A method, device and electronic equipment for assessing the risk of ship collision in complex water areas

Abstract

The application relates to a complex water area ship collision risk assessment method, device and electronic equipment, and belongs to the technical field of ship traffic management and safety monitoring, wherein the method comprises the following steps: acquiring ship navigation data; performing clustering processing on ship position point information in the ship navigation data to obtain ship cluster information; constructing a multi-ship collision risk measurement model based on time-varying collision risk and a ship encounter situation complexity model based on a complex network according to the ship navigation data and the ship cluster information; performing linear combination on the multi-ship collision risk measurement model and the ship encounter situation complexity model to obtain a ship collision risk assessment model; and determining a regional ship collision risk value according to the ship collision risk assessment model. The application improves the precision of ship collision avoidance and improves the safety of ship navigation.

Description

Technical Field

[0001] This invention relates to the field of ship traffic management and safety monitoring technology, and in particular to a method, device and electronic equipment for assessing ship collision risks in complex waters. Background Technology

[0002] Maritime transport is an indispensable and vital component of global trade and economic development. However, frequent ship collisions in complex waters pose serious challenges to navigation safety and maritime traffic management. Current methods for assessing and warning of ship collision risks have many limitations, such as insufficient adaptability to complex waters and difficulties in real-time monitoring of dynamic collision risks.

[0003] Traditional ship collision risk assessment methods are mainly based on static data and simplified models, which cannot fully consider the dynamic environment of complex waters and the interaction of multiple factors. Although the widely used AIS (Automatic Identification System) technology provides real-time position and status information of ships, it still has limitations such as incomplete information acquisition and simple analysis methods.

[0004] The existing technical problems mainly include, but are not limited to: 1. lack of accurate collision risk assessment methods for complex waters; 2. insufficiently advanced technical means for real-time monitoring of dynamic collision risks; 3. the ability of early warning systems to predict collision hazards needs to be improved; 4. low efficiency in data processing and analysis, and insufficient intelligence in decision support. Summary of the Invention

[0005] In view of this, it is necessary to provide a method, apparatus and electronic device for assessing ship collision risk in complex waters, in order to solve the technical problem that there is no accurate collision risk assessment method in complex waters in the prior art.

[0006] To address the above problems, this invention provides a method for assessing ship collision risks in complex waters, comprising:

[0007] Acquire ship navigation data;

[0008] Clustering is performed on the ship position information in the ship navigation data to obtain ship settlement information;

[0009] Based on the ship navigation data and the ship settlement information, a multi-ship collision risk measurement model based on time-varying collision risk is constructed, as well as a ship encounter situation complexity model based on complex networks.

[0010] A ship collision risk assessment model is obtained by linearly combining the multi-ship collision risk measurement model and the ship encounter situation complexity model.

[0011] Based on the aforementioned ship collision risk assessment model, the regional ship collision risk value is determined.

[0012] In one possible implementation, the step of clustering the ship position information in the ship navigation data to obtain ship settlement information includes:

[0013] A preset density-based clustering algorithm is used to cluster the ship position points in the ship navigation data at different times to obtain the ship settlement division results;

[0014] The ship settlement division results include initial ship settlement information and isolated ship noise point information. The isolated ship noise point information is then removed to obtain the ship settlement information.

[0015] In one possible implementation, the ship navigation data includes ship type, length, speed, and navigation environment; the step of constructing a multi-ship collision risk measurement model based on time-varying collision risk, using the ship navigation data and the ship settlement information, includes:

[0016] Using a pre-defined four-dimensional ship domain as a framework, and ship type, ship length, speed and navigation environment as variables, a dynamic ship domain is constructed.

[0017] Identify the vessel itself and other vessels in a meeting situation with it, and determine the meeting process data of the vessel itself and other vessels;

[0018] Based on the encounter process data of this vessel and other vessels and the dynamic vessel domain, the boundary of the vessel safety domain is determined;

[0019] Based on the aforementioned boundaries of the ship safety domain, the conditions under which a ship is at risk of collision are determined, and a speed barrier model for collision risk is constructed based on these conditions.

