A method and device for constructing a ship safety domain model

Abstract

The embodiment of the present application discloses a method and device for constructing a ship safety domain model. A specific implementation of the method includes: obtaining key parameters that affect the degree of danger of a ship encountering; in response to the key parameters, constructing the danger membership functions corresponding to the key parameters respectively; in response to the danger membership functions, calculating the collision danger of the ship and the obstacle ship; in response to the collision danger, constructing a ship encounter situation distribution model, obtaining nodes on the ship encounter situation distribution model, calculating the node vectors of the nodes and constructing the danger influence function corresponding to the node vector, constructing a safety level model, and respectively calculating the boundary vectors of the ship and a single obstacle ship and multiple obstacle ships under the encounter situation distribution. The ship domain safety model constructed by this implementation can effectively identify the collision danger of a single target ship or multiple target ships, and can provide a technical reference for the research and development of ship intelligent navigation systems with autonomous collision avoidance capabilities.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of ship safety, and specifically to a method and device for constructing a ship safety field model. Background Art

[0002] Since the concept of ship domain was proposed in 1971, ship domain has been widely used in marine traffic engineering. It is of great significance in navigation situation assessment and ship collision avoidance. Ship safety domain is the generalization of safety distance and is widely used in ship collision risk assessment, dangerous approach detection, and waterway risk analysis.

[0003] The shape and size of the ship safety field model are affected by many factors, such as ship parameters, ship speed, encounter type, surrounding environment type, ship maneuverability and other factors. The ship safety field can be divided into experimental data statistics-based, expert knowledge-based and analytical expression-based types according to research methods. Nowadays, many studies on ship safety field models are based on one or more of the above three methods. Among them, the model based on experimental data statistics has the characteristics of being greatly affected by the water type and experimental data, and usually establishes models for specific waters and specific ship types. Models based on expert knowledge rely heavily on the selection of survey experts and crew members. Therefore, while this type of model reflects the practicality of the ship field model, it also has a certain degree of subjectivity.

[0004] Traditional ship safety models have limitations in the quantitative calculation of collision risk factors:

[0005] 1) When approaching ships from different directions, the same method is used to calculate the risk level, without considering the changes in the influence of various factors in different directions. For example, in the case of a head-on encounter, DCPA may be zero, but the actual impact is not zero.

[0006] 2) The risk calculation method based only on DCPA and TCPA cannot guarantee the reliability of collision avoidance.

[0007] 3) The same static model is adopted under different encounter situations, and the model changes when multiple ships encounter the ship at the same time are not considered. Summary of the invention

[0008] The embodiments of the present application propose a method and device for constructing a ship safety domain model to solve the technical problems mentioned in the above background technology section.

[0009] In a first aspect, an embodiment of the present application provides a method for constructing a ship safety domain model, the method comprising: obtaining key parameters that affect the degree of danger encountered by the ship, wherein the key parameters include the distance between the own ship and the obstacle ship, the speed ratio of the own ship and the obstacle ship, the relative side angle of the own ship and the obstacle ship, the closest encounter distance between the own ship and the obstacle ship, and the minimum encounter time between the own ship and the obstacle ship; in response to the key parameters, constructing a danger membership function corresponding to the key parameters respectively, the danger membership function including the danger membership function of the distance between the own ship and the obstacle ship, the danger membership function of the speed ratio of the own ship and the obstacle ship, the relative side angle of the own ship and the obstacle ship, the closest encounter distance between the own ship and the obstacle ship, and the minimum encounter time between the own ship and the obstacle ship. Angle danger membership function, the closest encounter distance danger membership function of own ship and obstacle ship and the minimum encounter time danger membership function of own ship and obstacle ship; in response to the danger membership function, calculate the collision risk of own ship and obstacle ship; in response to the collision risk, construct a ship encounter situation distribution model, obtain the nodes on the ship encounter situation distribution model, calculate the node vectors of the nodes and construct the danger influence function corresponding to the node vector, and construct a safety level model; in response to the danger influence function and the safety level model, calculate the boundary vectors of own ship and a single obstacle ship and multiple obstacle ships under the encounter situation distribution model respectively.

[0010] In some embodiments, the distance danger membership function between the own ship and the obstacle ship is specifically:

[0011]

[0012] Where U D is the distance hazard membership function between the own ship and the obstacle ship, D is the distance between the own ship and the obstacle ship, D1 is the latest avoidance distance, and D2 is the distance at which avoidance measures can be taken;

[0013] The specific dangerous membership function of the speed ratio between the own ship and the obstacle ship is:

[0014]

[0015] Where U K is the speed ratio hazard membership function between the own ship and the obstacle ship, K is the speed ratio between the own ship and the obstacle ship and K ≥ 0, a is the encounter angle and the range of a is 0°~180°;

[0016] The relative side angle hazard membership function between the own ship and the obstacle ship is as follows:

[0017]

[0018] In the formula, is the relative side angle hazard membership function between the own ship and the obstacle ship, θ2 is the side angle of the own ship relative to the obstacle ship, and the range of θ2 is 0~360°;

[0019] The specific hazard membership function of the closest encounter distance between the own ship and the obstacle ship is:

[0020]

[0021] Where U DCPA is the hazard membership function of the closest encounter distance between the own ship and the obstacle ship, DCPA is the closest encounter distance between the own ship and the obstacle ship, d1 represents the minimum safe distance at which the obstacle ship can safely encounter the own ship, and d2 is the absolute safe encounter distance between the two ships;

