Rasterization lane navigation system water area collision risk identification method and device

Abstract

The invention relates to the technical field of ship traffic safety and risk assessment, in particular to a rasterized lane navigation system water area collision risk identification method and device. According to the method, rasterization processing is carried out on a lane-dividing navigation system water area, and the lane-dividing navigation system water area collision risk identification method is constructed from the aspects of navigation lane-dividing congestion degree, ship course deviation degree, ship tracking meeting condition and ship track position distribution on the basis of the ship field, a stimulation response theory, a distribution curve feature identification method and the like. According to the invention, on one hand, a maritime traffic supervisor can be helped to supervise and analyze the collision risk of the lane navigation system water area of the jurisdiction water area, and the traffic supervision and organization work of the traffic supervisor can be promoted; and on the other hand, data support can be provided for researches such as prediction of the collision risk of the lane-based navigation system water area, evaluation of the setting effect of the lane-based navigation system, scheme change and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of ship traffic safety and risk assessment, and in particular to a rasterized method and device for identifying collision risks in a traffic separation system water area. Background Art

[0002] In recent years, with the continuous growth of the global economy, the volume of maritime cargo transportation has continued to grow, and more ships are needed to carry and transport cargo, resulting in increasingly busy maritime ship traffic routes, especially in ports and their surrounding waters, important waterways and straits, where the volume of ships continues to rise, and we need to face more complex ship traffic situations and trends. Under the complex ship traffic conditions, maritime traffic accidents occur frequently, especially the incidence of ship collision accidents is gradually increasing, which seriously threatens maritime traffic safety.

[0003] In order to regulate the increasingly busy and complex ship traffic, since the last century, relevant research on ship routing has been carried out by maritime traffic scholars from all over the world, and fruitful achievements have been made in practical application. Its landmark achievement is the establishment of the Dover Strait Traffic Separation System in 1967. It effectively alleviates the risk of collision in busy waters by regulating the original chaotic ship traffic, separating traffic flows in opposite directions through navigation lanes, and imposing corresponding navigation regulations on the ships therein. However, with the increasing busyness and complexity of ship traffic, the navigation safety of ships cannot be guaranteed to be completely safe even in the waters of the traffic separation system. The complex ship traffic conditions have increased the chances of ships encountering each other, resulting in an increase in the risk of ship collision.

[0004] At the same time, busy and complex ship traffic will cause greater situational awareness pressure on maritime traffic regulators, which will have a certain impact on their ability to accurately and fully identify maritime traffic situations and monitor collision risks.

[0005] In order to reduce and avoid ship collision accidents, many scholars have conducted research on ship collision risks. From the perspective of the scope of research, it can be divided into micro-collision risk research that focuses on the collision risk between ships with the main purpose of ship collision avoidance, and macro-collision risk research that focuses on the overall collision risk of waters with the main purpose of maritime traffic supervision and analysis. These studies have made certain contributions to the safety of maritime traffic. A comprehensive analysis of these studies found that the current quantitative and analytical research on the overall collision risk of waters is mostly focused on open waters, and there is less consideration of restricted waters such as traffic separation schemes. In some studies on the overall collision risk or risk of waters with traffic separation schemes, most studies still start with the influencing factors or parameters of collision risk at the spatial or temporal level of general open waters. However, due to the water characteristics of the traffic separation scheme and the restrictions of relevant regulations, the impact of these traditional collision risk influencing factors on collision risk in the traffic separation scheme is different from that in general open waters. At the same time, these studies lack consideration from the perspective of the water characteristics of the traffic separation scheme and relevant regulations in the selection of collision risk influencing factors or control variables, resulting in insufficient objectivity and accuracy of the identified collision risk results. On the other hand, current research on collision risks in traffic separation schemes mostly estimates relevant risk values ​​from a macro perspective, lacking precise analysis at the spatial and temporal levels. This leads to limited application scenarios of the research and poor scalability, and its help for maritime traffic regulation is also relatively limited. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides a rasterized method and device for identifying collision risks in waters of traffic separation schemes. The present invention makes full use of ship traffic data, fully considers the characteristics of the waters and navigation regulations in the process of identifying collision risks in waters of traffic separation schemes, and driven by a large amount of ship traffic data, can more objectively and accurately identify the ship collision risks in waters of traffic separation schemes, and can perform spatiotemporal characterization and analysis of collision risks.

[0007] The technical means adopted by the present invention are as follows:

[0008] A rasterized method for identifying collision risks in a traffic separation system water area comprises the following steps:

[0009] Obtain basic information of ships in the waters of the traffic separation scheme, and construct a traffic information set ST of ships in the waters of the traffic separation scheme, wherein the basic information of ships includes ship timestamp, ship MMSI, ship longitude, ship latitude, ship speed, ship heading and ship length; obtain basic information of the waters of the traffic separation scheme, and construct a traffic information set TI of the waters of the traffic separation scheme, wherein the basic information of the waters includes the location, scale and recommended heading of the waters of the traffic separation scheme;

[0010] The coordinate system of the traffic separation system waters is rotated to make the navigation lanes parallel to the horizontal axis of the coordinate system, and the traffic information of ships sailing in them is transformed at the same angle. The traffic separation system waters are rasterized to generate the water grid RG. mn ;