[0020] Based on the relationship between the ship's speed and the speed barrier model of collision risk, determine whether a risk exists;

[0021] Based on the speed barrier model, a multi-ship collision risk measurement model based on time-varying collision risk is constructed.

[0022] In one possible implementation, constructing a ship encounter situation complexity model based on a complex network, using the ship navigation data and the ship settlement information, includes:

[0023] Based on ship trajectory data, network nodes are determined according to the location of each ship in complex waters;

[0024] Determine the edge connection rules and edge weights for the ship encounter situation complexity network;

[0025] Based on traffic density factor and traffic conflict factor, and with network nodes, edge rules and edge weights as conditions, a ship encounter situation complexity model based on complex networks is constructed.

[0026] In one possible implementation, the linear combination of the multi-ship collision risk measurement model and the ship encounter situation complexity model to obtain the ship collision risk assessment model includes:

[0027] The initial ship collision risk assessment model is obtained by linearly combining the multi-ship collision risk measurement model and the ship encounter situation complexity model.

[0028] Determine the Shalipur value of the ships in each of the aforementioned ship settlement information;

[0029] Based on the numerical results of the initial ship collision risk assessment model and the aforementioned Shalip value, a ship collision risk assessment model for the region is determined.

[0030] In one possible implementation, the ship collision risk assessment model for the area can be expressed by the following formula:

[0031]

[0032]

[0033] Among them, CCR j This represents the numerical results of the collision risk for each settlement; CRI i The ship collision risk index; S j S represents the Saliph value of the j-th settlement. i Let represent the Shalipur value of vessel i, M-RCR represent the numerical result of regional collision risk, i represent vessel i, n represent the number of vessels, j represent settlement j, and m represent the number of settlements.

[0034] In one possible implementation, after determining the regional ship collision risk value, the following is also included:

[0035] The spatiotemporal distribution characteristics of the collision risk value of ships in the area are displayed by using a preset thermal animation method.

[0036] Secondly, the present invention also provides a device for assessing ship collision risks in complex waters, comprising:

[0037] The acquisition module is used to acquire ship navigation data;

[0038] The ship settlement information determination module is used to perform clustering processing on the ship position point information in the ship navigation data to obtain ship settlement information;

[0039] The model building module is used to construct a multi-ship collision risk measurement model based on time-varying collision risk and a ship encounter situation complexity model based on complex networks, based on the ship navigation data and the ship settlement information.

[0040] The ship collision risk assessment module is used to linearly combine the multi-ship collision risk measurement model and the ship encounter situation complexity model to obtain the ship collision risk assessment model.

[0041] The risk value determination module is used to determine the regional ship collision risk value based on the ship collision risk assessment model.

[0042] Thirdly, the present invention also provides an electronic device, comprising: a processor and a memory;

[0043] The memory stores a computer-readable program that can be executed by the processor;

[0044] When the processor executes the computer-readable program, it implements the steps in the complex waterway ship collision risk assessment method as described above.

[0045] Fourthly, the present invention also provides a computer-readable storage medium storing one or more programs that can be executed by one or more processors to implement the steps in the complex waterway ship collision risk assessment method as described above.

[0046] The beneficial effects of this invention are as follows: First, ship navigation data is acquired; then, ship position information in the navigation data is clustered to obtain ship cluster information; based on the navigation data and the cluster information, a multi-ship collision risk measurement model based on time-varying collision risk and a ship encounter situation complexity model based on complex networks are constructed; subsequently, the multi-ship collision risk measurement model and the ship encounter situation complexity model are linearly combined to obtain a ship collision risk assessment model; finally, based on the collision risk assessment model, the regional ship collision risk value is determined. This invention achieves the goal of identifying high-risk ships and areas to solve the problem of collision risk assessment in waterways, thereby improving the situational awareness of regional collision risks among maritime authorities and crew members, and enhancing the safety of ship navigation. Attached Figure Description

[0047] Figure 1 A schematic diagram of an embodiment of the ship collision risk assessment method in complex waters provided by the present invention;

[0048] Figure 2 The framework diagram for ship navigation data preprocessing in the ship collision risk assessment method for complex waters provided by the present invention;

[0049] Figure 3 The flowchart of an embodiment of the ship collision risk assessment method in complex waters provided by the present invention is as follows:

[0050] Figure 4 The method for assessing ship collision risks in complex waters provided by this invention includes a multi-ship encounter behavior situation identification diagram.

