Smart silt removal method and control system based on water depth changes

Abstract

This invention relates to the technology of silt prevention and removal, and more specifically to a smart silt removal method and control system in response to changes in water depth. When removing silt from a shipping channel, the invention first segments the channel, then classifies the channel segments according to the water depth of each segment, and applies a smart silt removal method to the channel according to the floating type of channel. In particular, for the first type of channel, due to the characteristic that silt easily settles in the segment, a support vector machine is used to combine the channel's position and past silt accumulation amounts to achieve accurate and effective smart prediction of the silt removal depth. For the second type of channel, due to the characteristic that silt accumulation is less likely to occur, a fixed pattern is adopted to determine the channel silt removal plan, and through the plan of this invention, the targetability and efficiency of establishing the silt removal method can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of silt prevention and removal, and specifically to a smart silt removal method and control system based on water depth changes.

Background Art

[0002] The deposition of mud and sand weakens the flood discharge capacity of the estuary, affects the upstream drainage and irrigation environment, deteriorates the downstream navigation conditions, threatens the normal operation of the sluice, and the deposition occurring in front of the wharf, harbor and waterway affects the entry and departure of ships at the wharf and the transportation efficiency, hindering the economic development. In addition, severe mud and sand deposition increases the later operation cost, the silt deposition between columns affects the structural safety of high-column wharves, frequent silt removal also affects ship berthing, and a reasonable and standardized silt reduction plan must be established to reduce the deposition intensity during the operation period to ensure the safety of ship entry, departure and berthing.

[0003] In the prior art, when removing silt in a harbor and wharf, generally a dredger or a hopper dredger and other devices are used to perform dredging to complete silt removal. After dredging, the dredged silt is transferred to a designated area and discarded. However, when removing silt in such a way, long-distance silt dumping is required, resulting in a decrease in the efficiency of silt removal, restricting the normal operation of the harbor and wharf areas and ensuring the normal operation of navigation safety and construction safety. Therefore, the silt removal operation cannot proceed continuously and silt removal must be carried out at certain time intervals, so automatic silt removal and prevention cannot be continuous, and there is a lack of effective defensive ability against mud and sand deposition during the daily operation of the harbor and wharf.

[0004] Conventional technologies include solutions for smart silt removal in shipping lanes. For example, a Chinese invention patent (CN116844065A) discloses a GIS-based smart identification and management method for shipping silt removal. This method collects shipping silt images based on GIS technology, performs preprocessing and incremental feature extraction to obtain features of the shipping silt images, optimally solves them for a sophisticated silt type identification model constructed using an improved L-BFGS algorithm, inputs the extracted features of the shipping silt images into the optimal sophisticated silt type identification model, the model outputs the corresponding silt identification type, and manages the shipping silt based on the identified silt identification type. The present invention converts a navigation silt image to a floating scale, displays edge pixels at the floating scale, achieves multi-scale edge extraction and image segmentation, extracts the spatial characteristics of the navigation silt image in a progressive manner to identify silt, and further performs navigation silt management by combining silt types with navigation areas corresponding to floating image blocks. However, the above method cannot identify navigation types during the process of smart silt removal of navigation routes, the computational load is large in the process of probing the overall silt removal plan, it is not efficient, and the targeting is not high. [Overview of the project] [Problems that the invention aims to solve]

[0005] The object of the present invention is to provide a channel silt removal method and control system based on water depth changes to improve the targetability and efficiency of channel silt removal.

