A method, system and device for real-time prediction of scour pit shape of a water-based pile foundation

Abstract

The application discloses a real-time prediction method, system and equipment for a scour pit shape of a pile foundation on water, and relates to the field of scour pit shape prediction. The method comprises the following steps: determining a layout direction according to the diameter of the pile foundation and application requirements; laying multiple sensors at a set distance apart in each layout direction; in each layout direction, monitoring the water bottom depth away from the pile foundation position by using a monitoring ship or an underwater robot carrying the sensors; acquiring monitoring data of the sensors in each layout direction; establishing a GM(1, 1) grey model corresponding to the layout direction by using a grey system theory; determining the GM(1, 1) grey model completed by iteration in the corresponding layout direction according to the water bottom depth in each layout direction; and determining the shape of the scour pit in the corresponding layout direction by using the GM(1, 1) grey model completed by iteration and real-time monitoring data in the corresponding layout direction. The application can improve the real-time performance and efficiency of the scour pit shape prediction.

Description

Technical Field

[0001] This invention relates to the field of scour pit morphology prediction, and in particular to a method, system and equipment for real-time prediction of scour pit morphology in underwater pile foundations. Background Technology

[0002] Bridges, as lifeline engineering projects, must withstand various natural disasters. Among the many factors contributing to bridge disasters, pile foundation scour is one of the main causes of bridge damage. Most bridge flooding is due to scour reducing the foundation depth, leading to a significant decrease in the pile foundation's bearing capacity. Pile foundation scour is catastrophic; flooded bridge damage will disrupt road traffic, hinder the delivery of relief supplies, and cause enormous losses to people's lives and property. With the increasing number of bridges spanning rivers and seas, the problem of bridge pile foundation scour is becoming more severe. Therefore, effectively obtaining the morphology of bridge pile foundation scour pits and ensuring they remain within a safe and controllable range is an urgent problem to be solved.

[0003] Since the 1950s, with the development of fluid dynamics and mathematics, the problem of bridge foundation scour has received widespread research attention both at home and abroad. Various calculation methods for scour pits have been gradually developed. Since the 1970s, research on the morphology of scour pits using prediction methods has emerged. However, most existing methods for obtaining the morphology of scour pits rely on surveying techniques.

[0004] Compared to using surveying techniques to obtain the morphology of scour pits, predicting the morphology of scour pits through a few monitoring points can significantly save manpower and material resources and quickly obtain the scour pit morphology. However, existing prediction methods are all static and lack a mechanism to update existing models or make further predictions using real-time monitoring data. To address these needs, there is an urgent need to provide a new real-time prediction method for the morphology of scour pits in underwater pile foundations, capable of predicting the scour pit morphology through real-time monitoring data. Summary of the Invention

[0005] The purpose of this invention is to provide a method, system, and device for real-time prediction of scour pit morphology in underwater pile foundations, which can improve the real-time performance and efficiency of scour pit morphology prediction.

[0006] To achieve the above objectives, the present invention provides the following solution:

[0007] A method for real-time prediction of scour pit morphology in underwater pile foundations includes:

[0008] The layout direction is determined based on the diameter of the pile foundation and the application requirements; each layout direction is on a circle with the center of each underwater pile foundation as the center, and the intervals are set at angles.

[0009] Multiple sensors are deployed at predetermined intervals in each deployment direction;

[0010] In each deployment direction, a monitoring vessel or underwater robot carrying sensors is used to monitor the underwater depth far from the pile foundation location;

[0011] Acquire monitoring data from sensors in each deployment direction; and establish a GM(1,1) grey model for the corresponding deployment direction using grey system theory.

[0012] The GM(1,1) gray model iteratively completed in each deployment direction is determined based on the underwater depth in each deployment direction.

[0013] The shape of the scour pit in the corresponding layout direction is determined by using the iteratively completed GM(1,1) gray model and real-time monitoring data in the corresponding layout direction.