[0051] Figure 5 The collision risk assessment method for ships in complex waters provided by this invention is based on a safety boundary model diagram in the dynamic ship domain.

[0052] Figure 6 A schematic diagram of the speed domain projection of multiple ship encounters in the complex waterway collision risk assessment method provided by the present invention.

[0053] Figure 7 The flowchart of an embodiment of the ship collision risk assessment method in complex waters provided by the present invention is as follows:

[0054] Figure 8 This is a schematic diagram of an embodiment of the ship optimal anchorage selection device provided by the present invention;

[0055] Figure 9 This is a schematic diagram of the operating environment of an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0056] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0057] A specific embodiment of the present invention discloses a method for assessing ship collision risks in complex waters. Please refer to [link / reference]. Figure 1 ,include:

[0058] S101. Obtain ship navigation data;

[0059] S102. Cluster the ship position information in the ship navigation data to obtain ship settlement information;

[0060] S103. Based on the ship navigation data and the ship settlement information, construct a multi-ship collision risk measurement model based on time-varying collision risk, and construct a ship encounter situation complexity model based on complex networks.

[0061] S104. Linearly combine the multi-ship collision risk measurement model and the ship encounter situation complexity model to obtain the ship collision risk assessment model.

[0062] S105. Determine the regional ship collision risk value based on the aforementioned ship collision risk assessment model.

[0063] In this embodiment, ship navigation data is first acquired; then, the ship position information in the navigation data is clustered to obtain ship cluster information; based on the navigation data and the cluster information, a multi-ship collision risk measurement model based on time-varying collision risk and a ship encounter situation complexity model based on complex networks are constructed; subsequently, the multi-ship collision risk measurement model and the ship encounter situation complexity model are linearly combined to obtain a ship collision risk assessment model; finally, based on the ship collision risk assessment model, the regional ship collision risk value is determined. This invention achieves the goal of identifying high-risk ships and areas to solve the problem of collision risk assessment in waterways, thereby improving the situational awareness of regional collision risks among maritime authorities and crew members, and enhancing the safety of ship navigation.

[0064] In step S101, ship navigation data can be obtained through information data transmitted in real time by the AIS device, or through other devices. The ship navigation data includes time, ship number, location information, and motion status.

[0065] Furthermore, this embodiment of the invention proposes a method for rapidly and synchronously processing ship AIS data using the Python platform. This method mainly comprises four parts: data extraction, data cleaning, data interpolation, and data transformation. The AIS data preprocessing framework diagram is shown below. Figure 2 As shown. First, the acquired AIS data for the waterway is decoded and converted into a readable format. The data is saved as a txt file and then input into Python to extract the required data types, including time, MMS, latitude and longitude, heading, and speed. Next, ship tracks within a certain range are filtered, and outliers, such as position coordinates and headings outside the reasonable range, are processed. Missing and duplicate values ​​are filled and deleted to filter out unreasonable ship tracks, completing the data cleaning. Based on this, cubic spline interpolation is used to interpolate and repair the cleaned data. Finally, data transformation is performed, mainly including converting time information (YYYY-MM-DDHH:MM:SS) to corresponding timestamps; projecting latitude and longitude coordinates onto a plane coordinate system (in meters) using the Mercator projection method; and converting speed information to meters per second in knots.

[0066] In some embodiments, the process of clustering the ship position information in the ship navigation data to obtain ship settlement information is described in the following example. Figure 3 ,include:

[0067] S301. A preset density-based clustering algorithm is used to cluster the ship position points in the ship navigation data at different times to obtain the ship settlement division results.

