Marine mixed high-density ship area navigation situation discrimination method

Abstract

The invention, which belongs to the field of ship navigation safety control, discloses a navigation situation discrimination method for an offshore mixed high-density ship area, and the method comprises the steps: obtaining ship supervision data of the offshore mixed high-density ship area; constructing a ship navigation situation discrimination index system based on the ship supervision data; calculating the comprehensive weight of each index based on a combined weighting method; constructing an interval grade of each index, calculating an expectation, an entropy and a hyper-entropy corresponding to each grade, and according to the comprehensive weight and the expectation, the entropy and the hyper-entropy of the index interval grade, judging the cloud certainty degree of the index belonging to each risk grade; and based on a maximum membership degree principle, processing the cloud certainty degree of the judgment index belonging to each risk level so as to acquire a navigation situation risk level. According to the invention, ship high-density area identification is carried out in a maritime mixed traffic scene, so that a shore-based supervisor is assisted to judge the risk level of the found high-ship-density area in a water area, and the navigation situation identification capability of the supervisor is improved.

Description

Technical Field

[0001] The present invention relates to the field of ship navigation safety control, and in particular to a method for distinguishing the navigation situation in a mixed high-density ship area at sea. Background Art

[0002] In the future, maritime traffic scenarios will enter a transitional period of mixing manned ships with various levels of intelligent ships. Changes in regulatory objects and regulatory scenarios will not only increase the objects of information interaction and the amount of information interacted in the waters, but will also cause more regulatory pressure on water regulators, making it more difficult for regulators to judge the navigation status of ships in the waters. At the same time, the existence of the shore-based remote control center of intelligent ships will cause delays in the interaction process between regulators and intelligent ships, resulting in delayed regulatory decisions. Most of the existing situation assessment studies are navigation situation and risk analysis studies for traditional ships, and a small number of studies are situation analysis for unmanned aerial vehicles. In addition, a large number of analytical studies are quantitative analyses from the perspective of the ship itself, and there are few large-scale water navigation situation assessment methods for supervision.

[0003] In order to assist shore-based supervisors in grasping the overall navigation situation in the waters and discovering high-risk ship navigation areas earlier, a navigation situation assessment and analysis method is needed that takes into account factors such as hydrological meteorology in high-density ship areas, the proportion of smart ships, and ship density from the perspective of overall water supervision. Summary of the invention

[0004] In view of the shortcomings of the prior art, the present invention provides a method for distinguishing the navigation situation in a mixed high-density ship area at sea. The present invention identifies a high-density ship area in a mixed traffic scenario at sea, thereby assisting shore-based supervisors in judging the risk level of the high-density ship area in the waters they have discovered, and improving the supervisors' ability to identify the navigation situation.

[0005] The technical means adopted by the present invention are as follows:

[0006] A method for determining navigation situation in a mixed high-density ship area at sea comprises the following steps:

[0007] S1. Obtaining ship supervision data of a mixed high-density ship area at sea, where the mixed high-density ship area at sea is an area with dense ship traffic flow at sea, and where manned ships, remote-controlled ships and unmanned ships are mixed sailing;

[0008] S2. Constructing a ship navigation situation identification index system based on the ship supervision data, wherein the ship navigation situation identification index system includes hydrological and meteorological indicators and navigation situation indicators;

[0009] S3. Calculate the comprehensive weight of each indicator based on the combined weighting method, wherein the first weight of the combination in the combined weighting method is calculated by the order relationship method, and the second weight is calculated by the extension correlation function method;

[0010] S4. According to the preset indicator interval, construct the interval level of each indicator, calculate the expectation, entropy and super entropy corresponding to each interval level, and judge the cloud certainty of the indicator belonging to each interval level according to the expectation, entropy and super entropy of the indicator interval level, and finally determine the comprehensive cloud certainty in combination with the comprehensive weight;

[0011] S5. Based on the maximum membership principle, the cloud certainty of the discrimination index belonging to each risk level is processed to obtain the navigation situation risk level.

[0012] Furthermore, the ship supervision data includes hydrological and meteorological data and ship navigation data;

[0013] The hydrometeorological data include wind, wave and visibility data;

[0014] Ship navigation data includes ship longitude, ship latitude, cargo type, ship length, speed, heading and ship intelligence level.