[0006] To solve the technical problems mentioned above, the present invention specifically provides the following technical solutions. [Means for solving the problem]

[0007] The smart silt removal method based on water depth changes includes the following steps:

[0008] S1: Obtain the water depth of the silt removal channel, S2: The aforementioned route is segmented, and the route is divided into n segments, each of which is S1, S2, ..., Sn. S3: Obtain the minimum water depth for each section of the route. S4: Classify the sections of each route according to the minimum water depth and obtain the route section type. If the route section is of route type 1, proceed to S5. If the route section is of route type 2, proceed to S6. S5: Silt removal will be carried out on the section of the route using the first silt removal plan, Specifically, S5 means, S5.1: Obtain the location type of the section of the channel, the annual sedimentation volume of the section of the channel, the average depth, and the minimum depth. S5.2: Construct a silt removal depth prediction model, S5.3: Obtain a dataset for training the support vector machine model, S5.4: Train a support vector machine model using the aforementioned dataset. S5.5: The location type of the channel section, the annual sedimentation volume of the channel section, the average water depth, and the minimum water depth obtained in S5.1 are input into the support vector machine model to predict the silt removal depth of the channel section and realize smart silt removal of the channel section. S: Silt removal will be carried out in the section of the route using the second silt removal plan.

[0009] Preferably, S1 is specifically as follows:

[0010] S1.1: Arrange the measurement line, S1.2: Navigation positioning is performed via a GNSS receiver or CORS technology. S1.3: Perform sound velocity calibration, S1.4: Observe the tide level, S1.5 External field data collection is performed. Prepare the S1.6 drawing.

[0011] Preferably, S1.1 specifically involves arranging the measurement lines at 2 cm intervals along the shipping lane, with a higher density in coastal areas, and immediately performing supplemental measurements in uncovered areas or areas that do not meet the coverage requirements. Specifically, S1.2 involves performing navigation positioning using GNSS-RTK or CORS, setting up a mobile station, receiving differential signals transmitted by a coastal reference station via a radio broadcasting station, and performing real-time navigation with centimeter-level accuracy. Specifically, S1.3 involves using a sound velocity profiler to measure the speed of sound before, during, and after measuring the water depth, and performing sound velocity calibration for water depth at different time points according to the measured speed of sound. Specifically, S1.4 involves placing one temporary tidal level observation station within the measurement area where the shipping lane is located, and correcting the tidal level during the depth measurement period using a single base station correction method. Specifically, S1.5 involves directing a command line along the positioned measurement line to measure along the measurement line until the entire measurement area is covered, completing the measurement coverage of the measurement line, and deriving the recorded data. Specifically, S1.6 involves post-processing the data collected in S1.5 to generate a digital linear diagram, drawing contour lines, and then using Southern CASS 10.1 version drafting software to create a drawing legend according to the specifications, with the basic contour distance being 1m and the altitude being indicated in decimeters.

[0012] Preferably, the route is divided into n sections in a manner that divides it equally according to distance.

[0013] Preferably, if the minimum water depth of the classification target route in S4 is less than the set threshold, it is classified as a first route type, and if the minimum water depth of the route to be classified is equal to or greater than the set threshold, it is classified as a second route type.

[0014] Preferably, in S4, the setting threshold is 14.5 km.

[0015] Preferably, in the step S5.2, the silt removal depth prediction model is a support vector machine model, the kernel function of the support vector machine is a linear kernel function, and the penalty coefficient of the support vector machine is 0.09.

[0016] Preferably, in the step S5.4, it is determined whether the support vector machine model is trained through accuracy, precision, recall rate, and F1 value.

[0017] Preferably, in the step S6, the second silt removal plan is to set the water depth of the section of the route to 20 km.

[0018] According to still another aspect of the present invention, there is provided a smart silt removal method and control system based on water depth change, the control system uses the smart silt removal method based on the water depth change mentioned above, and the control system A water depth acquisition module for acquiring the water depth of the route for silt removal; A route segmentation module that segments the route, divides the route into n segments, which are S1, S2,...., Sn respectively; A minimum water depth acquisition module for acquiring the minimum water depth of each section of the route; A route classification model that classifies each section of the route according to the minimum water depth to obtain the section type of the route. If the section of the route is the first route type, it enters the first silt removal plan control module. If the section of the route is the second route type, it enters the second silt removal plan control module; A first silt removal plan control module that uses the first silt removal plan to remove silt from the section of the route; A second silt removal plan control module that uses the second silt removal plan to perform silt removal on the section of the route.

Advantages of the Invention

[0019] The present invention has the following beneficial effects compared with the prior art.

[0020] When performing channel silt removal, after first performing segment processing on the channel, classification is performed on each segment of the channel according to the water depth of the segment of the channel, and different channel smart silt removal methods are adopted for the floating types of the channels. In particular, in the case of the first channel type, due to the characteristic that the silt of the segment of the channel is easily deposited, by combining the position of the channel and the past sediment deposition amount of mud and sand through a support vector machine, accurate and effective smart prediction of the silt removal depth can be realized.

[0021] Also, due to the characteristic that silt deposition of the second channel type is not likely to occur, a fixed pattern is used to determine the channel silt removal plan, and according to the plan of the present invention, the targeting and efficiency of formulating the silt removal method can be improved.

Brief Description of the Drawings

[0022] To more clearly explain the embodiments of the present invention or the technical solutions of the prior art, the following attached drawings necessary for explaining the following embodiments or the prior art are briefly introduced. Of course, the attached drawings described below are merely illustrative, and for those of ordinary skill in the art, without creative labor, other implementation drawings can be obtained by expanding the provided attached drawings.

[0023] [Figure 1] It is a flowchart of the smart silt removal method based on the water depth change provided by the embodiment of the present invention. [Figure 2] It is a flowchart for obtaining the water depth of the silt removal channel provided by the embodiment of the present invention. [Figure 3] It is a flowchart for performing silt removal on the segment of the channel using the first silt removal plan provided by the embodiment of the present invention.

Modes for Carrying Out the Invention

[0024] The following will clearly and completely describe the technical solutions of the embodiments of the present invention in conjunction with the accompanying drawings of the embodiments of the present invention, and of course the embodiments described are not all embodiments but only a part of the embodiments of the present invention. All other embodiments obtained by a general expert in the art without creative work based on the embodiments of the present invention are within the scope of the protection of the present invention.

[0025] The following sections will first describe the concepts related to this application by combining the attached drawings. It should be noted that the following explanations of each concept are merely for the purpose of making the content of this application easier to understand and do not impose any limitations on the scope of protection of this application. At the same time, the embodiments and features of the embodiments of this application can be combined with each other if there are no conflicts. The following sections will describe this application in detail by combining embodiments with reference to the attached drawings.

[0026] As shown in Figure 1, the present invention provides an intelligent silt removal method based on water depth changes, which specifically includes the following steps.

[0027] S1: Obtain the water depth of the silt removal channel.

[0028] Shipping lanes are the foundation of water transport. To ensure the safe passage of vessels, shipping lanes must have sufficient depth, width, and radius of curvature, appropriate current velocity, flow conditions, and sufficient surface clearance.

[0029] Specifically, shipboard or unmanned vessel bathymetry systems are used to measure underwater topography at high speed, high resolution, and high accuracy; GNSS receivers are combined with CORS technology for positioning; and real-time navigation and depth data are collected via data processing software.

[0030] The aforementioned data processing software is Hydro Survey software.

[0031] More specifically, as shown in Figure 2, S1 is as follows:

[0032] S1.1: Arrange the measurement lines.

[0033] Here, the measurement lines are arranged at 2 cm intervals along the shipping lanes, with a higher density along the coast, and supplementary measurements are immediately carried out in areas that are not covered or do not meet the coverage requirements.

[0034] S1.2: Navigation positioning is performed via a GNSS receiver or CORS technology. Navigation and positioning are performed using GNSS-RTK or CORS, and a mobile station is set up to receive differential signals transmitted from a coastal reference station via a radio broadcasting station, ensuring real-time navigation with centimeter-level accuracy and precise positioning.

[0035] S1.3: Perform sound velocity calibration.