[0068] S302. The ship settlement division result includes initial ship settlement information and isolated ship noise point information. The isolated ship noise point information is removed to obtain ship settlement information.

[0069] In this embodiment, by using the density-based noise spatial clustering method (DBSCAN) and setting reasonable parameters for the DBSCAN algorithm, ships in the waterway are divided into different ship clusters and ship noise points, thereby identifying multi-ship encounter situations.

[0070] The DBSCAN algorithm includes the following steps:

[0071] First, ship navigation data is collected. The DBSCAN algorithm package is called, and the algorithm parameters are set appropriately. In this embodiment, parameters Eps = 2 and Minpt = 6nm. These parameter values ​​match actual ship collision scenarios (collisions involving at least two ships) and simulate the normal operating range of shipboard radar. After the algorithm executes, ships in the water are divided into different ship clusters. Ships not included in any cluster are considered noise points, thus completing the identification of multi-ship encounter situations. It should be noted that identified ship noise points are considered not to pose a collision risk to other ships; therefore, in this embodiment, isolated ship noise points are discarded. Figure 4 As shown.

[0072] In some embodiments, the ship navigation data includes ship type, length, speed, and navigation environment; the step of constructing a multi-ship collision risk measurement model based on time-varying collision risk according to the ship navigation data and the ship settlement information includes:

[0073] Using a pre-defined four-dimensional ship domain as a framework, and ship type, ship length, speed and navigation environment as variables, a dynamic ship domain is constructed.

[0074] Identify the vessel itself and other vessels in a meeting situation with it, and determine the meeting process data of the vessel itself and other vessels;

[0075] Based on the encounter process data of this vessel and other vessels and the dynamic vessel domain, the boundary of the vessel safety domain is determined;

[0076] Based on the aforementioned boundaries of the ship safety domain, the conditions under which a ship is at risk of collision are determined, and a speed barrier model for collision risk is constructed based on these conditions.

[0077] Based on the relationship between the ship's speed and the speed barrier model of collision risk, determine whether a risk exists;

[0078] Based on the speed barrier model, a multi-ship collision risk measurement model based on time-varying collision risk is constructed.

[0079] In this embodiment, variables such as ship characteristics (ship type, length, speed, etc.) and the waterway navigation environment are incorporated into the ship domain. Using a four-dimensional ship domain (QSD) as a framework, variables such as ship type (T), length (L), speed (V), and navigation environment (E) are introduced and their parameters are calibrated to construct a dynamic ship domain adapted to the characteristics of ship traffic flow in complex waterways. This domain serves as a standard for determining whether there is a spatial risk of collision between ships. The QSD construction is shown below:

[0080]

[0081]

[0082] R starb =(0.2+k) DT )L

[0083] R port = (0.2 + 0.75k) DT )L

[0084] Among them, R fore R aft R starb R port It represents the radius of the ship's domain in four different directions, where L is the ship's length and k is the radius of the domain in four different directions. AD ,k DT These are the transverse and longitudinal coefficients of the ship.

[0085] Furthermore, select multi-ship encounter process data A{L A ,P A (t),V A (t)},B{L B ,P B (t),V B (t)},C{L C ,P C (t),V C Assuming vessel A is the main vessel and vessels B and C are other vessels in the encounter situation, the boundary of the vessel safety domain is determined based on the marked dynamic vessel domain and the characteristics of the encountering vessels. The safety boundary model diagram based on the dynamic vessel domain is shown below. Figure 5 As shown.

[0086] The conditions under which a ship is at risk of collision, after considering safety boundaries, can be transformed into:

[0087]

[0088] Among them, P A (t c ) and P B (t c ) indicates that at t c Let _t ...

[0089] Based on the trajectory data of the ship encounter process, the collision risk assessment condition P is... A (t c ) and P B (t c Replacing it with a model that considers speed, we obtain a speed barrier model that poses a collision risk:

[0090]

[0091] Where t0 is the collision risk analysis time, t i P is a point in time during the encounter between the ships after time t0. A (t0) represents the position of the ship at time t0, P shipj (t i ) for t i The position of his ship at that moment.