[0015] Furthermore, the hydrological and meteorological indexes include wind index, wave index and visibility index;

[0016] The navigation status indicators include the proportion of smart ships, the proportion of ships with relative motion trends, the proportion of hazardous chemicals ships, the proportion of large ships and the ship density index in the water area.

[0017] Furthermore, the calculation method of the smart ship proportion index is as follows:

[0018] First, calculate the proportion of smart ships according to the following formula:

[0019] p=n i / n(n i ,n∈N * )

[0020] Among them, p represents the proportion of smart ships, n i represents the number of smart ships, n represents the number of ships in the maritime mixed high-density ship area, N * represents the set of natural numbers that do not include 0;

[0021] Then the proportion of smart ships is mapped to the normalized β function to obtain the smart ship proportion index:

[0022]

[0023]

[0024] Among them, a and b represent the preset adjustment parameters, and I(p) represents the proportion of smart ships;

[0025] The calculation method of the proportion index of ships with relative motion trend is as follows:

[0026] First, the motion trend state between ships is calculated based on the distance information and relative speed information between ships:

[0027]

[0028] Among them, η represents the motion trend state of ship i and ship j, represents the relative distance between ship i and ship j, represents the relative speed between ship i and ship j. When η<0, the two ships are in a convergence state, and when η>0, the two ships are in a separation state.

[0029] Then, the number of ship pairs with relative motion trends in the mixed high-density ship area at sea is obtained according to the motion trend status between ships, thereby obtaining the proportion index of ships with relative motion trends:

[0030]

[0031] Among them, R represents the proportion of ships with relative movement trend, n r It indicates the number of ship pairs with relative motion trends in the mixed high-density ship area at sea;

[0032] The calculation method of the hazardous chemicals ship ratio index is as follows:

[0033] Da=n a / n(n a ∈N * )

[0034] Among them, Da represents the proportion of ships carrying hazardous chemicals, n a Indicates the number of ships carrying hazardous chemicals;

[0035] The calculation method of the large-scale ship proportion index is as follows:

[0036] H=n h / n(n h ∈N * )

[0037] Among them, H represents the proportion of large ships, n h Indicates the number of ships with an overall length of 250 meters and above;

[0038] The calculation method of the ship density index in the waters is as follows:

[0039] First, calculate the average density of ships in the mixed high-density ship area at sea:

[0040]

[0041] Among them, d mean represents the average density of ships in the mixed high-density ship area at sea, d imin represents the minimum distance between ship i and its surrounding ships,

[0042] Then, the Gaussian function is used to reflect the impact of ship density on the navigation situation in some waters. The specific calculation method is as follows:

[0043]

[0044] Among them, f Gauss (d mean ) represents the ship density index of the water area, and σ is the preset adjustment parameter.

[0045] Furthermore, the calculation method of the comprehensive weight of each indicator is as follows:

[0046]

[0047]

[0048] β=1-α

[0049] Among them, W represents the comprehensive weight, represents the first weight, ω b represents the second weight, m ​​represents the number of indicators, and p i represents the vector of the first weight sorted in ascending order;

[0050] The calculation method of the first weight is as follows:

[0051] Obtaining the importance ranking relationship of each indicator in a preset ship navigation situation judgment indicator system, wherein the importance ranking relationship of each indicator includes the ratio of importance between adjacent indicators;

[0052] The first weight of the lowest-importance indicator among the m indicators sorted by importance is calculated according to the following formula:

[0053]

[0054] Among them, ω a (m) represents the first weight of the mth indicator after being sorted by importance, γ i ,i=2,3,...m represents the ratio of the importance of the i-1th indicator to the i-th indicator;

[0055] By weight ω a (m) The calculation formula for the weights of the m-2, m-1, ..., 3, 2 indicators is:

[0056]

[0057] The second weight is calculated as follows:

[0058] For the classic domain v corresponding to the level j of index i ij =[a ij ,b ij ],

[0059] If a ij ≤ b ij , then

[0060]

[0061] If a ij >b ij , then

[0062]

[0063] but

[0064]

