Intelligent navigation method and system based on surplus water depth management

Abstract

The invention discloses an intelligent navigation method and system based on surplus water depth management, and the method comprises the steps: firstly, generating a map model for a target sea area, obtaining grid water depth and forecast tide level data in an analysis period, and setting feasible and infeasible regions; thirdly, dividing the sea area into a plurality of unit areas, extracting water depth and tide level characteristic data, and performing area clustering by using a Mean Shift algorithm to obtain a plurality of area groups; and then, by taking the region groups as units, dynamically analyzing the target ship draft, predicting the average surplus water depth of each region group, and grading the average surplus water depth. And finally, in the map model, according to the level of the region group, setting path cost, planning a navigation path by adopting an A * algorithm, and generating a plurality of optimized paths, thereby effectively improving the navigation safety and efficiency, and realizing accurate navigation risk analysis and management based on the surplus water depth.

Description

Technical Field

[0001] The present invention relates to the field of intelligent navigation, and more specifically, to an intelligent navigation method and system based on under-keel clearance management. Background Art

[0002] Under-keel clearance is an important analysis parameter in navigation, which is of great significance for ocean navigation and changes with the actual draft and actual water depth. The factors causing draft changes include various ones, such as the trim and list of the ship, navigation sinkage, fuel and supplies consumption, change of trim, different seawater densities, ship draft increment caused by waves, etc. The factors affecting the actual water depth include tides, meteorological water level rise and fall, sediment deposition, etc. And the accurate analysis of under-keel clearance directly affects the safety of navigation planning.

[0003] However, traditional under-keel clearance often analyzes based on static monitoring data and static sea area data, lacking dynamic analysis ability, making it difficult to analyze potential risks in actual navigation. And the navigation planning based on under-keel clearance often lacks a dynamic regional feature analysis process, resulting in low navigation safety and navigation efficiency, being difficult to avoid potential risk factors and difficult to comprehensively improve navigation efficiency. Summary of the Invention

[0004] The present invention overcomes the defects of the prior art and provides an intelligent navigation method and system based on under-keel clearance management.

[0005] The first aspect of the present invention provides an intelligent navigation method based on under-keel clearance management, including: S101: Generate a map model based on the target sea area. In an analysis period, obtain the water depth data and predicted tide level data based on grid data in the target sea area and set the feasible area and infeasible area; S102: In the map model, divide the target sea area into multiple unit areas. For each unit area, extract feature data in two dimensions of water depth and tide level, and use the feature data as sample data to perform regional clustering analysis based on the Mean Shift algorithm to obtain multiple area groups; S103: Take the area group as the analysis unit, dynamically analyze the draft depth of the target ship, predict the average under-keel clearance in each area group, and classify the area groups based on the average under-keel clearance; S104: In the map model, set the path cost according to the area group level, take the unit area as the moving unit, perform navigation planning based on the A* algorithm, and generate multiple optimized paths.

[0006] In this solution, the S101 is specifically: Construct a two-dimensional visual map model based on the scope of the target sea area; Obtain the water depth data and predicted tide level data based on grid data within the target sea area; Conduct dynamic water depth assessment based on the water depth data and predicted tide level data, and set preliminary feasible areas and infeasible areas in combination with the fixed draft depth of the target ship.

[0007] In this solution, the S102 is specifically as follows: In the map model, divide the target sea area into multiple unit areas to ensure that the area and contour of each unit area are consistent; For a unit area, perform multi-dimensional information extraction and information feature vectorization on the water depth data and predicted tide level data to obtain water depth features and tide level features; Analyze the water depth and tide level feature data of each unit area. Using the water depth features and tide level features as sample data, based on the Mean Shift algorithm, use the sample data of each unit area as the initial center point for clustering iteration, and map and divide multiple area groups based on the clustering results.

[0008] In this solution, the area clustering analysis includes: For each unit area, regard each sample data as a data point, set the bandwidth H, and use each data point as the initial center point; Obtain the neighborhood points of the initial center point based on H. When determining the neighborhood points, introduce the standard Euclidean distance to calculate the distance between data points, and use the average distance of the water depth features and tide level features in the two data points as the data point distance; Based on the Mean Shift algorithm, calculate the vector from the neighborhood point to the center point, and perform weighted averaging on the vector through the Gaussian kernel function to obtain the mean shift vector; Move and update the center point according to the mean shift vector for all initial center points in a loop until the iteration times are reached or the moving distance of the initial center point is less than the first preset distance; After the iteration is completed, among the initial center points, determine the points within the second preset distance range as a cluster to obtain the clustering result; Map and divide the unit area based on the clustering result to obtain multiple area groups.