[0011] The ship longitude and latitude information in the traffic information set ST of the water area of ​​the traffic separation system is uploaded to the water area grid RG. mn Mapping is performed to construct a ship domain model SD for ships in the traffic separation scheme waters i , and move the ship area to the water grid RG mn Mapping is performed and the traffic lane congestion factor CR is constructed according to the mapped grid conditions. cl ;

[0012] The heading information in the traffic information set ST of the traffic separation system water area is uploaded to the water area grid RG mn Mapping is performed and the ship course deviation factor CR of the traffic lane is constructed using the stimulus response theory. cd ;

[0013] The ship position, speed and heading information in the traffic information set ST of the traffic separation system water area is uploaded to the water area grid RG mn Mapping is performed to determine the overtaking vessel in the traffic separation scheme and map the overtaking vessel’s area to the water grid RG mn Mapping is performed to construct the ship overtaking factor CR for the traffic lane ot ;

[0014] The ship longitude and latitude information in the traffic information set ST of the water area of ​​the traffic separation system is uploaded to the water area grid RG. mn Mapping is performed, and the mapped water area grids are accumulated to the recommended course direction of the navigation channel to form the ship track position distribution of the navigation channel. The skewness coefficient and kurtosis coefficient are used to jointly identify the track position distribution characteristics and construct the ship track position factor CR of the navigation channel. tp ;

[0015] The traffic lane congestion factor CR cl , Ship course deviation factor CR of traffic lane cd , overtaking of ships in traffic lanes will encounter factor CR ot and the ship track position factor CR of the traffic lane tp Weighted synthesis is performed to obtain the collision risk results of the navigation lane waters in the instantaneous traffic separation system, based on the water grid RG mn By performing weighted synthesis, the temporal and spatial distribution of collision hazards in the navigation lane waters of the traffic separation scheme is obtained.

[0016] The present invention also discloses a rasterized traffic separation system water area collision risk identification device, which is used to implement the above method, comprising:

[0017] A basic information acquisition module is used to acquire basic information of ships in the waters of the traffic separation scheme and construct a traffic information set ST of ships in the waters of the traffic separation scheme. The basic information of ships includes ship timestamp, ship MMSI, ship longitude, ship latitude, ship speed, ship heading and ship length; acquire basic information of the waters of the traffic separation scheme and construct a waters information set TI of the traffic separation scheme. The basic information of the waters includes the location, scale and recommended heading of the waters of the traffic separation scheme;

[0018] The coordinate conversion module is used to rotate the coordinate system of the navigation separation system waters to make the navigation lanes parallel to the horizontal axis of the coordinate system, and to perform coordinate transformation of the traffic information of ships sailing in the navigation lanes at the same angle, and to perform rasterization processing on the navigation separation system waters to generate the water grid RG. mn ;

[0019] The traffic lane congestion factor construction module is used to convert the ship longitude and latitude information in the ship traffic information set ST of the traffic lane water area into the water area grid RG. mn Mapping is performed to construct a ship domain model SD for ships in the traffic separation scheme waters i , and move the ship area to the water grid RG mn Mapping is performed and the traffic lane congestion factor CR is constructed according to the mapped grid conditions. cl ;

[0020] The ship heading deviation degree factor construction module is used to convert the heading information in the ship traffic information set ST in the water area of ​​the traffic separation system into the water area grid RG mn Mapping is performed and the ship course deviation factor CR of the traffic lane is constructed using the stimulus response theory. cd ;

[0021] The ship overtaking encounter factor construction module is used to transmit the ship position, speed and heading information in the traffic information set ST of the water area of ​​the traffic separation system to the water area grid RG. mn Mapping is performed to determine the overtaking vessel in the traffic separation scheme and map the overtaking vessel’s area to the water grid RG mn Mapping is performed to construct the ship overtaking factor CR for the traffic lane ot ;

[0022] The ship track position factor construction module is used to convert the ship longitude and latitude information in the ship traffic information set ST of the water area of ​​the traffic separation system into the water area grid RG mnMapping is performed, and the mapped water area grids are accumulated to the recommended course direction of the navigation channel to form the ship track position distribution of the navigation channel. The skewness coefficient and kurtosis coefficient are used to jointly identify the track position distribution characteristics and construct the ship track position factor CR of the navigation channel. tp ;

[0023] The navigation lane water collision risk identification module is used to convert the navigation lane congestion factor CR cl , Ship course deviation factor CR of traffic lane cd , overtaking of ships in traffic lanes will encounter factor CR ot and the ship track position factor CR of the traffic lane tp Weighted synthesis is performed to obtain the collision risk results of the navigation lane waters in the instantaneous traffic separation system, based on the water grid RG mn By performing weighted synthesis, the temporal and spatial distribution of collision hazards in the navigation lane waters of the traffic separation scheme is obtained.

[0024] Compared with the prior art, the present invention has the following advantages:

[0025] 1. The rasterized method and device for identifying collision risks in traffic separation waters provided by the present invention can make full use of ship traffic data. As a data-driven model, the method and device for identifying collision risks in traffic separation waters provided by the present invention can more accurately quantify the collision risks in traffic separation waters driven by massive ship traffic data.