[0022] The minimum encounter time hazard membership function between the own ship and the obstacle ship is as follows:

[0023]

[0024] Where U TCPA is the minimum encounter time hazard membership function between the own ship and the obstacle ship, D1 represents the latest avoidance distance, D2 represents the distance at which avoidance measures can be taken, and V R represents the relative speed of the target ship, DCPA is the closest encounter distance between the own ship and the obstacle ship, TCPA is the minimum encounter time between the own ship and the obstacle ship, t1 is the shortest time that the obstacle ship can safely encounter the own ship, and t2 is the absolute safe encounter time of the two ships. In some embodiments, the specific expression of the collision risk between the own ship and the obstacle ship is:

[0025]

[0026] In the formula, CR i is the collision risk between the own ship and the obstacle ship, i represents the i-th obstacle ship, Ki is the speed ratio between the own ship and the i-th obstacle ship, θ2i is the relative side angle between the own ship and the i-th obstacle ship, Di is the distance between the own ship and the i-th obstacle ship, DCPAi is the closest encounter distance between the own ship and the i-th obstacle ship, TCPAi is the minimum encounter time between the own ship and the i-th obstacle ship, and U Ki is the speed ratio hazard membership function between the ship and the i-th obstacle ship, U Di is the distance danger membership function between the ship and the i-th obstacle ship, is the relative side angle hazard membership function between the ship and the i-th obstacle ship, U DCPAi is the closest encounter distance between the ship and the i-th obstacle ship, and U TCPAi is the minimum encounter time hazard membership function between the ship and the i-th obstacle ship, a K is the speed ratio hazard membership function weight, is the relative side angle hazard membership function weight, a D is the weight of the dangerous membership function of the distance between the two ships, a DCPA is the weight of the nearest encounter distance hazard membership function, a TCPA is the minimum encounter time hazard membership function weight, where

[0027] In some embodiments, constructing a ship encounter situation distribution model and obtaining nodes on the ship encounter situation distribution model are specifically:

[0028] With the ship's heading as 0° and the ship as the center of the circle, the space ranging from 0° to 360° is divided into encounter situation, crossing situation and overtaking situation. The spatial range of the encounter situation includes 0°~5° and 355°~360°, the spatial range of the crossing situation includes 5°~112.5° and 247.5°~355°, and the spatial range of the overtaking situation is 112.5°~247.5°. The crossing situation and the overtaking situation are equally divided into several equal areas within their respective spatial ranges by several bisectors passing through the center of the circle, and the other end of the bisector relative to the center of the circle is taken as the node on the ship encounter situation distribution model.

[0029] In some embodiments, the crossing situation is divided into 4 equal areas, and the overtaking situation is divided into 3 equal areas.

[0030] In some embodiments, the specific steps of calculating the node vector of the node and constructing the risk impact function corresponding to the node vector are:

[0031] When the directional risk of the calculated node is 0, the length of the node vector is:

[0032]

[0033] Where, d bi is the length of the node vector when the directional risk of the node is 0, d max is the maximum radius of the ship encounter situation distribution model;

[0034] Construct the danger influence function corresponding to the node vector, specifically:

[0035]

[0036] In the formula, G i is the risk impact function, a G is the amplitude variable that changes with the azimuth of the approaching ship, θ bi is the angle of each node direction of the model, and θ1 is the azimuth of the incoming ship.

[0037] In some embodiments, building a security level model specifically includes:

[0038] A security level model including a blockade area and an observation area is established, and the longitudinal radius of the front area, the longitudinal radius of the rear area and the lateral diameter of the blockade area and the observation area are calculated respectively, and the maximum and minimum radius are taken as the maximum radius and minimum radius of the security level model respectively. The security level model includes a first security level model and a second security level model.

[0039] In some embodiments, the longitudinal radius of the front area, the longitudinal radius of the rear area, and the transverse diameter of the blocked area in the first security level model are calculated as follows:

[0040]

[0041] in,

[0042]

[0043] In the formula, R bf , R ba , S b are the longitudinal radius of the front area, the longitudinal radius of the rear area and the transverse diameter of the blocked area of ​​the first safety level model, respectively, where k AD is the gain of the advance distance, k DT is the gain of the gyration diameter, A D is the approach distance, D T is the initial turning diameter, L is the length of the ship, Vo is the speed of the ship, d min1 is the minimum radius of the first safety level model, d max1 is the maximum radius of the first safety level;

[0044] The longitudinal radius of the front area, the longitudinal radius of the rear area and the transverse diameter of the blocked area in the second safety level model are calculated as follows:

[0045]

[0046] In the formula, R wf , R wa , S w are the longitudinal radius of the front area, the longitudinal radius of the rear area and the transverse diameter of the second-level blockade area, L is the length of the ship, Vo is the speed of the ship, d min2 is the minimum radius of the second safety level model, d max2 is the maximum radius of the second safety level, and kn is the unit of ship speed.

[0047] In some embodiments, the boundary vectors between the own ship and a single obstacle ship and multiple obstacle ships under the encounter situation distribution model are calculated as follows:

[0048] Calculate the vector length of each node direction in the single ship encounter state:

[0049] D si =d bi +(d max -d min )·CR i ·G i

[0050] Where D si is the vector length of each node direction in the single ship encounter state, d bi is the length of the node vector when the directional risk of the node is 0, d min is the minimum radius of the ship encounter situation distribution model, d max is the maximum radius of the ship encounter situation distribution model, CR i is the collision risk between the own ship and the obstacle ship, G i is the risk impact function;

[0051] Based on the vector length of each node direction in the state of single ship encounter, the vector length of each node direction when multiple ships encounter the ship at the same time is calculated, and the maximum vector in each node direction is selected as the boundary vector of the ship domain model under the situation of multiple ships encountering:

[0052] D mi =max(D si (j))

[0053] Where D mi is the vector length of each node direction in the multi-ship encounter state, D si is the vector length of each node direction in the single ship encounter state.

