CN114595776A - Ship collision risk assessment method and device and storage medium - Google Patents

Ship collision risk assessment method and device and storage medium Download PDF

Info

Publication number
CN114595776A
CN114595776A CN202210247597.4A CN202210247597A CN114595776A CN 114595776 A CN114595776 A CN 114595776A CN 202210247597 A CN202210247597 A CN 202210247597A CN 114595776 A CN114595776 A CN 114595776A
Authority
CN
China
Prior art keywords
ship
collision
target
scene
risk
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210247597.4A
Other languages
Chinese (zh)
Inventor
余庆
柯冉绚
林婷婷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jimei University
Original Assignee
Jimei University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jimei University filed Critical Jimei University
Priority to CN202210247597.4A priority Critical patent/CN114595776A/en
Publication of CN114595776A publication Critical patent/CN114595776A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/257—Belief theory, e.g. Dempster-Shafer

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Pure & Applied Mathematics (AREA)
  • Educational Administration (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Marketing (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Development Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Primary Health Care (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Algebra (AREA)
  • Probability & Statistics with Applications (AREA)
  • Evolutionary Computation (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a ship collision risk assessment method and an application method thereof, which are used for dynamically assessing ship collision risks under different conditions. The framework identifies collision results under different conditions based on the experience of the captain of the vessel, evaluates collision parameters, and weights the importance of each collision parameter. The evidence reasoning method is used for summarizing the information, real-time collision risk assessment is allowed to be carried out on collision results, each ship collision parameter is assessed under different collision conditions, and scientific and effective analysis and intelligent management on ship traffic are achieved.