[0026] 2. The rasterized method and device for identifying collision risks in waters of a navigation separation system provided by the present invention fully consider the characteristics of waters of a navigation separation system and the navigation regulations for ships in the navigation lanes, and utilize concepts and theories such as ship domain, stimulus response theory, and distribution curve feature recognition to comprehensively and fully construct a waters collision risk identification model in navigation lanes from the perspectives of multiple influencing factors such as the degree of congestion in navigation lanes, the degree of deviation of ship headings, ship overtaking encounters, and the distribution of ship track positions. This allows the collision risks in waters of a navigation separation system to be quantified more objectively and accurately.

[0027] 3. The rasterized method and device for identifying collision hazards in waters with a navigation separation system provided by the present invention pre-rasterizes the study waters during the process of model construction, corresponds the ship traffic information to the water grid, and assigns grid attributes to it, so that the constructed collision hazard model for waters with a navigation separation system can characterize the spatiotemporal distribution of the collision hazards in the navigation lanes, and can more accurately and intuitively characterize the collision hazards, while making the method have better scalability. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0029] Figure 1 The present invention is a flow chart of a rasterized method for identifying collision risks in waters with a traffic separation system.

[0030] Figure 2 Schematic diagram of the rotation of the coordinate system for studying the water area in an embodiment of the present invention.

[0031] Figure 3 Schematic diagram of rasterization processing of traffic lanes in an embodiment of the present invention.

[0032] Figure 4 Schematic diagram of the activity grid in the ship field in an embodiment of the present invention.

[0033] Figure 5 Schematic diagram of traffic lane congestion distribution in an embodiment of the present invention.

[0034] Figure 6 Schematic diagram of data interpolation operation in an embodiment of the present invention.

[0035] Figure 7 Schematic diagram of a ship overtaking area in an embodiment of the present invention.

[0036] Figure 8 Schematic diagram of the calculation process of the track position distribution factor in an embodiment of the present invention.

[0037] Fig. 9 This is an example of characterizing the spatial distribution of collision risks of traffic lanes in an embodiment of the present invention.

[0038] Fig.10 This is an example of characterizing the time distribution of collision risk of traffic lanes in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0040] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0041] The present invention provides a rasterized method for identifying collision risks in traffic separation waters. The main process is as follows: Figure 1 As shown, the specific steps include:

[0042] S1. Obtain basic information of ships in the waters of the traffic separation scheme, and construct a ship traffic information set ST for the waters of the traffic separation scheme. The basic ship information includes ship timestamp, ship MMSI, ship longitude, ship latitude, ship speed, ship heading and ship length. Obtain basic information of the waters of the traffic separation scheme, and construct a waters information set TI for the traffic separation scheme. The basic waters information includes the location, scale and recommended heading of the waters of the traffic separation scheme.

[0043] This step collects ship traffic related information, such as ship longitude, ship latitude, ship speed, ship heading, ship length, etc., through various sensors to build a ship traffic information set for the waters of the traffic separation system. According to the nautical chart and relevant regulations, the location, water scale, recommended heading and other information parameters of the waters of the traffic separation system are obtained to build the waters of the traffic separation system information set. The above data sets provide data preparation for the subsequent stages.

[0044] Specifically, first, extract the static and dynamic information of the ship from various navigation sensors, including the ship's time stamp i , Ship Mobile Service Identification Code MMSI i 、Ship longitude long i , ship latitude lat i 、Ship speed i 、Ship heading course i 、ShipLength i , construct the ship traffic information set ST in the traffic separation system water area. For a certain ship i, its ship traffic information set is expressed as follows:

[0045] ST i ={TimeStampi ,MMSI i ,long i ,lat i ,speed i ,course i ,ShipLength i}i=1,2,3…,n

[0046] At the same time, obtain relevant information about the study waters, that is, the traffic lanes of the traffic separation system, including the endpoint coordinates Length of traffic lane TL , Width of traffic lane TL , recommended course r The recommended courses in the two sides of the traffic lanes are opposite. Construct the traffic lane separation water area information set TI, which is specifically expressed as follows:

[0047] TI = {Location edge ,Lenh TL ,Width TL ,course r}

[0048] The above information set will be used in the coordinate transformation, water rasterization, and construction of various factors in the following stages.

[0049] S2. Rotate the coordinate system of the waters of the traffic separation system so that the navigation lanes are parallel to the horizontal axis of the coordinate system, and transform the traffic information of ships sailing in the waters at the same angle, rasterize the waters of the traffic separation system, and generate the water grid RG. mn .

[0050] This step rotates the coordinate system of the traffic separation system so that the traffic lanes are parallel to the meridian direction, and the ship-related information is transformed accordingly. In the traffic lanes after the coordinate transformation, rasterization is performed according to the size of the traffic lanes, and several square water grids are established, and labelled with serial numbers.

[0051] Specifically, in order to facilitate subsequent rasterization processing, model construction and related calculations, the coordinate system of the study waters needs to be rotated first, such as Figure 2 As shown, the study waters, i.e., the navigation lanes of the traffic separation system, are made parallel to the meridian direction. Specifically, according to the endpoint coordinates Location in the traffic separation system waters information set TI edge Obtain the angle θ between the traffic lane and the meridian, and rotate the coordinate system of the traffic lane according to this angle θ:

[0052] long i ′=longi *cosθ+lat i sinθ

[0053] lat i ′=lat i *cosθ-long i sinθ

[0054] In the new coordinate system, the endpoint coordinates Location edge Transform to Location in the new coordinate system edge ′.