[0092] Based on this, whether the ship's speed falls into the speed barrier set is used as the standard for whether a collision risk exists; based on historical multi-ship encounter spatiotemporal data and combined with Boolean logic operations, the multi-ship encounter situation is projected into the ship speed space.

[0093] A schematic diagram of the speed domain projection of multiple ships meeting is shown below. Figure 6 As shown.

[0094] Based on this, the speed obstacle encountered by multiple ships is defined as:

[0095]

[0096] in, The union of obstacles created by multiple ships in the velocity space.

[0097] Furthermore, by combining the speed characteristics of potential collision vessels in the water, i.e. the speed space, a set of the vessel's speeds is constructed, and a multi-vessel collision risk measurement model based on TCR is established.

[0098]

[0099] Where, N collision (t) represents the number of sets of velocities that lead to the collision at time t, and N(t) represents the number of sets of velocities that the ship could achieve before the collision occurs.

[0100] Based on this, the overlapping portion of the speed obstacle set and the sailing speed set of multiple ships in the multi-ship encounter situation is extracted from each settlement in the water, and the area of ​​this portion is calculated. By calculating the proportion of this area in the sailing speed set of the ship, the collision risk of ships in the multi-ship encounter situation can be obtained, which can be expressed by the following formula:

[0101]

[0102] Among them, TCR (i)QSD To mitigate the collision risk of a single vessel in situations where multiple vessels meet, VO QSD VO is the area of ​​the overlapping region between the set of speed obstacles caused by other vessels' safety zones and the set of speeds of the ship itself. region This represents the area of ​​the region encompassing the ship's speed.

[0103] In some embodiments, constructing a complex network-based ship encounter situation complexity model based on the ship navigation data and the ship settlement information includes:

[0104] Based on ship trajectory data, network nodes are determined according to the location of each ship in complex waters;

[0105] Determine the edge connection rules and edge weights for the ship encounter situation complexity network;

[0106] Based on traffic density factor and traffic conflict factor, and with network nodes, edge rules and edge weights as conditions, a ship encounter situation complexity model based on complex networks is constructed.

[0107] In this embodiment, each ship is considered as a node in the network and is determined as an edge connection rule for the complex network, introducing a ship proximity rate R. ij The degree of convergence and divergence between two ships is represented by the projection of their relative velocities onto their relative distance:

[0108]

[0109] in, and Let R be the relative distance and relative speed between the two ships. ij A value greater than or equal to 0 indicates that the two ships are sailing in parallel or in separate areas, and there is no connecting edge between them; if R ij A value less than 0 indicates that the ships tend to converge, and two ships form a connecting edge.

[0110] Finally, the edge weights of the complex traffic situation network are determined. Traffic density factor and traffic conflict factor are selected to calculate the complexity between two ships, mapping the complexity between ship pairs to the weights of the complex network. The calculation formula is as follows:

[0111]

[0112] Where, θ ij The angle at which the trajectories of the two ships intersect.

[0113] Furthermore, based on the above process, a complex network of waterway traffic situation is obtained. Indicators such as node degree k and vertex strength S in the network are selected to measure and normalize the complexity of the ship encounter situation. The calculation process is as follows:

[0114]

[0115]

[0116]

[0117] Among them, U i Let M represent the complexity of the encounter situation for a single vessel, and M represent the complexity of the traffic situation in the entire complex waterway. i This represents the normalized numerical value of the situational complexity encountered by a single ship.

[0118] In some embodiments, the multi-ship collision risk measurement model and the ship encounter situation complexity model are linearly combined to obtain a ship collision risk assessment model. (See also...) Figure 7 ,include:

[0119] S701. Linearly combine the multi-ship collision risk measurement model and the ship encounter situation complexity model to obtain an initial ship collision risk assessment model.