[0065] Where: v(x i ) represents the sample value of the i-th indicator; v ij represents the value range of the i-th indicator corresponding to the j-th level in the classic domain; r ij represents the correlation between the i-th indicator and level j,

[0066] Since the greater the level of the data falling into index i, the greater the weight of the index where the data belongs, then the index correlation degree r i It can be calculated by the following formula:

[0067]

[0068] In the formula: j represents the interval level that the sample value of indicator i falls into,

[0069] The second weight of indicator i can be calculated by the following formula:

[0070]

[0071] Furthermore, the calculation methods of expectation, entropy and super entropy corresponding to each interval level are as follows:

[0072]

[0073]

[0074]

[0075]

[0076] in, represents the expectation of interval rank t, represents the entropy of interval level t, represents the super entropy of interval level t, represents the upper limit value of interval level t, represents the lower limit of the interval level t, [γ] is the interval The order of the inner normal density function, taking the largest integer, C t The value is σ t is the interval length of level interval t, and λ is a preset constant.

[0077] Furthermore, the calculation method of the cloud certainty of each indicator belonging to each risk level is as follows:

[0078] Input the index value x into the forward finite interval cloud generator composed of different level intervals of the index to which it belongs, and the cloud certainty of each risk index belonging to each risk level can be obtained:

[0079]

[0080] Among them, μ(x) represents the cloud certainty that each risk indicator belongs to each risk level, E n ' is a For expectations, is a normal random number with standard deviation; x is a For expectation, E n ′ is a normal random number with standard deviation, It is the expected value of the leftmost edge interval of the index to which the index value x belongs; It is the expected value of the rightmost edge interval of the index to which the index value x belongs; It is the maximum value of the rightmost edge interval of the index to which the index value x belongs;

[0081] In order to reduce the impact of randomness on the calculation results, the cloud certainty of the calculated index i corresponding to level j is calculated 100 times and the sum is averaged. The specific calculation formula is as follows:

[0082]

[0083] in, It represents the cloud certainty of level j corresponding to the index i after adding and averaging. It represents the cloud certainty of level j corresponding to indicator i calculated for the tth time.

[0084] Furthermore, the calculation method of the comprehensive cloud certainty is as follows:

[0085]

[0086] Among them, U j represents the comprehensive cloud certainty of risk level j, W i It represents the comprehensive weight of indicator i, and m represents the number of indicators.

[0087] Furthermore, the method for obtaining the navigation situation risk level is as follows:

[0088] L=max{U1,U2,...,U j}

[0089] Among them, L represents the navigation situation risk level, U1, U2, ..., U j Indicates the comprehensive cloud certainty corresponding to different risk levels.

[0090] Compared with the prior art, the present invention has the following advantages:

[0091] 1. The present invention proposes a method for distinguishing the navigation situation in a mixed high-density ship area at sea, which can effectively assist shore-based supervisors in distinguishing the situation in a high-density ship area in a supervised water area mixed with a variety of intelligent ships, thereby improving the level of supervision of mixed high-density ship areas at sea.

[0092] 2. The present invention proposes a navigation situation identification index system for mixed high-density ship areas and designs a quantitative calculation method for multiple navigation situation indexes. This method can effectively reflect the water characteristics of mixed high-density ship areas.

[0093] 3. The present invention proposes to use a combined weight calculation method to calculate the comprehensive weight, and calculate the situation risk level of the mixed high-density ship area through a finite interval cloud model. The situation identification results obtained by this method can effectively reduce the energy expenditure of shore-based supervisors in supervising mixed high-density ship areas, and improve the ability to judge the mixed situation.

[0094] Based on the above reasons, the present invention can be widely promoted in the fields of marine mixed high-density ship areas and navigation area situation determination. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] 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.

[0096] Figure 1 The present invention is a flow chart of a method for determining the navigation situation in a mixed high-density ship area at sea.

[0097] Figure 2 This is the evaluation index system architecture of the present invention.

[0098] Figure 3 It is a schematic diagram of the relative movement trend of the present invention.

[0099] Figure 4 It is a schematic diagram of the navigation situation risk level result of the present invention. DETAILED DESCRIPTION

[0100] 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.

[0101] 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.