[0009] In this solution, the S103 is specifically as follows: In an area group, obtain the estimated passing time and speed of the target ship, and dynamically calculate the predicted draft depth and excess water depth of the target ship in combination with the water depth data and predicted tide level data of each corresponding unit area; Within an area group, equalize the excess water depth of each unit area to obtain the average excess water depth; Set the level of each area group according to the magnitude of the average excess water depth.

[0010] In this solution, the S104 is specifically as follows: In the map model, set the starting point and the ending point of the target ship. Based on the A* algorithm, use the unit area as the moving unit, and based on the level of the area group, set the priority corresponding to each unit area. Set the path cost for each unit area based on the priority, and conduct the shortest path search to obtain multiple sailing paths. Combined with the infeasible areas, avoid and optimize the multiple sailing paths to generate multiple optimized paths.

[0011] In this solution, each area group includes one or more unit areas. The water depth data, the predicted tide level data, and the optimized paths are all visually and dynamically displayed through the map model.

[0012] The second aspect of the present invention also provides an intelligent navigation system based on the management of the additional water depth. The system includes: a memory and a processor. The memory includes an intelligent navigation program based on the management of the additional water depth. When the intelligent navigation program based on the management of the additional water depth is executed by the processor, the following steps are implemented: S101: Generate a map model based on the target sea area. In an analysis period, obtain the water depth data and the predicted tide level data based on the grid data in the target sea area, and set the feasible areas and the infeasible areas. S102: In the map model, divide the target sea area into multiple unit areas. For each unit area, extract the feature data in two dimensions of the water depth and the tide level, and use the feature data as the sample data to conduct regional clustering analysis based on the Mean Shift algorithm to obtain multiple area groups. S103: Take the area group as the analysis unit, dynamically analyze the draft of the target ship, and predict the average additional water depth in each area group. Classify the area groups based on the average additional water depth. S104: In the map model, set the path cost according to the area group level, use the unit area as the moving unit, conduct the navigation planning based on the A* algorithm, and generate multiple optimized paths.

[0013] The third aspect of the present invention also provides a computer-readable storage medium. The computer-readable storage medium includes an intelligent navigation program based on the management of the additional water depth. When the intelligent navigation program based on the management of the additional water depth is executed by the processor, the steps of the intelligent navigation method based on the management of the additional water depth as described in any one of the above are implemented.

[0014] The present invention discloses an intelligent navigation method and system based on redundant water depth management. First, a map model is generated for the target sea area, and grid water depth and predicted tide level data are obtained within the analysis period, and feasible and infeasible areas are set. Next, the sea area is divided into multiple unit areas, the water depth and tide level characteristic data are extracted, and the Mean Shift algorithm is used for regional clustering to obtain multiple regional groups. Subsequently, taking the regional groups as units, the draft depth of the target ship is dynamically analyzed, the average redundant water depth of each regional group is predicted and classified. Finally, in the map model, the path cost is set according to the regional group level, and the A* algorithm is used to plan the navigation path to generate multiple optimized paths, effectively improving the navigation safety and efficiency, and realizing the accurate navigation risk analysis and management based on the redundant water depth. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The flowchart of an intelligent navigation method based on redundant water depth management according to the present invention is shown; Figure 2 The block diagram of an intelligent navigation system based on redundant water depth management according to the present invention is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.

[0017] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention may be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0018] Figure 1 The flowchart of an intelligent navigation method based on redundant water depth management according to the present invention is shown.