[0120] S702. Determine the Shalip value of each ship in the ship settlement information;

[0121] S703. Based on the numerical results of the initial ship collision risk assessment model and the Shalip value, determine the ship collision risk assessment model for the region.

[0122] In step S701, a linear combination method is used to integrate the collision risks of multiple ships and the complexity of the ship encounter situation. The final result is used as the collision risk of a single ship. The calculation process is as follows:

[0123]

[0124] Among them, CRI i For ship collision risk index, w a and w b Here are the weighting coefficients, and w a +w b =1, which can be adjusted as needed depending on the situation and the influence of waterway traffic conditions and navigation environment.

[0125] When CCR i If the M-RCR value exceeds the set risk threshold, the system will issue a warning notification.

[0126] In step S702, the Shapely value from cooperative game theory is introduced. Originally applied in economics, the Shapely value measures the contribution of each member to the collective. In this embodiment, the Shapely value is used to identify the contribution of each vessel in the settlement to the area's collision risk. The Shapely value of each vessel in the settlement can be expressed by the following formula:

[0127]

[0128] Where i represents ship i; M is the group formed by ship i; v refers to the number of ships in group M; N represents the group formed by all ships; n represents the total number of ships in group N; A(M) represents the total collision risk of all ships in group M; A(M-{i}) represents the total collision risk of all ships when ship i is not in group M; S i This represents the Shalipur value of ship i.

[0129] Based on the collision risk assessment results and the shape value of each vessel, the area collision risk is finally assessed from a macro perspective. The following formula is used for calculation:

[0130]

[0131]

[0132] Among them, CCR j This represents the numerical results of the collision risk for each settlement; CRI i The ship collision risk index; S j S represents the Saliph value of the j-th settlement. i Let represent the Shalipur value of vessel i, M-RCR represent the numerical result of regional collision risk, i represent vessel i, n represent the number of vessels, j represent settlement j, and m represent the number of settlements.

[0133] When CCR j If the M-RCR value exceeds the set risk threshold, the system will issue a warning notification.

[0134] Finally, the collision risk assessment results were saved as a CSV file and imported into QGIS software. EPSG:4326 was selected as the geodetic coordinate system, and a heatmap was chosen. Appropriate parameters were set in the function bar, and the collision risk visualization operation was performed. The above experimental steps were repeated to obtain the collision risk visualization results for the water area at different times. Based on these results, the spatiotemporal distribution characteristics of the water area's collision risk were displayed.

[0135] Based on the above-mentioned method for assessing ship collision risks in complex waters, this invention also provides a device for assessing ship risks in complex waters, such as... Figure 8 As shown, it includes: acquisition module 810, ship settlement information determination module 820, model building module 830, ship collision risk assessment model 840, and risk value determination module 850.

[0136] Module 810 is used to acquire ship navigation data;

[0137] The ship settlement information determination module 820 is used to perform clustering processing on the ship position point information in the ship navigation data to obtain ship settlement information.

[0138] The model building module 830 is used to build a multi-ship collision risk measurement model based on time-varying collision risk and a ship encounter situation complexity model based on complex networks, based on the ship navigation data and the ship settlement information.

[0139] The ship collision risk assessment model 840 is used to linearly combine the multi-ship collision risk measurement model and the ship encounter situation complexity model to obtain the ship collision risk assessment model.

[0140] The risk value determination module 850 is used to determine the regional ship collision risk value based on the ship collision risk assessment model.

[0141] like Figure 9 As shown, based on the aforementioned method for assessing ship collision risks in complex waters, this invention also provides an electronic device, which can be a mobile terminal, desktop computer, laptop, handheld computer, server, or other computing electronic device. This electronic device includes a processor 910, a memory 920, and a display 930. Figure 9 Only some components of the electronic device are shown; however, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0142] In some embodiments, memory 920 may be an internal storage unit of the electronic device, such as a hard disk or memory. In other embodiments, memory 920 may be an external storage device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Furthermore, memory 920 may include both internal and external storage devices. Memory 920 is used to store application software and various types of data installed on the electronic device, such as program code installed on the electronic device. Memory 920 may also be used to temporarily store data that has been output or will be output. In one embodiment, memory 920 stores a complex waterway ship collision risk assessment program 940, which can be executed by processor 910 to implement the complex waterway ship collision risk assessment method of the various embodiments of this application.