Description

Ship collision risk assessment method and device and storage medium
Technical Field
The invention relates to the field of sea area intelligent transportation, in particular to a ship collision risk assessment method and device and a storage medium.
Background
The risk of a vessel collision remains a concern in busy waters and complex navigation environments. In some particular coastal areas, high density of marine traffic tends to increase the probability of vessel collisions, usually higher than in open seas. As a backbone of the development of unmanned ships and intelligent transportation systems, various collision models have been proposed for real-time collision assessment and decision support for avoidance. These models use collision parameters to describe the state of the vessel in the event of an encounter and quantify the risk through mathematical or inferential methods.
Previous research results have shown that an effective, systematic, real-time collision model is necessary, but most models have their limitations. For example, there is no consensus on setting risk thresholds; due to the inherent complex environment, uncertainty and lack of information on weather conditions, ship and traffic conditions, human factors, etc., the model does not cover many features of casual situations; some models attempt to cover environmental features but lack sensitivity to model inputs and few have been proposed in the past. Therefore, there is a need to develop a comprehensive framework for reliable collision risk assessment. The framework needs to be able to dynamically assess the risk of collision in different scenarios while taking into account differences between the scene features.
Disclosure of Invention
In order to overcome the problems of the prior art, the invention provides a ship collision risk assessment method, which comprises the following steps:
s101, acquiring ship traffic AIS data, and performing noise reduction processing on the ship traffic AIS data, wherein the ship traffic AIS data comprises position variables of a ship, ship speed, ship route, water area where the ship is located, weather conditions, ship visibility, ship real-time traffic factors and ship information;
s102, calculating a collision parameter between the ship and a target ship, and quantizing the weight of the collision parameter by an AHP decision method, wherein the collision parameter is used for describing the dynamic motion characteristics of the ship, and comprises the following steps: the calculation formulas of the relative distance between the position variable of the ship and the target ship, the relative azimuth of the ship and the target ship, the shortest time TCPA met by the ship and the target ship and the shortest distance DCPA between the ship and the target ship are as follows:
Figure BDA0003545461210000021
Figure BDA0003545461210000022
where OS and TS denote the ship and the target ship, respectively, d denotes a relative distance, vOSAnd vTSRespectively representing the speed of the ship and the speed of a target ship, and calculating the relative speed v according to the speed of the ship and the speed of the target shiprAnd alpha and beta represent relative bulwarks;
s103, constructing a ship meeting scene according to the ship traffic AIS data, wherein the ship meeting scene comprises: when the target ship passes over the ship, the target ship yields to the ship, when the target ship yields to the ship under the condition of ship crossing, and when the target ship and the ship form a pair driving, and when the target ship and the ship mutually avoid; the ship meeting scene comprises a plurality of scene elements, each ship meeting scene is preset with an evaluation rule corresponding to the scene element one by one, and each scene element also comprises a plurality of factor states;
s104, comparing the scene elements and the factor states with scene labels in the evaluation rules to determine the evaluation rules corresponding to the meeting scenes of the ship, wherein the evaluation rules comprise collision parameter limit values, collision parameter weights and risk avoidance distances;
s105, comparing the collision parameters of the meeting scene of the ship with the collision parameter limit values and the risk avoidance distance, and calculating the collision parameters and the collision parameter weight through an evidence reasoning algorithm to obtain the ship collision risk of the meeting scene.
The invention can also make the following improvement on the basis of the above scheme.
Further, the relative distance d and the relative velocity vrRespectively calculated by the following formula:
Figure BDA0003545461210000023
Figure BDA0003545461210000031
where Lon and Lat respectively represent longitude and latitude coordinates of a position variable of a ship, OS and TS respectively represent a ship and a target ship, and θOSAnd thetaTSRespectively representing the respective heading of the two vessels.
Further, the meeting scene of the ship comprises a plurality of scene elements, and the scene elements comprise ship identity, ship tonnage, water area where the ship is located, weather conditions, ship visibility, real-time ship traffic factors and ship avoidance behaviors.
Further, the acquired ship traffic AIS data is screened, and the ship traffic AIS data which do not belong to the ship meeting scene in S103 are removed.
Further, each scene factor also comprises a plurality of factor states, wherein the ship identity factors comprise ship states which limit the handling capacity or are not handled, ship states which are caught and ships which do not belong to the two ship states; the tonnage factors of the ship comprise a ship state with the tonnage smaller than 500GT and a ship state with the tonnage larger than or equal to 500 GT; the factors of the water area of the ship comprise a port water area state, a limited water area state and an open water area state; the weather condition factors include general weather conditions and severe weather conditions; the ship visibility factors comprise a good visibility state with visibility more than or equal to 2 nautical miles and a poor visibility state with visibility less than 2 nautical miles; the real-time traffic factors of the ship comprise ship cross meeting, opposite driving meeting and overtaking; the ship avoidance responsibility factors comprise a way-giving state and a course-keeping state.
Further, the S105 includes: setting the shortest meeting time of the ship and the target ship as TCPA, the shortest distance between the ship and the target ship as DCPA and the relative distanceIs set as the weight of the collision parameter
Figure BDA0003545461210000032
Wherein the content of the first and second substances,
Figure BDA0003545461210000033
respectively representing the weight of a collision parameter of the shortest time TCPA met by the ship and the target ship, the weight of a collision parameter of the shortest distance DCPA between the ship and the target ship and the weight of a collision parameter of the relative distance, wherein k represents the kth rule, and then the collision risk r of the target ship is determinedTSComprises the following steps:
Figure BDA0003545461210000034
wherein i represents the ith factor state, i belongs to N, and psi represents an evidence reasoning algorithm;
further, calculating a collision risk r of the target vessel by an evidence reasoning algorithm ΨTSThe method comprises the following steps:
s201, comparing the collision parameters
Figure BDA0003545461210000035
By degree of membership (gamma)1,γ2,…,γt) Showing that when the weight w of the collision parameter is determined, the collision parameter is expressed by the following formula
Figure BDA0003545461210000036
Degree of membership (gamma)1,γ2,…,γt) Converting into a basic probability specific gravity m;
m＝wγ
s202: dividing the basic probability weights m into the determined probability weights
Figure BDA0003545461210000041
And uncertain probability specific gravity
Figure BDA0003545461210000042
Namely that
Figure BDA0003545461210000043
Wherein when
Figure BDA0003545461210000044
The above-mentioned
Figure BDA0003545461210000045
And
Figure BDA0003545461210000046
the calculation formula is as follows:
Figure BDA0003545461210000047
Figure BDA0003545461210000048
Figure BDA0003545461210000049
s203: will be described in
Figure BDA00035454612100000410
And
Figure BDA00035454612100000411
the combined membership is calculated by the following formula:
Figure BDA00035454612100000412
Figure BDA00035454612100000413
Figure BDA00035454612100000414
Figure BDA00035454612100000415
wherein m 'represents the evaluation rule before merging, K' represents the weight value corresponding to the evaluation rule, miRepresenting the ith evaluation rule basic probability proportion,
Figure BDA00035454612100000416
representing the basic probability proportion obtained after the comprehensive evaluation rule,
Figure BDA00035454612100000417
represents the specific gravity of the probability of uncertainty,
Figure BDA00035454612100000418
representing the uncertain probability proportion obtained after the ith evaluation rule is synthesized,
Figure BDA00035454612100000419
the representative is to determine the probability specific gravity,
Figure BDA00035454612100000420
