete pouring construction management based on the predicted formwork elevation, real-time image data of the bridge construction characteristics under the predicted formwork elevation as the real-time concrete load increases are acquired during the bridge formwork construction. This real-time image data is then analyzed using the same analytical method as the experimental image data to obtain the real-time elevation and real-time axis corresponding to different real-time concrete loads. Then, by calculating the difference between the real-time elevation and the predicted formwork elevation, the real-time deflection trend of the bridge corresponding to different real-time concrete loads can be determined. Furthermore, using the second experimental deflection trend and the real-time deflection trend, the predicted formwork elevation is optimized to generate a formwork elevation compensation value to adjust the predicted formwork elevation. This allows for fine-tuning of the formwork height during concrete pouring, ensuring the accuracy of the formwork elevation and improving the linear quality of the beam segment pouring.

[0052] Specifically, based on the deflection trend of the second experiment and the real-time deflection trend, the predicted formwork elevation is optimized and analyzed to obtain the formwork elevation compensation value, so as to dynamically fine-tune the predicted formwork elevation before concrete curing. This can further include: Based on the real-time concrete load and loading volume, the full load corresponding to the full load volume of the beam segment is predicted, and the full load of the concrete is obtained. The first deflection difference trend is obtained by calculating the deflection difference between the second experimental deflection trend and the real-time deflection trend corresponding to the current real-time concrete load. Based on the first deflection difference trend, the deflection difference trend between the current real-time concrete load and the full concrete load is predicted to obtain the second deflection difference trend. The second downward deflection difference trend and the second experimental downward deflection trend are merged to obtain the downward deflection compensation trend; By searching for the corresponding deflection data in the deflection compensation trend under full load concrete load, the full load compensation deflection data is obtained. Based on the full-load compensation deflection data and the design elevation, the formwork elevation compensation value is obtained to dynamically fine-tune the predicted formwork elevation before concrete curing.

[0053] When optimizing the predicted formwork elevation, a laser detector can be used to detect the pouring height of concrete after each quantitative pour to calculate the loading volume corresponding to the real-time concrete load. However, due to factors such as concrete mix design, the full-load concrete load corresponding to the full-load volume of the beam segment cannot be accurately calculated. Therefore, based on the linear relationship between the continuously increasing real-time concrete load and its loading volume, the full-load concrete load corresponding to the full-load volume of the beam segment can be dynamically predicted in real time. This ensures the effectiveness of fine-tuning the predicted formwork elevation each time, allowing for small, multiple adjustments to reduce the difficulty of adjustment. Therefore, after each prediction of the full-load concrete load based on the real-time concrete load, the real-time deflection trend corresponding to the increase from zero to the current real-time concrete load can be compared with the second experimental deflection trend optimized through experimental construction. This allows for the calculation of the deflection difference between the two, and based on the calculated deflection differences, the corresponding first deflection difference trend can be plotted. Then, using the first deflection difference trend corresponding to the real-time concrete load, a second deflection difference trend corresponding to the real-time concrete load as it increases from the current real-time concrete load to the full concrete load is predicted in real time. Furthermore, this second deflection difference trend is integrated into the predicted deflection trend, thus deriving the deflection compensation trend after compensation. Finally, using the full concrete load predicted each time, deflection compensation data is searched within the corresponding deflection compensation trend to find the full-load compensation deflection data after each increase in real-time concrete load. By summing the full-load compensation deflection data and the design elevation, the formwork elevation compensation value is accurately calculated. This allows for dynamic fine-tuning of the formwork elevation during the continuous concrete pouring process, ensuring the correspondence between the formwork elevation and the design elevation after pouring, and improving the linearity of the beam segment pouring.

[0054] Please see Figure 2The present invention also provides an intelligent monitoring system 11 based on AI for cantilever bridges, comprising: an acquisition unit 111 for acquiring experimental image data of the experimental environment temperature and bridge construction characteristics as the experimental load increases during the bridge cantilever test phase; an analysis unit 112 for performing linear analysis on the experimental image data to obtain the experimental elevation and experimental axis corresponding to different experimental loads; an experimental trend analysis unit 113 for obtaining the first experimental deflection trend corresponding to different experimental loads based on the experimental elevation and the preset experimental formwork elevation; a prediction trend analysis unit 114 for performing trend prediction based on the experimental environment temperature, experimental elevation, and experimental axis using a constructed deflection trend prediction model to obtain the predicted deflection trend; a trend comparison unit 115 for comparing the first experimental deflection trend with the predicted deflection trend to generate a cantilever construction adjustment strategy for optimizing the cantilever construction; and a construction management unit 116 for managing concrete pouring construction based on the predicted formwork elevation corresponding to the optimized second experimental deflection trend.