[0054] In a second aspect, an embodiment of the present application provides a device for constructing a ship safety domain model, the device comprising:

[0055] A key parameter acquisition module is configured to acquire key parameters that affect the degree of danger of encountering a ship, wherein the key parameters include the distance between the own ship and the obstacle ship, the speed ratio between the own ship and the obstacle ship, the relative side angle between the own ship and the obstacle ship, the closest encounter distance between the own ship and the obstacle ship, and the minimum encounter time between the own ship and the obstacle ship;

[0056] A danger membership function construction module is configured to respond to key parameters and construct danger membership functions corresponding to the key parameters, wherein the danger membership functions include a danger membership function of the distance between the own ship and the obstacle ship, a danger membership function of the speed ratio between the own ship and the obstacle ship, a danger membership function of the relative side angle between the own ship and the obstacle ship, a danger membership function of the closest encounter distance between the own ship and the obstacle ship, and a danger membership function of the minimum encounter time between the own ship and the obstacle ship;

[0057] A collision risk calculation module is configured to calculate the collision risk between the own ship and the obstacle ship in response to the risk membership function;

[0058] A ship encounter situation distribution model construction module is configured to respond to the collision risk, construct a ship encounter situation distribution model, obtain nodes on the ship encounter situation distribution model, calculate node vectors of the nodes, and construct a risk influence function corresponding to the node vector to construct a safety level model;

[0059] The ship safety domain model building module is configured to respond to the hazard impact function and the safety level model, and calculate the boundary vectors between the ship and a single obstacle ship and multiple obstacle ships under the encounter situation distribution.

[0060] The method and device for constructing a ship safety domain model provided in the embodiment of the present application comprehensively considers the ship speed ratio, relative position, distance between the two ships, DCPA and TCPA factors between the ship and the target ship in the encounter between the ship and a single ship or multiple ships, constructs a risk membership function to effectively evaluate the risk of ship collision, brings the risk of the target ship into the influence function, and calculates the component of the ship in the direction of each node of the domain model. The constructed ship domain safety model can effectively identify the collision risk of a single target ship or multiple target ships to construct a ship safety model, which can provide a technical reference for the research and development of ship intelligent navigation systems with autonomous collision avoidance capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0062] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0063] Figure 2 is a flow chart of an embodiment of a method for constructing a ship safety domain model according to the present application;

[0064] Figure 3 It is a ship encounter situation distribution map according to this application;

[0065] Figure 4 It is a security level model according to this application;

[0066] Figure 5 It is a relationship diagram between the radius of each blockade area and the ship speed according to this application;

[0067] Figure 6 It is a relationship diagram between the radius size and ship speed of the observation area according to this application;

[0068] Figure 7 is a schematic diagram of a ship field model in an encounter situation according to the present application;

[0069] Figure 8is a schematic diagram of a ship field model under a cross situation according to the present application;

[0070] Fig. 9 is a schematic diagram of a ship field model in an overtaking situation according to the present application;

[0071] Fig.10 It is a comparison diagram of the radius of the ship field model at each node of the encounter situation according to the present application;

[0072] Fig.11 It is a comparison diagram of the radius size of the ship field model at each node of the cross situation according to this application;

[0073] Fig.12 It is a comparison diagram of the radius size of the ship field model at each node of the overtaking situation according to the present application;

[0074] Fig.13 is a schematic diagram of a ship field model of multiple ships meeting according to the meeting scenario 1 of the present application;

[0075] Fig.14 is a schematic diagram of a ship field model of multiple ships meeting according to the meeting scenario 2 of the present application;

[0076] Fig.15 It is a comparison diagram of the radius sizes at the nodes of the multi-ship encounter field model according to the encounter scenario 1 of the present application;

[0077] Fig.16 It is a comparison diagram of the radius sizes at the nodes of the multi-ship encounter field model according to the encounter scenario 2 of the present application;

[0078] Fig.17 is a flow chart of an embodiment of a device for constructing a ship safety domain model according to the present application;

[0079] Fig.18 It is a structural diagram of a computer system of a terminal device or server suitable for implementing an embodiment of the present application. DETAILED DESCRIPTION

[0080] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It should also be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0081] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0082] Figure 1An exemplary system architecture 100 is shown to which the method for processing information or the apparatus for processing information according to the embodiments of the present application can be applied.

[0083] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0084] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0085] The terminal devices 101 , 102 , and 103 may be various electronic devices with communication functions, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0086] The server 105 may be a server that provides various services, such as a background information processing server that processes the verification request information sent by the terminal devices 101, 102, and 103. The background information processing server may analyze the received verification request information and obtain a processing result (such as verification success information that indicates that the verification request is a legitimate request).

[0087] It should be noted that the method for processing information provided in the embodiment of the present application is generally executed by the server 105, and accordingly, the device for processing information is generally set in the server 105. In addition, the method for sending information provided in the embodiment of the present application is generally executed by the terminal devices 101, 102, 103, and accordingly, the device for sending information is generally set in the terminal devices 101, 102, 103.

[0088] It should be noted that the server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services), or it can be implemented as a single software or software module. No specific limitation is made here.