representing the determined probability proportion, m, obtained after the i-th evaluation rule is integratedjRepresenting the proportion of the basic probability obtained after j evaluation rules are fused, wherein i represents the ith evaluation rule, j represents the j evaluation rules, and N represents the total number of the evaluation rules;
s204, carrying out normalization processing on the merged membership degree and the unallocated membership degree to obtain ship collision analysis:
Figure BDA0003545461210000051
Figure BDA0003545461210000052
wherein, δ and δDRepresents(s)1,s2,…,st) Normalized membership and normalized unassigned membership.
Further, the step S204 includes that the Collision Risk Collision Risk of the target shipTSCarrying out quantization processing through the following utility function;
Figure BDA0003545461210000053
wherein u islIs the utility value s assigned to the factor StatelAnd l ∈ t. Collision Risk Collision of the own shipOSCollision Risk Collision for all of the target vesselsTSThe sum of Collision risks of (1), i.e. Collision Riskos＝∑Collision RiskTS。
The invention also aims to provide an application device of the ship collision risk assessment method, which comprises a memory and a processor, wherein the memory stores at least one program, and the at least one program is executed by the processor to realize the ship collision risk assessment method.
It is a further object of the present invention to provide a computer-readable storage medium, in which at least one program is stored, and the at least one program is executed by the processor to implement the method for assessing risk of collision of a ship as described above.
The invention has the beneficial effects that: the method comprises the steps of evaluating collision risks from a plurality of data sources in real time by using a plurality of methods, describing dynamic motion of a ship under the encountering condition through collision parameters, constructing a real-time meeting scene of the ship, converting risk cognition of a captain into a plurality of evaluation rules, evaluating ship navigation risks by matching the corresponding evaluation rules for the meeting scene of the ship, summarizing the real-time collision risks of each collision result by an evidence reasoning method, evaluating each ship collision parameter under different collision conditions, and scientifically and effectively analyzing and intelligently managing ship traffic.
Drawings
The invention is further illustrated by the following figures and examples.
FIG. 1 is a schematic flow chart of a ship collision risk assessment method according to the present invention;
FIG. 2 is a schematic illustration of a ship trajectory in an embodiment of the present invention;
FIG. 3 is a line drawing of a collision parameter of target vessel No. 1 in an embodiment of the present invention;
FIG. 4 is a line drawing of a collision parameter of target vessel No. 2 in an embodiment of the present invention;
FIG. 5 is a line drawing of collision parameters of No. 3 target vessel in an embodiment of the present invention;
FIG. 6 is a pie chart of the types of scenarios encountered by the ship in the embodiment of the present invention;
FIG. 7 is a schematic diagram illustrating a pairing of a ship encounter scenario and an evaluation rule according to an embodiment of the present disclosure;
fig. 8 is a schematic diagram (left diagram) of the safe distance and the action distance in the ship crossing scene and a schematic diagram of the safe distance and the action distance in the general overtaking scene according to the embodiment of the present invention;
FIG. 9 is a diagram illustrating weighting results of collision parameters according to an embodiment of the present invention;
fig. 10 is a schematic view of collision risk distribution in the embodiment of the present invention.
Detailed Description
The following examples are further illustrative and supplementary to the present invention, and the examples are given only for the purpose of explaining the present invention and do not limit the scope of the present invention in any way.
As shown in fig. 1, the present invention provides a method for evaluating a collision risk of a ship, comprising the steps of:
s101, acquiring ship traffic AIS data, and performing noise reduction processing on the ship traffic AIS data, wherein the ship traffic AIS data comprises position variables of a ship, ship speed, ship route, water area where the ship is located, weather conditions, ship visibility, ship real-time traffic factors and ship information;
s102, calculating collision parameters between the ship and the target ship, wherein the collision parameters are used for describing dynamic motion characteristics of the ship and comprise: the calculation formulas of the relative distance between the position variable of the ship and the target ship, the relative azimuth of the ship and the target ship, the shortest time TCPA met by the ship and the target ship and the shortest distance DCPA between the ship and the target ship are as follows:
Figure BDA0003545461210000061
Figure BDA0003545461210000062
wherein OS and TS represent the ship and the target ship, respectively, d represents a relative distance, vOSAnd vTSRespectively representing the speed of the ship and the speed of a target ship, and calculating the relative speed v according to the speed of the ship and the speed of the target shiprAnd alpha and beta represent relative bulwarks;
s103, constructing a ship meeting scene according to the ship traffic AIS data, wherein the ship meeting scene comprises the following steps: a scene in which the target ship yields to the own ship when the target ship passes over the own ship, a scene in which the target ship yields to the own ship when the target ship crosses a ship, a scene in which the target ship and the own ship form a pair and the target ship and the own ship dodge each other, and the like; the ship meeting scene comprises a plurality of scene elements, each ship meeting scene is preset with an evaluation rule corresponding to the scene element one by one, and each scene element also comprises a plurality of factor states;
s104, comparing the scene elements and the factor states with scene labels in the evaluation rules to determine the evaluation rules corresponding to the meeting scenes of the ship, wherein the evaluation rules comprise collision parameter limit values, collision parameter weights and risk avoidance distances;
s105, comparing the collision parameters of the meeting scene of the ship with the collision parameter limit values and the risk avoidance distance, and calculating the collision parameters and the collision parameter weight through an evidence reasoning algorithm to obtain the ship collision risk of the meeting scene.
The method comprises the steps of evaluating collision risks from a plurality of data sources in real time by using a plurality of methods, describing dynamic motion of a ship under an encounter condition through collision parameters, constructing a real-time encounter scene of the ship, converting risk cognition of a captain into a plurality of evaluation rules, evaluating ship navigation risks by matching the ship encounter scene with the corresponding evaluation rules, summarizing the real-time collision risks of each collision result through an evidence reasoning method, evaluating each ship collision parameter under different collision conditions, and scientifically, effectively and intelligently managing ship traffic.
In this embodiment, the collected ship AIS data includes ship traffic AIS data and ship risk data, and the ship AIS data is subjected to noise reduction processing, which mainly provides data support for subsequent collision risk assessment work. Vessel AIS dynamic data is used to characterize risk associated with marine traffic flow and weather information is used to characterize the hydrometeorological environment. In addition, static vessel information (e.g., vessel position variables, vessel course) is also needed to account for risk limits for different types of vessels. The collected AIS data is filtered and inserted according to its temporal-spatial law. Therefore, the AIS data noise cancellation and interpolation process is performed by the fast fourier transform method. The ship traffic AIS data comprise position variables of a ship, ship speed and ship route. The following description is made in detail with reference to an actual sea traffic scene.
The present invention develops a complex navigation network by studying a busy commercial airline connecting northern europe with the mediterranean sea in the sea area outside the continental coast of portugal, in which passing ships share water areas such as fishing boats, passenger ships, and oil tankers with different types of ships going to and leaving ports of the country, from mediterranean sea to north america, from africa to northern europe, and from northern europe to south america. Therefore, it is necessary to assess collisions between vessels in the water not only to support decision-making for avoidance, but also to support local vessel traffic service management. The ship collision risk evaluation method of the invention is used for evaluating the condition of multiple ship encounters in coastal waters of portugal continent. The selected scenario includes a one-time multi-ship encounter observed on day 1 of month 10 of 2015. The acquired real-time weather information of the current day is cloudy, namely the visible range of ships in the sea area is large, wherein traffic conditions in the sea area of the current day relate to four ships: a mooring vessel, a rolling cargo vessel, a common cargo vessel and a tanker. The detailed information of these vessels is shown in table 1.