[0055] It should be noted that the AI-based intelligent monitoring system 11 for cantilever bridges provided in the above embodiments and the AI-based intelligent monitoring method for cantilever bridges provided in the above embodiments belong to the same concept. The specific ways in which each module and unit performs its operations have been described in detail in the method embodiments and will not be repeated here. In practical applications, the AI-based intelligent monitoring system 11 for cantilever bridges provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0056] Please see Figure 3 The electronic device 1 may include a memory 12, a processor 13 and a bus, and may also include a computer program stored in the memory 12 and executable on the processor 13, such as an AI-based intelligent monitoring program for cantilever bridges.

[0057] The memory 12 includes at least one type of readable storage medium, including flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 1, such as a portable hard drive of the electronic device 1. In other embodiments, the memory 12 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 1. Furthermore, the memory 12 can include both internal and external storage units of the electronic device 1. The memory 12 can be used not only to store application software and various types of data installed on the electronic device 1, such as code for intelligent monitoring of AI-based cantilever bridges, but also to temporarily store data that has been output or will be output.

[0058] In some embodiments, the processor 13 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 13 is the control unit of the electronic device 1, connecting various components of the electronic device 1 via various interfaces and lines. It executes programs or modules stored in the memory 12 (e.g., intelligent monitoring programs based on AI cantilever bridges) and calls data stored in the memory 12 to perform various functions and process data in the electronic device 1.

[0059] The processor 13 executes the operating system of the electronic device 1 and various installed applications. The processor 13 executes the applications to implement the steps in the above-described intelligent monitoring method for AI-based cantilever bridges.

[0060] For example, the computer program may be divided into one or more modules, which are stored in the memory 12 and executed by the processor 13 to complete this application. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the electronic device 1. For example, the computer program may be divided into units in an AI-based intelligent monitoring system for cantilever bridges.

[0061] The integrated unit implemented as a software functional module can be stored in a computer-readable storage medium, which can be non-volatile or volatile. The software functional module, stored in the storage medium, includes several instructions to cause a computer device (which may be a personal computer, a computer device, or a network device, etc.) or a processor to execute some functions of the AI-based intelligent monitoring method for cantilever bridges described in the various embodiments of this application.

[0062] In summary, the intelligent monitoring method and system for cantilever bridges based on AI disclosed in this invention utilizes the experimental environment temperature during the experimental phase after the cantilever bridge's suspended platform is installed, and experimental image data obtained under different experimental loads. After analyzing the experimental elevation and axis from the experimental image data, the experimental deflection trend can be plotted. Then, the experimental deflection trend is compared with the predicted deflection trend obtained under the corresponding conditions through a deflection trend prediction model. This allows for the determination of whether there are problems in the cantilever bridge suspended platform construction under the current experimental load, and the accurate identification of the corresponding adjustment strategy for the suspended platform construction. This facilitates timely optimization and adjustment of the cantilever bridge suspended platform construction. Furthermore, by using the second experimental deflection trend obtained from the adjusted experimental load tests, the pre-set full-load formwork elevation can be predicted more accurately, ensuring that the predicted formwork elevation can more precisely match the concrete pouring construction, making the setting of the formwork elevation more scientific and reasonable. Furthermore, to ensure the accuracy of the predicted formwork elevation, real-time elevation and axis measurements can be performed using real-time image data corresponding to different real-time concrete loads during concrete pouring. This determines the bridge's real-time deflection trend. Based on a comparison between the second experimental deflection trend and the real-time deflection trend, a real-time formwork elevation compensation value is generated. This ensures the linearity and levelness of the corresponding beam segment during the construction of the cantilever bridge, improves construction accuracy and efficiency, ensures the bridge construction quality meets design standards, reduces subsequent finishing work, and lowers construction costs. Therefore, this invention effectively overcomes the various shortcomings of existing technologies and has high industrial application value.