[0102] like Figure 1 The present invention provides a method for determining navigation situation in a mixed high-density ship area at sea, which mainly includes the following steps:

[0103] S1. Obtain ship supervision data in mixed and high-density ship areas at sea.

[0104] Specifically, in this application, the mixed high-density ship area at sea refers to an area with dense ship traffic flow at sea, and there are various intelligent level ships such as manned ships, remote-controlled ships and unmanned ships in the area. Furthermore, the ship supervision data is divided into hydrological and meteorological data and ship navigation data. Among them, the hydrological and meteorological data includes: wind, wave and visibility data, and the ship navigation data includes: ship longitude, ship latitude, cargo type, ship length, speed, heading and ship intelligence level.

[0105] S2. Constructing a ship navigation situation identification index system based on the ship supervision data.

[0106] like Figure 2 As shown, the ship navigation situation identification index system in the present invention includes hydrological and meteorological indicators and navigation situation indicators. Specifically, the hydrological and meteorological indicators include: wind, wave and visibility indicators; the navigation situation indicators include: intelligent ship proportion index, ship proportion index with relative motion trend, hazardous chemical ship proportion index, large ship proportion index and water area ship density index.

[0107] As a preferred implementation of the present invention, this embodiment provides a quantitative calculation method for five navigation status indicators. The specific calculation method is as follows:

[0108] 1) For the calculation of the impact of the proportion of smart ships, assume that the total number of ships in the water area is n, and the number of smart ships is n i . Then the proportion of smart ships is:

[0109] p=n i / n(n i ,n∈N * )

[0110] Assuming that the proportion p of smart ships in the water area is monotonically increasing in the interval [0, λ) and monotonically decreasing in the interval [λ, 1], the above proportion p is mapped to the normalized β function. In this embodiment, the two parameters a and b of the β function are both 2.5. The specific calculation is as follows:

[0111]

[0112]

[0113] 2) The proportion of ships with relative motion trends is calculated based on the relative motion trend between the two ships, that is, the rate of change of the relative distance between the ships. The specific calculation formula is as follows:

[0114]

[0115] in is the relative distance between the two ships, Indicates the relative speed between the two ships. Figure 3 As shown in the figure, when η<0, the relative distance between the two ships becomes smaller, the two ships are in a convergence state, and have a relative motion trend; when η>0, it indicates that the relative distance between the two ships becomes larger, the two ships are in a separation state, and have no relative motion trend;

[0116] For the ship pairs with relative motion trend in the regulatory waters, it is denoted as n r , then the proportion of ships with relative motion trend can be expressed as:

[0117]

[0118] 3) For the calculation of the proportion of ships carrying hazardous chemicals, let n a represents the number of ships carrying hazardous chemicals, n is the total number of ships in the waters, and the proportion of ships carrying hazardous chemicals is calculated as follows:

[0119] Da=n a / n(n a ∈N * )

[0120] 4) For the calculation of the proportion of large ships, ships with a total length of 250 meters or more are considered large ships, and their number is recorded as n h , then the calculation method is as follows:

[0121] H=n h / n(n h ∈N * )

[0122] 5) For the calculation of the impact of ship density, the minimum distance d between ship i and its surrounding ships in the high ship density waters is assumed to be min , then the average density of ships in the water area can be expressed as:

[0123]

[0124] The Gaussian function is used to reflect the impact of ship density on the navigation situation in some waters. The specific calculation method is as follows:

[0125]

[0126] In this embodiment, σ=1.58.

[0127] S3. Calculate the comprehensive weight of each indicator based on the combined weighting method, wherein the first weight of the combination in the combined weighting method is calculated by the order relationship method, and the second weight is calculated by the extension correlation function method.

[0128] In specific implementation, as a preferred embodiment of the present invention, the present invention combines the combined weighting method of weights to calculate the comprehensive weight of the index, assuming that the first weight calculated by the order relationship method is w a , the second weight calculated by the extension correlation function method is w b , the final comprehensive weight can be calculated by the difference coefficient method. The specific calculation formula is as follows:

[0129]

[0130]

[0131] β=1-α

[0132] Among them, W represents the comprehensive weight, represents the first weight, ω b represents the second weight, m ​​represents the number of indicators, which is preferably 7 in this embodiment, and p i Represents the vector of first weights sorted in ascending order.