Figure BDA0003545461210000081
TABLE 1
The method comprises the steps of simulating and constructing a ship meeting scene according to ship AIS data, collecting ship AIS data according to a preset period, wherein the period for collecting the ship AIS data is one hour, namely 16:30 to 17:29 of the day, totally obtaining 240 ship position records of the day, and the extraction rate of recorded ship dynamic information is 1 minute. And judging whether the current ship meeting scene belongs to the following scene or not to filter the AIS data, and reserving and determining three meeting scene conditions, as shown in FIG. 2. 1) When (target ship No. 1) TS1 crosses the OS, according to COLREG, the OS should be relinquished. 2) When (target vessel # 2) TS2 gives way to the vessel in a cross situation. 3) When (target vessel 3) TS3 overtakes the ship and gives way to the latter.
Specifically, in this embodiment, collision parameters between the own ship and the target ship are calculated, the collision parameters are used for describing dynamic motion characteristics of the ship, and the collision parameters include: the calculation formulas of the relative distance between the position variable of the ship and the target ship, the relative azimuth of the ship and the target ship, the shortest time TCPA met by the ship and the target ship and the shortest distance DCPA between the ship and the target ship are as follows:
Figure BDA0003545461210000091
Figure BDA0003545461210000092
where OS and TS denote the ship and the target ship, respectively, d denotes a relative distance, vOSAnd vTSRespectively representing the speed of the ship and the speed of a target ship, and calculating to obtain a relative speed v through the speed of the ship and the speed of the target shiprAnd α and β denote relative port angles. The relative distance d and the relative velocity vrRespectively calculated by the following formula:
Figure BDA0003545461210000093
Figure BDA0003545461210000094
where Lon and Lat respectively represent longitude and latitude coordinates of a position variable of a ship, OS and TS respectively represent a ship and a target ship, and θOSAnd thetaTSRespectively representing the respective heading of the two vessels.
In this embodiment, a ship encounter scene is extracted and constructed according to the ship risk data, where the ship encounter scene includes a plurality of scene elements. In the past, the method establishes the rules based on the international maritime collision avoidance
(COLREG). The meeting scenes are roughly divided into three types, namely, driving meeting, cross meeting and pursuing. One of the limitations of previous research is that they physically study collisions between vessels without taking into account the surrounding environment and vessel conditions. However, the experience and risk limits under certain circumstances to assess the risk of collision, i.e. the criteria for risk assessment during actual sea environment navigation, are not the same as in previous studies. For example, in situations of poor visibility, the risk of collision of a vessel in distress is higher than in situations of good visibility, and the vessel should take evasive action over a greater distance.
In order to improve the accuracy of risk calculation, the invention develops a scene matching engine to collect risk limits under different meeting scenes and corresponding measures to be taken. The scenario engine evaluates collisions through cognitive hierarchical paths and uses rules to define risk criteria under different circumstances. Therefore, the ship encounter scene is divided into a plurality of scene factors (H1, H2.., Hp), wherein p represents the number of scene factors, the scene factors also comprise i factor states, and then the scene factors are represented as
Figure BDA0003545461210000101
And is simplified into
Figure BDA0003545461210000102
Figure BDA0003545461210000103
Which follows a rule reflecting the degree of risk of the crew in the encounter. Each rule contains three important components. 1) Limits on collision parameters (e.g., DCPA, TCPA); 2) distance that the vessel should take action or avoid intrusion; 3) weight of collision parameter. The limit value determines whether a target vessel is at risk of collision with the own vessel and is used to classify the state of the collision parameter. Where the distance between the two vessels determines the result of the collision, if the distance between the two vessels is greater than the low risk distance, there is no risk of collision (i.e., rTS ═ 0), and if the safe distance of the vessel is invaded by TS, the risk of collision between the two vessels is greatest (i.e., rTS ═ 1).
The crash parameter Q needs to be converted into a degree of membership for each state, i.e., (γ)1(s1),γ2(s2),…,γt(st)). State set(s)1,s2,…,st) Is to use the limit (U) given in the scene matching engine1,U2,…,Ut) Defined, the degree of membership is calculated using a linear correlation function. For example, if (t ═ 3) is assumed, "s" is used1＝high risk”、“s2＝medium risk "and" s3DCPA is described in three states (t 3) with a limit of Uhigh risk＝0.5nm,Umedium risk＝2nm，Ulow riskA DPCA value of 4.5 ═ 6nm may be discretized into a set of degrees of membership (0, "high risk", 0.375, "medium risk" and 0.625, "low risk").
Obtaining an evaluation rule corresponding to the ship meeting scene through comparison between the scene element and the scene label in a risk evaluation framework of the ship meeting scene; and calculating the collision parameters and the collision parameter weights in the evaluation rules through an evidence reasoning algorithm to obtain the ship collision risk. Setting the shortest meeting time of the ship and the target ship as TCPA, the shortest distance between the ship and the target ship as DCPA and the weight set of the collision parameters of the relative distance as
Figure BDA0003545461210000104
Wherein the content of the first and second substances,
Figure BDA0003545461210000105
respectively representing the weight of a collision parameter of the shortest time TCPA (thermal shock absorption), the weight of a collision parameter of the shortest distance DCPA (direct current analysis) between the ship and the target ship and the weight of a collision parameter of the relative distance, wherein k represents the kth rule, then the collision risk r of the target ship is determinedTSComprises the following steps:
Figure BDA0003545461210000106
i represents the ith factor state i ∈ N, and psi represents an evidence reasoning algorithm;
calculating the collision risk r of the target vessel by a proof reasoning algorithm ΨTSThe collision parameter
Figure BDA0003545461210000107
By degree of membership (gamma)1,γ2,…,γt) Indicates, when the weight of the parameterAfter re-determination, the collision parameter is determined by the following formula
Figure BDA0003545461210000108
Degree of membership (gamma)1,γ2,…,γt) Is converted into a basic probability specific gravity m,
m＝wγ (5)
w is the collision parameter weight, and the basic probability proportion m is divided into determined probability proportions
Figure BDA0003545461210000111
And uncertain probability specific gravity
Figure BDA0003545461210000112
Namely, it is
Figure BDA0003545461210000113
Wherein the content of the first and second substances,
Figure BDA0003545461210000114
Figure BDA0003545461210000115
the above-mentioned
Figure BDA0003545461210000116
And
Figure BDA0003545461210000117
the calculation formula is as follows:
Figure BDA0003545461210000118
Figure BDA0003545461210000119
Figure BDA00035454612100001110
will be describedThe above-mentioned
Figure BDA00035454612100001111
And
Figure BDA00035454612100001112
the combined membership is calculated by the following formula.
Figure BDA00035454612100001113
Figure BDA00035454612100001114
Figure BDA00035454612100001115
Figure BDA00035454612100001116
Then, after normalization processing is carried out on the merged membership degree and the unallocated membership degree, ship collision analysis is obtained:
Figure BDA00035454612100001117
Figure BDA00035454612100001118
wherein, δ and δDRepresents(s)1,s2,…,st) Normalized combined membership and normalized unassigned membership; the Collision risk Collision RiskTS of the target ship is quantified through the following utility function.
Figure BDA00035454612100001119
Wherein u islIs a utility value s assigned to the factor statelAnd l e t, setting the utility value of the factor state according to the risk preference of the user personnel, wherein the value is usually in the range of 0-9.
Collision Risk Collision of the own shipOSCollision Risk Collision for all of the target vesselsTSThe sum of Collision risks of (1), i.e. Collision Riskos＝∑Collision RiskTS。