[0014] Optionally, determining the iteratively completed GM(1,1) gray model for each deployment direction based on the underwater depth specifically includes:

[0015] The predicted value generated by the GM(1,1) grey model is used as input to iteratively update the grey model. If the predicted value of the iteratively updated GM(1,1) grey model is consistent with the bottom depth in the corresponding deployment direction, the iterative update is completed; if not, the predicted value of the iteratively updated GM(1,1) grey model is used as input again to continue iterative updates until the predicted value is consistent with the bottom depth in the corresponding deployment direction.

[0016] Optionally, determining the layout direction based on the diameter of the pile foundation and application requirements specifically includes:

[0017] When the diameter of the pile foundation is 5m or less, four layout directions are determined;

[0018] When the diameter of the pile foundation is 5m-10m, determine 4-8 layout directions;

[0019] When the diameter of the pile foundation is 10m or more, eight layout directions are determined.

[0020] Optionally, the deployment of multiple sensors at predetermined intervals in each deployment direction specifically includes:

[0021] In each deployment direction, a fixed rod is installed at a fixed height underwater, and sensors are installed on the fixed rod at the same set intervals.

[0022] Optionally, the length of the fixing rod is less than 2.5m.

[0023] Optionally, the step of determining the shape of the scour pit in the corresponding deployment direction using the iteratively completed GM(1,1) gray model and real-time monitoring data in the corresponding deployment direction further includes:

[0024] If the monitoring time of the monitoring vessel or underwater robot exceeds the set effective prediction time, the underwater depth far from the pile foundation location will be re-monitored using the monitoring vessel or underwater robot.

[0025] The GM(1,1) gray model in the corresponding deployment direction is updated by using the re-monitored bottom depth.

[0026] A real-time prediction system for the morphology of scour pits in underwater pile foundations includes:

[0027] The deployment direction determination module is used to determine the deployment direction based on the diameter of the pile foundation and application requirements; each deployment direction is on a circle centered at the center of each underwater pile foundation, with a set angle as the interval.

[0028] The sensor deployment module is used to deploy multiple sensors at predetermined intervals in each deployment direction.

[0029] The underwater depth monitoring module is used to monitor the underwater depth far from the pile foundation location in each deployment direction using a monitoring vessel or underwater robot carrying sensors.

[0030] The GM(1,1) grey model building module is used to acquire the monitoring data of the sensors in each deployment direction; and to build the GM(1,1) grey model in the corresponding deployment direction using grey system theory.

[0031] The GM(1,1) gray model iterative update module is used to determine the GM(1,1) gray model iteratively completed in the corresponding deployment direction based on the water depth in each deployment direction.

[0032] The real-time shape prediction module for scour pits is used to determine the shape of scour pits in the corresponding layout direction using the iteratively completed GM(1,1) gray model and real-time monitoring data in the corresponding layout direction.

[0033] A device for real-time prediction of the morphology of scour pits in underwater pile foundations includes: at least one processor, at least one memory, and computer program instructions stored in the memory. When the computer program instructions are executed by the processor, the method for real-time prediction of the morphology of scour pits in underwater pile foundations is implemented.

[0034] Optionally, the memory is a computer-readable storage medium.

[0035] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0036] This invention provides a method, system, and device for real-time prediction of scour pit morphology in underwater pile foundations. By deploying a small number of sensors around the pile foundation, and only during the model building phase requiring the use of a monitoring vessel (or underwater robot) to monitor scour conditions far from the pile foundation, the scour pit morphology can be predicted in real time using an iterative GM(1,1) model method, saving significant manpower and material costs. Furthermore, only the direction of underwater sensor deployment and the number of sensors required in each direction need to be determined based on the pile foundation diameter and specific application requirements, eliminating the need to manually specify numerous parameters and reducing the influence of human factors on the prediction results. This invention innovatively uses the prediction results of the previous iteration as input data for the next iteration, ultimately providing a prediction method that can predict scour pit morphology based on real-time monitoring data. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 A schematic diagram of the real-time prediction method for the morphology of scour pits in underwater pile foundations provided by the present invention.

[0039] Figure 2 This is a schematic diagram showing the four deployment directions;

[0040] Figure 3 A schematic diagram showing the eight deployment directions;

[0041] Figure 4 A schematic diagram illustrating the use of a monitoring vessel / underwater robot for depth monitoring;

[0042] Figure 5 A schematic diagram of the GM(1,1) grey model after multiple iterations and updates. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] The purpose of this invention is to provide a method, system, and device for real-time prediction of scour pit morphology in underwater pile foundations, which can improve the real-time performance and efficiency of scour pit morphology prediction.

[0045] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0046] like Figure 1 As shown, the present invention provides a method for real-time prediction of the morphology of scour pits in underwater pile foundations, comprising:

[0047] S101, Determine the layout direction according to the diameter of the pile foundation and the application requirements; Each layout direction is on a circle with the center of each pile foundation underwater as the center, and at intervals of a set angle.

[0048] like Figure 2 As shown, when the diameter of the pile foundation is 5m or less, four layout directions are determined.

[0049] When the diameter of the pile foundation is 5m-10m, determine 4-8 layout directions.

[0050] like Figure 3 As shown, when the diameter of the pile foundation is 10m or more, eight layout directions are determined.

[0051] S102, multiple sensors are deployed at predetermined intervals in each deployment direction; multiple (more than 3) sensors are deployed at fixed intervals in each direction. The sensors are depth sensors.

[0052] In each deployment direction, a fixed pole is installed at a fixed height underwater, and sensors are installed on the fixed pole at equal predetermined intervals. The depth corresponding to the location of the sensor is measured. To allow normal passage for vessels, the length of the fixed pole is less than 2.5m.

[0053] Generally, the larger the pile diameter, the more directions of sensors need to be deployed for the pile; the higher the required prediction accuracy, the more directions need to be deployed and the more sensors are needed in each direction.

[0054] S103, in each deployment direction, using a monitoring vessel or underwater robot carrying sensors, monitors the underwater depth far from the pile foundation location, and as... Figure 4 As shown;

[0055] Record the distance from the location to the pile foundation and the corresponding depth (preprocess the depth data to keep it consistent with the sensor reference installed on the fixed rod).

[0056] S104, acquire the monitoring data of the sensor in each deployment direction; and establish the GM(1,1) grey model in the corresponding deployment direction using grey system theory;

[0057] S105, determine the GM(1,1) gray model iteratively completed in each deployment direction based on the underwater depth, and as follows: Figure 5As shown;

[0058] S105 specifically includes:

[0059] The predicted value generated by the GM(1,1) grey model is used as input to iteratively update the grey model. If the predicted value of the iteratively updated GM(1,1) grey model is consistent with the bottom depth in the corresponding deployment direction, the iterative update is completed; if not, the predicted value of the iteratively updated GM(1,1) grey model is used as input again to continue iterative updates until the predicted value is consistent with the bottom depth in the corresponding deployment direction.

[0060] Specifically, in the i-th iteration calculation, let the data sequence be...

[0061] To obtain the data sequence of equidistant scour pit depths for real-time monitoring, For sequence 1-AGO sequence (single-accumulation sequence):

[0062]

[0063] in make

[0064] in make This is the mean form of the GM(1,1) model, which is essentially a difference equation. Here, -a is the development coefficient, and b is the grey effect. Parameter vector.

[0065] The least squares method can be used for estimation:

[0066]

[0067] Where Y and B are respectively:

[0068]

[0069] The whitening differential equation for the mean-form GM(1,1) model is:

[0070]

[0071] Its time response is:

[0072]

[0073] The cumulative reduction equation and time response equation of the mean-form GM(1,1) model can be expressed as follows:

[0074]

[0075]

[0076] Establish the corresponding GM(1,1) model and calculate the development coefficient -a and the gray action amount b. Using the k value corresponding to the distance, the predicted value of the scour pit depth can be calculated using the cumulative reduction formula.