[0133] The calculation method of the first weight is as follows:

[0134] Obtaining the importance ranking relationship of each indicator in a preset ship navigation situation judgment indicator system, wherein the importance ranking relationship of each indicator includes the ratio of importance between adjacent indicators;

[0135] The first weight of the lowest-importance indicator among the m indicators sorted by importance is calculated according to the following formula:

[0136]

[0137] Among them, ω a (m) represents the first weight of the mth indicator after being sorted by importance, γ i ,i=2,3,...m represents the ratio of the importance of the i-1th indicator to the i-th indicator;

[0138] By weight ω a (m) The calculation formula for the weights of the m-2, m-1, ..., 3, 2 indicators is:

[0139]

[0140] The second weight is calculated as follows:

[0141] For the classic domain v corresponding to the level j of index i ij =[a ij ,b ij], the classic domain includes two interval styles, one is from small to large, and the other is from large to small. Therefore, for the two cases, this application makes the following distinction settings:

[0142] If a ij ≤ b ij , then

[0143]

[0144] If a ij >b ij , then

[0145]

[0146] No matter which form the classical domain adopts, it will not affect the parameter values ​​of the following calculations:

[0147]

[0148] Where: v(x i ) represents the sample value of the i-th indicator; v ij In the classical domain i The value range of the index corresponding to the jth level; r ij represents the correlation between the i-th indicator and level j,

[0149] Since the greater the level of the data falling into index i, the greater the weight of the index where the data belongs, then the index correlation degree r i It can be calculated by the following formula:

[0150]

[0151] In the formula: j represents the interval level that the sample value of indicator i falls into,

[0152] The second weight of indicator i can be calculated by the following formula:

[0153]

[0154] S4. According to the preset indicator interval, construct the interval level of each indicator, calculate the expectation, entropy and super entropy corresponding to each interval level, and judge the cloud certainty of the indicator belonging to each risk level according to the expectation, entropy and super entropy of the indicator interval level, and finally determine the comprehensive cloud certainty by combining the comprehensive weight.

[0155] In specific implementation, as a preferred embodiment of the present invention, the present invention calculates the navigation situation risk level through a finite interval cloud model. First, construct each index interval level; second, calculate the expectation, entropy and super entropy of each index interval level; then, calculate the comprehensive cloud certainty; finally, determine the navigation situation risk level.

[0156] In specific implementation, as a preferred embodiment of the present invention, the interval t of the index is set to The specific calculation methods of the corresponding expectation, entropy and super entropy parameters are as follows:

[0157]

[0158]

[0159]

[0160]

[0161] Where: represents the expectation of interval rank t, represents the entropy of interval level t, represents the super entropy of interval level t, represents the upper limit value of interval level t, represents the lower limit of the interval level t, [γ] is the interval The order of the inner normal density function, taking the largest integer, C t Expressed as or Its value does not affect the calculation results, σ t is the interval length of the grade interval t; λ is a constant, which is taken as 0.01 in this paper.

[0162] In specific implementation, as a preferred embodiment of the present invention, the index value x is input into a positive finite interval cloud generator composed of different level intervals of the index to which it belongs, and the calculation is cyclically calculated T times, so that the cloud certainty of each risk index belonging to each risk level can be obtained. The specific calculation method is as follows:

[0163]

[0164]

[0165] μ(x) represents the cloud certainty that each risk indicator belongs to each risk level, E n ' is a For expectations, is a normal random number with standard deviation; x is a For the expectation E n ′ is a normal random number with standard deviation, It is the expected value of the leftmost edge interval of the index to which the index value x belongs; It is the expected value of the rightmost edge interval of the index to which the index value x belongs; It is the maximum value of the rightmost edge interval of the index to which the index value x belongs;

[0166] In order to reduce the impact of randomness on the calculation results, the cloud certainty of the calculated index i corresponding to level j is calculated 100 times and the sum is averaged. The specific calculation formula is as follows:

[0167]

[0168] in, It represents the cloud certainty of level j corresponding to the index i after adding and averaging. It represents the cloud certainty of level j corresponding to indicator i calculated for the tth time.

[0169] S5. Based on the maximum membership principle, the cloud certainty of the discrimination index belonging to each risk level is processed to obtain the navigation situation risk level.