[0143] In some embodiments, processor 910 may be a central processing unit (CPU), microprocessor or other data processing chip, used to run program code stored in memory 920 or process data, such as executing a method for assessing ship collision risks in complex waters.

[0144] In some embodiments, display 930 may be an LED display, a liquid crystal display, a touch-screen liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 930 is used to display information from the electronic equipment for assessing ship collision risks in complex waters and to provide a user interface for visualization. Components 910-930 of the electronic equipment communicate with each other via a system bus.

[0145] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0146] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for assessing ship collision risk in complex waters, characterized in that, include: Acquire ship navigation data; Clustering is performed on the ship position information in the ship navigation data to obtain ship settlement information; Based on the ship navigation data and the ship settlement information, a multi-ship collision risk measurement model based on time-varying collision risk is constructed, as well as a ship encounter situation complexity model based on complex networks. A ship collision risk assessment model is obtained by linearly combining the multi-ship collision risk measurement model and the ship encounter situation complexity model. Based on the aforementioned ship collision risk assessment model, the regional ship collision risk value is determined; The ship navigation data includes ship type, length, speed, and navigation environment; The step of constructing a multi-ship collision risk measurement model based on time-varying collision risk, using the ship navigation data and ship settlement information, includes: Using a pre-defined four-dimensional ship domain as a framework, and ship type, ship length, speed and navigation environment as variables, a dynamic ship domain is constructed. Identify the vessel itself and other vessels in a meeting situation with it, and determine the meeting process data of the vessel itself and other vessels; Based on the encounter process data of this vessel and other vessels and the dynamic vessel domain, the boundary of the vessel safety domain is determined; Based on the aforementioned boundaries of the ship safety domain, the conditions under which a ship is at risk of collision are determined, and a speed barrier model for collision risk is constructed based on these conditions. Based on the relationship between the ship's speed and the speed barrier model of collision risk, determine whether a risk exists; Based on the speed barrier model, a multi-ship collision risk measurement model based on time-varying collision risk is constructed. The step of constructing a complex network-based ship encounter situation complexity model based on the ship navigation data and ship settlement information includes: Based on ship trajectory data, network nodes are determined according to the location of each ship in complex waters; Determine the edge connection rules and edge weights for the ship encounter situation complexity network; Based on traffic density factor and traffic conflict factor, and with network nodes, edge rules and edge weights as conditions, a ship encounter situation complexity model based on complex network is constructed. The linear combination of the multi-ship collision risk measurement model and the ship encounter situation complexity model yields a ship collision risk assessment model, including: The initial ship collision risk assessment model is obtained by linearly combining the multi-ship collision risk measurement model and the ship encounter situation complexity model. Determine the Shalipur value of the ships in each of the aforementioned ship settlement information; Based on the numerical results of the initial ship collision risk assessment model and the Shalip value, the ship collision risk assessment model for the region is determined. The initial ship collision risk assessment model is as follows: in, The ship collision risk index. and These are the weighting coefficients, and + =1, subject to adjustment based on the situation and the influence of waterway traffic conditions and navigation environment. in, To mitigate the collision risk of a single vessel in a multi-vehicle encounter situation, The area of ​​the overlapping region between the set of speed obstacles caused by other vessels' safety zones and the set of speeds of the ship itself. This represents the area of ​​the region encompassing the ship's speed.

2. The method for assessing ship collision risk in complex waters according to claim 1, characterized in that, The process of clustering the ship position information in the ship navigation data to obtain ship settlement information includes: A preset density-based clustering algorithm is used to cluster the ship position points in the ship navigation data at different times to obtain the ship settlement division results; The ship settlement division results include initial ship settlement information and isolated ship noise point information. The isolated ship noise point information is then removed to obtain the ship settlement information.