The scene factors comprise ship identity, ship tonnage, water areas where ships are located, weather conditions, ship visibility, real-time ship traffic factors and ship avoidance responsibility, each scene factor further comprises a plurality of factor states, and the factor states correspond to the scene labels one to one.
In conjunction with the previous description of specific application examples of marine domains outside the continental coast of portugal teeth, the calculated relative orientations, relative distances, DCPA, TCPA, and the obtained velocities and flight lines of the collision parameters TS1, TS2, and TS3 between OS and TS are shown in fig. 3, 4, and 5, respectively.
Where fig. 3 shows the variation of parameters between the OS and TS1 of the ship. Initially, TS1 relative orientation is 259.6 degrees, relative distance is 3.73 nautical miles (nm). At this time, DCPA and TCPA between the two ships was 3.65 nautical miles and 1368 seconds. Since TS1 takes several deceleration and acceleration processes, its speed drops to 9.2 knots at 16:57 and then rises to the highest speed of 17.4 knots, and maintains this speed. 16:50, TS1 passed the OS port at a relative distance of 0.229 nautical miles with a TCPA of 0 seconds.
FIG. 4 shows the parameter changes for TS2 and OS under a pass-through condition. At the beginning, the relative distance between the two vessels was 4.77 nautical miles. As the speed of the two vessels increases, the relative distance between the two vessels is first maintained at about 4 nautical miles. At 17:03, the relative distance drops to 0.27 nautical miles, at which time TS2 passes through the OS from its port.
FIG. 5 shows the change in the race between OS and TS 3. The relative distance between the two vessels and DCPA is small at the beginning. In addition, the speed of both ships is very low (i.e., 6.4 knots for TS3 and 6.7 knots for OS). TS3 increased the speed beyond OS at 16:40 and over OS at 17:03, with a smaller distance between the two vessels, 0.11 nm.
The scene factors comprise ship identity, ship tonnage, water area where the ship is located, weather conditions, ship visibility, ship real-time traffic factors and ship avoidance responsibility, each scene factor further comprises a plurality of factor states, and the factor states correspond to the scene labels one to one. The relevant factor status of each scene factor and its description are shown in table 2.
Figure BDA0003545461210000121
Figure BDA0003545461210000131
TABLE 2
The following describes H7 (avoidance responsibility), H2 (tonnage) and the status of the factors associated therewith for each scenario factor:
definition of responsibility for vessel collisions: the encountered ship is divided into three states according to the responsibility of the avoidance maneuver. According to COLREGs, clause 27, all vessels sailing should give way to vessels that are not commanded or have limited maneuverability, and these vessels are classified as the first state. The second state is that according to the regulations of col regs item 18, the ship engaged in the fishing activities should take different collision avoidance measures to give way to the ship engaged in the fishing. As shown in fig. 6, in COLREG, the responsibility of the ship to avoid is clear according to the relative orientation of two meeting ships. FIG. 6 shows the three encounter scenarios listed in COLREG (i.e., encounter, intersection, and pursuit of the drives). When two ships meet on a peer or near peer course (relative orientation between 352.5 ° and 7.5 °), the two ships should reroute starboard, ensuring that each other (i.e., OS and TS1) is passed on port. If the OS has other vessels on its starboard side and the relative orientation is between 7.5 ° and 112.5 °, the OS is defined as a let-way vessel and should remain unobstructed by incoming and outgoing vessels (i.e., TS 2). Conversely, if the OS has another vessel (i.e., TS4) on its port with a relative bearing between 247.5 and 352.5, then the OS is defined as a vessel that is maintaining its course and speed. If the OS is overtaken by a vessel driving from an orientation between 112.5 and 247.5, both vessels are in overtaken condition, the OS should maintain its heading, and TS3 should be at a distance from the OS. It should be noted, however, that if the party is a vessel with limited maneuverability or an unoperated vessel, the operating system must give way to the party according to the COLREGs. On the basis, three states of head-on, crossing and pursuing are used for describing the meeting condition, and two states of a way-giving ship and a course-keeping ship are used for describing the avoidance responsibility.
As to tonnage considerations, the present study defines two states, namely small ships with tonnage less than 500GT and others, since the handling capacity of the ship is affected by the tonnage. In the event of an encounter, a large boat requires more space than a small boat to ensure safe passage. Ships with different tonnages can select different distances to avoid in actual operation. Meanwhile, port water areas, restricted water areas (such as navigation channels and shallow water areas) and open water areas are three states of water area factors in the model. Each water zone requires specific criteria to assess the risk of collision. In addition, factors related to the environment include weather conditions and visibility. Handling difficulties in bad weather (e.g. storms, strong winds) are much higher than in normal weather conditions, whereas low visibility is associated with high risk.
In COLREG, the responsibility of avoiding a ship is defined according to the relative orientation of two meeting ships. FIG. 6 shows the three encounter scenarios listed in COLREG (i.e., encounter, intersection, and pursuit of the drives). When two ships meet on a peer or near peer course (relative orientation between 352.5 ° and 7.5 °), the two ships should reroute starboard, ensuring that each other (i.e., OS and TS1) is passed on port. If the OS has other vessels on its starboard side and the relative orientation is between 7.5 ° and 112.5 °, the OS is defined as a let-way vessel and should remain unobstructed by incoming and outgoing vessels (i.e., TS 2). Conversely, if the OS has another vessel (i.e., TS4) on its port with a relative bearing between 247.5 and 352.5, then the OS is defined as a vessel that is maintaining its course and speed. If the OS is overtaken by a vessel driving from an orientation between 112.5 and 247.5, both vessels are in overtaken condition, the OS should maintain its heading, and TS3 should be at a distance from the OS. It should be noted, however, that if the party is a vessel with limited maneuverability or an unoperated vessel, the operating system must give way to the party according to the COLREGs. On the basis, three states of head-on, crossing and pursuing are used for describing the meeting condition, and two states of a way-giving ship and a course-keeping ship are used for describing the avoidance responsibility.
And establishing an evaluation rule according to the collision parameter limit value, the collision parameter weight and the ship risk avoidance distance, and presetting scene labels corresponding to the evaluation rule one by one. As shown in fig. 7, since the factor states correspond to the scene tags one to one, the evaluation rule for evaluating the navigation risk in the meeting scene can be matched by comparing the factor state in the scene factors of the meeting scene with the scene tags in the evaluation rule, for example, the first rule represents an meeting scene
Figure BDA0003545461210000141
Last rule
Figure BDA0003545461210000142
Also represents a meeting scenario, the first rule shown in FIG. 7 represents a meeting scenario
Figure BDA0003545461210000143
The first and second cases are expressed as
Figure BDA0003545461210000144
And rule 352 is activated. The third case is expressed as
Figure BDA0003545461210000145
And activates the rule 330. In theory, these rules cover the total possible occurrence of 3 × 2 × 3 × 2 ═ 432. According to the requirements of COLREGs, the operating system should yield vessels that have limited maneuverability or are not under command at any time, so if one is not available
Figure BDA0003545461210000146
Then
Figure BDA0003545461210000147
(see Table 2). Thus, the total number of rules in the engine is 432-72-360, which needs to be developed in the scene matching engine to simulate all possible scenarios.
Although only two rules are used in the research in the present embodiment, it is within the scope of the present invention to establish an evaluation rule through all the collision parameter limit values, the collision parameter weights, and the ship risk avoiding distances, and to evaluate the ship voyage according to the evaluation rule, where the process of establishing rules 330 and 352 is described below.
1) Distance of travel and safe passing distance. In the 352 nd rule, the distance of action between two ordinary ships (i.e., the distance of travel
Figure BDA0003545461210000151
) The distance of action that the vessel should take in good weather conditions is defined by an empirical equation. The equation is given as follows:
Figure BDA0003545461210000152
meanwhile, safe approach distances for different orientations are defined by the following formula used by Hu et al (2020):