[0170] In specific implementation, as a preferred embodiment of the present invention, the comprehensive cloud certainty of each navigation situation risk level is as follows: Figure 4 As shown, according to the maximum membership principle, the final risk warning level L can be obtained. The specific calculation formula is as follows:

[0171] L=max{U1,U2,L,U j}

[0172] Among them, L represents the navigation situation risk level, U1, U2, ..., U j Indicates the comprehensive cloud certainty corresponding to different risk levels.

[0173] 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 method for determining navigation status in a mixed high-density ship area at sea, characterized in that: The following steps are involved: S1. Obtaining ship supervision data of a mixed high-density ship area at sea, where the mixed high-density ship area at sea is an area with dense ship traffic flow at sea, and where manned ships, remote-controlled ships and unmanned ships are mixed sailing; S2. Constructing a ship navigation situation identification index system based on the ship supervision data, wherein the ship navigation situation identification index system includes hydrological and meteorological indicators and navigation situation indicators; S3. Calculate the comprehensive weight of each indicator based on the combined weighting method, wherein the first weight of the combination in the combined weighting method is calculated by the order relationship method, and the second weight is calculated by the extension correlation function method; S4. According to the preset indicator interval, the interval level of each indicator is constructed, the expectation, entropy and super entropy corresponding to each interval level are calculated, and the cloud certainty of the indicator belonging to each interval level is determined according to the expectation, entropy and super entropy of the indicator interval level, and finally the comprehensive cloud certainty is determined by combining the comprehensive weight; S5. Based on the maximum membership principle, the cloud certainty of the discrimination index belonging to each risk level is processed to obtain the navigation situation risk level.

2. A method for determining navigation status in a mixed high-density ship area at sea according to claim 1, characterized in that: The ship supervision data includes hydrological and meteorological data and ship navigation data; The hydrometeorological data include wind, wave and visibility data; Ship navigation data includes ship longitude, ship latitude, cargo type, ship length, speed, heading and ship intelligence level.

3. The method for determining the navigation situation in a mixed high-density ship area at sea according to claim 1 is characterized in that: The hydrological and meteorological indicators include wind indicators, wave indicators and visibility indicators; The navigation status indicators include the proportion of smart ships, the proportion of ships with relative motion trends, the proportion of hazardous chemicals ships, the proportion of large ships and the ship density index in the water area.

4. A method for determining navigation status in a mixed high-density ship area at sea according to claim 3, characterized in that: The calculation method of the smart ship proportion index is as follows: First, calculate the proportion of smart ships according to the following formula: p=n i / n(n i ,n∈N * ) Among them, p represents the proportion of smart ships, n i represents the number of smart ships, n represents the number of ships in the maritime mixed high-density ship area, N * represents the set of natural numbers that do not include 0; Then the proportion of smart ships is mapped to the normalized β function to obtain the smart ship proportion index: Among them, a and b represent the preset adjustment parameters, and I(p) represents the proportion index of smart ships; The calculation method of the index of the proportion of ships with relative motion trend is as follows: First, the motion trend state between ships is calculated based on the distance information and relative speed information between ships: Among them, η represents the motion trend state of ship i and ship j, represents the relative distance between ship i and ship j, represents the relative speed between ship i and ship j. When η<0, the two ships are in a convergence state, and when η>0, the two ships are in a separation state. Then, the number of ship pairs with relative motion trends in the mixed high-density ship area at sea is obtained according to the motion trend status between ships, thereby obtaining the proportion index of ships with relative motion trends: Among them, R represents the proportion of ships with relative movement trend, n r It indicates the number of ship pairs with relative motion trends in the mixed high-density ship area at sea; The calculation method of the hazardous chemicals ship ratio index is as follows: Da=n a / n(n a ∈N * ) Among them, Da represents the proportion of ships carrying hazardous chemicals, n a Indicates the number of ships carrying hazardous chemicals; The calculation method of the large-scale ship proportion index is as follows: H=n h / n(n h ∈N * ) Among them, H represents the proportion of large ships, n h Indicates the number of ships with an overall length of 250 meters and above; The calculation method of the ship density index in the waters is as follows: First, calculate the average density of ships in the mixed high-density ship area at sea: Among them, d mean represents the average density of ships in the mixed high-density ship area at sea, d imin represents the minimum distance between ship i and its surrounding ships, Then, the Gaussian function is used to reflect the impact of ship density on the navigation situation in some waters. The specific calculation method is as follows: Among them, f Gauss (d mean ) represents the ship density index of the water area, and σ is the preset adjustment parameter.