[0055] At the same time, corresponding coordinate transformation is performed on the coordinates and heading of the ship in the traffic separation system to form its new position coordinates and new heading in the traffic lane after the coordinate system is rotated.

[0056] The navigation lanes after the coordinate system rotation are rasterized according to the lane length Length in the navigation system waters information set TI. TL and traffic lane width Width TL Determine the size of the grid appropriately. Here we take a 0.25nmile*0.25nmile square grid as an example. Figure 3 As shown, the grid numbers are marked from left to right and from top to bottom, represented by #1, #2, #3, .... Each water area grid obtains label attributes.

[0057] S3. Construct relevant collision risk factors from four perspectives, namely, the degree of traffic lane congestion, the degree of ship course deviation, the situation of ship overtaking and the distribution of ship track positions, which affect the collision risk of traffic separation scheme. In the process of factor construction, the mapping of various information and results to the water area grid is realized.

[0058] S31, the ship longitude and latitude information in the ship traffic information set ST in the water area of ​​the traffic separation system is uploaded to the water area grid RG mn Mapping is performed to construct a ship domain model SD for ships in the traffic separation scheme waters i , and move the ship area to the water grid RG mn Mapping is performed and the traffic lane congestion factor CR is constructed according to the mapped grid conditions. cl .

[0059] Specifically, the longitude of the ship in the traffic information set ST of the water area of ​​the traffic separation system is converted into i , ship latitude lat i 、ShipLength i Information to Water Grid RG mn Mapping is performed so that the longitude of each ship i is long iWith latitude lat i Corresponding to a water grid RG mn , mark its label mn.

[0060] For each ship i, a ship domain model is constructed. The domain shape is an ellipse, the major axis radius is 4 times the ship length, and the minor axis radius is 1.6 times the ship length.

[0061] Using the properties of the ellipse focus, a and b represent the lengths of the major and minor axes of the ellipse, and c represents the focal length of the ellipse. mn The center point (long P ,lat P ) as the basis, the ship field SD of each ship i i Water Grid RG mn To map:

[0062]

[0063] If PF1+PF2≤2a, the center point P of the water area grid is within the elliptical area, and the water area grid is marked as a ship area activity grid, such as Figure 4 shown.

[0064] At a certain moment, count the number of active grids in all ship areas n RG-SD , and the traffic lane congestion factor at that moment is obtained according to the following formula:

[0065]

[0066] N RG Represents the total number of water area rasters.

[0067] On a time scale, for a grid in a rasterized traffic lane, the danger of the grid during a period of time (from time t1 to t2) can be obtained based on the frequency of its occupation by ships:

[0068]

[0069] Δt is the length of unit time, f RG-SDt1-t2 Indicates the frequency of the grid being active due to ship coverage from time t1 to t2. Based on this value, the spatial distribution of collision risk caused by congestion in the traffic lane from time t1 to t2 can be characterized, such as Figure 5 shown.

[0070] S32, the heading information in the traffic information set ST of the water area of ​​the traffic separation system is sent to the water area grid RG mn Mapping is performed and the ship course deviation factor CR of the traffic lane is constructed using the stimulus response theory.cd .

[0071] Specifically, the vessel course in the traffic information set ST of the traffic separation system water area is converted into i Water Grid RG mn Mapping, the mapped ship course i Based on the ship's timestamp i The interpolated heading to a preset time point is aligned with a water grid RG mn Correspondingly, mark its label mn. The interpolation process is as follows Figure 6 shown.

[0072] According to the idea of ​​least squares method, through the ship's heading course i Recommended course r Calculate the heading deviation from time t1 to t2 in a grid:

[0073]

[0074] Represents the total number of headings mapped to the grid from time t1 to t2.

[0075] Furthermore, according to the stimulus response theory, the heading deviation is considered as a visual stimulus, and the heading deviation factor of a certain water grid from time t1 to t2 is established:

[0076]

[0077] in, With CR cd is the heading deviation factor, CR cd It is a generalized expression. It is the heading deviation factor specific to the grid (RG) and indicating the time period (t1 to t2).

[0078] S33, the ship position, speed and heading information in the traffic information set ST of the water area of ​​the traffic separation system is transmitted to the water area grid RG mn Mapping is performed to determine the overtaking vessel in the traffic separation scheme and map the overtaking vessel’s area to the water grid RG mn Mapping is performed to construct the ship overtaking factor CR for the traffic lane ot .

[0079] Specifically, the longitude of the ship in the traffic information set ST of the water area of ​​the traffic separation system is converted into i , ship latitude lat i 、Ship speed i 、Ship heading coursei 、ShipLength i Water Grid RG mn Mapping is done so that each piece of information is associated with a specific water grid RG mn Correspondingly, mark its label mn.

[0080] According to the International Regulations for Preventing Collisions at Sea, the overtaking situation in the traffic lane is judged and the overtaking ship is identified. The judgment conditions set include:

[0081] 1) The speed of the overtaking vessel is higher than that of the overtaking vessel.

[0082] 2) The overtaking vessel should be within the visible range of the stern lights of the overtaken vessel.