[0089] It should be understood that Figure 1The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0090] like Figure 2 As shown in the figure, the method of constructing the ship safety domain model includes:

[0091] S201: Acquire key parameters that affect the degree of danger of encountering a ship, wherein the key parameters include the distance between the own ship and the obstacle ship, the speed ratio between the own ship and the obstacle ship, the relative side angle between the own ship and the obstacle ship, the closest encounter distance between the own ship and the obstacle ship, and the minimum encounter time between the own ship and the obstacle ship;

[0092] In a specific embodiment, the collision risk is a key parameter for measuring and classifying the degree of danger of a ship encounter situation, and is an important basis for determining whether to take evasive action. It is widely used in collision avoidance and traffic engineering research. This application takes the speed ratio between the ship and the obstacle ship, the relative side angle between the ship and the obstacle ship, the closest encounter distance and the closest encounter time as the main consideration parameters, and takes into account the ship's deceleration performance and steering performance, and finally determines the collision risk posed by the obstacle ship to the ship.

[0093] S202: In response to the key parameters, constructing the danger membership functions corresponding to the key parameters respectively, the danger membership functions including the danger membership function of the distance between the own ship and the obstacle ship, the danger membership function of the speed ratio between the own ship and the obstacle ship, the danger membership function of the relative side angle between the own ship and the obstacle ship, the danger membership function of the closest encounter distance between the own ship and the obstacle ship, and the danger membership function of the closest encounter time between the own ship and the obstacle ship;

[0094] In a specific embodiment, the distance danger membership function between the own ship and the obstacle ship is specifically:

[0095]

[0096] Where U D is the distance hazard membership function between the own ship and the obstacle ship, D is the distance between the own ship and the obstacle ship, D1 is the latest avoidance distance, and D2 is the distance where avoidance measures can be taken;

[0097] The specific dangerous membership function of the speed ratio between the own ship and the obstacle ship is:

[0098]

[0099] Where U K is the speed ratio hazard membership function between the own ship and the obstacle ship, K is the speed ratio between the own ship and the obstacle ship and K ≥ 0, a is the encounter angle and a∈(0°,180°).

[0100] The relative side angle hazard membership function between the own ship and the obstacle ship is as follows:

[0101]

[0102] In the formula, is the relative side angle hazard membership function between the own ship and the obstacle ship, θ2 is the side angle of the own ship relative to the obstacle ship, and θ2∈(0°,360°);

[0103] The specific hazard membership function of the closest encounter distance between the own ship and the obstacle ship is:

[0104]

[0105] Where U DCPA is the hazard membership function of the closest encounter distance between the own ship and the obstacle ship, DCPA is the closest encounter distance between the own ship and the obstacle ship, d1 represents the minimum safe distance at which the obstacle ship can safely encounter the own ship, and d2 is the absolute safe encounter distance between the two ships;

[0106] The specific hazard membership function of the closest encounter time between the own ship and the obstacle ship is:

[0107]

[0108]

[0109] Where U TCPA is the hazard membership function of the closest encounter time between the own ship and the obstacle ship, D1 represents the latest avoidance distance, D2 represents the distance at which avoidance measures can be taken, and VR represents the relative speed of the target ship.

[0110] S203: In response to the risk membership function, calculating the collision risk between the own ship and the obstacle ship;

[0111] Assume that the number of obstacle ships within the detectable range around the ship is N, and the relevant data of the ith obstacle ship is: the speed ratio between the ship and the ith obstacle ship is K i , the relative side angle between the ship and the i-th obstacle ship θ2i, the closest encounter distance DCPAi ， The nearest encounter distance TCPAi, the corresponding danger membership functions are U Ki , U Di , U DCPAi ,U TCPAi , all belong to [0,1], where i = 0, 1, 2, ···, N. The corresponding weights are: speed ratio hazard membership function weight a K , relative side angle hazard membership function weight The weight of the dangerous membership function of the distance between the two ships is a D , the nearest encounter distance danger membership function weight a DCPA , the nearest time danger membership function weight aTCPA ,in

[0112] The danger level CR of the obstacle ship relative to the own ship i , can be calculated by substituting formula (1) to formula (6) into formula (7):

[0113]

[0114] S204: In response to the collision risk, construct a ship encounter situation distribution model, obtain nodes on the ship encounter situation distribution model, calculate node vectors of the nodes, and construct a risk influence function corresponding to the node vector to construct a safety level model;

[0115] like Figure 3 As shown in the figure, it is a model for the distribution of ship encounter situations. Due to different encounter situations, the collision risk of the target ship is different. According to the distribution of ship encounter situations, with the bow direction as 0°, the space within 360° around the ship is divided into three categories: encounter situation (0°, 5°) U (355°, 360°), crossing situation (5°, 112.5°) U (247.5°, 355°), and overtaking situation (112.5°, 247.5°). Since the space occupied by the crossing situation and the overtaking situation is relatively large, taking the midline as the boundary vertex will result in too few vertices in the polygonal model, which cannot effectively represent the danger of different directions of the ship. Therefore, it is divided as follows: 1. The two crossing situation areas are divided into four areas by the bisector; 2. The overtaking situation area is divided into three areas. The midline of each area is taken as the direction of the corresponding boundary of the ship safety area. In the following introduction, the vertices of the model in this direction are called nodes.

[0116] In order to calculate the size Di of each node vector, we first need to determine a basic ship domain model, the model size of which is the model size when the danger of the incoming ship is zero. The vector dbi of the basic model in the direction of each node is determined by formula (8):

[0117]

[0118] Where, d max is the maximum radius of the reference model, d max The type can be derived from the following safety level model.