5. The method for determining the navigation situation in a mixed high-density ship area at sea according to claim 1 is characterized in that: The calculation method of the comprehensive weight of each indicator is as follows: β＝1-α Among them, W represents the comprehensive weight, represents the first weight, ω b represents the second weight, m ​​represents the number of indicators, and p i represents the vector of the first weight sorted in ascending order; The calculation method of the first weight is as follows: Obtaining the importance ranking relationship of each indicator in a preset ship navigation situation judgment indicator system, wherein the importance ranking relationship of each indicator includes the ratio of importance between adjacent indicators; The first weight of the lowest-importance indicator among the m indicators sorted by importance is calculated according to the following formula: in, represents the first weight of the mth indicator after being sorted by importance, γ i ,i=2,3,...m represents the ratio of the importance of the i-1th indicator to the i-th indicator; By weight The calculation formula for the weights of the m-2, m-1, ..., 3, 2 indicators is: The second weight is calculated as follows: For the classic domain v corresponding to the level j of index i ij =[a ij ,b ij ], If a ij ≤ b ij , then If a ij >b ij , then but Where: v(x i ) represents the sample value of the i-th indicator; v ij represents the value range of the i-th indicator corresponding to the j-th level in the classic domain; r ij represents the correlation between the i-th indicator and level j, Since the greater the level of the data falling into index i, the greater the weight of the index where the data belongs, then the index correlation degree r i It can be calculated by the following formula: In the formula: j represents the interval level that the sample value of indicator i falls into, The second weight of indicator i can be calculated by the following formula:

6. The method for determining the navigation situation in a mixed high-density ship area at sea according to claim 1, characterized in that: The calculation methods of expectation, entropy and super entropy corresponding to each interval level are as follows: in, represents the expectation of interval rank t, represents the entropy of interval level t, represents the super entropy of interval level t, represents the upper limit value of interval level t, represents the lower limit of the interval level t, [γ] is the interval The order of the inner normal density function, taking the largest integer, C t The value is σ t is the interval length of level interval t, and λ is a preset constant.

7. A method for determining navigation status in a mixed high-density ship area at sea according to claim 6, characterized in that: The calculation method of cloud certainty of each indicator belonging to each risk level is as follows: Input the index value x into the forward finite interval cloud generator composed of different level intervals of the index to which it belongs, and the cloud certainty of each risk index belonging to each risk level can be obtained: Among them, μ(x) represents the cloud certainty of each risk indicator belonging to each risk level, E n ' is a For expectations, is a normal random number with standard deviation; x is a For expectation, E n ′ is a normal random number with standard deviation, is the expected value of the leftmost edge interval of the index to which the index value x belongs; It is the expected value of the rightmost edge interval of the index to which the index value x belongs; It is the maximum value of the rightmost edge interval of the index to which the index value x belongs; In order to reduce the impact of randomness on the calculation results, the cloud certainty of the calculated index i corresponding to level j is calculated 100 times and the sum is averaged. The specific calculation formula is as follows: in, It represents the cloud certainty of level j corresponding to the index i after adding and averaging. It represents the cloud certainty of level j corresponding to indicator i calculated for the tth time.

8. A method for determining navigation status in a marine mixed high-density ship area according to claim 7, characterized in that: The calculation method of comprehensive cloud certainty is as follows: Among them, U j represents the comprehensive cloud certainty of risk level j, W i It represents the comprehensive weight of indicator i, and m represents the number of indicators.

9. The method for determining the navigation situation in a mixed high-density ship area at sea according to claim 1, characterized in that: The method for obtaining the navigation situation risk level is as follows: L=max{U1,U2,...,U j } Among them, L represents the navigation situation risk level, U1, U2, ..., U j Indicates the comprehensive cloud certainty corresponding to different risk levels.

Images