[0083] 3) The overtaking vessel should be within the overtaking sector of the overtaken vessel and its heading should be between the opposite extension direction of the overtaking sector boundary (towards the overtaken vessel). Figure 7 shown.

[0084] Ships that meet the above three conditions are identified as overtaking ships. The identified overtaking ships are mapped to the water grid according to the method in 1.

[0085] At a certain moment, count the number of active grids in the area of ​​all overtaking ships n RG-OS , and the ship overtaking situation factor at that moment is obtained according to the following formula:

[0086]

[0087] N RG Represents the total number of water area rasters.

[0088] On a time scale, for a grid in a rasterized traffic lane, the danger of the grid during a period of time (from time t1 to t2) can be obtained based on the frequency of the grid being occupied by the overtaking ship area:

[0089]

[0090] S34, the ship longitude and latitude information in the traffic information set ST of the water area of ​​the traffic separation system is uploaded to the water area grid RG mn Mapping is performed, and the mapped water area grids are accumulated to the recommended course direction of the navigation channel to form the ship track position distribution of the navigation channel. The skewness coefficient and kurtosis coefficient are used to jointly identify the track position distribution characteristics and construct the ship track position factor CR of the navigation channel. tp .

[0091] Specifically, the longitude of the ship in the traffic information set ST of the water area of ​​the traffic separation system is converted intoi , ship latitude lat i Water Grid RG mn Mapping is done so that each piece of information is associated with a specific water grid RG mn Correspondingly, mark its label mn.

[0092] The mapped water area grids are accumulated toward the recommended course direction of the navigation lane to form the ship track position distribution of the navigation lane.

[0093] Calculate the skewness coefficient C of the distribution at this location s_tp and excess kurtosis coefficient C k_tp , to calculate the deviation between the position distribution curve and the Gaussian distribution, such as Figure 8 As shown:

[0094]

[0095] Among them, index_RG i Represents the label index of grid i, index_RG represents the average of all grid label indexes, n_RG s_track and n_RG k_track Indicates the number of grid label numbers, σ_RG s_track and σ_RG k_track Represents the standard deviation of the grid number labels.

[0096] Then, the negative exponential function is used to establish the track position distribution factor from time t1 to t2:

[0097]

[0098] Among them, CR tp and are track position distribution factors, CR tp For general expression, The time ends (t1 to t2) are indicated.

[0099] S4. After synthesizing the obtained factors, the collision risk result of the water area of ​​the traffic separation system is obtained, and the spatial and temporal distribution representation of the collision risk based on the water area grid is realized. Specifically, the traffic separation congestion factor CR cl , Ship course deviation factor CR of traffic lane cd , overtaking of ships in traffic lanes will encounter factor CR ot and the ship track position factor CR of the traffic lane tp Weighted synthesis is performed to obtain the collision risk results of the navigation lane waters in the instantaneous traffic separation system, based on the water grid RG mn By performing weighted synthesis, the temporal and spatial distribution of collision hazards in the navigation lane waters of the traffic separation scheme is obtained.

[0100] Specifically, after completing the above traffic lane congestion factor CR cl , ship course deviation factor CR cd , the ship overtaking situation factor CR ot , ship track position factor CR tp After calculation, they are weighted and synthesized, and weights are set for each factor to obtain the collision risk result CR of the navigation separation waters at a certain moment.

[0101] CR=ω1CR cl +ω2CR cd +ω3CR ot +ω4CR tp

[0102] Among them, ω is the weight of the four collision risk factors, which can be taken as 0.25 initially. It can be further adjusted dynamically according to the characteristics of the traffic separation system and the ship traffic therein, relevant regulations and research purposes. For example, if the width of the navigation lane is narrow, the weight of the track position distribution factor can be appropriately reduced. If there is a regulation prohibiting overtaking, the weight of the overtaking encounter factor can be reduced. In addition, it can also be adjusted according to the purpose of the research. For example, if the danger between traffic in the navigation lane and traffic crossing the navigation lane is specially studied, the weight of the course deviation factor can be increased. In addition, if there is no traffic crossing the navigation lane, the weight of the course deviation factor can be appropriately reduced.

[0103] For a water grid, the collision risk result CR_RG of the water grid can be obtained by weighting the water grid factor obtained above. t1-t2 :

[0104]

[0105] Based on the above results, the temporal and spatial distribution of collision risk in traffic lanes can be characterized.

[0106] Fig. 9 The method for identifying collision risks in waters of a traffic separation scheme using a rasterized method provided by the present invention is used to characterize the spatial distribution of collision risks in the south navigation lane of the Laotieshan traffic separation scheme for one hour, wherein the collision risk size of each water grid is represented by grayscale. Fig.10The 12-hour time distribution representation of the collision risk of the south navigation lane of the Laotieshan navigation separation system obtained after adopting the rasterized method and device for identifying collision risks in the navigation separation system waters provided by the present invention indicates the change of the collision risk over time within the 12 hours. The results obtained by this embodiment can further help maritime traffic supervisors to carry out more accurate and efficient supervision and analysis of collision risks in the navigation separation system waters, and provide a data basis for safety research in the navigation separation system waters.

[0107] Another aspect of the embodiment of the present invention further discloses a rasterized device for identifying collision risks in a traffic separation system water area, which is used to implement the above method, and includes:

[0108] A basic information acquisition module is used to acquire basic information of ships in the waters of the traffic separation scheme and construct a traffic information set ST of ships in the waters of the traffic separation scheme. The basic information of ships includes ship timestamp, ship MMSI, ship longitude, ship latitude, ship speed, ship heading and ship length; acquire basic information of the waters of the traffic separation scheme and construct a waters information set TI of the traffic separation scheme. The basic information of the waters includes the location, scale and recommended heading of the waters of the traffic separation scheme;

[0109] The coordinate conversion module is used to rotate the coordinate system of the navigation separation system waters to make the navigation lanes parallel to the horizontal axis of the coordinate system, and to perform coordinate transformation of the traffic information of ships sailing in the navigation lanes at the same angle, and to perform rasterization processing on the navigation separation system waters to generate the water grid RG. mn ;

[0110] The traffic lane congestion factor construction module is used to convert the ship longitude and latitude information in the ship traffic information set ST of the traffic lane water area into the water area grid RG. mn Mapping is performed to construct a ship domain model SD for ships in the traffic separation scheme waters i , and move the ship area to the water grid RG mn Mapping is performed and the traffic lane congestion factor CR is constructed according to the mapped grid conditions. cl ;

[0111] The ship heading deviation degree factor construction module is used to convert the heading information in the ship traffic information set ST in the water area of ​​the traffic separation system into the water area grid RG mn Mapping is performed and the ship course deviation factor CR of the traffic lane is constructed using the stimulus response theory. cd ;

[0112] The ship overtaking encounter factor construction module is used to transmit the ship position, speed and heading information in the traffic information set ST of the water area of ​​the traffic separation system to the water area grid RG. mnMapping is performed to determine the overtaking vessel in the traffic separation scheme and map the overtaking vessel’s area to the water grid RG mn Mapping is performed to construct the ship overtaking factor CR for the traffic lane ot ;

[0113] The ship track position factor construction module is used to convert the ship longitude and latitude information in the ship traffic information set ST of the water area of ​​the traffic separation system into the water area grid RG mn Mapping is performed, and the mapped water area grids are accumulated to the recommended course direction of the navigation channel to form the ship track position distribution of the navigation channel. The skewness coefficient and kurtosis coefficient are used to jointly identify the track position distribution characteristics and construct the ship track position factor CR of the navigation channel. tp ;

[0114] The navigation lane water collision risk identification module is used to convert the navigation lane congestion factor CR cl , Ship course deviation factor CR of traffic lane cd , overtaking of ships in traffic lanes will encounter factor CR ot and the ship track position factor CR of the traffic lane tp Weighted synthesis is performed to obtain the collision risk results of the navigation lane waters in the instantaneous traffic separation system, based on the water grid RG mn By performing weighted synthesis, the temporal and spatial distribution of collision hazards in the navigation lane waters of the traffic separation scheme is obtained.

[0115] As for a rasterized embodiment of a device for identifying collision risks in waters with separated traffic lanes of the present invention, since it corresponds to the above embodiment of a rasterized method for identifying collision risks in waters with separated traffic lanes, the description is relatively simple. For relevant similarities, please refer to the partial description in the above embodiment of a method for identifying collision risks in waters with separated traffic lanes, which will not be described in detail here.

[0116] The present invention first performs rasterization processing on the waters of the navigation separation scheme, and based on methods such as the ship field, stimulus response theory and distribution curve feature recognition, constructs a method for identifying collision risks in the waters of the navigation separation scheme from the perspectives of the degree of congestion in the navigation lanes, the degree of deviation of the ship's course, the situation of ship overtaking encounters and the distribution of ship track positions. Driven by a large amount of marine traffic data, this method can accurately identify the collision risks in the waters of the navigation separation scheme and can characterize them from the perspective of time and space distribution. On the one hand, this invention can help maritime traffic regulators to better supervise and analyze the collision risks in the waters of the navigation separation scheme in their jurisdiction, and promote their traffic supervision and organization work; on the other hand, it can provide data support for the prediction of collision risks in the waters of the navigation separation scheme, the evaluation of the effectiveness of the establishment of the navigation separation scheme and the change plan.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A rasterized method for identifying collision risks in traffic separation waters, characterized in that: The following steps are involved: Obtain basic information of ships in the waters of the traffic separation scheme, and construct a traffic information set ST of ships in the waters of the traffic separation scheme, wherein the basic information of ships includes ship timestamp, ship MMSI, ship longitude, ship latitude, ship speed, ship heading and ship length; obtain basic information of the waters of the traffic separation scheme, and construct a traffic information set TI of the waters of the traffic separation scheme, wherein the basic information of the waters includes the location, scale and recommended heading of the waters of the traffic separation scheme; The coordinate system of the traffic separation system waters is rotated to make the navigation lanes parallel to the horizontal axis of the coordinate system, and the traffic information of ships sailing in them is transformed at the same angle. The traffic separation system waters are rasterized to generate the water grid RG. mn ; The ship longitude and latitude information in the traffic information set ST of the water area of ​​the traffic separation system is uploaded to the water area grid RG. mn Mapping is performed to construct a ship domain model SD for ships in the traffic separation scheme waters i , and move the ship area to the water grid RG mn Mapping is performed and the traffic lane congestion factor CR is constructed according to the mapped grid conditions. cl ; The heading information in the traffic information set ST of the traffic separation system water area is uploaded to the water area grid RG mn Mapping is performed and the stimulus response theory is used to construct the ship course deviation factor CR of the traffic lane. cd ; The ship position, speed and heading information in the traffic information set ST of the traffic separation system water area is uploaded to the water area grid RG mn Mapping is performed to determine the overtaking vessel in the traffic separation scheme and map the overtaking vessel’s area to the water grid RG mn Mapping is performed to construct the ship overtaking factor CR for the traffic lane ot ; The ship longitude and latitude information in the traffic information set ST of the water area of ​​the traffic separation system is uploaded to the water area grid RG. mn Mapping is performed, and the mapped water area grids are accumulated to the recommended course direction of the navigation channel to form the ship track position distribution of the navigation channel. The skewness coefficient and kurtosis coefficient are used to jointly identify the track position distribution characteristics and construct the ship track position factor CR of the navigation channel. tp ; The traffic lane congestion factor CR cl , Ship course deviation factor CR of traffic lane cd , overtaking of ships in traffic lanes will encounter factor CR ot and the ship track position factor CR of the traffic lane tp Weighted synthesis is performed to obtain the collision risk results of the navigation lane waters in the instantaneous traffic separation system, based on the water grid RG mn By performing weighted synthesis, the temporal and spatial distribution of collision hazards in the navigation lane waters of the traffic separation scheme is obtained.

