Intelligent dredging method based on water depth change, and control system

Abstract

An intelligent dredging method based on a water depth change, and a control system. During navigation channel dredging, a navigation channel is first divided into sections; then, on the basis of the water depth of each navigation channel section, the navigation channel section is classified; and on the basis of different types of navigation channels, different intelligent navigation channel dredging methods are used. In particular, for a first navigation channel type, the accurate and effective intelligent prediction for a dredging depth can be realized on the basis of the characteristic that sludge at the navigation channel section is prone to deposition and by means of a support vector machine combined with the position and historical silt deposition amount of the navigation channel; moreover, with regard to a second navigation channel type in which a navigation channel is not prone to sludge deposition, a channel dredging scheme is determined by using a fixed mode. By means of the method and the control system, the pertinence and efficiency of formulating a dredging method can be improved.

Description

An intelligent dredging method and control system based on water depth changes Technical Field

[0001] The present invention relates to the technical field of silt prevention and desilting technology, and in particular to an intelligent desilting method and control system based on water depth changes. Background Art

[0002] Sedimentation weakens the flood discharge capacity of river estuaries, impacts upstream drainage and irrigation, worsens downstream navigation conditions, and threatens the normal operation of sluice gates. Sedimentation along the pier front, in the harbor basin, and in the waterway affects ship access and transportation efficiency, hindering economic development. Furthermore, severe sedimentation increases operational costs, while siltation between piles affects the structural safety of high-pile piers. Frequent silt removal also hinders berthing of ships. To reduce the intensity of sedimentation during the operational period, guidance is needed to develop a rational, regularized sediment reduction plan to ensure the safety of ships entering and leaving the port, as well as berthing and unberthing.

[0003] In the prior art, when dredging harbors and docks, dredging is generally accomplished by dredging with a dredger or a trailing suction hopper vessel. After dredging, the dredged silt is transported to a designated area for dumping. However, when dredging is performed in this manner, the dredging efficiency is low due to the need for dumping silt over a long distance, and the normal operation of the harbor and dock areas needs to be restricted to ensure navigation safety and construction safety. Therefore, the dredging work cannot be carried out continuously, but needs to be carried out after a period of time. Automatic dredging and anti-silting of silt cannot be carried out on a regular basis, which makes the harbor and dock lack the ability to effectively resist silt deposition in daily operation.

[0004] There are solutions for intelligent dredging of waterways in the prior art. For example, a Chinese invention patent (CN116844065A) discloses a GIS-based intelligent identification and management method for waterway dredging. The method includes: collecting waterway silt images based on GIS technology and performing preprocessing and progressive feature extraction operations to obtain waterway silt image features; using an improved L-BFGS algorithm to optimize and solve the constructed silt category accurate identification model; inputting the extracted waterway silt image features into the optimal silt category accurate identification model, the model outputting the corresponding silt identification category, and performing waterway silt management based on the identified silt identification category. The invention converts the channel silt image into different scales and marks the edge pixels at different scales to achieve multi-scale edge extraction and image segmentation. It uses a progressive approach to extract the spatial features of the channel silt image and identify the silt, and then manages the channel silt in the channel areas corresponding to different image blocks in combination with the silt category. However, the above scheme does not identify the channel type during the intelligent dredging process of the channel, resulting in a large amount of computation, low efficiency, and lack of pertinence in the formulation of the entire dredging plan. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent dredging method and control system based on water depth changes, so as to improve the pertinence and efficiency of waterway dredging.