Figure BDA0003545461210000153
therefore, equation 16 is used to calculate the travel distance of the 8 sectors of TS relative to the azimuth. The boundaries of the distance of action are shown as blue lines in fig. 8. The safe passing distance of 8 sectors of relative orientation is also shown as red line in fig. 8. Thus, ships outside the travelling distance have a lower risk of collision, ships between the travelling distance and the safe passage distance have a medium risk, and ships within the safe passage distance have a high risk of collision. In rule 330, the distance of action and the safe passing distance are defined by the captain of the vessel having experience in sailing. To collect this information, a survey was conducted using a marine simulator. During the simulation, five invited captain's are asked to avoid surrounding vessels and the distance they decide to take collision avoidance action is recorded (see fig. 8 b).
Wherein the DCPA and TCPA limits for the crash parameters in the evaluation rules are calculated to indicate that the distances from high to low of 135 °, 180 °, 90 °, 45 ° and 0 ° are 3.01 nautical miles, 2.46 nautical miles, 1.71 nautical miles, 1.14 nautical miles and 1.0 nautical miles, respectively. A risk model is established based on a linear regression method. It was found that the DCPA limits for different relative orientations were 1.39 (relative orientation 0 °), 1.37 (relative orientation 45 °), 1.16 (relative orientation 90 °), 0.82 (relative orientation 135 °), and 0.48 (relative orientation 180 °). Thus, the study defines the high risk limits for DCPA as 1.39 (relative orientation 0 °), 1.37 (relative orientation 45 °), 1.16 (relative orientation 90 °), 0.82 (relative orientation 135 °), and 0.48 nautical miles (relative orientation 180 °). The safety limit is 2 nautical miles, as required by COLREGs. The TCPA limits used in both rules are 300 seconds (high risk), 600 seconds (medium) and 1200 seconds (low risk).
The domain of the vessel is related to factors such as the size of the vessel, operability and hydrologic conditions. The present study employed the empirical ship domain proposed by Hansen et al (2013) to define the critical distance for the highest collision risk for all ship domain intrusions. The domain is an ellipse with a length of about 8 ship lengths (4.5 ship lengths in front of the center of the ellipse and 3.5 ship lengths behind). The width of the ellipse is 0.7 times the length of the boat on both sides. As shown in table 1, the length of the OS is 74 meters, the domain size of the OS is 0.18 nautical miles at the bow, 0.14 nautical miles at the stern, and 0.03 nautical miles at the beam.
In the present invention, regarding the configuration of the collision parameter weight, the weight distribution in 330 th and 352 nd evaluation rules is obtained from the judgment of experts by an Analysis Hierarchical Process (AHP) decision method. This method provides a way to quantify the weights and estimate the relative magnitudes of the factors by pairwise comparisons. To ensure the reliability of the judgment result, the method defines a Consistency Ratio (CR) to verify the consistency of the judgment, wherein if CR >0.1, the paired judgment is not authentic. The obtained determination is used in the AHP to calculate the weight of the collision parameter. The results are shown in Table 3.
Figure BDA0003545461210000161
TABLE 3
And finally summarizing the collision parameters in the evaluation rule and calculating the collision parameter weight through an evidence reasoning algorithm to obtain the ship collision risk. The calculation is performed once per minute, dynamically updating the collision risk. Evidence reasoning algorithms are used in the aggregation process. The aggregation process applies an evidence-based reasoning calculation program (IDS) to reduce workload (Yang and Wang, 2015), an example of computing collision risk is described below.
In the first step, all collision parameters are converted into membership. For example, at 16:49, TS1 is on the port side of the OS, with a relative orientation of 217.9 and a relative distance of 0.189 nm. According to the rule 352, using equations 16 and 17, the distance of action and safe passing distance of TS1 are calculated to be 1.354nm and 0.858 nm, respectively. Relative distance (1-0.189/0.858 ═ 0.79 converted to a high risk, 0.189/0.858 ═ 0.21, medium risk, 0, low risk). Also, the results of the calculation for TCPA are: high risk ═ 1, medium risk ═ 0, low risk ═ 0; the calculation for DCPA was: high risk 0.78, medium risk 0.22, low risk 0.
Second, the weight assignment of the collision parameters is obtained from the rules 352. As shown in table 3, the weight assignment is set as shown in fig. 9.
And thirdly, performing the step of. The degree of membership and the weight assignment for each parameter are input to the evidence reasoning algorithm and the results are shown in fig. 10.
The fourth step sets the utility value of the collision risk state to uhigh＝1,umedium＝0.5and u low0. TS1 at 16: the collision risk at 49 is calculated from formula 15 as 0.8768 × 1+0.1232 × 0.5+0 × 0 — 0.9384.
And other target vessels are evaluated by the method described above.
The invention also provides an application device of the ship collision risk assessment method, which comprises a memory and a processor, wherein the memory stores at least one section of program, and the at least one section of program is executed by the processor to realize the ship collision risk assessment method. As an executable scheme, the application device of the ship collision risk assessment method may be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The system/electronic device may include, but is not limited to, a processor, a memory. It will be understood by those skilled in the art that the above-described constituent structures of the system/electronic device are only examples of the system/electronic device, and do not constitute a limitation on the system/electronic device, and may include more or less components than those described above, or some components in combination, or different components. For example, the system/electronic device may further include an input/output device, a network access device, a bus, and the like, which is not limited in this embodiment of the present invention.
Further, as an executable solution, the processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, and the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, the processor being the control center for the system/electronic device, various interfaces and lines connecting the various parts of the overall system/electronic device.
The memory may be used to store computer programs and/or modules that the processor implements by running or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory, various functions of the system/electronic device. The memory can mainly comprise a program storage area and a data storage area, wherein the program storage area can store an operating system and an application program required by at least one function; the storage data area may store data created according to the use of the mobile phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid state storage device.
The present invention also provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above-mentioned method according to the embodiment of the present invention. The system/electronic device integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium and used by a processor to implement the steps of the above-described embodiments of the method. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer memory, Read-only memory (ROM), Random Access Memory (RAM), software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is appropriately increased or decreased as required by legislation and patent practice in the jurisdiction.
The reader should understand that in the description of this specification, reference to the description of the terms "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described method embodiments are merely illustrative, and for example, the division of steps into only one logical functional division may be implemented in practice in another way, for example, multiple steps may be combined or integrated into another step, or some features may be omitted, or not implemented.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. A ship collision risk assessment method is characterized by comprising the following steps:
s101, acquiring ship traffic AIS data, and performing noise reduction processing on the ship traffic AIS data, wherein the ship traffic AIS data comprises position variables of a ship, ship speed, ship route, water area where the ship is located, weather conditions, ship visibility, ship real-time traffic factors and ship information;
s102, calculating a collision parameter between the ship and a target ship, and quantizing the weight of the collision parameter by an AHP decision method, wherein the collision parameter is used for describing the dynamic motion characteristics of the ship, and comprises the following steps: the calculation formulas of the relative distance between the position variable of the ship and the target ship, the relative azimuth of the ship and the target ship, the shortest time TCPA met by the ship and the target ship and the shortest distance DCPA between the ship and the target ship are as follows:
Figure FDA0003545461200000011
Figure FDA0003545461200000012
where OS and TS denote the ship and the target ship, respectively, d denotes a relative distance, vOSAnd vTSRespectively representing the speed of the ship and the speed of a target ship, and calculating the relative speed v according to the speed of the ship and the speed of the target shiprAnd alpha and beta represent relative bulwarks;
s103, constructing a ship meeting scene according to the ship traffic AIS data, wherein the ship meeting scene comprises: when the target ship passes over the ship, the target ship yields to the ship, when the target ship yields to the ship under the condition of ship crossing, and when the target ship and the ship form a pair driving, and when the target ship and the ship mutually avoid; the ship meeting scene comprises a plurality of scene elements, each ship meeting scene is preset with an evaluation rule corresponding to the scene element one by one, and each scene element also comprises a plurality of factor states;
s104, comparing the scene elements and the factor states with scene labels in the evaluation rules to determine the evaluation rules corresponding to the meeting scenes of the ship, wherein the evaluation rules comprise collision parameter limit values, collision parameter weights and risk avoidance distances;
s105, comparing the collision parameters of the meeting scene of the ship with the collision parameter limit values and the risk avoidance distance, and calculating the collision parameters and the collision parameter weight through an evidence reasoning algorithm to obtain the ship collision risk of the meeting scene.
2. The method according to claim 1, wherein the relative distance d and the relative velocity v arerRespectively calculated by the following formulas:
Figure FDA0003545461200000021
Figure FDA0003545461200000022
where Lon and Lat represent longitude and latitude coordinates of position variables of the ship, OS and TS represent the ship and the target ship, respectively, and θ representsOSAnd thetaTSRespectively representing the respective heading of the two vessels.
3. The method according to claim 2, wherein the ship encounter scene comprises a plurality of scene elements, and the scene elements comprise ship identity, ship tonnage, water area where the ship is located, weather conditions, ship visibility, ship real-time traffic factors and ship avoidance behavior.
4. The method for assessing the risk of ship collision according to claim 3, wherein the collected ship traffic AIS data is screened to remove the ship traffic AIS data which do not belong to the ship encounter scenario as described in S103.
5. The ship collision risk assessment method according to claim 4, characterized in that: each scene factor also comprises a plurality of factor states, wherein the ship identity factors comprise a ship state which limits the handling capacity or is not handled, a ship state which is engaged in catching and a ship which does not belong to the two ship states; the tonnage factors of the ship comprise a ship state with the tonnage smaller than 500GT and a ship state with the tonnage larger than or equal to 500 GT; the factors of the water area of the ship comprise a port water area state, a limited water area state and an open water area state; the weather condition factors include general weather conditions and severe weather conditions; the ship visibility factors comprise a good state with visibility more than or equal to 2 seas and a poor state with visibility less than 2 seas; the real-time traffic factors of the ship comprise ship cross meeting, opposite driving meeting and overtaking; the ship avoidance responsibility factors comprise a way-giving state and a course-keeping state.
6. The ship collision risk assessment method according to claim 5, characterized in that: the S105 includes: setting the shortest meeting time of the ship and the target ship as TCPA, the shortest distance between the ship and the target ship as DCPA and the weight set of the collision parameters of the relative distance as
Figure FDA0003545461200000023
Wherein the content of the first and second substances,
Figure FDA0003545461200000024
respectively representing the weight of a collision parameter of the shortest time TCPA met by the ship and the target ship, the weight of a collision parameter of the shortest distance DCPA between the ship and the target ship and the weight of a collision parameter of the relative distance, wherein k represents the kth rule, and then the collision risk r of the target ship is determinedTSComprises the following steps:
Figure FDA0003545461200000031
where i represents the ith factor state, i ∈ N, and Ψ represents the evidence reasoning algorithm.
7. The method for assessing the risk of collision of a ship as set forth in claim 6, wherein the method comprisesIs characterized in that: calculating the collision risk r of the target vessel by a proof reasoning algorithm ΨTSThe method comprises the following steps:
s201, comparing the collision parameters
Figure FDA0003545461200000032
By degree of membership (gamma)1,γ2,…,γt) Showing that when the weight w of the collision parameter is determined, the collision parameter is determined by the following formula
Figure FDA0003545461200000033
Degree of membership (gamma)1,γ2,…,γt) Conversion to basic probability specific gravity m:
m＝wγ
s202, dividing the basic probability proportion m into determined probability proportions
Figure FDA0003545461200000034
And uncertain probability specific gravity
Figure FDA0003545461200000035
Namely that
Figure FDA0003545461200000036
Wherein the content of the first and second substances,
Figure FDA0003545461200000037
the above-mentioned
Figure FDA0003545461200000038
And
Figure FDA0003545461200000039
the calculation formula is as follows:
Figure FDA00035454612000000310
Figure FDA00035454612000000311
Figure FDA00035454612000000312
s203, subjecting the
Figure FDA00035454612000000313
And
Figure FDA00035454612000000314
the combined membership is calculated by the following formula:
Figure FDA00035454612000000315
Figure FDA00035454612000000316
Figure FDA00035454612000000317
Figure FDA00035454612000000318
wherein m 'represents the evaluation rule before merging, K' represents the weight value corresponding to the evaluation rule, miRepresenting the ith evaluation rule basic probability proportion,
Figure FDA00035454612000000319
representing the basic probability proportion obtained after comprehensively evaluating the rules,
Figure FDA00035454612000000320
representing the probability proportion of uncertainty existing in the evaluation result after fusion,
Figure FDA0003545461200000041
representing the probability of uncertainty obtained after the ith evaluation rule is synthesized,
Figure FDA0003545461200000042
representing the determined probability weightings subject to fusion and taking into account the evidence weights,
Figure FDA0003545461200000043
representing the determined probability proportion, m, obtained after the i-th evaluation rule is integratedjRepresenting the proportion of the basic probability obtained after j evaluation rules are fused, wherein i represents the ith evaluation rule, j represents the j evaluation rules, and N represents the total number of the evaluation rules;
s204, carrying out normalization processing on the merged membership degree and the unallocated membership degree to obtain ship collision analysis:
Figure FDA0003545461200000044
Figure FDA0003545461200000045
wherein, δ and δDRepresents(s)1,s2,…,st) Normalized membership and normalized unassigned membership.
8. The ship collision risk assessment method according to claim 7, characterized in that: the S204 also comprises that the Collision Risk Collision Risk of the target shipTSCarrying out quantization processing through the following utility function;
Figure FDA0003545461200000046
wherein u islIs a utility value s assigned to the factor statelAnd l ∈ t. Collision Risk Collision of the own shipOSCollision Risk Collision for all of the target vesselsTSThe sum of Collision risks of (1), i.e. Collision Riskos＝∑Collision RiskTS。
9. An application device of a ship collision risk assessment method, characterized by comprising a memory and a processor, wherein the memory stores at least one program, and the at least one program is executed by the processor to realize the ship collision risk assessment method according to any one of claims 1 to 8.
10. A computer-readable storage medium, wherein at least one program is stored in the storage medium, and the at least one program is executed by the processor to implement the ship collision risk assessment method according to any one of claims 1 to 8.
CN202210247597.4A 2022-03-14 2022-03-14 Ship collision risk assessment method and device and storage medium Pending CN114595776A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210247597.4A CN114595776A (en) 2022-03-14 2022-03-14 Ship collision risk assessment method and device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210247597.4A CN114595776A (en) 2022-03-14 2022-03-14 Ship collision risk assessment method and device and storage medium