[0077] In the i-th iteration, the predicted depth of the scour pit at the corresponding distance is calculated using a data sequence of m data. If the predicted depth of the scour pit at the corresponding distance is consistent with the depth data measured by the monitoring vessel (or underwater robot), the iteration stops and the iteration number n = i is recorded. Otherwise, the first m+1 predicted data obtained in this iteration are used as the input sequence for the (i+1)-th iteration.

[0078] S106. The shape of the scour pit in the corresponding layout direction is determined by using the iteratively completed GM(1,1) gray model and the real-time monitoring data in the corresponding layout direction.

[0079] Specifically, when real-time depth data is detected, the first iteration calculation is performed using the detected data. Then, the predicted data obtained from the previous iteration calculation is used as the input sequence for the next iteration, until the number of iterations is n. The predicted value of this calculation is then used to predict the morphology of the scour pit.

[0080] This invention deploys a small number of sensors around the pile foundation. Only during the model building stage is a monitoring vessel (or underwater robot) needed to monitor the scour conditions far from the pile foundation. The morphology of the scour pit is predicted by an iterative GM(1,1) model method.

[0081] Following S106 are:

[0082] If the monitoring time of the monitoring vessel or underwater robot exceeds the set effective prediction time, the underwater depth far from the pile foundation location will be re-monitored using the monitoring vessel or underwater robot.

[0083] The GM(1,1) gray model in the corresponding deployment direction is updated by using the re-monitored bottom depth.

[0084] Corresponding to the above method, the present invention also provides a real-time prediction system for the morphology of scour pits in underwater pile foundations, comprising:

[0085] The deployment direction determination module is used to determine the deployment direction based on the diameter of the pile foundation and application requirements; each deployment direction is on a circle centered at the center of each underwater pile foundation, with a set angle as the interval.

[0086] The sensor deployment module is used to deploy multiple sensors at predetermined intervals in each deployment direction.

[0087] The underwater depth monitoring module is used to monitor the underwater depth far from the pile foundation location in each deployment direction using a monitoring vessel or underwater robot carrying sensors.

[0088] The GM(1,1) grey model building module is used to acquire the monitoring data of the sensors in each deployment direction; and to build the GM(1,1) grey model in the corresponding deployment direction using grey system theory.

[0089] The GM(1,1) gray model iterative update module is used to determine the GM(1,1) gray model iteratively completed in the corresponding deployment direction based on the water depth in each deployment direction.

[0090] The real-time shape prediction module for scour pits is used to determine the shape of scour pits in the corresponding layout direction using the iteratively completed GM(1,1) gray model and real-time monitoring data in the corresponding layout direction.

[0091] In order to execute the methods corresponding to the above embodiments and achieve the corresponding functions and technical effects, the present invention also provides a real-time prediction device for the morphology of scour pits in water-based pile foundations, characterized in that it includes: at least one processor, at least one memory, and computer program instructions stored in the memory, wherein when the computer program instructions are executed by the processor, the real-time prediction method for the morphology of scour pits in water-based pile foundations is implemented.

[0092] The memory is a computer-readable storage medium.

[0093] Based on the above description, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned computer storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0094] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to the method section.

[0095] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for real-time prediction of the morphology of scour pits in underwater pile foundations, characterized in that, include: The layout direction is determined based on the diameter of the pile foundation and the application requirements; each layout direction is on a circle with the center of each underwater pile foundation as the center, and the intervals are set at angles. Multiple sensors are deployed at predetermined intervals in each deployment direction; In each deployment direction, a monitoring vessel or underwater robot carrying sensors is used to monitor the underwater depth far from the pile foundation location; Acquire the monitoring data of the sensors in each deployment direction; and establish the GM(1,1) grey model in the corresponding deployment direction using grey system theory; The GM(1,1) gray model iteratively completed in each deployment direction is determined based on the underwater depth in each deployment direction. The shape of the scour pit in the corresponding deployment direction is determined by using the iteratively completed GM(1,1) gray model and real-time monitoring data in the corresponding deployment direction. The process of determining the iteratively completed GM(1,1) gray model for each deployment direction based on the underwater depth in each deployment direction specifically includes: The predicted value generated by the GM(1,1) grey model is used as input to iteratively update the grey model. If the predicted value of the iteratively updated GM(1,1) grey model is consistent with the bottom depth in the corresponding deployment direction, the iterative update is completed; if not, the predicted value of the iteratively updated GM(1,1) grey model is used as input again to continue iterative updates until the predicted value is consistent with the bottom depth in the corresponding deployment direction.

2. The method for real-time prediction of scour pit morphology in underwater pile foundations according to claim 1, characterized in that, The determination of the layout direction based on the diameter of the pile foundation and application requirements specifically includes: When the diameter of the pile foundation is 5m or less, four layout directions are determined; When the diameter of the pile foundation is 5m-10m, determine 4-8 layout directions; When the diameter of the pile foundation is 10m or more, eight layout directions are determined.

3. The method for real-time prediction of scour pit morphology in underwater pile foundations according to claim 1, characterized in that, The deployment of multiple sensors at predetermined intervals in each deployment direction specifically includes: In each deployment direction, a fixed rod is installed at a fixed height underwater, and sensors are installed on the fixed rod at the same set intervals.

4. The method for real-time prediction of scour pit morphology in underwater pile foundations according to claim 3, characterized in that, The length of the fixing rod is less than 2.5m.

5. The method for real-time prediction of scour pit morphology in underwater pile foundations according to claim 1, characterized in that, The process of determining the shape of scour pits in the corresponding deployment direction using the iteratively completed GM(1,1) gray model and real-time monitoring data in the corresponding deployment direction further includes: If the monitoring time of the monitoring vessel or underwater robot exceeds the set effective prediction time, the underwater depth far from the pile foundation location will be re-monitored using the monitoring vessel or underwater robot. The GM(1,1) gray model in the corresponding deployment direction is updated by using the re-monitored bottom depth.

6. A real-time prediction system for the morphology of scour pits in underwater pile foundations, used to implement the real-time prediction method for the morphology of scour pits in underwater pile foundations as described in any one of claims 1-5, characterized in that, include: The layout direction determination module is used to determine the layout direction based on the diameter of the pile foundation and application requirements; Each layout direction is on a circle centered at the center of each underwater pile foundation, with a set angle as the interval; The sensor deployment module is used to deploy multiple sensors at predetermined intervals in each deployment direction. The underwater depth monitoring module is used to monitor the underwater depth far from the pile foundation location in each deployment direction using a monitoring vessel or underwater robot carrying sensors. The GM(1,1) grey model building module is used to acquire the monitoring data of the sensors in each deployment direction; and to build the GM(1,1) grey model in the corresponding deployment direction using grey system theory. The GM(1,1) gray model iterative update module is used to determine the GM(1,1) gray model iteratively completed in the corresponding deployment direction based on the bottom depth in each deployment direction. The real-time shape prediction module for scour pits is used to determine the shape of scour pits in the corresponding layout direction using the iteratively completed GM(1,1) gray model and real-time monitoring data in the corresponding layout direction.

7. A device for real-time prediction of the morphology of scour pits in underwater pile foundations, characterized in that, include: The method comprises at least one processor, at least one memory, and computer program instructions stored in the memory, wherein when the computer program instructions are executed by the processor, a real-time prediction method for the morphology of scour pits in underwater pile foundations as described in any one of claims 1-5 is implemented.

8. The real-time prediction device for the morphology of scour pits in underwater pile foundations according to claim 7, characterized in that, The memory is a computer-readable storage medium.

Images