[0006] In order to solve the above technical problems, the present invention specifically provides the following technical solutions:

[0007] An intelligent dredging method based on water depth changes includes the following steps:

[0008] S1: Get the water depth of the dredging channel;

[0009] S2: Segment the waterway; divide the waterway into n segments, namely S1, S2, ..., Sn;

[0010] S3: Get the minimum water depth of each channel;

[0011] S4: Classify each waterway section according to the minimum water depth to obtain the type of the waterway section. If the waterway section is of the first waterway type, proceed to S5; if the waterway section is of the second waterway type, proceed to S6;

[0012] S5: Use the first dredging plan to dredge the channel section;

[0013] The S5 is specifically:

[0014] S5.1: Obtain the location type, annual sedimentation volume, average water depth, and minimum water depth of the waterway section;

[0015] S5.2: Develop a model for predicting dredging depth;

[0016] S5.3: Obtain a data set for training the support vector machine model;

[0017] S5.4: Using the dataset to train a support vector machine model;

[0018] S5.5: Input the location type, annual sedimentation volume, average water depth, and minimum water depth of the waterway section obtained in S5.1 into the support vector machine model to predict the desilting depth of the waterway section, thereby realizing intelligent desilting of the waterway section;

[0019] S6: Use the second dredging plan to dredge this section of the channel.

[0020] Preferably, the S1 is specifically:

[0021] S1.1: Lay out survey lines;

[0022] S1.2: Navigation and positioning using GNSS receivers or CORS technology;

[0023] S1.3: Sound velocity correction;

[0024] S1.4: Tide level observation;

[0025] S1.5 Field data collection;

[0026] S1.6 is plotted.

[0027] Preferably, S1.1 specifically includes: the survey lines are laid out along the waterway at a spacing of 2 cm, with denser spacing near the shore, and areas that are not covered or do not meet coverage requirements are promptly supplemented with surveys;

[0028] S1.2 specifically includes: using GNSS-RTK or CORS for navigation and positioning, setting up a mobile station to receive differential signals sent by the shore reference station via radio, and navigating with centimeter-level real-time accuracy;

[0029] S1.3 specifically states: when performing water depth measurement, use a sound velocity profiler to measure sound velocity before, during, and after the measurement, and perform sound velocity correction on the water depth according to the measured sound velocity at each time period;

[0030] S1.4 specifically states: a temporary tide level station is set up in the survey area where the waterway is located, and the tide level during the sounding period is corrected using the single-station correction method;

[0031] S1.5 specifically includes: according to the laid-out survey line, directing the vessel to measure along the survey line until the entire survey area is covered, completing coverage measurement of the survey line, and exporting recorded data;

[0032] Said S1.6 specifically includes: performing data post-processing on the data collected in said step S1.5, generating a digital line drawing, and drawing isobaths, and then using Southern CASS 10.1 version drawing software, the legend is drawn according to the specification, the basic isobath interval is 1 m, and the elevation is annotated to decimeters.

[0033] Preferably, the waterway is divided into n sections in equal distances.

[0034] Preferably, in said S4: if the minimum water depth of the waterway to be classified is less than a set threshold, it is the first waterway type; if the minimum water depth of the broken waterway to be classified is greater than or equal to the set threshold, it is the second waterway type.

[0035] Preferably, in S4, the set threshold is 14.5 km.

[0036] Preferably, in S5.2, the dredging 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.

[0037] Preferably, in S5.4, whether the support vector machine model is trained is determined by accuracy, precision, recall and F1 value.

[0038] Preferably, in said S6, said second dredging plan is: making the water depth of the channel section 20 km.

[0039] According to another aspect of the present invention, a control system for an intelligent dredging method based on water depth changes is provided. The control system adopts the above-mentioned intelligent dredging method based on water depth changes, and the control system further includes:

[0040] Channel water depth acquisition module, used to obtain the water depth of the dredging channel;

[0041] A channel segmentation module is used to segment the channel; the channel is divided into n segments, namely S1, S2, ..., Sn;

[0042] Minimum water depth acquisition module, used to obtain the minimum water depth of each section of the channel;

[0043] A waterway classification model is used to classify each waterway section according to the minimum water depth to obtain the type of the waterway section. If the waterway section is of the first waterway type, the first dredging scheme control module is entered; if the waterway section is of the second waterway type, the second dredging scheme control module is entered;

[0044] A first dredging scheme control module, configured to dredge the waterway section using a first dredging scheme;

[0045] The second dredging scheme control module is used to adopt the second dredging scheme to dredge the waterway section.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] When dredging a waterway, the present invention first divides the waterway into sections, then classifies each section of the waterway according to its water depth, and adopts different intelligent dredging methods for different types of waterways. In particular, for the first type of waterway, based on the characteristic of easy silt accumulation in this section of the waterway, the support vector machine is combined with the location of the waterway and the historical amount of silt accumulation to achieve accurate and effective intelligent prediction of the dredging depth.