[0036] Since the speed of sound changes depending on factors such as seawater salinity and temperature, when conducting water depth measurements, a sound velocity profiler is used to measure the speed of sound before, during, and after the measurement, and the measured sound velocity is used to perform sound velocity calibration for water depth at different time points.

[0037] S1.4: Observe the tide level.

[0038] In accordance with the characteristics of the location where the shipping lane is situated, one temporary tidal level observation station will be placed within the measurement area where the shipping lane is located, and the tidal level for the depth measurement period will be corrected using a single base station correction method to ensure that the tidal level data satisfies the accuracy requirements for underwater measurement and detection.

[0039] More specifically, in this embodiment, the temporary tidal level observation station is equipped with a tidal level observation instrument, which uses an automatic tide meter to observe the tidal level, and the tidal level data is saved in real time. The zero point altitude of the temporary tidal level observation station is measured at the nearest high-level level with an accuracy of 4th magnitude, the water level observation sampling interval is set to observe once every 10 minutes, the sampling frequency is set to 1 Hz, and the sampling time is 40 seconds. The mean wave disappearance method is used to ensure that the tidal level curve is smooth, and the water level observation error is ±1 cm.

[0040] S1.5: Collect external field data.

[0041] Based on the positioned measurement lines, the vessel is instructed to measure along the measurement lines until the entire measurement area is covered, completing the measurement coverage of the measurement lines and deriving the recorded data.

[0042] S1.6: Create the drawing.

[0043] The data collected in step S1.5 is post-processed to generate a digital linear diagram and draw contour lines. Then, using the Southern CASS 10.1 version drawing software, the legend of the drawing is drawn according to the rules, the basic contour distance is 1m, and the altitude is recorded to the decimal point.

[0044] Therefore, more accurate silt removal channel depth data can be obtained.

[0045] S2: The aforementioned route is segmented, and the route is divided into n segments, each of which is S1, S2, ..., Sn.

[0046] Specifically, the aforementioned route is divided into n sections by dividing it into equal distances.

[0047] For example, if the aforementioned route is 100 km long and is divided into 10 sections, the lengths of the routes S1, S2, ..., Sn will all be 10 km long.

[0048] S3: Obtain the minimum water depth for each section of the route.

[0049] In fact, water depth data for the shipping route can be obtained through the operation in S1, and then the minimum water depth of each section of the shipping route is defined as the minimum water depth of each section of the shipping route.

[0050] S4: The sections of each route are classified according to the minimum water depth, and the route type is obtained. If the route section is of route type 1, proceed to S5; if the route section is of route type 2, proceed to S6.

[0051] Specifically, if the minimum water depth of the route to be classified is less than the set threshold, it is classified as a first-type route; if the minimum water depth of the route to be classified is greater than or equal to the set threshold, it is classified as a second-type route. Here, the set threshold is 14.5 km.

[0052] This embodiment demonstrates that smart silt removal in shipping lanes can be achieved by using a floating silt removal system that adapts to the current water depth conditions of the lanes, thereby increasing the efficiency of silt removal.

[0053] S5: Silt removal will be carried out on the section of the channel using the first silt removal plan. In the case of the first channel type, the minimum water depth in the channel section is small, and mud and sand deposits are likely to occur in this channel section. Therefore, deposits may continue to occur in a short period of time after silt removal using general silt removal methods. At this stage, general silt removal methods are optimized to achieve smart silt removal and improve the efficiency of silt removal.

[0054] Specifically, as shown in Figure 3, S5 is as follows:

[0055] S5.1: Obtain the location type of the section of the channel, the annual sedimentation volume of the section of the channel, the average depth, and the minimum depth.

[0056] Here, the positional type of the section of the said shipping route is whether the section of the shipping route is at the entrance or not at the entrance. Here, the average water depth is the average value of the water depth over the section of the route in question. The annual sediment volume of the aforementioned shipping route is the sediment volume of the section of that route over the past year.

[0057] S5.2: Construct a model to predict silt removal depth.