2. The rasterized method for identifying collision risk in traffic separation waters according to claim 1, characterized in that: The vessel traffic information set ST in the traffic separation system area is: ST i ={TimeStamp i ,MMSI i ,long i ,lat i ,speed i ,course i ,ShipLength i }i=1,2,3…,n Among them, TimeStamp i Indicates ship timestamp, MMSI i Indicates the ship's longitude. i Indicates the ship mobile service identification code, lat i Indicates the ship's latitude, speed i Indicates the ship's speed, course i Indicates the ship's heading, ShipLength i Indicates the length of the ship; The traffic separation scheme water area information set TI is: TI={Location edge ,Length TL ,Width TL ,course r } Among them, Location edge =(long edgej ,lat edgej ) represents the endpoint coordinates, Lengh TL Indicates the length of the traffic lane, Width TL Indicates the width of the traffic lane, course r Indicates the recommended heading.

3. The rasterized method for identifying collision risk in traffic separation waters according to claim 2, characterized in that: The coordinate system of the traffic separation system waters is rotated to make the navigation lanes parallel to the horizontal axis of the coordinate system, and the traffic information of ships sailing in them is transformed at the same angle. The traffic separation system waters are rasterized to generate the water grid RG. mn ,include: According to the endpoint coordinates Location in the traffic separation system waters information set TI edge Obtain the angle θ between the navigation lane and the meridian, and rotate the coordinate system of the navigation lane according to the angle θ to make the navigation lane parallel to the meridian. edge Transform to Location in the new coordinate system edge ′, the latitude and longitude and heading information of the ship in the traffic information set ST of the water area of ​​the traffic separation system are also transformed according to the angle θ; According to the lane length Length in the traffic separation waters information set TI TL and traffic lane width Width TL , the traffic lanes in the traffic separation system are divided into a number of square water grids RG mn The radial and latitudinal grids are represented by #1, #2, #3,… from left to right and from top to bottom.

4. The rasterized method for identifying collision risk in traffic separation waters according to claim 2, characterized in that: The ship longitude and latitude information in the traffic information set ST of the water area of ​​the traffic separation system is uploaded to the water area grid RG. mn Mapping is performed to construct a ship domain model SD for ships in the traffic separation scheme waters i , and move the ship area to the water grid RG mn Mapping is performed and the traffic lane congestion factor CR is constructed according to the mapped grid conditions. cl ,include: The longitude of the ship in the traffic information set ST of the traffic separation system water area is long i , ship latitude lat i 、ShipLength i Information to Water Grid RG mn Mapping is performed so that the longitude of each ship i is long i With latitude lat i Corresponding to a water grid RG mn , mark its label mn; For each ship i, a ship domain model is constructed. The domain shape is an ellipse. Using the focal property of the ellipse, each water grid RG mn The center point of each ship i is taken as the reference, and the ship area SD i Water Grid RG mn Mapping is performed; Align ship timestamps i , count the number of grids occupied by the rasterized ship area, and construct the traffic lane congestion factor CR at the instantaneous moment cl , for a water grid RG mn ,The crowding degree factor is obtained by the ratio of the number of grids in the ,active ship area and the elapsed time.

5. The rasterized method for identifying collision risk in traffic separation waters according to claim 2, characterized in that: The heading information in the traffic information set ST of the traffic separation system water area is uploaded to the water area grid RG mn Mapping is performed and the stimulus response theory is used to construct the ship course deviation factor CR of the traffic lane. cd ,include: The vessel course in the traffic information set ST of the traffic separation system water area i Water Grid RG mn Mapping, the mapped ship course i Based on the ship's timestamp i The interpolated heading to a preset time point is aligned with a water grid RG mn Correspondingly, mark its label mn; According to the course of the ship i Recommended course r Calculate the course deviation degree in a certain grid, use the stimulus perception theory, consider the course deviation as a visual stimulus, and construct the ship course deviation degree factor CR in the traffic lane. cd .