Publications (1)

Publication Number Publication Date
CN114595776A true CN114595776A (en) 2022-06-07

Family

ID=81808763

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210247597.4A Pending CN114595776A (en) 2022-03-14 2022-03-14 Ship collision risk assessment method and device and storage medium

Country Status (1)

Country Link
CN (1) CN114595776A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115273557A (en) * 2022-07-01 2022-11-01 中远海运科技股份有限公司 AIS-based underway ship collision risk detection and early warning method and system
CN116029554A (en) * 2023-02-28 2023-04-28 武汉理工大学 Risk assessment method based on parameter correction of limited water area ship risk assessment model

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115273557A (en) * 2022-07-01 2022-11-01 中远海运科技股份有限公司 AIS-based underway ship collision risk detection and early warning method and system
CN116029554A (en) * 2023-02-28 2023-04-28 武汉理工大学 Risk assessment method based on parameter correction of limited water area ship risk assessment model
CN116029554B (en) * 2023-02-28 2023-12-15 武汉理工大学 Risk assessment method based on parameter correction of limited water area ship risk assessment model

Similar Documents

Publication Publication Date Title
Mallam et al. The human element in future Maritime Operations–perceived impact of autonomous shipping
Murray et al. An AIS-based deep learning framework for regional ship behavior prediction
Adland et al. The value of meteorological data in marine risk assessment
Silveira et al. A multicriteria outranking approach for ship collision risk assessment
CN114595776A (en) Ship collision risk assessment method and device and storage medium
Sahin et al. A novel process model for marine accident analysis by using generic fuzzy-AHP algorithm
Endrina et al. Risk analysis for RoPax vessels: A case of study for the Strait of Gibraltar
Yang et al. AIS-based intelligent vessel trajectory prediction using bi-LSTM
Hu et al. Collision risk assessment based on the vulnerability of marine accidents using fuzzy logic
Teixeira et al. Risk of maritime traffic in coastal waters
Fiskin et al. Decision tree and logistic regression analysis to explore factors contributing to harbour tugboat accidents
Dua Hijacked: Piracy and economies of protection in the Western Indian Ocean
Gende et al. Active whale avoidance by large ships: components and constraints of a complementary approach to reducing ship strike risk
van Westrenen et al. Improving conflicts detection in maritime traffic: Case studies on the effect of traffic complexity on ship collisions
Zhao et al. High-fidelity data supported ship trajectory prediction via an ensemble machine learning framework
Pietrzykowski et al. The autonomous navigation system of a sea-going vessel
Yu et al. Framework and application of multi-criteria ship collision risk assessment
Wu et al. The influence of weather conditions on the relative incident rate of fishing vessels
Liu et al. Application of cloud model and bayesian network to piracy risk assessment
Lee et al. Seafarers’ awareness-based domain modelling in restricted areas
Lee et al. Risk-informed collision avoidance system design for maritime autonomous surface ships
Adhita et al. Ship navigation from a Safety-II perspective: A case study of training-ship operation in coastal area
Zhu et al. Spatial-temporal analysis method of ship traffic accidents involving data field: An evidence from risk evolution of ship collision
Madsen et al. Safe and efficient maneuvering of a Maritime Autonomous Surface Ship (MASS) during encounters at sea: A novel approach
Zhang et al. Constructing a decision-support system for safe ship-navigation using a Bayesian network

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination