Marine floating bridge safety monitoring method and system

Abstract

The invention relates to the technical field of floating bridge safety monitoring, and discloses a marine floating bridge safety monitoring method and system. The method comprises the following steps: firstly, determining a stress threshold by using a conventional simulation method, and storing the data in a floating bridge response database; then real-time images of the wharf boat and the floating bridge are obtained in real time, and real-time displacement data between the wharf boat and the floating bridge can be accurately obtained by analyzing the images; when the real-time displacement data is larger than or equal to displacement data pre-stored in a database, it is indicated that large relative displacement occurs between the wharf boat and the floating bridge, at the moment, the system can dynamically adjust the original stress threshold value according to the current real-time displacement data, the water flow speed, the vehicle load and other factors, and the stress threshold value is adjusted to be larger than the original stress threshold value. And the stress condition under the actual condition can be reflected more accurately, so that the accuracy of safety assessment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of floating bridge safety monitoring, and in particular to a method and system for monitoring the safety of an offshore floating bridge. Background Art

[0002] When conducting a safety assessment of a floating bridge structure, it is particularly important to use various simulation methods to obtain the stress distribution of the pontoon and the floating bridge under different displacement conditions and during the movement of various vehicles. This simulation method can not only help engineers understand the response behavior of the floating bridge structure under complex working conditions, but also provide a scientific basis for design optimization. Specifically, different types of vehicle loads and their dynamic effects on the floating bridge structure are considered during the simulation process, which helps to identify potential weak links so that corresponding reinforcement measures can be taken or the design scheme can be adjusted. In addition, by quantitatively analyzing the stress thresholds under different working conditions, it can be ensured that the floating bridge can withstand the expected traffic flow and environmental loads in actual use, ensuring the safety of pedestrians and vehicles.

[0003] However, when the integrity of the floating bridge structure is challenged, such as when a large relative displacement occurs between the pontoon and the pontoon due to the action of water flow, the stress threshold obtained through the above simulation may no longer be applicable. This is because the pontoon is one of the important supporting points of the pontoon, and its position change will directly affect the stability and bearing capacity of the entire structure. For example, when the river flow rate increases, the pontoon may move due to the impact of the water flow, resulting in deviations in the spacing and angle between the pontoon and the pontoon. These changes will not only change the actual stress state of the pontoon, but may also cause significant changes in the original stress distribution pattern, thereby affecting the effectiveness of the previously determined safety threshold.

[0004] Therefore, there is an urgent need for a safety monitoring method and system for offshore floating bridges that can obtain stress thresholds with higher accuracy to evaluate the safety of floating bridges under large displacement conditions and formulate more reasonable maintenance and management strategies. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a method for monitoring the safety of an offshore floating bridge, comprising the following steps: S1: The stress thresholds of different vehicles at different positions of the floating bridge under different displacement conditions of the pontoon and the floating bridge are obtained by finite element simulation method, and a floating bridge response database is constructed; S2: acquiring real-time images of the pontoon and the floating bridge, and analyzing the real-time images to obtain real-time displacement data of the pontoon and the floating bridge, wherein the real-time displacement data includes a distance deviation and an angle deviation between the pontoon and the floating bridge; S3: Compare the real-time displacement data with the displacement data in the floating bridge response database to determine the final stress threshold: If the real-time displacement data is less than the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is used as the final stress threshold; If the real-time displacement data is greater than or equal to the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is corrected according to the real-time displacement data, water flow velocity, and vehicle load to obtain a final stress threshold; S4: Perform safety monitoring on the offshore floating bridge based on the final stress threshold.

[0006] Preferably, the stress threshold in the floating bridge response database is corrected according to the real-time displacement data, water flow velocity, and vehicle load to obtain the final stress threshold, which specifically includes: S31: constructing a stress threshold correction model, taking the structural characteristic parameters of the floating bridge as basic variables, the real-time displacement data as correction variables, and the vehicle load and water flow velocity as reference variables, to establish the stress threshold correction model; the input of the stress threshold correction model includes the structural characteristic parameters of the floating bridge, the real-time displacement data, the water flow velocity, and the vehicle load, and the output is the final stress threshold; the structural characteristic parameters of the floating bridge are used to represent the structural characteristics of the floating bridge, including the length of the floating bridge; S32: Determine the correction coefficient, and perform fitting based on the finite element simulation data and the actual test data to determine the correction coefficient in the stress threshold correction model; S33: According to the structural characteristic parameters of the floating bridge, the real-time displacement data, the water flow velocity, and the vehicle load, the stress threshold in the floating bridge response database is corrected through the stress threshold correction model to obtain a final stress threshold.

[0007] Preferably, the final stress threshold is calculated using the following formula:

[0008] Among them, σ corrected represents the final stress threshold after correction, σ original represents the stress threshold in the floating bridge response database, is the distance deviation in the real-time displacement data, is the angle deviation in the real-time displacement data, L is the length of the pontoon in the structural characteristic parameters, θ is the angle between the pontoon and the pontoon, α, β and γ are correction coefficients, P is the vehicle load, and P max represents the maximum vehicle load, V represents the water velocity, V max Indicates the maximum water flow velocity.

[0009] Preferably, the real-time displacement data of the pontoon and the floating bridge are obtained by analyzing the real-time image, specifically including: S21: performing denoising processing on the real-time image using the MOG2 algorithm; S22: using EfficientDet to determine the bounding box coordinates of the floating bridge and the pontoon in the real-time image after the denoising process; and intercepting the images of the floating bridge and the pontoon area according to the bounding box coordinates; S23: Based on the images of the floating bridge and the pontoon area, using the Mask R-CNN model, separate them from the real-time image to obtain pixel-level contour masks of the floating bridge and the pontoon; S24: determining the final images of the floating bridge and the pontoon through a transfer learning model according to the pixel-level contour masks of the floating bridge and the pontoon; S25: Based on the selected reference object, in the final image of the floating bridge and the pontoon, determine the real-time displacement data of the pontoon and the floating bridge.

[0010] Preferably, in S25, based on the selected reference object, in the final image of the floating bridge and the pontoon, the real-time displacement data of the pontoon and the floating bridge is determined, specifically: S251: respectively obtaining the actual size of the selected reference object and the pixel spacing in the final image of the floating bridge and the pontoon; S252: Calculate a scale factor based on the actual size and the pixel pitch; S253: respectively obtaining coordinates of the pontoon and the floating bridge in the final images of the floating bridge and the pontoon; S254: Based on the scale factor, determine the real-time displacement data of the pontoon and the floating bridge according to the coordinates of the pontoon and the floating bridge in the final image of the floating bridge and the pontoon.

[0011] Preferably, the calculation formula for the real-time displacement data of the pontoon and the floating bridge is: ; ; in, is the distance deviation in the real-time displacement data, is the angle deviation in real-time displacement data, k is the scale factor, x 趸船 is the x-axis coordinate of the pontoon in the final image of the pontoon and the pontoon, and y is 趸船 is the y-axis coordinate of the pontoon in the final image of the pontoon and the pontoon, x 浮桥 is the x-axis coordinate of the pontoon in the final image of the pontoon and the pontoon, and y is the 浮桥 is the y-axis coordinate of the pontoon in the final image of the pontoon and the barge.

[0012] Preferably, the scaling factor k is calculated using the following formula: ; Among them, L real Indicates the actual size of the selected reference object, L pixelRepresents the pixel spacing of the selected reference objects in the final images of the pontoon and barge.

[0013] Preferably, after the denoising process is performed in S21, the step further includes performing distortion correction on the lens of the image acquisition device.

[0014] On the other hand, the present application also provides a safety monitoring system for an offshore floating bridge, which implements any of the above-mentioned safety monitoring methods for an offshore floating bridge, and the system comprises: A floating bridge response database construction module is used to obtain stress thresholds at different positions of the floating bridge when different vehicles travel on the floating bridge under different displacement conditions of the pontoon and the floating bridge through a finite element simulation method, and to construct a floating bridge response database; A real-time displacement data acquisition module is used to acquire real-time images of the pontoon and the floating bridge, and analyze the real-time displacement data of the pontoon and the floating bridge from the real-time images, wherein the real-time displacement data includes the distance deviation and angle deviation between the pontoon and the floating bridge; The final stress threshold acquisition module is used to compare the real-time displacement data with the displacement data in the floating bridge response database: If the real-time displacement data is less than the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is used as the final stress threshold; If the real-time displacement data is greater than or equal to the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is corrected according to the real-time displacement data, water flow velocity, and vehicle load to obtain a final stress threshold; The safety monitoring module is used to perform safety monitoring on the offshore floating bridge based on the final stress threshold.

[0015] The embodiments of the present invention have the following technical effects: A method for monitoring the safety of an offshore floating bridge in the present application first uses a conventional simulation method to determine a stress threshold and stores this data in a floating bridge response database; then real-time images of a pontoon and a floating bridge are acquired in real time, and by analyzing these images, real-time displacement data between the pontoon and the floating bridge can be accurately obtained; when the real-time displacement data is greater than or equal to the displacement data pre-stored in the database, it indicates that a large relative displacement has occurred between the pontoon and the floating bridge. At this time, the system will dynamically adjust the original stress threshold according to multiple factors such as the current real-time displacement data, water flow velocity, and vehicle load, so as to more accurately reflect the stress condition under actual conditions, thereby improving the accuracy of the safety assessment.

[0016] Through the above process, especially the dynamic correction of stress threshold, this technical solution effectively reduces the error that may be caused by the large relative displacement between the pontoon and the floating bridge. This method not only takes into account the changes in the structure itself, but also comprehensively considers the influence of the external environment (such as water flow velocity) and use conditions (such as vehicle load), thereby ensuring that the final stress threshold is closer to the actual working conditions, greatly improving the safety of the offshore floating bridge. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of the steps of a method for monitoring safety of an offshore floating bridge provided by an embodiment of the present invention; Figure 2 It is a flow chart of the calculation steps of the final stress threshold provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0020] Traditional floating bridge safety monitoring methods rely on static simulation data, which makes it difficult to cope with dynamic interference such as pontoon displacement and water flow impact in actual environments. The present invention captures structural changes through real-time image analysis, combines external factors such as water flow velocity and vehicle load, and dynamically corrects stress thresholds to achieve the transition from "static simulation" to "dynamic adaptation". It takes into account both the structural mechanical properties and the dynamic impact of the environment. By building a "simulation-perception-correction" closed-loop system, offline simulation data is integrated with online perception data to ensure that the stress threshold always fits the actual working conditions.

[0021] Figure 1 1 is a flow chart of the steps of a method for monitoring the safety of an offshore floating bridge provided by an embodiment of the present invention. Figure 1 As shown, the present application provides a method for monitoring safety of an offshore floating bridge, comprising the following steps: S1: The stress thresholds of different vehicles at different positions of the floating bridge under different displacement conditions of the pontoon and the floating bridge are obtained by finite element simulation method, and a floating bridge response database is constructed; S2: acquiring real-time images of the pontoon and the floating bridge, and analyzing the real-time images to obtain real-time displacement data of the pontoon and the floating bridge, wherein the real-time displacement data includes a distance deviation and an angle deviation between the pontoon and the floating bridge, and is used to reflect the structural dynamic changes of the pontoon and the floating bridge; In some embodiments, the real-time displacement data of the pontoon and the floating bridge are obtained by analyzing the real-time image, specifically including: S21: performing denoising processing on the real-time image using the MOG2 algorithm; The MOG2 algorithm, namely the Mixture of Gaussians 2, is a background segmentation algorithm based on the Gaussian Mixture Model (GMM). When it comes to special application scenarios such as pontoons and floating bridges, the algorithm can accurately separate the target object from the displacement image. By using the Gaussian mixture model to model the probability distribution of pixels, the MOG2 algorithm can effectively distinguish the pixel changes caused by background changes (such as water surface fluctuations, lighting changes, etc.) from the actual displacement of the target object. With its strong adaptability and robustness, it shows excellent performance in processing image separation tasks in complex dynamic scenes, providing strong technical support for the safety monitoring of offshore floating bridges.

[0022] In some embodiments, after the denoising process is performed in S21, the lens of the image acquisition device is further subjected to distortion correction. Lens distortion may cause deformation of the captured image, affecting the actual shape, size and relative position relationship of the object, which is particularly disadvantageous for applications that rely on image analysis. Therefore, the lens of the image acquisition device is subjected to distortion correction to improve the quality and accuracy of the image and ensure that the information extracted from the image is authentic and reliable.

[0023] S22: using EfficientDet to determine the bounding box coordinates of the floating bridge and the pontoon in the real-time image after the denoising process; and intercepting the images of the floating bridge and the pontoon area according to the bounding box coordinates; For example, the EfficientDet model is an efficient target detection model based on deep learning, which combines the powerful feature extraction capabilities of EfficientNet and multiple target detection strategies. When locating the bounding boxes of the pontoon and the pontoon in the real-time image based on this model, the following specific steps can be included: S221: Model input and preprocessing Input image: Get real-time images of the pontoon and floating bridge. The resolution is recommended to be ≥1920×1080 to ensure clear details.

[0024] Preprocessing process: Optical flow method assistance: The optical flow method is used to estimate the motion trend of objects in the image sequence, preliminarily screen out areas that may contain floating bridges and barges, narrow the detection range, and reduce the calculation amount of the EfficientDet model.

[0025] Image enhancement: Use data enhancement techniques such as random cropping, color jittering, and rotation to simulate various lighting and angle changes and improve model robustness.

[0026] Resizing: Uniformly resize the images to the EfficientDet model input size (e.g. 512×512 or 640×640), keeping the aspect ratio to avoid object deformation.

[0027] S222: Model architecture optimization Feature fusion: The bidirectional Feature Pyramid Network (BiFPN) is introduced to fuse information multiple times between feature maps of different scales to enhance the capture of details of different sizes of floating bridges and pontoons.

[0028] Anchor frame design: Customize the size of the anchor frame according to the common aspect ratio of floating bridges and pontoons to improve the matching degree between the anchor frame and the target. For example, for a long floating bridge, set an anchor frame with an aspect ratio of 3:1 or 5:1; for nearly square objects such as pontoons, use a 1:1 anchor frame.

[0029] Loss function adjustment: Combine the intersection over union (IoU) loss and confidence loss to guide the model to accurately locate the bounding box. Introduce dynamic trade-off parameters to automatically adjust the proportion of classification loss and regression loss to deal with the problem of imbalanced target categories in complex backgrounds.

[0030] S223: Post-processing strategy NMS improvement: Soft-NMS or Diou-NMS is used instead of traditional NMS to allow the existence of appropriately overlapping bounding boxes, reduce the probability of false deletion, and smoothly filter the final box according to the confidence level.

[0031] False alarm suppression: Set the bounding box confidence threshold ≥ 0.8, and remove falsely detected targets by combining contextual information (such as whether the relative positions of the pontoon and the barge conform to physical logic).

[0032] S23: Based on the images of the floating bridge and the pontoon area, using the Mask R-CNN model, separate them from the real-time image to obtain pixel-level contour masks of the floating bridge and the pontoon; Exemplarily, S23 is specifically: S231: Model input and preprocessing Input image: A live image with bounding boxes of the pontoon and barge located.

[0033] Preprocessing: Semantic segmentation mask: First, use a pre-trained semantic segmentation model (such as DeepLab) to generate rough masks of the pontoon and the pontoon to provide prior information for Mask R-CNN.

[0034] Edge enhancement: Apply the Canny operator or Hough transform to detect image edges, enhance the outlines of the floating bridge and barge, and assist Mask R-CNN in extracting pixel-level boundaries.

[0035] S232: Model architecture optimization Feature pyramid expansion: Add deeper feature pyramid layers to improve the ability to describe small details (such as floating bridge connections and gaps on the edges of pontoons).

[0036] Attention mechanism: Integrate SENet or CBAM attention module to focus on the key areas of the pontoon and barge, weaken background interference, and improve the rationality of feature weight distribution.

[0037] Mask generation: A layered mask generation strategy is used to first generate an overall target mask, and then generate detailed masks for key areas (such as floating bridge main beams and pontoon mooring points) to enhance contour accuracy.

[0038] S233: Post-processing strategy Contour refinement: Use mathematical morphological operations (such as opening and closing operations, skeletonization) to denoise and smooth the extracted pixel-level contours, and repair contour defects caused by light and shadow changes or image noise.

[0039] Multi-view correction: A multi-view geometry method is introduced to correct the contour distortion caused by the difference in viewing angles based on the masks generated by images from different camera viewpoints, thus ensuring the consistency of the contour in three-dimensional space.

[0040] S24: determining the final images of the floating bridge and the pontoon through a transfer learning model according to the pixel-level contour masks of the floating bridge and the pontoon; S25: Based on the selected reference object, in the final image of the floating bridge and the pontoon, determine the real-time displacement data of the pontoon and the floating bridge.

[0041] For example, fixed markers (such as mooring piles and bridge piers) at both ends of the floating bridge are selected as reference objects to ensure that their size is stable, easy to identify and clearly visible in the image. Traditional calibration requires additional installation of markers, which is costly and easy to damage. The present invention uses the inherent structure of the floating bridge as a reference object, which not only reduces costs but also avoids human intervention.

[0042] Displacement calculation needs to solve the problem of image scale distortion. The pixel-physical mapping relationship is established through reference object calibration to eliminate lens distortion and perspective error and ensure data reliability. Therefore, in some embodiments, in S25, based on the selected reference object, the real-time displacement data of the pontoon and the pontoon are determined in the final image of the pontoon and the pontoon, specifically: S251: respectively obtaining the actual size of the selected reference object and the pixel spacing in the final image of the floating bridge and the pontoon; S252: Calculating a scale factor based on the actual size and the pixel pitch; S253: respectively obtaining coordinates of the pontoon and the floating bridge in the final images of the floating bridge and the pontoon; S254: Based on the scale factor, determine the real-time displacement data of the pontoon and the floating bridge according to the coordinates of the pontoon and the floating bridge in the final image of the floating bridge and the pontoon.

[0043] In some embodiments, the calculation formula for the real-time displacement data of the pontoon and the floating bridge is: ; ; in, is the distance deviation in the real-time displacement data, is the angle deviation in real-time displacement data, k is the scale factor, x 趸船 is the x-axis coordinate of the pontoon in the final image of the pontoon and the pontoon, and y is 趸船 is the y-axis coordinate of the pontoon in the final image of the pontoon and the pontoon, x 浮桥 is the x-axis coordinate of the pontoon in the final image of the pontoon and the pontoon, and y 浮桥 is the y-axis coordinate of the pontoon in the final image of the pontoon and the pontoon. The position of the center of the pontoon and the pontoon contour in the image, the above x and y coordinates are extracted by the segmentation mask. The geometric center of the contour mask is taken to reduce the error caused by local deformation.

[0044] In some embodiments, the scaling factor k is calculated using the following formula: ; Among them, L real Indicates the actual size of the selected reference object, obtained through engineering drawings or field measurements; L pixel represents the pixel spacing of the selected reference object in the final image of the floating bridge and the pontoon, extracted by image analysis. The scaling factor k is the conversion coefficient between the pixel distance and the actual distance, calibrated by the reference object; MOG2 algorithm: A background separation algorithm based on a mixed Gaussian model, used to eliminate dynamic interference such as water surface reflections and waves. EfficientDet: An efficient target detection model that balances computing resources and detection accuracy through compound scaling. MaskR-CNN: An instance segmentation model that can output pixel-level contours of targets to improve displacement measurement accuracy.

[0045] Displacement data extraction needs to solve the problem of image interference in complex water environments. Through the four-stage pipeline of "denoising-positioning-segmentation-calibration", data accuracy is gradually improved: Image preprocessing: Use polarization filters to eliminate water surface reflections and reduce image noise; apply the MOG2 algorithm to separate dynamic foreground (floating bridge, pontoon) from static background (water surface, sky). Dynamic background separation filters out interference from water surface fluctuations.

[0046] Target positioning: Input the preprocessed image into the EfficientDet model, output the bounding box coordinates of the pontoon and the pontoon; optimize the anchor frame design (3:1 aspect ratio for the pontoon and 1:1 for the pontoon) to improve positioning efficiency. Target detection locates the pontoon and pontoon areas.

[0047] Contour segmentation: Crop the target area based on the bounding box and input it into the Mask R-CNN model to generate a pixel-level mask; repair contour breaks or noise through morphological operations (dilation, erosion). Instance segmentation extracts precise contours.

[0048] Displacement calculation: Select fixed reference objects (such as mooring piles) at both ends of the floating bridge to calculate the proportional factor between the pixel and the actual distance; calculate the distance deviation (Δd) and angle deviation (Δθ) based on the center coordinates of the mask. Geometric calibration maps pixel displacement to physical quantities.

[0049] By combining computer vision and deep learning, automated, non-contact displacement monitoring is achieved, which is especially suitable for harsh water environments.

[0050] S3: Compare the real-time displacement data with the displacement data in the floating bridge response database to determine the final stress threshold: If the real-time displacement data is less than the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is used as the final stress threshold; If the real-time displacement data is greater than or equal to the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is corrected according to the real-time displacement data, water flow velocity, and vehicle load to obtain a final stress threshold; In some embodiments, the stress threshold in the floating bridge response database is modified according to the real-time displacement data, water flow velocity, and vehicle load to obtain the final stress threshold, see Figure 2 , including: S31: constructing a stress threshold correction model, taking the structural characteristic parameters of the floating bridge as basic variables, the real-time displacement data as correction variables, and the vehicle load and water flow velocity as reference variables, to establish the stress threshold correction model; the input of the stress threshold correction model includes the structural characteristic parameters of the floating bridge, the real-time displacement data, the water flow velocity, and the vehicle load, and the output is the final stress threshold; the structural characteristic parameters of the floating bridge are used to represent the structural characteristics of the floating bridge, including the length of the floating bridge; S32: Determine the correction coefficient, and perform fitting based on the finite element simulation data and the actual test data to determine the correction coefficient in the stress threshold correction model; Exemplarily, stress thresholds under different working conditions are generated based on finite element simulation data; real stress data are obtained through actual experiments (such as hydraulic laboratory loading tests); and the least squares method is used for fitting to minimize the error between the model prediction value and the measured value.

[0051] S33: According to the structural characteristic parameters of the floating bridge, the real-time displacement data, the water flow velocity, and the vehicle load, the stress threshold in the floating bridge response database is corrected through the stress threshold correction model to obtain a final stress threshold.

[0052] In some embodiments, the final stress threshold is calculated using the following formula:

[0053] Among them, σ corrected represents the final stress threshold after correction, which represents the safety stress value after dynamic adjustment according to real-time displacement, water flow velocity, and vehicle load; σ original represents the stress threshold in the floating bridge response database, which is the static stress value predetermined by finite element simulation; is the distance deviation in the real-time displacement data, reflecting the horizontal displacement of the pontoon relative to the floating bridge (unit: meter); L represents the length of the floating bridge in the structural characteristic parameters (unit: meter), representing the influence of the overall size of the floating bridge on the stress distribution; is the angle deviation in the real-time displacement data (unit: radian or degree), reflecting the inclination degree between the pontoon and the floating bridge; θ represents the angle between the pontoon and the floating bridge, usually the angle under the design or initial state (unit: radian or degree); α, β and γ are correction coefficients, which are obtained by fitting the finite element simulation data and the actual test data, and are used to adjust the weights of different parameters on the final stress threshold; P represents the vehicle load (unit: kilonewton or ton), which represents the real-time load of the vehicle on the floating bridge; P max It represents the maximum vehicle load (unit: kN or ton), which is determined according to the design carrying capacity of the floating bridge; V represents the water velocity (unit: m / s), which reflects the dynamic influence of the water flow in the water area where the floating bridge is located; V max Indicates the maximum water flow velocity (unit: m / s), a threshold value set based on the flow resistance of the floating bridge structure.

[0054] The length L of the pontoon is a key structural parameter. A longer pontoon may generate a larger bending moment at the same displacement, thus affecting the stress distribution. When the real-time displacement data (Δd and Δθ) exceeds the preset threshold, it means that there is a large change in the connection between the pontoon and the pontoon, which may lead to stress redistribution inside the structure. For example, a large distance deviation Δd may cause tension or compression of the pontoon, while an angle deviation Δθ may lead to increased torsion or shear stress.

[0055] Next, the water velocity V affects the hydrodynamic loads on the pontoon. Higher flow velocities increase the lateral forces on the pontoon, which may cause structural vibration or deflection, thus affecting the stress. The vehicle load P is a dynamic load, and different vehicle weights and distributions will directly change the local stress of the pontoon. When the vehicle load is close to the maximum vehicle load P max When the original stress threshold is adjusted, it may not be sufficient to cope with the actual working conditions and needs to be adjusted dynamically.

[0056] The correction terms in the formula take these factors into account: α combines the relative effects of distance deviation and vehicle load, β relates to angle deviation and water velocity, and γ deals with the cross-effect of the two. The correction coefficients α, β, and γ are determined through finite element simulation and actual data fitting to ensure the theoretical reliability and practicality of the model.

[0057] Therefore, the revised model can dynamically reflect the complex stress conditions under actual working conditions by integrating structural parameters, real-time displacement, environmental loads and dynamic loads. When the real-time displacement data is greater than or equal to the displacement data in the floating bridge response database, the system automatically adjusts the stress threshold, avoiding the shortcomings of the traditional static model, ensuring the accuracy and timeliness of the safety assessment, and thus significantly improving the safety of the floating bridge.

[0058] The formula combines the real-time displacement deviation (Δd, Δθ), vehicle load (P / PmaxP) and water velocity (V / V max ), dynamically correct the original stress threshold (σ original ), so that the corrected stress threshold (σ corrected ) is more in line with actual working conditions, thereby improving the accuracy of floating bridge safety monitoring.

[0059] Correction coefficient α: quantifies the coupling effect of distance deviation and vehicle load on stress. Correction coefficient β: quantifies the coupling effect of angle deviation and water velocity on stress. Correction coefficient γ: combines the interaction of distance deviation and angle deviation to capture the nonlinear effect under complex displacement.

[0060] S4: Perform safety monitoring on the offshore floating bridge based on the final stress threshold.

[0061] On the other hand, the present application also provides a safety monitoring system for an offshore floating bridge, which implements any of the above-mentioned safety monitoring methods for an offshore floating bridge, and the system comprises: A floating bridge response database construction module is used to obtain stress thresholds at different positions of the floating bridge when different vehicles travel on the floating bridge under different displacement conditions of the pontoon and the floating bridge through a finite element simulation method, and to construct a floating bridge response database; A real-time displacement data acquisition module is used to acquire real-time images of the pontoon and the floating bridge, and analyze the real-time displacement data of the pontoon and the floating bridge from the real-time images, wherein the real-time displacement data includes the distance deviation and angle deviation between the pontoon and the floating bridge; The final stress threshold acquisition module is used to compare the real-time displacement data with the displacement data in the floating bridge response database: If the real-time displacement data is less than the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is used as the final stress threshold; If the real-time displacement data is greater than or equal to the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is corrected according to the real-time displacement data, water flow velocity, and vehicle load to obtain a final stress threshold; The safety monitoring module is used to perform safety monitoring on the offshore floating bridge based on the final stress threshold.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring the safety of an offshore floating bridge, characterized in that: The steps include: S1: The stress thresholds of different vehicles at different positions of the floating bridge under different displacement conditions of the pontoon and the floating bridge are obtained by finite element simulation method, and a floating bridge response database is constructed; S2: acquiring real-time images of the pontoon and the floating bridge, and analyzing the real-time images to obtain real-time displacement data of the pontoon and the floating bridge, wherein the real-time displacement data includes a distance deviation and an angle deviation between the pontoon and the floating bridge; S3: Compare the real-time displacement data with the displacement data in the floating bridge response database to determine the final stress threshold: If the real-time displacement data is less than the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is used as the final stress threshold; If the real-time displacement data is greater than or equal to the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is corrected according to the real-time displacement data, water flow velocity, and vehicle load to obtain a final stress threshold; S4: Perform safety monitoring on the offshore floating bridge based on the final stress threshold.

2. A method for monitoring safety of an offshore floating bridge according to claim 1, characterized in that: According to the real-time displacement data, water velocity, and vehicle load, the stress threshold in the floating bridge response database is corrected to obtain the final stress threshold, including: S31: constructing a stress threshold correction model, taking the structural characteristic parameters of the floating bridge as basic variables, the real-time displacement data as correction variables, and the vehicle load and water flow velocity as reference variables, to establish the stress threshold correction model; the input of the stress threshold correction model includes the structural characteristic parameters of the floating bridge, the real-time displacement data, the water flow velocity, and the vehicle load, and the output is the final stress threshold; the structural characteristic parameters of the floating bridge are used to represent the structural characteristics of the floating bridge, including the length of the floating bridge; S32: Determine the correction coefficient, and perform fitting based on the finite element simulation data and the actual test data to determine the correction coefficient in the stress threshold correction model; S33: According to the structural characteristic parameters of the floating bridge, the real-time displacement data, the water flow velocity, and the vehicle load, the stress threshold in the floating bridge response database is corrected through the stress threshold correction model to obtain a final stress threshold.

3. A method for monitoring safety of an offshore floating bridge according to claim 2, characterized in that: The final stress threshold is calculated using the following formula: ； Among them, σ corrected represents the final stress threshold after correction, σ original represents the stress threshold in the floating bridge response database, is the distance deviation in the real-time displacement data, is the angle deviation in the real-time displacement data, L is the length of the pontoon in the structural characteristic parameters, θ is the angle between the pontoon and the pontoon, α, β and γ are correction coefficients, P is the vehicle load, and P max represents the maximum vehicle load, V represents the water velocity, V max Indicates the maximum water flow velocity.

4. A method for monitoring safety of an offshore floating bridge according to claim 1, characterized in that: The real-time displacement data of the pontoon and the floating bridge are obtained by analyzing the real-time image, including: S21: performing denoising processing on the real-time image using the MOG2 algorithm; S22: using EfficientDet to determine the bounding box coordinates of the floating bridge and the pontoon in the real-time image after the denoising process; and intercepting the images of the floating bridge and the pontoon area according to the bounding box coordinates; S23: Based on the images of the floating bridge and the pontoon area, using the Mask R-CNN model, separate them from the real-time image to obtain pixel-level contour masks of the floating bridge and the pontoon; S24: determining the final images of the floating bridge and the pontoon through a transfer learning model according to the pixel-level contour masks of the floating bridge and the pontoon; S25: Based on the selected reference object, determine the real-time displacement data of the pontoon and the pontoon in the final image of the pontoon and the pontoon.

5. A method for monitoring safety of an offshore floating bridge according to claim 4, characterized in that: In S25, based on the selected reference object, in the final image of the floating bridge and the pontoon, the real-time displacement data of the pontoon and the floating bridge is determined, specifically: S251: respectively obtaining the actual size of the selected reference object and the pixel spacing in the final image of the floating bridge and the pontoon; S252: Calculating a scale factor based on the actual size and the pixel pitch; S253: respectively obtaining coordinates of the pontoon and the floating bridge in the final images of the floating bridge and the pontoon; S254: Based on the scale factor, determine the real-time displacement data of the pontoon and the floating bridge according to the coordinates of the pontoon and the floating bridge in the final image of the floating bridge and the pontoon.

6. A method for monitoring safety of an offshore floating bridge according to claim 5, characterized in that: The calculation formula for the real-time displacement data of the pontoon and the floating bridge is: ； ； in, is the distance deviation in the real-time displacement data, is the angle deviation in real-time displacement data, k is the scale factor, x 趸船 is the x-axis coordinate of the pontoon in the final image of the pontoon and the pontoon, and y is 趸船 is the y-axis coordinate of the pontoon in the final image of the pontoon and the pontoon, x 浮桥 is the x-axis coordinate of the pontoon in the final image of the pontoon and the pontoon, and y is the 浮桥 is the y-axis coordinate of the pontoon in the final image of the pontoon and the barge.

7. A method for monitoring safety of an offshore floating bridge according to claim 5, characterized in that: The scaling factor k is calculated using the following formula: ； Among them, L real Indicates the actual size of the selected reference object, L pixel Represents the pixel spacing of the selected reference objects in the final images of the pontoon and barge.

8. A method for monitoring safety of an offshore floating bridge according to claim 4, characterized in that: After the denoising process is performed in S21, the process further includes performing distortion correction on the lens of the image acquisition device.

9. A safety monitoring system for an offshore floating bridge, which implements the safety monitoring method for an offshore floating bridge according to any one of claims 1 to 8, characterized in that: The system comprises: A floating bridge response database construction module is used to obtain stress thresholds at different positions of the floating bridge when different vehicles travel on the floating bridge under different displacement conditions of the pontoon and the floating bridge through a finite element simulation method, and to construct a floating bridge response database; A real-time displacement data acquisition module is used to acquire real-time images of the pontoon and the floating bridge, and analyze the real-time displacement data of the pontoon and the floating bridge from the real-time images, wherein the real-time displacement data includes the distance deviation and angle deviation between the pontoon and the floating bridge; The final stress threshold acquisition module is used to compare the real-time displacement data with the displacement data in the floating bridge response database: If the real-time displacement data is less than the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is used as the final stress threshold; If the real-time displacement data is greater than or equal to the displacement data in the floating bridge response database, the stress threshold in the floating bridge response database is corrected according to the real-time displacement data, water flow velocity, and vehicle load to obtain a final stress threshold; The safety monitoring module is used to perform safety monitoring on the offshore floating bridge based on the final stress threshold.

Images