[0063] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. An intelligent monitoring method for cantilever bridges based on AI, characterized in that, include: To acquire experimental image data of the experimental environment temperature and the bridge construction characteristics as the experimental load increases during the bridge hanging basket test phase; The experimental image data is linearly analyzed to obtain the experimental elevation and experimental axis corresponding to different experimental loads; Based on the experimental elevation and the preset experimental model elevation, the first experimental deflection trend corresponding to different experimental loads is obtained; Based on the experimental ambient temperature, the experimental elevation, and the experimental axis, a downward deflection trend prediction model is constructed to predict the downward deflection trend. The first experimental deflection trend is compared with the predicted deflection trend to generate a hanging basket construction adjustment strategy for optimizing the hanging basket construction. Concrete pouring construction management is carried out by using the predicted formwork elevation corresponding to the optimized and adjusted second experimental deflection trend.

2. The intelligent monitoring method for AI-based cantilever bridges according to claim 1, characterized in that, Linear analysis is performed on the experimental image data to obtain the experimental elevation and experimental axis corresponding to different experimental loads, including: Feature recognition and bounding selection are performed on the preset bridge construction features in the experimental image data to obtain feature categories and feature bounding boxes; The preset bridge construction feature model corresponding to the feature category is rotated to adjust the view angle of the preset bridge construction feature model to match the feature frame. The size ratio is obtained by comparing each of the first linear dimensions of the preset bridge construction feature model under the corresponding view angle with the corresponding second linear dimensions in the feature frame; The elevation markers and axis markers corresponding to the experimental image data are identified to obtain the image elevation dimensions and axis spatial data; The image elevation dimensions are proportionally converted according to the stated size ratio to obtain the experimental elevation. The experimental axis is obtained by performing linear analysis on the spatial data of the axis based on the view angle adjustment.

3. The intelligent monitoring method for AI-based cantilever bridges according to claim 1, characterized in that, The downward deflection trend prediction model is constructed in the following manner: Acquire historical image data of bridge construction characteristics corresponding to different historical construction loads during different historical environmental temperatures and bridge formwork construction stages. The bridge construction features in the historical image data are identified and analyzed to obtain the corresponding historical elevations and historical axes; Based on the historical elevation and historical axis corresponding to each historical ambient temperature under different historical construction loads, a historical deflection dataset corresponding to each historical ambient temperature is obtained; Based on the historical deflection dataset, the historical deflection trend of the deflection data as a function of historical construction loads is obtained; A deflection trend prediction model is obtained by training the model using the historical elevation, historical axis, and historical deflection trend obtained under different historical environmental temperatures and construction loads.

4. The intelligent monitoring method for AI-based cantilever bridges according to claim 1, characterized in that, Based on the experimental elevation and the preset experimental model elevation, the first experimental deflection trend corresponding to different experimental loads is obtained, including: Based on the experimental elevation and the preset experimental model elevation, the experimental deflection data corresponding to different experimental loads are calculated. Trends were plotted based on the experimental deflection data corresponding to different experimental loads to obtain the first experimental deflection trend of the bridge.

5. The intelligent monitoring method for AI-based cantilever bridges according to claim 1, characterized in that, The first experimental deflection trend is compared with the predicted deflection trend to generate a hanging basket construction adjustment strategy for optimizing the hanging basket construction, including: The difference between the first experimental downward deflection trend and the predicted downward deflection trend is calculated to obtain the difference dataset. , This represents the first experimental deflection data corresponding to each experimental load. This represents the predicted deflection data corresponding to each experimental load; For the difference dataset Numerical detection is performed on each first difference data point in the dataset; When the difference dataset If some of the first difference data points are greater than the difference threshold, then the difference dataset is used as a reference. For each first difference data point, a difference change trend is obtained, wherein the difference change trend includes a first change trend corresponding to the first difference data being greater than the difference threshold and a second change trend corresponding to the first difference data being less than the difference threshold; Each benchmark change trend in the benchmark change trend library is compared with the difference change trend to obtain the target benchmark change trend that is closest to the difference change trend; Find the hanging basket construction adjustment strategy corresponding to the change trend of the target benchmark, so as to optimize and adjust the hanging basket construction.