[0119] In order to reasonably divide the relative positions of other ships in the area around this ship, and to solve the problem that previous studies in the field of ships only describe the size of the collision risk by the size of the collision risk, but do not give specific measures for the collision risk standard value, the ship safety field model proposed in this application takes into account two different safety levels, and the size of the ship field safety model at different safety levels will also be different. When the obstacle ship enters the model area under the first safety level, a very urgent meeting situation will be formed. At this time, this ship can no longer avoid the obstacle ship by turning the rudder alone, and corresponding speed control is required to avoid the obstacle ship. When the obstacle ship enters the model area under the second safety level, a relatively urgent meeting situation will be formed. At this time, this ship should take evasive action to make the obstacle ship avoid the area as soon as possible.

[0120] This embodiment is based on the concepts and models of blocking area and watching area established by Kijima and Furukawa, such as Figure 4 As shown, to select different levels of d min and d max The selection method is: calculate the longitudinal radius of the front and rear areas of the blocked area and the observation area and the transverse diameter of the left and right areas respectively, and take the maximum and minimum radius as the d for calculating the first and second safety level models. min and d max .

[0121] Among them, the first security level model is:

[0122] The longitudinal radius and transverse diameter of the front and rear areas of the blocked area in the Kijima model are R bf , R ba , S b , the corresponding radius is calculated as:

[0123]

[0124] in,

[0125]

[0126] In the formula, k AD is the gain of the advance distance, k DT is the gain of the gyration diameter, A D is the approach distance, D T is the initial diameter of the turn, L is the length of the ship, and Vo is the speed of the ship.

[0127] Under the condition of the same ship length L, the relationship between the ship speed Vo and the radius of the blockade area is as follows: Figure 5 As shown, Figure 5is the Kijima model. It can be seen from the figure that as the ship speed increases, the forward diameter R bf It is always the maximum radius; when the ship speed is less than 10.38kn, the minimum radius is the transverse diameter S b , when the ship speed is greater than 10.38kn, the minimum radius is the transverse diameter R ba Therefore, the first safety level model parameters are

[0128]

[0129] In a specific embodiment, the second security level model is:

[0130] The longitudinal radius and transverse diameter of the front and rear areas of the observation area in the Kijima model are R wf , R wa , S w , the corresponding radius is calculated as:

[0131]

[0132] Under the same ship length L, the relationship between the ship speed Vo and the radius of the Kijima model observation area is as follows: Figure 6 As shown in the figure, it can be concluded that as the ship speed increases, the forward diameter Rwf is always the maximum radius; when the ship speed is less than 10.38kn, the minimum radius is the transverse diameter Sw, and when the ship speed is greater than 10.38kn, the minimum radius is the transverse diameter Rwa. Therefore, the first safety level model parameters are

[0133]

[0134] After calculating the collision risk CR of the i-th ship i , in order to determine the collision risk CR i and the size of each node vector D i It is necessary to determine an influence function that can accurately describe the danger degree of each node direction in the ship domain model. This influence function can divide the danger value into vectors in the direction of each node according to the relative orientation of the incoming ship, that is, the danger degree in the direction of the incoming ship is the largest, and the danger degrees on both sides gradually decrease with this direction as the center.

[0135] Commonly used influence functions include parabolic function, square wave function, Gaussian function, triangular wave function, Gamma function, etc. Through comparison, it is found that the functions suitable for the requirements of this application are Gaussian function and triangular wave. Since the value of the triangular wave function at the vertex varies greatly, the boundary of the incoming ship direction will be too abrupt and vary greatly when used in the ship domain model. Therefore, the Gaussian function is selected as the influence function. In order to better construct the ship domain model, this application has made appropriate improvements to the Gaussian function and introduced an amplitude variable a that changes with the azimuth of the incoming ship.G , the improved Gaussian function is

[0136]

[0137] in,

[0138]

[0139] In the formula, θ bi is the angle of each node direction of the domain model, and θ1 is the azimuth of the incoming ship.

[0140] S205: In response to the hazard influence function and the safety level model, the boundary vectors between the own ship and a single obstacle ship and multiple obstacle ships under the encounter situation distribution are calculated respectively.

[0141] Therefore, the vector length D of each node direction in the single ship encounter state is si for

[0142] D si =d bi +(d max -d min )·CR i ·G i (16)

[0143] When multiple ships encounter the ship at the same time, the vector length D of each node direction mi The method for determining is: first determine the vector length of each node direction when each ship encounters the ship alone, and then select the maximum vector in each node direction as the boundary vector of the ship domain model under the multi-ship encounter situation.

[0144] D mi =max(D si (j)) (17)

[0145] In addition to the single-ship encounter situation, this application also conducts a comparative analysis of the models for multi-ship encounter situations, and verifies the effectiveness of the ship safety model proposed in this application from multiple aspects.

[0146] In a specific embodiment, when a single ship encounters its own ship:

[0147] This application mainly studies the ship field model under three typical encounter situations, namely, the encounter situation, the crossing situation and the overtaking situation. The simulation parameters of different encounter situations are shown in Table 1.

[0148] Table 1 Single ship encounter parameters

[0149]

[0150] Figure 7 , Figure 8and Fig. 9 The field models of various ships are shown respectively in three encounter situations of single ship: head-on encounter, crossing and overtaking. Fig.10 , Fig.11 and Fig.12 The radius of each model at the node is shown respectively in the three encounter situations of single ship: head-on encounter, crossing and overtaking.