[0048] Furthermore, since the second channel type is not prone to siltation, a fixed mode is adopted to determine the channel dredging plan; through the scheme of the present invention, the pertinence and efficiency of the dredging method can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other implementation drawings based on the provided drawings without inventive effort.

[0050] FIG1 is a schematic diagram of a flow chart of an intelligent dredging method based on water depth changes provided by an embodiment of the present invention;

[0051] FIG2 is a schematic diagram of a process for obtaining the water depth of a dredging channel according to an embodiment of the present invention;

[0052] FIG3 is a schematic diagram of a process for dredging the waterway section using the first dredging solution according to an embodiment of the present invention. Modes for Carrying Out the Invention

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0054] The following first describes the concepts involved in this application with reference to the accompanying drawings. It should be noted that the following description of each concept is intended only to make the content of this application easier to understand and does not limit the scope of protection of this application. At the same time, the embodiments and features in the embodiments of this application can be combined with each other unless there is a conflict. The following detailed description of this application will be made with reference to the accompanying drawings and in conjunction with the embodiments.

[0055] As shown in FIG1 , the present invention provides an intelligent dredging method based on water depth changes, which specifically includes the following steps:

[0056] S1: Get the water depth of the dredging channel;

[0057] Waterways are the foundation of water transportation. To ensure normal navigation of ships, waterways must have the following conditions: sufficient water depth, width, sufficient bending radius, appropriate flow speed and flow pattern, and sufficient water clearance.

[0058] Specifically, a ship-borne bathymetric system or an unmanned vessel bathymetric system is used to conduct rapid, high-resolution, and high-precision measurements of underwater terrain, equipped with a GNSS receiver using CORS technology for positioning, and data processing software for real-time navigation and water depth data collection;

[0059] The data processing software is Hydro Survey software.

[0060] In addition, as shown in FIG2 , the S1 is specifically as follows:

[0061] S1.1: Lay out survey lines;

[0062] The survey lines are laid out at 2 cm intervals along the waterway, with denser spacing near the shore. Areas that are not covered or do not meet coverage requirements are promptly resurveyed.

[0063] S1.2: Navigation and positioning using GNSS receivers or CORS technology;

[0064] Using GNSS-RTK or CORS for navigation and positioning, a rover is set up to receive differential signals sent by the shore reference station via radio, providing real-time and accurate navigation at the centimeter level, thus ensuring precise positioning for detection work;

[0065] S1.3: Sound velocity correction;

[0066] Since the speed of sound varies with factors such as seawater salinity and temperature, a sound velocity profiler is used to measure the speed of sound before, during, and after the measurement. The water depth is then corrected for the speed of sound according to the measured speed.

[0067] S1.4: Tide level observation;

[0068] According to the characteristics of the waterway location, a temporary tide level station is set up in the survey area where the waterway is located. The tide level during the sounding period is corrected using the single-station correction method to ensure that the tide level data can meet the accuracy requirements of underwater measurement and detection;

[0069] Furthermore, in this embodiment, the temporary tide station is provided with a tide observation instrument, which uses an automatic tide gauge to observe the tide level, and the tide level data is stored in real time. The zero point elevation of the temporary tide station is measured from the nearest high-level leveling point with fourth-class leveling accuracy. The water level observation sampling interval is set to observe once every 10 minutes, the sampling frequency is set to 1 Hz, the sampling time is 40 seconds, and the average wave elimination method is used to ensure that the tide curve is smooth and the water level observation error is ±1 cm.

[0070] S1.5: Field data collection;

[0071] According to the laid-out survey line, the vessel is directed to measure along the survey line until the entire survey area is covered, the coverage measurement of the survey line is completed, and the recorded data is exported.

[0072] S1.6: Draw a diagram;

[0073] The data collected in step S1.5 were post-processed to generate a digital line map and draw the isobaths. Then, the Southern CASS version 10.1 drawing software was used. The legend was drawn according to the specifications, with the basic isobath interval being 1 m and the elevation annotated to decimeters.

[0074] In this way, more accurate water depth data of the dredging channel can be obtained.

[0075] S2: Segment the waterway; divide the waterway into n segments, namely S1, S2, ..., Sn;

[0076] Specifically, the waterway is divided into n sections in a manner of equal distance division;

[0077] For example, if the waterway is 100 km long and is divided into 10 segments, then the lengths of S1, S2, ..., Sn are all 10 km long;

[0078] S3: Get the minimum water depth of each channel;

[0079] In fact, through the operation of S1, the water depth data of the channel can be obtained, and then the minimum value of the water depth of each section of the channel is defined as the minimum water depth of each section of the channel;

[0080] S4: Classify each waterway section according to the minimum water depth to obtain the type of the waterway section. If the waterway section is of the first waterway type, proceed to S5; if the waterway section is of the second waterway type, proceed to S6;

[0081] Specifically, if the minimum water depth of the waterway to be classified is less than the set threshold, it is the first waterway type; if the minimum water depth of the broken waterway to be classified is greater than or equal to the set threshold, it is the second waterway type;

[0082] Wherein, the set threshold is 14.5km;

[0083] In this embodiment, different dredging methods are adopted according to the current water depth of the waterway, which can achieve intelligent dredging of the waterway and improve the efficiency of dredging.

[0084] S5: Use the first dredging plan to dredge the channel section;

[0085] Among them, for the first channel type, the minimum water depth of this section of the channel is relatively small, and this section of the channel is prone to siltation. Therefore, conventional dredging methods may continue to cause siltation within a short period of time after dredging. Therefore, in this step, the conventional dredging method is optimized to achieve intelligent dredging to improve the efficiency of dredging.

[0086] Specifically, as shown in FIG3 , the S5 is specifically as follows:

[0087] S5.1: Obtain the location type, annual sedimentation volume, average water depth, and minimum water depth of the waterway section;

[0088] The location type of the waterway section is: the waterway section is at the mouth and the waterway section is not at the mouth;

[0089] The average water depth is the average water depth of the waterway section;

[0090] The annual sedimentation of the waterway in question is the sedimentation of that section of waterway in the past year;

[0091] S5.2: Develop a model for predicting dredging depth;

[0092] Wherein, the dredging depth prediction model is a support vector machine model;

[0093] A support vector machine (SVM) is a generalized linear classifier that performs binary classification on data using supervised learning. Its decision boundary is the maximum-margin hyperplane found on the learning samples. SVM uses a hinge loss function to calculate empirical risk and incorporates a regularization term to optimize structural risk. It is a sparse and robust classifier. SVM can perform nonlinear classification using kernel methods and is a common kernel learning method.

[0094] The basic idea of ​​a support vector machine is to transform the actual spatial problem into a new high-dimensional space through nonlinear transformation, and then reconstruct the optimal linear classification surface in this new space. This nonlinear transformation is performed by constructing an appropriate kernel function. When the dimensionality of the high-dimensional space is relatively large, the inner product calculation in the transformed high-dimensional feature space can be achieved by operating on the kernel function in the original actual space. This means that even if the dimensionality of the high-dimensional feature space is relatively large, the complexity of the algorithm's implementation is almost unchanged. Accordingly, the dimensionality curse that occurs in the implementation of the computation in the high-dimensional space is effectively solved.

[0095] 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.

[0096] S5.3: Obtain a data set for training the support vector machine model;

[0097] The dataset contains the annual sedimentation volume, average water depth, and minimum water depth data for each section of the waterway over the past 10 years. Technicians then annotate the annual data for each section of the dataset, noting the desilting depth, thus forming a dataset.

[0098] S5.4: Using the dataset to train a support vector machine model;

[0099] Specifically, the accuracy, precision, recall and F1 value are used to determine whether the support vector machine model is trained;

[0100] The accuracy is calculated as follows: the accuracy of the model on the test set is the number of samples predicted correctly divided by the total number of samples; a high accuracy indicates a high effectiveness of the model.

[0101] The precision rate is specifically: the proportion of samples predicted as positive by the model that are actually positive. The recall rate represents the proportion of samples predicted as positive by the model among the samples that are actually positive. High precision and recall rates both indicate high model effectiveness.

[0102] The recall rate is specifically the proportion of samples that are actually positive that are predicted as positive by the model; a high recall rate indicates that the model is more effective.

[0103] The F1 value (F1 Score) is specifically the harmonic mean of precision and recall. The higher the F1 value, the more effective the model.

[0104] S5.5: Input the location type, annual sedimentation volume, average water depth, and minimum water depth of the waterway section obtained in S5.1 into the support vector machine model to predict the desilting depth of the waterway section, thereby realizing intelligent desilting of the waterway section;

[0105] Through the above steps, when determining the dredging depth, the location of the waterway and the historical sediment accumulation are taken into consideration, and an accurate and effective intelligent prediction of the dredging depth can be achieved.

[0106] S6: Use the second dredging plan to dredge the channel section;

[0107] Specifically, the second dredging plan is: making the water depth of the channel section 20km;

[0108] In fact, for the second channel type, the water depth of this channel is relatively deep, which means that sludge accumulation is not easy to occur in this section of the channel. Therefore, adopting a simpler dredging plan can improve the pertinence and efficiency of the dredging method.

[0109] Embodiment 2: This embodiment further includes a control system for an intelligent dredging method based on water depth changes. The control system adopts the intelligent dredging method based on water depth changes of embodiment 1, and the control system further includes:

[0110] Channel water depth acquisition module, used to obtain the water depth of the dredging channel;

[0111] A channel segmentation module is used to segment the channel; the channel is divided into n segments, namely S1, S2, ..., Sn;

[0112] Minimum water depth acquisition module, used to obtain the minimum water depth of each section of the channel;

[0113] A waterway classification model is used to classify each waterway section according to the minimum water depth to obtain the type of the waterway section. If the waterway section is of the first waterway type, the first dredging scheme control module is entered; if the waterway section is of the second waterway type, the second dredging scheme control module is entered;

[0114] A first dredging scheme control module, configured to dredge the waterway section using a first dredging scheme;

[0115] The second dredging scheme control module is used to adopt the second dredging scheme to dredge the waterway section.

[0116] Embodiment three. This embodiment includes an electronic device, including a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor. When the program or instruction is executed by the processor, the various steps of the intelligent dredging method based on water depth changes in embodiment one are implemented, and the same technical effect can be achieved.

[0117] Embodiment 4: This embodiment includes a computer-readable storage medium on which a data processing program is stored. The data processing program is executed by a processor to execute the various steps of the intelligent dredging method based on water depth changes in embodiment 1.

[0118] Those skilled in the art will appreciate that the embodiments herein may be provided as methods, apparatuses (devices), or computer program products. Therefore, the present invention may take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. These include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVDs) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery medium.

[0119] This document is described with reference to flowcharts and / or block diagrams of methods, apparatuses (devices), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowcharts and / or one or more blocks in the block diagrams.

[0120] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the steps of the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0121] The embodiments and / or implementation methods described above are only used to illustrate the preferred embodiments and / or implementation methods for realizing the technology of the present invention, and are not intended to impose any formal restrictions on the implementation methods of the technology of the present invention. Any person skilled in the art may make some changes or modifications to other equivalent embodiments without departing from the scope of the technical means disclosed in the content of the present invention, but they should still be regarded as technologies or embodiments that are essentially the same as the present invention. Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art 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 embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An intelligent dredging method based on water depth changes, characterized in that: The specific steps include: S1: Get the water depth of the dredging channel; S2: Segment the waterway; divide the waterway into n segments, namely S1, S2, ..., Sn; S3: Get the minimum water depth of each channel; S4: Classify each waterway section according to the minimum water depth to obtain the type of the waterway section. If the waterway section is of the first waterway type, proceed to S5; if the waterway section is of the second waterway type, proceed to S6; S5: Use the first dredging plan to dredge the channel section; The S5 is specifically: S5.1: Obtain the location type, annual sedimentation volume, average water depth, and minimum water depth of the waterway section; S5.2: Establish a desilting depth prediction model using a support vector machine model; S5.3: Obtain a data set for training the support vector machine model; S5.4: Using the dataset to train a support vector machine model; S5.5: Input the location type, annual sedimentation volume, average water depth, and minimum water depth of the waterway section obtained in S5.1 into the support vector machine model to predict the desilting depth of the waterway section, thereby realizing intelligent desilting of the waterway section; S6: Use the second dredging plan to dredge this section of the channel.

2. The intelligent dredging method based on water depth change according to claim 1 is characterized in that: The S1 is specifically: S1.1: Lay out survey lines; S1.2: Navigation and positioning using GNSS receivers or CORS technology; S1.3: Sound velocity correction; S1.4: Tide level observation; S1.5: Field data collection; S1.6: Draw a graph.

3. The intelligent dredging method based on water depth change according to claim 2 is characterized in that: S1.1 specifically states: the survey lines are laid out at 2 cm intervals along the waterway, with denser spacing near the shore, and any areas that are not covered or do not meet coverage requirements are promptly resurveyed; S1.2 specifically includes: using GNSS-RTK or CORS for navigation and positioning, setting up a mobile station to receive the differential signal sent by the shore reference station via the radio; S1.3 specifically states: when performing water depth measurement, use a sound velocity profiler to measure sound velocity before, during, and after the measurement, and perform sound velocity correction on the water depth according to the measured sound velocity at each time period; S1.4 specifically states: deploy temporary tide stations within the survey area where the waterway is located, and use the single-station correction method to correct the tide level during the sounding period; S1.5 specifically includes: commanding the vessel to measure along the laid survey line until the entire survey area is covered, completing coverage measurement of the survey line, and exporting recorded data; Said S1.6 specifically includes: performing data post-processing on the data collected in said S1.5, generating a digital line drawing, and drawing isobaths, which are then drawn according to the specifications using drawing software, with the basic isobath interval being 1 m and elevations annotated to decimeters.

4. The intelligent dredging method based on water depth change according to claim 1 is characterized in that: In S2, the waterway is divided into n sections in equal distances.

5. The intelligent dredging method based on water depth change according to claim 1 is characterized in that: In said S4: if the minimum water depth of the waterway to be classified is less than the set threshold, it is the first waterway type; if the minimum water depth of the waterway to be classified is greater than or equal to the set threshold, it is the second waterway type.

6. The intelligent dredging method based on water depth change according to claim 5 is characterized in that: In S4, the threshold is set to 14.5 km.

7. The intelligent dredging method based on water depth change according to claim 1 is 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 intelligent dredging method based on water depth change according to claim 1 is characterized in that: In S5.4, whether the support vector machine model is trained is determined by the accuracy, precision, recall and F1 value.

9. The intelligent dredging method based on water depth change according to claim 1 is characterized in that: In S6, the second dredging plan is: the minimum water depth of the channel is 20 km.

10. A control system for an intelligent dredging method based on water depth changes, the control system adopting the intelligent dredging method based on water depth changes according to any one of claims 1 to 9, characterized in that: The control system further comprises: Channel water depth acquisition module, used to obtain the water depth of the dredging channel; A channel segmentation module is used to segment the channel; the channel is divided into n segments, namely S1, S2, ..., Sn; Minimum water depth acquisition module, used to obtain the minimum water depth of each section of the channel; A waterway classification model is used to classify each waterway according to the minimum water depth to obtain a waterway type. If the waterway is of the first waterway type, the first dredging scheme control module is entered; if the waterway is of the second waterway type, the second dredging scheme control module is entered; A first dredging scheme control module, configured to dredge the waterway section using a first dredging scheme; The second dredging scheme control module is used to adopt the second dredging scheme to dredge the waterway section.

Images