3. The method for assessing ship collision risk in complex waters according to claim 1, characterized in that, The ship collision risk assessment model for the area can be expressed by the following formula: in, This represents the numerical results of the collision risk for each settlement; The ship collision risk index; Indicates the first j The Saliph value of a settlement, Indicates a ship i The Salipur value, This indicates the numerical results of the regional collision risk. i Indicates a ship i , n Indicates the number of ships, j Represents settlement j , m Indicates the number of settlements.

4. The method for assessing ship collision risk in complex waters according to claim 1, characterized in that, After determining the area's ship collision risk value, the following is also included: The spatiotemporal distribution characteristics of the collision risk value of ships in the area are displayed by using a preset thermal animation method.

5. A device for assessing ship collision risk in complex waters, characterized in that, include: The acquisition module is used to acquire ship navigation data; The ship settlement information determination module is used to perform clustering processing on the ship position point information in the ship navigation data to obtain ship settlement information; The model building module is used to construct a multi-ship collision risk measurement model based on time-varying collision risk and a ship encounter situation complexity model based on complex networks, based on the ship navigation data and the ship settlement information. The ship collision risk assessment module is used to linearly combine the multi-ship collision risk measurement model and the ship encounter situation complexity model to obtain the ship collision risk assessment model. The risk value determination module is used to determine the regional ship collision risk value based on the ship collision risk assessment model. The ship navigation data includes ship type, length, speed, and navigation environment; The step of constructing a multi-ship collision risk measurement model based on time-varying collision risk, using the ship navigation data and ship settlement information, includes: Using a pre-defined four-dimensional ship domain as a framework, and ship type, ship length, speed and navigation environment as variables, a dynamic ship domain is constructed. Identify the vessel itself and other vessels in a meeting situation with it, and determine the meeting process data of the vessel itself and other vessels; Based on the encounter process data of this vessel and other vessels and the dynamic vessel domain, the boundary of the vessel safety domain is determined; Based on the aforementioned boundaries of the ship safety domain, the conditions under which a ship is at risk of collision are determined, and a speed barrier model for collision risk is constructed based on these conditions. Based on the relationship between the ship's speed and the speed barrier model of collision risk, determine whether a risk exists; Based on the speed barrier model, a multi-ship collision risk measurement model based on time-varying collision risk is constructed. The step of constructing a complex network-based ship encounter situation complexity model based on the ship navigation data and ship settlement information includes: Based on ship trajectory data, network nodes are determined according to the location of each ship in complex waters; Determine the edge connection rules and edge weights for the ship encounter situation complexity network; Based on traffic density factor and traffic conflict factor, and with network nodes, edge rules and edge weights as conditions, a ship encounter situation complexity model based on complex network is constructed. The linear combination of the multi-ship collision risk measurement model and the ship encounter situation complexity model yields a ship collision risk assessment model, including: The initial ship collision risk assessment model is obtained by linearly combining the multi-ship collision risk measurement model and the ship encounter situation complexity model. Determine the Shalipur value of the ships in each of the aforementioned ship settlement information; Based on the numerical results of the initial ship collision risk assessment model and the Shalip value, the ship collision risk assessment model for the region is determined. The initial ship collision risk assessment model is as follows: in, The ship collision risk index. and These are the weighting coefficients, and + =1, subject to adjustment based on the situation and the influence of waterway traffic conditions and navigation environment. in, To mitigate the collision risk of a single vessel in a multi-vehicle encounter situation, The area of ​​the overlapping region between the set of speed obstacles caused by other vessels' safety zones and the set of speeds of the ship itself. This represents the area of ​​the region encompassing the ship's speed.

6. An electronic device, characterized in that, include: Processor and memory; The memory stores a computer-readable program that can be executed by the processor; When the processor executes the computer-readable program, it implements the steps in the complex waterway ship collision risk assessment method as described in claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the steps in the complex waterway collision risk assessment method as described in claims 1-4.

Images