[0151] As can be seen from the figure, in the encounter situation, the radius of the observation area in the second safety level model in the direction of the incoming ship is increased by 0.2655Nm compared with that in the Kijima model, and the radius of the blockade area in the first safety level model in the direction of the incoming ship is increased by 0.1327 compared with that in the Kijima model, but the model in the stern direction is basically similar to the Kijima model. In the crossing situation, the radius of the observation area in the second safety level model in the direction of the incoming ship is increased by 0.1905Nm compared with that in the Kijima model, and the radius of the blockade area in the first safety level model in the direction of the incoming ship is increased by 0.0737Nm compared with that in the Kijima model, but the model in the stern and port direction is basically similar to the Kijima model. In the overtaking situation, the radius of the observation area in the second safety level model in the direction of the incoming ship is increased by 0.1991Nm compared with that in the Kijima model, and the radius of the blockade area in the first safety level model in the direction of the incoming ship is increased by 0.0921Nm compared with that in the Kijima model, but the model in the bow direction is basically similar to the Kijima model. Since the Fujii model only considers the influence of the ship's length L on the model, and the Wang model considers the influence of the ship speed V on its basis, the Fujii model and the Wang model are basically the same in size and shape in the three results, and the radius size is obviously smaller than the ship field model under the first and second safety levels.

[0152] In a specific embodiment, when multiple ships encounter the ship:

[0153] When multiple ships meet, this application sets up two different meeting scenarios to compare and analyze the models under the complex meeting situation of multiple ships. The parameters of the two encounters are shown in Table 2.

[0154] Table 2 Multi-ship encounter parameters

[0155]

[0156] Fig.13 and Fig.14 The following are the simulation results of each ship domain model under two multi-ship encounter scenarios: encounter scenario 1 and encounter scenario 2.

[0157] Fig.15 and Fig.16 The radius of each model at the node in two multi-ship encounter scenarios, encounter scenario 1 and encounter scenario 2, is shown respectively. Fig.15 It can be seen that in the meeting scenario 1, the radius of the observation area in the second safety level model in the direction of the three approaching ships increased by 0.2158Nm, 0.1272Nm, and 0.0897Nm respectively compared with the Kijima model. Fig.16 It can be seen that in the meeting scenario 1, the radius of the blockade area in the first safety level model in the direction of the three approaching ships is increased by 0.1079Nm, 0.0755Nm, and 0.0513Nm respectively compared with the Kijima model. It can be seen from the simulation results that the ship domain model proposed in this application can effectively adjust the shape and size of the model according to the direction of the approaching ship to cope with the complex encounter situation of multiple ships.

[0158] In a specific embodiment, Fig.17 As shown, a flowchart 1000 of an apparatus for constructing a ship safety domain model includes:

[0159] S1001: a key parameter acquisition module, configured to acquire key parameters that affect the degree of danger of encountering a ship, wherein the key parameters include the distance between the own ship and the obstacle ship, the speed ratio between the own ship and the obstacle ship, the relative side angle between the own ship and the obstacle ship, the closest encounter distance between the own ship and the obstacle ship, and the closest encounter time between the own ship and the obstacle ship;

[0160] S1002: a danger membership function construction module is configured to respond to key parameters and construct danger membership functions corresponding to the key parameters, the danger membership functions including the danger membership function of the distance between the own ship and the obstacle ship, the danger membership function of the speed ratio between the own ship and the obstacle ship, the danger membership function of the relative side angle between the own ship and the obstacle ship, the danger membership function of the closest encounter distance between the own ship and the obstacle ship, and the danger membership function of the minimum encounter time between the own ship and the obstacle ship;

[0161] S1003: a collision risk calculation module, configured to calculate the collision risk between the own ship and the obstacle ship in response to the risk membership function;

[0162] S1004: A ship encounter situation distribution model construction module is configured to respond to the collision risk, construct a ship encounter situation distribution model, obtain nodes on the ship encounter situation distribution model, calculate node vectors of the nodes, and construct a risk influence function corresponding to the node vector to construct a safety level model;

[0163] S1005: A ship safety domain model building module, in response to the hazard impact function and the safety level model, calculates the boundary vectors of the ship and a single obstacle ship and multiple obstacle ships under the encounter situation distribution.

[0164] This application constructs a dynamic ship domain model that takes into account two safety levels. The model takes into account factors such as the scale, speed, heading, encounter angle, relative distance, TCPA and DCPA of the ship and other ships. By establishing a dangerous membership function for different influencing factors and combining the improved Gaussian influence function to derive its influence relationship on the ship domain model, the domain model can be adjusted accordingly as the navigation status of the ship and the target ship changes. At the same time, the model is divided into regions based on the three encounter situations of encounter, crossing and overtaking, and the nodes of the corresponding boundaries are obtained, so that the domain model can effectively reflect the risk of ship collision under different encounter types, different speeds and distances, and provide support for the automatic obstacle avoidance of intelligent ships and the needs of risk analysis.

[0165] like Fig.18 As shown, the computer system 1100 includes a central processing unit (CPU) 1101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage part 1108 into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the system 1100 are also stored. The CPU 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0166] The following components are connected to the I / O interface 1105: an input section 1106 including a keyboard, a mouse, etc.; an output section 1107 including a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN card, a modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to the I / O interface 1105 as needed. A removable medium 1111, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1110 as needed, so that a computer program read therefrom is installed into the storage section 1108 as needed.

[0167] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1109, and / or installed from the removable medium 1111. When the computer program is executed by the central processing unit (CPU) 1101, the above functions defined in the method of the present application are executed. It should be noted that the computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable medium or any combination of the above two. The computer-readable medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus or a device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus or a device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0168] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0169] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0170] The modules involved in the embodiments described in the present application can be implemented by software or hardware. The modules described can also be set in a processor. For example, they can be described as: a processor includes a key parameter acquisition module, a danger membership function construction module, a collision risk calculation module, a ship encounter situation distribution model construction module and a ship safety field model construction module. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the key parameter acquisition module can also be described as "a module configured to obtain key parameters that affect the degree of danger of ship encounters, wherein the key parameters include the distance between the ship and the obstacle ship, the speed ratio between the ship and the obstacle ship, the relative side angle between the ship and the obstacle ship, the closest encounter distance between the ship and the obstacle ship, and the closest encounter time between the ship and the obstacle ship".

Claims

1. A method for constructing a ship safety domain model, characterized in that: The method comprises: Obtaining key parameters that affect the degree of danger of encountering a ship, wherein the key parameters include the distance between the own ship and the obstacle ship, the speed ratio between the own ship and the obstacle ship, the relative side angle between the own ship and the obstacle ship, the closest encounter distance between the own ship and the obstacle ship, and the minimum encounter time between the own ship and the obstacle ship; In response to the key parameters, constructing the danger membership functions corresponding to the key parameters respectively, the danger membership functions including the danger membership function of the distance between the own ship and the obstacle ship, the danger membership function of the speed ratio between the own ship and the obstacle ship, the danger membership function of the relative side angle between the own ship and the obstacle ship, the danger membership function of the closest encounter distance between the own ship and the obstacle ship, and the danger membership function of the minimum encounter time between the own ship and the obstacle ship; In response to the risk membership function, calculating the collision risk between the own ship and the obstacle ship; In response to the collision risk, a ship encounter situation distribution model is constructed, nodes on the ship encounter situation distribution model are obtained, node vectors of the nodes are calculated, and a risk influence function corresponding to the node vector is constructed to construct a safety level model; In response to the hazard influence function and the safety level model, respectively calculating the boundary vectors between the own ship and a single obstacle ship and multiple obstacle ships under the encounter situation distribution model; The specific steps of calculating the node vector of the node and constructing the risk influence function corresponding to the node vector are: When the directional risk of the node is calculated to be 0, the length of the node vector is: Where, d bi is the length of the node vector when the directional risk of the node is 0, d max is the maximum radius of the ship encounter situation distribution model; Construct the risk impact function corresponding to the node vector, specifically: In the formula, G i is the risk impact function, a G is the amplitude variable that changes with the azimuth of the approaching ship, θ bi is the angle of each node direction of the model, θ1 is the azimuth of the incoming ship; The calculation of the boundary vectors between the own ship and a single obstacle ship and multiple obstacle ships under the encounter situation distribution model is specifically: Calculate the vector length of each node direction in the single ship encounter state: D si =d bi +(d max -d min )·CR i ·G i Where D si is the vector length of each node direction in the single ship encounter state, d bi is the length of the node vector when the directional risk of the node is 0, d min is the minimum radius of the ship encounter situation distribution model, d max is the maximum radius of the ship encounter situation distribution model, CR i is the collision risk between the own ship and the obstacle ship, G i is the risk impact function; Based on the vector length of each node direction in the single-ship encounter state, the vector length of each node direction when multiple ships encounter the ship at the same time is calculated, and the maximum vector in each node direction is selected as the boundary vector of the ship domain model in the multi-ship encounter situation: D mi =max(D si (j)) Where D mi is the vector length of each node direction in the multi-ship encounter state, D si is the vector length of each node direction in the single ship encounter state.

2. The method for constructing a ship safety domain model according to claim 1, characterized in that: The distance danger membership function between the own ship and the obstacle ship is specifically: Where U D is the distance hazard membership function between the own ship and the obstacle ship, D is the distance between the own ship and the obstacle ship, D1 is the latest avoidance distance, and D2 is the distance at which avoidance measures can be taken; The speed ratio hazard membership function between the own ship and the obstacle ship is specifically: Where U K is the speed ratio hazard membership function between the own ship and the obstacle ship, K is the speed ratio between the own ship and the obstacle ship and K ≥ 0, a is the encounter angle and the range of a is 0°~180°; The relative side angle hazard membership function between the own ship and the obstacle ship is specifically: In the formula, is the relative side angle hazard membership function between the own ship and the obstacle ship, θ2 is the side angle of the own ship relative to the obstacle ship, and the range of θ2 is 0~360°; The danger membership function of the closest encounter distance between the own ship and the obstacle ship is specifically: Where U DCPA is the hazard membership function of the closest encounter distance between the own ship and the obstacle ship, DCPA is the closest encounter distance between the own ship and the obstacle ship, d1 represents the minimum safe distance at which the obstacle ship can safely encounter the own ship, and d2 is the absolute safe encounter distance between the two ships; The minimum encounter time danger membership function of the own ship and the obstacle ship is specifically: Where U TCPA is the minimum encounter time hazard membership function between the own ship and the obstacle ship, D1 represents the latest avoidance distance, D2 represents the distance at which avoidance measures can be taken, and V R It represents the relative speed of the target ship, DCPA is the closest encounter distance between the own ship and the obstacle ship, TCPA is the minimum encounter time between the own ship and the obstacle ship, t1 is the shortest time that the obstacle ship can safely encounter the own ship, and t2 is the absolute safe encounter time of the two ships.