[0019] As Figure 1 shown, the first aspect of the present invention provides an intelligent navigation method based on redundant water depth management, including: S101: Generating a map model based on the target sea area, obtaining water depth data and predicted tide level data based on grid data within the target sea area within an analysis period, and setting a feasible area and an infeasible area; S102: In the map model, dividing the target sea area into multiple unit areas, for each unit area, extracting characteristic data in two dimensions of water depth and tide level, and using the characteristic data as sample data to perform regional clustering analysis based on the Mean Shift algorithm to obtain multiple regional groups; S103: Taking the regional group as the analysis unit, dynamically analyze the draft of the target ship, predict the average clearance depth in each regional group, and classify the regional groups based on the average clearance depth. S104: In the map model, set the path cost according to the regional group level, use the unit area as the moving unit, perform navigation planning based on the A* algorithm, and generate multiple optimized paths.

[0020] It should be noted that the map model and relevant hydrological data are specifically provided based on the S-100 hydrological data service platform. The water depth data and predicted tide level data correspond to S-102 water depth data and S-104 predicted tide level, both of which are online hydrological data. S-100 is a general hydrographic data model, specifically an international hydrographic standard. S-102 and S-104 are both navigation data specifications.

[0021] According to the embodiments of the present invention, the S101 is specifically: Based on the scope of the target sea area, construct a two-dimensional visual map model. Obtain the water depth data and predicted tide level data based on grid data within the target sea area. Conduct dynamic water depth assessment according to the water depth data and predicted tide level data, and set the preliminary feasible area and infeasible area in combination with the fixed draft of the target ship.

[0022] It should be noted that the analysis period is one navigation planning period. The map model is used to visualize sea area data and plan navigation routes. The water depth data includes actual water depth, water depth deviation, bottom type number, uncertainty range, etc., and the predicted tide level data includes high tide level, low tide level, tide time, meteorological information, etc. There are corresponding water depth data and predicted tide level data in each grid of the map model, and the data volume is determined based on the network resolution.

[0023] According to the embodiments of the present invention, the S102 is specifically: In the map model, divide the target sea area into multiple unit areas to ensure that the area and contour of each unit area are the same. For a unit area, perform multi-dimensional information extraction and information feature vectorization on the water depth data and predicted tide level data to obtain water depth features and tide level features. Analyze the water depth and tide level feature data of each unit area. Using the water depth features and tide level features as sample data, based on the Mean Shift algorithm, perform clustering iteration with the sample data of each unit area as the initial center point, and divide multiple regional groups based on the clustering results mapping.

[0024] It should be noted that the unit area is generally divided by grids and is used to optimize the path planning process.

[0025] According to an embodiment of the present invention, the regional clustering analysis includes: For each unit area, each sample data is regarded as a data point, a bandwidth H is set, and each data point is used as an initial center point; Based on H, neighborhood points of the initial center point are obtained. In the process of determining the neighborhood points, the standard Euclidean distance is introduced to calculate the distance between data points, and the distance mean of the water depth feature and the tide level feature in two data points is used as the data point distance; Based on the Mean Shift algorithm, the vector from the neighborhood point to the center point is calculated, and the vector is weighted and averaged through a Gaussian kernel function to obtain a mean shift vector; The initial center point is moved and updated according to the mean shift vector, and all initial center points are iteratively looped until the number of iterations is reached or the moving distance of the initial center point is less than the first preset distance; After the iteration is completed, among the initial center points, the points within the second preset distance range are judged as a cluster, and a clustering result is obtained; Based on the clustering result, the unit area is mapped and divided to obtain multiple area groups.

[0026] It should be noted that the Mean Shift algorithm is a density clustering method. In the analysis of sea areas, due to the large data density of the grid, the data differences in different sea areas are large and complex, and there is a large uncertainty in the clustering grouping form. Therefore, the present invention adopts the Mean Shift clustering algorithm to perform a certain number of iterative analyses, which can quickly classify the water depth and tide level features in multiple sea areas and provide data support for subsequent intelligent channel planning. The first and second preset distances are both distances set by the user.

[0027] According to an embodiment of the present invention, the S103 is specifically: In an area group, the predicted passing time and speed of the target ship are obtained, and in combination with the water depth data and the predicted tide level data of each corresponding unit area, the predicted draft depth and the extra depth of the target ship are dynamically calculated; Within an area group, the extra depths of each unit area are averaged to obtain an average extra depth; The level of each area group is set according to the size of the average extra depth.

[0028] It should be noted that the calculation of the extra depth is obtained through dynamic analysis in combination with the passing time, speed, water depth, and predicted tide level of the target ship. In setting the level of each area group based on the size of the average extra depth, the larger the average extra depth, the higher the level, that is, the higher the priority of the area group, and the lower the corresponding path cost is set.

[0029] According to an embodiment of the present invention, the S104 is specifically: In the map model, set the starting point and ending point of the target ship. Based on the A* algorithm, use the unit area as the moving unit, and based on the level of the area group, set the priority corresponding to each unit area. Set the path cost of each unit area based on the priority, and conduct the shortest path search to obtain multiple sailing paths; Combine the infeasible areas to avoid and optimize the multiple sailing paths to generate multiple optimized paths.

[0030] It should be noted that the unit areas within a region group have the same priority. The multiple optimized paths are paths generated by real-time dynamic analysis and are efficient routes for tide-dependent navigation, which have high guiding significance for the navigation planning process in complex sea areas.

[0031] According to an embodiment of the present invention, each region group includes one or more unit areas.

[0032] According to an embodiment of the present invention, the water depth data, predicted tide level data, and optimized paths are all visually and dynamically displayed through the map model.

[0033] It should be noted that the sea area information such as water depth data, predicted tide level data, and optimized paths is specifically dynamically displayed through multiple layers in the map model, and the resolution of the grid data can be dynamically adjusted based on the data transmission status.

[0034] It is worth mentioning here that the analysis of the underkeel clearance is of great significance for ocean navigation. It changes with the changes in the actual draft and actual water depth. The factors causing changes in the draft include various ones, such as the trim and list of the ship, navigation sinkage, fuel and supplies consumption, change in trim, different sea water densities, ship draft increment caused by waves, etc., while the factors affecting the actual water depth include tides, meteorological water level fluctuations, sediment deposition, etc., and the accurate analysis of the underkeel clearance directly affects the safety of navigation planning.

[0035] Traditional underkeel clearances are often analyzed based on static sea area data, lacking the ability of dynamic analysis, making it difficult to analyze the potential risks in actual navigation. Moreover, the navigation planning based on the underkeel clearance often lacks a dynamic regional feature analysis process, resulting in low navigation safety and navigation efficiency, making it difficult to avoid potential risk factors and difficult to comprehensively improve navigation efficiency.

[0036] Based on this, the present invention divides the target sea area into regions. For each unit region, the corresponding water depth and predicted tide level characteristics are dynamically obtained, and clustering analysis is performed based on the two-dimensional characteristics to divide into multiple region groups. Within a region group, the navigation characteristics and sea area characteristics are similar. Further, by dividing the region groups for unit region analysis, dynamic extra-depth calculation and analysis are performed for the same region group, and priorities are set. Based on the priorities, dynamic route planning is performed for the unit regions, improving the route efficiency of tidal navigation, enhancing the dynamic route planning ability for complex sea areas, effectively avoiding potential risk factors, and effectively performing regional dynamic classification planning for the target sea area. Further, based on the classification form and priorities of the region groups, the hydrological data of different regions can be dynamically and preferentially displayed, improving the accuracy of the navigation state assessment of the target sea area, effectively responding to sudden sea condition changes, and reducing the lag of decision support.

[0037] According to an embodiment of the present invention, it further includes: Select a real-time route from multiple optimized paths; In the map model, based on the real-time route, the corresponding passing unit regions are screened out and marked according to the region groups to which the passing unit regions belong, obtaining a real-time region group; At a historical time point, based on the direction and order of the real-time route, actual water depth data of the real-time region group is obtained and serialized to form a sequence of data; Based on multiple selected historical time points, multiple sequences of data are obtained; Construct an LSTM sequence network, and import the multiple sequences of data as training data into the sequence network for sequence feature learning and model training; During the actual navigation of the target ship, based on the passing points, real-time water depth and real-time draft depth data are extracted, and the extra-depth of the passing points is calculated. Based on the passing order, the extra-depth and real-time water depth data of the passing points are serialized to obtain a first real-time sequence and a second real-time sequence; The second real-time sequence is imported into the sequence network for prediction to obtain a predicted sequence. Through the predicted sequence and the real-time draft depth, the extra-depth of the predicted sequence is calculated to obtain a predicted extra-depth sequence; Based on the first real-time sequence and the predicted extra-depth sequence, real-time early warning assessment of the extra-depth double sequence of the target ship is performed, and navigation risk control of the target ship is carried out.

[0038] It should be noted that generally, there are multiple real-time region groups. The passing points can be set at passing unit regions or at preset distance intervals. The first real-time sequence is the real-time extra-depth sequence, and the second real-time sequence is the real-time draft depth sequence.

[0039] It is worth mentioning here that traditional ship navigation technology is difficult to effectively predict, analyze and give early warning of the extra depth of water. It often makes judgments based on manual experience combined with real-time data, with relatively low early warning decision-making ability, and it is difficult for ship platforms to adapt to the integrated route management of multiple ships. Based on this, the present invention obtains the draft and water depth data of the target ship in the real-time route (obtained based on real-time monitoring), generates a real-time sequence based on the passing route, and further obtains historical draft and water depth data based on the set real-time route for sequence feature learning, trains a prediction network based on LSTM. Through this network, real-time prediction of the extra depth of water of the target ship is carried out to obtain a prediction sequence, and dual early warning analysis is carried out by combining the real-time sequence and the prediction sequence of the extra depth of water, so as to safely and effectively regulate the navigation state of the target ship, effectively avoid potential navigation risks, and is applicable to the safe navigation analysis of multiple ships by the navigation platform.

[0040] Among the multiple historical time points, a preset number of time points can be selected as historical time points based on a selected historical navigation time period.

[0041] According to an embodiment of the present invention, in the regional clustering analysis, it further includes: Obtain the grid resolutions of the water depth data and the predicted tide level data, and dynamically allocate weights Q1 and Q2 through the grid resolutions; Based on H, obtain the neighborhood points of the initial center point, and introduce the standard Euclidean distance to calculate the distance between data points during the determination of neighborhood points; Calculate the distances of the water depth feature and the tide level feature in the two data points and perform weighted averaging based on Q1 and Q2 to obtain the data point distance.

[0042] It should be noted that the grid resolution can reflect the data accuracy. In the present invention, based on the real-time data transmission state of the navigation platform, the grid resolutions of the current water depth data and the predicted tide level data are obtained, and based on this, weight matching is performed on the two types of data and applied to the distance calculation in the clustering process, which can effectively improve the feature classification effect and clustering efficiency of the clustering unit area. The higher the grid resolution, the higher the weight Q is set.

[0043] Figure 2 The block diagram of an intelligent navigation system based on extra depth of water management according to the present invention is shown.

[0044] The second aspect of the present invention also provides an intelligent navigation system 2 based on extra depth of water management. The system includes: a memory 21 and a processor 22. The memory 21 includes an intelligent navigation program based on extra depth of water management. When the intelligent navigation program based on extra depth of water management is executed by the processor 22, the following steps are implemented: S101: Generate a map model based on the target sea area. During an analysis period, obtain the water depth data and predicted tide level data based on grid data within the target sea area, and set the feasible area and the infeasible area. S102: In the map model, divide the target sea area into multiple unit areas. For each unit area, extract the characteristic data in two dimensions of water depth and tide level, and use the characteristic data as sample data to perform regional clustering analysis based on the Mean Shift algorithm to obtain multiple area groups. S103: Take the area group as the analysis unit, dynamically analyze the draft depth of the target ship, predict the average under-keel clearance in each area group, and classify the area groups based on the average under-keel clearance. S104: In the map model, set the path cost according to the area group level, use the unit area as the moving unit, perform navigation planning based on the A* algorithm, and generate multiple optimized paths.

[0045] It should be noted that the map model and the relevant hydrological data are specifically provided based on the S-100 hydrological data service platform. The water depth data and the predicted tide level data correspond to the S-102 water depth data and the S-104 predicted tide level, both of which are online hydrological data. S-100 is a general hydrographic data model, specifically an international hydrographic standard. S-102 and S-104 are both navigation data specifications.

[0046] According to the embodiment of the present invention, the S101 is specifically as follows: Based on the scope of the target sea area, construct a two-dimensional visual map model. Obtain the water depth data and the predicted tide level data based on grid data within the target sea area. Perform dynamic water depth assessment according to the water depth data and the predicted tide level data, and combine the fixed draft depth of the target ship to set the preliminary feasible area and the infeasible area.

[0047] It should be noted that the analysis period is a navigation planning period. The map model is used to visualize the sea area data and plan the navigation route. The water depth data includes the actual water depth, water depth deviation, bottom type number, uncertainty range, etc. The predicted tide level data includes high tide level, low tide level, tide time, meteorological information, etc. There are corresponding water depth data and predicted tide level data in each grid in the map model, and the data volume is determined based on the network resolution.

[0048] According to the embodiment of the present invention, the S102 is specifically as follows: In the map model, divide the target sea area into multiple unit areas to ensure that the area and contour of each unit area are consistent. For a unit area, multi-dimensional information extraction and information feature vectorization are performed on the water depth data and the predicted tide level data to obtain the water depth feature and the tide level feature; Analyze the water depth and tide level feature data of each unit area. Using the water depth feature and the tide level feature as sample data, based on the Mean Shift algorithm, use the sample data of each unit area as the initial center point for clustering iteration, and map and divide multiple regional groups based on the clustering results.

[0049] It should be noted that the unit area is generally divided by a grid to optimize the path planning process.

[0050] According to the embodiment of the present invention, the regional clustering analysis includes: For each unit area, regard each sample data as a data point, set the bandwidth H, and use each data point as the initial center point; Based on H, obtain the neighborhood points of the initial center point. In the process of determining the neighborhood points, introduce the standard Euclidean distance to calculate the distance between data points, and use the distance mean of the water depth feature and the tide level feature in the two data points as the data point distance; Based on the Mean Shift algorithm, calculate the vector from the neighborhood point to the center point, and perform weighted averaging on the vector through the Gaussian kernel function to obtain the mean shift vector; According to the mean shift vector, move the initial center point and update the center point. Loop and iterate all the initial center points until the iteration times are reached or the moving distance of the initial center point is less than the first preset distance; After the iteration is completed, among the initial center points, determine the points within the second preset distance range as a cluster, and obtain the clustering result; Based on the clustering result, perform mapping division on the unit area to obtain multiple regional groups.

[0051] It should be noted that the Mean Shift algorithm is a density clustering method. In the analysis of sea areas, due to the large data density of the grid, the data differences in different sea areas are large and complex, and the clustering grouping form has great uncertainty. Therefore, the present invention adopts the Mean Shift clustering algorithm to perform a certain number of iterative analyses, which can quickly classify the water depth and tide level features in multiple sea areas and provide data support for subsequent intelligent channel planning. The first and second preset distances are both distances set by the user.

[0052] According to the embodiment of the present invention, the S103 is specifically: In a regional group, obtain the predicted passing time and speed of the target ship, and combine the water depth data and the predicted tide level data of each corresponding unit area to dynamically calculate the predicted draft depth and the extra draft depth of the target ship; Within a regional group, equalization is performed based on the extra depth of each unit area to obtain the average extra depth. The level of each regional group is set according to the magnitude of the average extra depth.

[0053] It should be noted that the calculation of the extra depth is obtained through dynamic analysis in combination with the passage time, speed, water depth, and predicted tide level of the target ship. In setting the level of each regional group based on the magnitude of the average extra depth, the greater the average extra depth, the higher the level, that is, the higher the priority of the regional group, and the lower the corresponding path cost is set.

[0054] According to an embodiment of the present invention, the S104 is specifically as follows: In the map model, the starting point and the ending point of the target ship are set. Based on the A* algorithm, with the unit area as the moving unit, and based on the level of the regional group, the priority corresponding to each unit area is set. The path cost of each unit area is set based on the priority, and the shortest path search is performed to obtain multiple navigation paths. Combined with the infeasible areas, multiple navigation paths are avoided and optimized to generate multiple optimized paths.

[0055] It should be noted that the priorities of the unit areas within a regional group are the same. The multiple optimized paths are paths generated through real-time dynamic analysis and are efficient routes for tide-dependent navigation, which have high guiding significance for the navigation planning process in complex sea areas.

[0056] According to an embodiment of the present invention, each regional group includes one or more unit areas.

[0057] According to an embodiment of the present invention, the water depth data, the predicted tide level data, and the optimized paths are all visually and dynamically displayed through the map model.

[0058] It should be noted that the sea area information such as the water depth data, the predicted tide level data, and the optimized paths is specifically dynamically displayed through multiple layers in the map model, and the resolution of the grid data can be dynamically adjusted based on the data transmission status.

[0059] It is worth mentioning here that the analysis of the extra depth is of great significance for ocean navigation. It changes with the changes in the actual draft and the actual water depth. The factors causing changes in the draft include various factors such as the trim and list of the ship, the navigation sinkage, the consumption of fuel and supplies, the change in the trim difference, the different seawater densities, the increase in the ship's draft caused by waves, etc., while the factors affecting the actual water depth include tides, meteorological water level changes, sediment deposition, etc., and the accurate analysis of the extra depth directly affects the safety of the navigation plan.

[0060] Traditional under-keel clearance often analyzes based on static sea area data, lacking dynamic analysis capabilities, making it difficult to analyze potential risks during actual navigation. Moreover, the navigation plan based on under-keel clearance often lacks a dynamic regional feature analysis process, resulting in low navigation safety and efficiency, making it difficult to avoid potential risk factors and comprehensively improve navigation efficiency.

[0061] Based on this, the present invention divides the target sea area into regions. For each unit region, it dynamically obtains the corresponding water depth and predicted tide level characteristics, conducts clustering analysis based on two-dimensional characteristics, and divides into multiple region groups. Within the region group, its navigation characteristics and sea area characteristics are similar. Further, by dividing region groups for unit region analysis, it calculates and analyzes the dynamic under-keel clearance for the same region group, sets priorities, and conducts dynamic route planning for unit regions based on priorities, improving the route efficiency of tide-dependent navigation, enhancing the dynamic route planning ability for complex sea areas, effectively avoiding potential risk factors, and effectively conducting regional dynamic classification planning for the target sea area. Furthermore, based on the classification form and priorities of region groups, it can dynamically and preferentially display the hydrological data of different regions, improving the accuracy of navigation state assessment for the target sea area, effectively responding to sudden sea condition changes, and reducing the lag of decision support.

[0062] The third aspect of the present invention also provides a computer-readable storage medium, which includes an intelligent navigation program based on under-keel clearance management. When the intelligent navigation program based on under-keel clearance management is executed by a processor, it realizes the steps of the intelligent navigation method based on under-keel clearance management as described in any one of the above.

[0063] The present invention discloses an intelligent navigation method and system based on under-keel clearance management. First, a map model is generated for the target sea area, and grid water depth and predicted tide level data are obtained within the analysis period, and feasible and infeasible regions are set. Then, the sea area is divided into multiple unit regions, water depth and tide level characteristic data are extracted, and the Mean Shift algorithm is used for regional clustering to obtain multiple region groups. Subsequently, taking the region group as a unit, it dynamically analyzes the draft depth of the target ship, predicts the average under-keel clearance of each region group and classifies them. Finally, in the map model, path costs are set according to the region group levels, and the A* algorithm is used to plan the navigation path, generating multiple optimized paths, effectively improving navigation safety and efficiency, and realizing accurate navigation risk analysis and management based on under-keel clearance.

[0064] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed with each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0065] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0066] In addition, each functional unit in the embodiments of the present invention can be all integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in a unit. The above integrated units can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0067] Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0068] Alternatively, if the above integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0069] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. An intelligent navigation method based on redundant water depth management, characterized in that, Including: S101: Generate a map model based on the target sea area. In an analysis period, obtain the water depth data and predicted tide level data based on grid data within the target sea area, and set the feasible area and the infeasible area. S102: In the map model, divide the target sea area into multiple unit areas. For each unit area, extract the feature data in two dimensions of water depth and tide level, and use the feature data as sample data to perform regional clustering analysis based on the Mean Shift algorithm to obtain multiple area groups. S103: Take the area group as the analysis unit, dynamically analyze the draft of the target ship, predict the average under-keel clearance in each area group, and classify the area groups based on the average under-keel clearance. S104: In the map model, set the path cost according to the area group level, use the unit area as the moving unit, perform navigation planning based on the A* algorithm, and generate multiple optimized paths.

2. The intelligent navigation method based on redundant water depth management according to claim 1, characterized in that, The S101 is specifically as follows: Based on the scope of the target sea area, construct a two-dimensional visual map model. Obtain the water depth data and predicted tide level data based on grid data within the target sea area. Perform dynamic water depth assessment according to the water depth data and predicted tide level data, and set the initial feasible area and infeasible area in combination with the fixed draft of the target ship.

3. The intelligent navigation method based on redundant water depth management according to claim 1, characterized in that, The S102 is specifically as follows: In the map model, divide the target sea area into multiple unit areas to ensure that the area and contour of each unit area are consistent. For a unit area, perform multi-dimensional information extraction and information feature vectorization on the water depth data and predicted tide level data to obtain the water depth feature and the tide level feature. Analyze the water depth and tide level feature data of each unit area, use the water depth feature and the tide level feature as sample data, and based on the Mean Shift algorithm, use the sample data of each unit area as the initial center point for clustering iteration, and divide multiple area groups based on the clustering result mapping.

4. The intelligent navigation method based on redundant water depth management according to claim 3, characterized in that, The regional clustering analysis includes: For each unit area, take each sample data as a data point, set the bandwidth H, and use each data point as the initial center point. Based on H, obtain the neighborhood points of the initial center point. In the process of determining the neighborhood points, introduce the standard Euclidean distance to calculate the distance between data points, and use the average value of the distances of the water depth feature and the tide level feature in the two data points as the data point distance. Based on the Mean Shift algorithm, calculate the vector from the neighborhood point to the center point, and perform weighted averaging on the vector through the Gaussian kernel function to obtain the mean shift vector. Move the initial center point according to the mean shift vector and update the center point, and loop and iterate all the initial center points until the iteration times are reached or the moving distance of the initial center point is less than the first preset distance. After the iteration is completed, among the initial center points, judge the points within the second preset distance as a cluster, and obtain the clustering result. Based on the clustering result, perform mapping division on the unit area to obtain multiple area groups.

5. The intelligent navigation method based on redundant water depth management according to claim 1, characterized in that, The S103 is specifically as follows: In an area group, obtain the estimated passing time and speed of the target ship, and dynamically calculate the predicted draft and under-keel clearance of the target ship in combination with the water depth data and predicted tide level data of each corresponding unit area. Within a regional group, equalization is performed based on the surplus water depth of each unit area to obtain the average surplus water depth. The level of each regional group is set according to the magnitude of the average surplus water depth.

6. The intelligent navigation method based on redundant water depth management according to claim 1, characterized in that, The S104 is specifically as follows: In the map model, set the starting point and the ending point of the target ship. Based on the A* algorithm, use the unit area as the moving unit, and based on the level of the regional group, set the priority corresponding to each unit area. Set the path cost for each unit area and perform the shortest path search to obtain multiple navigation paths. Combined with the infeasible areas, avoid and optimize the multiple navigation paths to generate multiple optimized paths.

7. The intelligent navigation method based on redundant water depth management according to claim 1, characterized in that, Each regional group includes one or more unit areas.

8. An intelligent navigation method based on under-keel clearance management according to claim 1, characterized in that, The water depth data, the predicted tide level data, and the optimized paths are all visually and dynamically displayed through the map model.

9. An intelligent navigation system based on under-keel clearance management, characterized in that, The system includes: a memory and a processor. The memory includes an intelligent navigation program based on surplus water depth management. When the intelligent navigation program based on surplus water depth management is executed by the processor, the following steps are implemented: S101: Generate a map model based on the target sea area. In an analysis period, obtain the water depth data and the predicted tide level data based on the grid data in the target sea area and set the feasible areas and the infeasible areas. S102: In the map model, divide the target sea area into multiple unit areas. For each unit area, extract the characteristic data in two dimensions of water depth and tide level, and use the characteristic data as the sample data. Based on the Mean Shift algorithm, perform regional clustering analysis to obtain multiple regional groups. S103: Take the regional group as the analysis unit, dynamically analyze the draft depth of the target ship, and predict the average surplus water depth in each regional group. Classify the regional groups based on the average surplus water depth. S104: In the map model, set the path cost according to the regional group level, use the unit area as the moving unit, perform the navigation planning based on the A* algorithm, and generate multiple optimized paths.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes an intelligent navigation program based on surplus water depth management. When the intelligent navigation program based on surplus water depth management is executed by the processor, the steps of the intelligent navigation method based on surplus water depth management described in any one of claims 1 to 8 are implemented.

Images