[0058] Here, the silt removal depth prediction model is a support vector machine model. A Support Vector Machine (SVM) is a type of Generalized Linear Classifier that performs binary classification on data using a supervised learning method. Its decision boundary is the Maximum-margin Hyperplane, which finds the solution for the learned samples. SVMs use a hinge loss function to calculate empirical risk and optimize structural risk by adding a normalization term to the solution system, making it a classifier that combines scarcity and robustness. SVMs can perform nonlinear classification via the kernel method and are one of the common kernel learning methods.

[0059] The fundamental idea of ​​support vector machines is to transform a real-world spatial problem into a new, nonlinear, higher-dimensional space and reconstruct an optimal linear classification surface in this new space. This process involves constructing an appropriate kernel function to perform such a nonlinear transformation. When the dimension of the higher-dimensional space is relatively large, the inner product calculation in the transformed higher-dimensional feature space can be realized by the kernel function operation in the original space. This means that even if the dimension of the higher-dimensional feature space is relatively large, the complexity of the algorithm's computational implementation hardly increases, and consequently, even if the curse of dimensionality appears during computation in the higher-dimensional space, the problem is solved in an effective way.

[0060] Specifically, the kernel function of the support vector machine is a linear kernel function, the penalty coefficient of the support vector machine is 0.09, and the limitations on other parameters are not specifically limited in this embodiment.

[0061] S5.3: Obtain a dataset for training the support vector machine model, Here, the dataset consists of annual sedimentation, average depth, and minimum depth data for each section of the shipping route over the past 10 years. Engineers represent the annual data for each section and indicate the silt removal depth to form the dataset.

[0062] S5.4: Train a support vector machine model using the aforementioned dataset. Specifically, the training of the support vector machine model is determined through accuracy, precision, recall rate, and F1 value. The aforementioned accuracy is specifically calculated by determining the accuracy of the model on the test set, i.e., the number of samples that were accurately predicted divided by the total number of samples. A higher accuracy indicates greater effectiveness of the model.

[0063] Specifically, the precision refers to the proportion of samples that were actually in the positive class among those that the model predicted to be in the positive class, and the recall rate refers to the proportion of samples that were actually in the positive class among those that were predicted to be in the positive class by the model. Both high precision and high recall rate indicate that the model is more effective.

[0064] The recall rate is specifically the proportion of genuine positive class samples that were predicted as positive class by the model. A high recall rate indicates high model effectiveness.

[0065] The F1 score is specifically the harmonic mean of accuracy and recall rate, and a higher F1 score indicates greater model effectiveness.

[0066] S5.5: The location type of the channel section, the annual sedimentation volume of the channel section, the average water depth, and the minimum water depth obtained in S5.1 are input into the support vector machine model to predict the silt removal depth of the channel section, thereby realizing smart silt removal of the channel section. By considering the location of the shipping lane and past sediment and sand deposits when determining the silt removal depth through the steps described above, accurate and effective smart predictions of the silt removal depth can be achieved.

[0067] S6: The second silt removal plan was adopted, and silt removal was carried out in the section of the shipping route in question. Specifically, the second silt removal plan involves reducing the water depth of the channel to 20 km. In practice, in the case of the second type of shipping channel, the water depth of the channel is relatively deep, indicating that silt deposition does not easily occur in this section of the channel. Therefore, by adopting a relatively simple silt removal plan, the targetability and efficiency of formulating a silt removal method can be improved.

[0068] Example 2: This example also includes a control system for a smart silt removal method based on water depth changes, the control system using the smart silt removal method based on water depth changes of Example 1, and the control system A channel depth acquisition module that acquires the water depth of the silt removal channel, The aforementioned route is segmented, and the route is divided into n segments, with each segment being a route segment module designated as S1, S2, ..., Sn. A minimum depth acquisition module that acquires the minimum water depth for each section of the shipping route, The system classifies each channel section according to the minimum water depth to obtain the channel section type. If the channel section is of the first channel type, it enters the first silt removal plan control module, and if the channel section is of the second channel type, it enters the second silt removal plan control module. A first silt removal plan control module that performs silt removal on a section of the route using the first silt removal plan, The system further includes a second silt removal control module that performs silt removal on a section of the route using the second silt removal scheme.