3. The method for constructing a ship safety domain model according to claim 1, characterized in that: The specific expression of the collision risk between the own ship and the obstacle ship is: In the formula, CR i is the collision risk between the own ship and the obstacle ship, i represents the i-th obstacle ship, Ki is the speed ratio between the own ship and the i-th obstacle ship, θ2i is the relative side angle between the own ship and the i-th obstacle ship, Di is the distance between the own ship and the i-th obstacle ship, DCPAi is the closest encounter distance between the own ship and the i-th obstacle ship, TCPAi is the minimum encounter time between the own ship and the i-th obstacle ship, and U Ki is the speed ratio hazard membership function between the ship and the i-th obstacle ship, U Di is the distance danger membership function between the ship and the i-th obstacle ship, is the relative side angle hazard membership function between the ship and the i-th obstacle ship, U DCPAi is the closest encounter distance between the ship and the i-th obstacle ship, and U TCPAi is the minimum encounter time hazard membership function between the ship and the i-th obstacle ship, a K is the speed ratio hazard membership function weight, is the relative side angle hazard membership function weight, a D is the weight of the dangerous membership function of the distance between the two ships, a DCPA is the weight of the nearest encounter distance hazard membership function, a TCPA is the minimum encounter time hazard membership function weight, where 4. The method for constructing a ship safety domain model according to claim 1, characterized in that: The construction of the ship encounter situation distribution model and obtaining the nodes on the ship encounter situation distribution model are specifically: Taking the heading of the own ship as 0° and the own ship as the center of the circle, the space in the range of 0° to 360° is divided into an encounter situation, a crossing situation and an overtaking situation, wherein the spatial range of the encounter situation includes 0°~5° and 355°~360°, the spatial range of the crossing situation includes 5°~112.5° and 247.5°~355°, and the spatial range of the overtaking situation is 112.5°~247.5°. The space of the crossing situation and the space of the overtaking situation are equally divided into a number of equal areas within their respective spatial ranges by a number of bisectors passing through the center of the circle, and the other end of the bisector relative to the center of the circle is taken as a node on the ship encounter situation distribution model.

5. The method for constructing a ship safety domain model according to claim 4, characterized in that: The crossing situation is divided into four equal areas, and the overtaking situation is divided into three equal areas.

6. The method for constructing a ship safety domain model according to claim 1, characterized in that: The construction of the security level model is specifically as follows: A security level model including a blockade area and an observation area is established, and the longitudinal radius of the front area, the longitudinal radius of the rear area, and the lateral diameter of the left and right areas of the blockade area and the observation area are calculated respectively, and the maximum and minimum radius are taken out as the maximum radius and minimum radius of the security level model respectively. The security level model includes a first security level model and a second security level model.

7. The method for constructing a ship safety domain model according to claim 6, characterized in that: The longitudinal radius of the front area, the longitudinal radius of the rear area and the transverse diameter of the blocked area in the first security level model are calculated as follows: in, In the formula, R bf , R ba , S b are respectively the longitudinal radius of the front area, the longitudinal radius of the rear area and the transverse diameter of the blocked area of ​​the first security level model, AD is the gain of the advance distance, k DT is the gain of the gyration diameter, A D is the approach distance, D T is the initial turning diameter, L is the length of the ship, Vo is the speed of the ship, d min1 is the minimum radius of the first safety level model, d max1 is the maximum radius of the first safety level model; The longitudinal radius of the front area, the longitudinal radius of the rear area and the transverse diameter of the blocked area in the second safety level model are calculated as follows: In the formula, R wf , R wa , S w are the longitudinal radius of the front area, the longitudinal radius of the rear area and the transverse diameter of the blockade area of ​​the second safety level, L is the length of the ship, Vo is the speed of the ship, d min2 is the minimum radius of the second safety level model, d max2 is the maximum radius of the second safety level, and kn is the unit of ship speed.

8. A device for constructing a ship safety domain model, characterized in that: The method for constructing a ship safety domain model according to any one of claims 1 to 7 is adopted, wherein the device comprises: A key parameter acquisition module is configured to acquire key parameters that affect the degree of danger of encountering a ship, wherein the key parameters include the distance between the own ship and the obstacle ship, the speed ratio between the own ship and the obstacle ship, the relative side angle between the own ship and the obstacle ship, the closest encounter distance between the own ship and the obstacle ship, and the minimum encounter time between the own ship and the obstacle ship; a danger membership function construction module, configured to construct danger membership functions corresponding to the key parameters in response to the key parameters, the danger membership functions including a danger membership function of the distance between the own ship and the obstacle ship, a danger membership function of the speed ratio between the own ship and the obstacle ship, a danger membership function of the relative side angle between the own ship and the obstacle ship, a danger membership function of the closest encounter distance between the own ship and the obstacle ship, and a danger membership function of the minimum encounter time between the own ship and the obstacle ship; A collision risk calculation module, configured to calculate the collision risk between the own ship and the obstacle ship in response to the risk membership function; a ship encounter situation distribution model construction module, configured to construct a ship encounter situation distribution model in response to the collision risk, obtain nodes on the ship encounter situation distribution model, calculate node vectors of the nodes, and construct a risk influence function corresponding to the node vector, and construct a safety level model; The ship safety domain model building module is configured to respond to the hazard impact function and the safety level model, and respectively calculate the boundary vectors between the ship and a single obstacle ship and multiple obstacle ships under the encounter situation distribution model.

Images