6. The intelligent monitoring method for AI-based cantilever bridges according to claim 5, characterized in that, Each benchmark change trend in the benchmark change trend library is compared with the difference change trend to obtain the target benchmark change trend that is closest to the difference change trend, including: The first change trend is compared with each benchmark change trend in the benchmark change trend library to obtain a first similarity value; Extract the baseline change trend corresponding to the first similarity value that is greater than the first similarity threshold; The second trend of change is compared with the baseline trend of change to obtain a second similarity value; Based on the first similarity value, the first weight corresponding to the first similarity value, the second similarity value, and the second weight corresponding to the second similarity value, a similarity index is obtained. The calculation formula for the similarity index is as follows: , This represents the first similarity value. Indicates the first weight. This represents the second similarity value. Indicates the second weight; The benchmark change trend corresponding to the largest similarity index is selected as the target benchmark change trend that is closest to the difference change trend.

7. The intelligent monitoring method for AI-based cantilever bridges according to claim 1, characterized in that, Concrete pouring construction management is carried out based on the predicted formwork elevation corresponding to the optimized and adjusted second experimental deflection trend, including: By searching for deflection data in the second experimental deflection trend under a preset full load, the predicted experimental deflection data corresponding to the preset full load is obtained, wherein the second difference data between the second experimental deflection trend and the predicted deflection trend is less than the difference threshold. Based on the predicted deflection data and design elevation, the predicted formwork elevation is obtained for concrete pouring construction management. The calculation formula for the predicted formwork elevation is as follows: ,in, Indicates the design elevation. This represents the predicted deflection data from the experiment.

8. The intelligent monitoring method for AI-based cantilever bridges according to claim 7, characterized in that, Based on the predicted deflection data from the experiment and the design elevation, the predicted formwork elevation is obtained for concrete pouring construction management, including: During the construction of the bridge formwork, real-time image data of the bridge construction characteristics are acquired as the real-time concrete load increases below the predicted formwork elevation. Linear analysis is performed on the real-time image data to obtain the real-time elevation and real-time axis corresponding to different real-time concrete loads; The real-time deflection trend of the bridge is calculated based on the real-time elevation and the predicted formwork elevation. Based on the second experimental deflection trend and the real-time deflection trend, the predicted formwork elevation is optimized and analyzed to obtain the formwork elevation compensation value, so as to dynamically fine-tune the predicted formwork elevation before concrete curing.

9. The intelligent monitoring method for AI-based cantilever bridges according to claim 8, characterized in that, Based on the second experimental deflection trend and the real-time deflection trend, the predicted formwork elevation is optimized and analyzed to obtain a formwork elevation compensation value, so as to dynamically fine-tune the predicted formwork elevation before concrete curing, including: Based on the real-time concrete load and loading volume, the full load corresponding to the full load volume of the beam segment is predicted to obtain the full load of the concrete. The first deflection difference trend is obtained by calculating the deflection difference between the second experimental deflection trend and the real-time deflection trend corresponding to the current real-time concrete load. Based on the first downward deflection trend, the downward deflection trend between the current real-time concrete load and the full concrete load is predicted to obtain the second downward deflection trend. The second downward deflection difference trend and the second experimental downward deflection trend are fused to obtain the downward deflection compensation trend; By searching for the corresponding deflection data in the deflection compensation trend using the full load of the concrete, the full load compensation deflection data is obtained. Based on the full-load compensation deflection data and the design elevation, the formwork elevation compensation value is obtained to dynamically fine-tune the predicted formwork elevation before concrete curing.

10. An intelligent monitoring system for cantilever bridges based on AI, characterized in that, include: The acquisition unit is used to acquire experimental image data of the experimental environment temperature and the bridge construction characteristics as the experimental load increases during the bridge hanging basket test phase. The analysis unit is used to perform linear analysis on the experimental image data to obtain the experimental elevation and experimental axis corresponding to different experimental loads; The experimental trend analysis unit is used to obtain the first experimental deflection trend corresponding to different experimental loads based on the experimental elevation and the preset experimental model elevation. The trend prediction analysis unit is used to predict the downward deflection trend by constructing a downward deflection trend prediction model based on the experimental environment temperature, the experimental elevation, and the experimental axis. The trend comparison unit is used to compare the first experimental deflection trend with the predicted deflection trend to generate a hanging basket construction adjustment strategy for optimizing the hanging basket construction. as well as The construction management unit is used to manage concrete pouring construction by using the predicted formwork elevation corresponding to the optimized and adjusted second experimental deflection trend.

Images