[0069] Example 3: This embodiment includes an electronic device, a processor, and a memory, the memory storing a program or instruction that can be executed by the processor, and when the program or instruction is executed by the processor, each stage of the intelligent silt removal method based on water depth change of Example 1 is realized, and the same technical effect can be obtained.

[0070] A data processing program is stored on the medium, and the data processing program is executed by the processor to perform each step of the smart silt removal method based on water depth changes in Example 1.

[0071] Technicians in the art should understand that the embodiments described herein are provided as methods, apparatus (devices), or computer program products. Therefore, embodiments may be described in the form of complete hardware embodiments, complete software embodiments, or embodiments combining software and hardware. These include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital video discs (DVDs) or other optical disc memories, magnetic cassettes, magnetic tapes, memory or other storage devices, or any other medium that stores desired information and can be accessed by a computer. Furthermore, as technicians in the art know, communication media may include any information transmission medium, generally containing computer-readable instructions, data structures, program modules, or other data such as data signal modulation like carriers or other transmission mechanisms.

[0072] This specification describes the methods, apparatus (devices), and computer program products of these embodiments with reference to flowcharts and / or block diagrams. It should be understood that computer program instructions can realize each process and / or block in a flowchart and / or block diagram, as well as the combination of processes and / or blocks in a flowchart and / or block diagram. Such computer program instructions are provided as a processor of a general-purpose computer, a dedicated computer, an embedded processor, or another programmable data processing device to generate an apparatus that realizes the functions specified in one process of a flowchart and / or one or more blocks of a block diagram through instructions executed by the processor of the computer or other programmable data processing device.

[0073] The instructions of such a computer program can also be stored in computer-readable memory, which can guide a computer or other programmable data processing device to work in a particular manner, and the instructions stored in this computer-readable memory can produce a product that includes an instruction unit, which can implement steps that realize a specified function in one or more processes of a flowchart and / or one or more blocks of a block diagram.

[0074] The examples and / or embodiments described above are merely for illustrating the best examples and / or embodiments for realizing the technology of the present invention, and there are no formal limitations on embodiments of the technology of the present invention. Any person skilled in the art may modify them in some way or in other equivalent ways without departing from the scope of the technical means disclosed herein, but these should still be considered to be substantially the same technology or embodiment as the present invention. It should be noted that the foregoing is merely a better example of the present invention and applicable technical principles. A person skilled in the art will understand that the present invention is not limited to the specific examples described herein, and that a variety of obvious modifications, readjustments, and substitutions are possible without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above examples, the present invention is not limited to the above examples and may include many other equivalent embodiments without departing from the idea of ​​the present invention, and the scope of the present invention is determined by the appended claims.

Claims

1. In a smart silt removal method based on water depth changes, the method is as follows: Step S1: Measuring the water depth of the silt removal channel: The aforementioned route is segmented, and the route is divided into n segments, each of which is S1, S2, ... Sn. Step S2: Step S3: Obtain the minimum water depth for each section of the shipping route: Step S4 involves classifying each section of the route according to the minimum water depth and obtaining the route type; if the section of the route is of the first route type, proceed to S5; if the section of the route is of the second route type, proceed to S6. In step S5, the first silt removal plan is adopted for the section of the shipping route in question, and silt is removed: Here, The aforementioned step S5 specifically refers to: S5.1: Route The location type of the section of the route, the annual sedimentation volume of the section of the route, the average water depth, and the minimum water depth are obtained. S5.2: Construct a silt removal depth prediction model via a support vector machine model. S5.3: Obtain a dataset for training the support vector machine model. S5.4: Train a support vector machine model using the dataset. S5.5: The location type of the channel section, the annual sedimentation amount of the channel section, the average water depth, and the minimum water depth obtained in S5.1 are input into the support vector machine model to predict the silt removal depth of the channel section, thereby realizing smart silt removal of the channel section. A smart silt removal method based on water depth changes, characterized by including step S6, which involves removing silt from a section of the waterway by adopting a second silt removal plan.