6. The rasterized method for identifying collision risk in traffic separation waters according to claim 2, characterized in that: The ship position, speed and heading information in the traffic information set ST of the water area of ​​the traffic separation system is uploaded to the water area grid R mn Mapping is performed to determine the overtaking vessel in the traffic separation scheme and map the overtaking vessel’s area to the water grid RG mn Mapping is performed to construct the ship overtaking factor CR for the traffic lane ot ,include: The longitude of the ship in the traffic information set ST of the traffic separation system water area is long i , ship latitude lat i 、Ship speed i 、Ship heading course i 、ShipLength i Water Grid RG mn Mapping is done so that each piece of information is associated with a specific water grid RG mn Correspondingly, mark its label mn; Set judgment conditions from four angles: speed, distance, direction, and direction to determine the overtaking ship in the traffic separation system waters, and map the identified overtaking ship's respective ship area to the waters grid; Count the number of active grids in the overtaking ship area at a certain moment, and use this to construct the ship overtaking encounter factor CR at that moment. ot , for a water grid RG mn The ship overtaking situation factor is obtained by the ratio of the accumulated number of activity grids in the overtaking ship area to the elapsed time.

7. The rasterized method for identifying collision risk in traffic separation waters according to claim 2, characterized in that: The ship longitude and latitude information in the traffic information set ST of the water area of ​​the traffic separation system is uploaded to the water area grid RG. mn Mapping is performed, and the mapped water area grids are accumulated to the recommended course direction of the navigation channel to form the ship track position distribution of the navigation channel. The skewness coefficient and kurtosis coefficient are used to jointly identify the track position distribution characteristics and construct the ship track position factor CR of the navigation channel. tp ,include: The longitude of the ship in the traffic information set ST of the traffic separation system water area is long i , ship latitude lat i Water Grid RG mn Mapping is done so that each piece of information is associated with a specific water grid RG mn Correspondingly, mark its label mn, The recommended heading direction of the mapped water grid to the navigation lane is accumulated to form the ship track position distribution of the navigation lane. The skewness coefficient and kurtosis coefficient of the current position distribution are calculated to obtain the degree of fit between the distribution and the Gaussian distribution, which is used as the basis to construct the ship track position factor CR of the navigation lane. tp .

8. A rasterized device for identifying collision risks in traffic separation waters, used to implement the method described in any one of claims 1 to 7, characterized in that: include: A basic information acquisition module is used to acquire basic information of ships in the waters of the traffic separation scheme and construct a traffic information set ST of ships in the waters of the traffic separation scheme. The basic information of ships includes ship timestamp, ship MMSI, ship longitude, ship latitude, ship speed, ship heading and ship length; acquire basic information of the waters of the traffic separation scheme and construct a traffic information set TI of the waters of the traffic separation scheme. The basic information of the waters includes the location, scale and recommended heading of the waters of the traffic separation scheme; The coordinate conversion module is used to rotate the coordinate system of the navigation separation system waters to make the navigation lanes parallel to the horizontal axis of the coordinate system, and to perform coordinate transformation of the traffic information of ships sailing in the navigation lanes at the same angle, and to perform rasterization processing on the navigation separation system waters to generate the water grid RG. mn ; The traffic lane congestion factor construction module is used to convert the ship longitude and latitude information in the ship traffic information set ST of the water area of ​​the traffic lane separation system into the water area grid RG. mn Mapping is performed to construct a ship domain model SD for ships in the traffic separation scheme waters i , and move the ship area to the water grid RG mn Mapping is performed and the traffic lane congestion factor CR is constructed according to the mapped grid conditions. cl ; The ship heading deviation degree factor construction module is used to convert the heading information in the ship traffic information set ST in the water area of ​​the traffic separation system into the water area grid RG mn Mapping is performed and the stimulus response theory is used to construct the ship course deviation factor CR of the traffic lane. cd ; The ship overtaking encounter factor construction module is used to transmit the ship position, speed and heading information in the traffic information set ST of the water area of ​​the traffic separation system to the water area grid RG. mn Mapping is performed to determine the overtaking vessel in the traffic separation scheme and map the overtaking vessel’s area to the water grid RG mn Mapping is performed to construct the ship overtaking factor CR for the traffic lane ot ; The ship track position factor construction module is used to convert the ship longitude and latitude information in the ship traffic information set ST of the water area of ​​the traffic separation system into the water area grid RG mn Mapping is performed, and the mapped water area grids are accumulated to the recommended course direction of the navigation channel to form the ship track position distribution of the navigation channel. The skewness coefficient and kurtosis coefficient are used to jointly identify the track position distribution characteristics and construct the ship track position factor CR of the navigation channel. tp ; The navigation lane water collision risk identification module is used to convert the navigation lane congestion factor CR cl , Ship course deviation factor CR of traffic lane cd , overtaking of ships in traffic lanes will encounter factor CR ot and the ship track position factor CR of the traffic lane tp Weighted synthesis is performed to obtain the collision risk results of the navigation lane waters in the instantaneous traffic separation system, based on the water grid RG mn By performing weighted synthesis, the temporal and spatial distribution of collision hazards in the navigation lane waters of the traffic separation scheme is obtained.

Images