2. Specifically, S1 refers to: S1.1: Arrange the measurement lines, S1.2: Navigation positioning is performed using a GNSS receiver or CORS technology. S1.3: Calibrate the speed of sound, S1.4: Observe the tide level, S1.5: Collect external field data, S1.6: The smart silt removal method based on water depth change according to claim 1, characterized by producing a drawing.

3. Specifically, S1.1 means, The aforementioned measurement lines are arranged at 2 cm intervals along the shipping lanes, and are more densely arranged along the coast, allowing for immediate supplemental measurements in uncovered areas or areas that do not meet the coverage requirements. Specifically, S1.2 involves performing navigation positioning using GNSS-RTK or CORS, setting up a mobile station, and receiving the differential signal transmitted by the coastal reference station via a radio broadcasting station. Specifically, S1.3 involves using a sound velocity profiler to measure the speed of sound before, during, and after measuring the water depth, and performing sound velocity calibration for water depth at different time points according to the measured speed of sound. Specifically, S1.4 involves setting up a temporary tidal level observation station in the measurement area where the shipping lane is located, and correcting the tidal level during the depth measurement period using the single base station correction method. Specifically, S1.5 involves measuring along the measurement line where the vessel is positioned until the entire measurement area is covered, completing the measurement coverage of the measurement line, and deriving the recorded data. The smart silt removal method based on water depth changes according to claim 2, wherein S1.6 specifically involves performing post-processing on the data collected in S1.5 to generate a digital linear diagram, drawing contour lines, and then using drafting software to draft according to the specified criteria, with the basic contour distance being 1 m and the altitude being expressed in decimeters.

4. The smart silt removal method based on water depth change according to claim 1, characterized in that, in S2, the waterway is divided into n parts in a manner that divides it equally according to distance.

5. The smart silt removal method based on water depth change according to claim 1, characterized in that, in S4 above, if the minimum water depth of the shipping route to be classified is less than a set threshold, it is classified into a first shipping route type, and if the minimum water depth of the shipping route to be classified is greater than or equal to a set threshold, it is classified into a second shipping route type.

6. The smart silt removal method based on water depth change according to claim 5, characterized in that, in S4, the setting threshold is 14.5 km.

7. The smart silt removal method based on water depth change according to claim 1, characterized in that, in S5.2, the kernel function of the support vector machine is a linear kernel function and the penalty coefficient of the support vector machine is 0.

09.

8. The smart silt removal method based on water depth change according to claim 1, characterized in that in S5.4, it is determined whether or not the support vector machine model has completed training through accuracy, precision, recall rate and F1 value.

9. In S6, the second silt removal method is characterized in that the minimum water depth of the shipping channel is 20 km, as described in claim 1, a smart silt removal method based on water depth change.

10. In a smart silt removal method control system based on water depth changes, the control system employs a smart silt removal method based on water depth changes according to any one of claims 1 to 9, and the control system is A channel depth acquisition module that acquires the water depth of the silt removal channel, The aforementioned route is segmented, and the route is divided into n segments, with route segment modules designated as S1, S2, ..., Sn respectively. A minimum depth acquisition module that acquires the minimum water depth for each section of the shipping route, The route classification model obtains a route type by classifying each section of the route based on the minimum water depth, and if the route is of the first route type, it enters the first silt removal plan control module, and if the route is of the second route type, it enters the second silt removal plan control module. A first silt removal plan control module that performs silt removal on a section of the route using the first silt removal plan, A smart silt removal method control system based on water depth changes, comprising: a second silt removal method control module that performs silt removal in a section of the channel using the second silt removal method.

Images