CN114464014A - Fuzzy logic based regional ship collision risk processing method, system and medium - Google Patents
Fuzzy logic based regional ship collision risk processing method, system and medium Download PDFInfo
- Publication number
- CN114464014A CN114464014A CN202210007235.8A CN202210007235A CN114464014A CN 114464014 A CN114464014 A CN 114464014A CN 202210007235 A CN202210007235 A CN 202210007235A CN 114464014 A CN114464014 A CN 114464014A
- Authority
- CN
- China
- Prior art keywords
- ship
- risk
- collision
- collision risk
- fuzzy logic
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G3/00—Traffic control systems for marine craft
- G08G3/02—Anti-collision systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/048—Fuzzy inferencing
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Radar, Positioning & Navigation (AREA)
- Fuzzy Systems (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Computational Linguistics (AREA)
- Ocean & Marine Engineering (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a fuzzy logic-based regional ship collision risk processing method, a fuzzy logic-based regional ship collision risk processing system and a fuzzy logic-based regional ship collision risk processing medium, which can be applied to the technical field of ships. According to the invention, after the ship risk area is determined, the ship motion state parameters and the natural environment parameters in the ship risk area are obtained, then the ship motion state parameters and the natural environment parameters are input into the fuzzy logic reasoning model to obtain more accurate collision risks between the ships, then the collision risk of each ship in the ship risk area is determined according to the collision risk between the ships, and then a ship collision risk thermodynamic diagram is generated according to the collision risk of each ship, so that a crew or a manager can more accurately master the ship risk state, thereby improving the safety of the ship driving process.
Description
Technical Field
The invention relates to the technical field of ships, in particular to a regional ship collision risk processing method, a regional ship collision risk processing system and a regional ship collision risk processing medium based on fuzzy logic.
Background
Along with large sea traffic volume, ship collision accidents are one of the most common marine accidents in the world, and serious loss of lives and properties and marine environmental pollution are caused. In the related art, the identification method for the ship collision risk mainly has the following aspects: the method comprises the steps that firstly, ship collision risk identification based on historical accident data is carried out, the data quality required by the method is high, and the accuracy of research results can be supported only by enough collision accident data; secondly, based on ship field risk identification, the method mainly considers the ship collision risk from the perspective of a single ship, a model in the ship field is closely related to the dynamic and static characteristics of the ship, dynamic and static information of all monitored ships cannot be acquired in some scenes, and an accurate ship field model cannot be established, so that the method cannot be well applied to research on the regional collision risk among multiple ships in ports and coastal waters; and thirdly, the method based on collision prevention parameters does not consider the influence of the natural environment on the collision risk of the ship and the collision consequence of the ship at the same time, and part of research only researches the collision risk of a single ship and considers no multi-ship risk, so that the method cannot be applied to ship collision prevention under the mutual interference influence of multiple ships.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a regional ship collision risk processing method, system and medium based on fuzzy logic, which can effectively improve the accuracy of a ship risk prediction result in a multi-ship driving state.
On one hand, the embodiment of the invention provides a regional ship collision risk processing method based on fuzzy logic, which comprises the following steps:
determining a ship risk area;
acquiring ship motion state parameters and natural environment parameters in the ship risk area, wherein the ship motion state parameters comprise a nearest meeting distance, a nearest meeting time and a collision position;
inputting the ship motion state parameters and the natural environment parameters into a fuzzy logic reasoning model to obtain collision risks among ships;
determining a collision risk for each vessel within the vessel risk area according to the collision risk between the vessels;
and generating a ship collision risk thermodynamic diagram according to the collision risk of each ship.
In some embodiments, the obtaining of the ship motion state parameter in the ship risk area comprises:
and determining ship motion state parameters according to AIS data in the ship risk area, wherein the nearest meeting distance comprises an ink card support distance, and the collision position is determined through a meeting included angle.
In some embodiments, the natural environment parameters include sea state, wind speed, and visibility;
the wind speed comprises five fuzzified language values representing wind speed grades, the wind speed grades at two ends adopt rectangular membership functions, and the wind speed grades in the middle three adopt triangular membership functions;
the sea condition comprises five fuzzified language values representing risk levels, the risk levels at two ends adopt trapezoidal membership functions, and the three wind speed levels in the middle adopt triangular membership functions;
the visibility includes a sea fog state.
In some embodiments, the inputting the ship motion state parameters and the natural environment parameters into a fuzzy logic reasoning model to obtain the collision risk between ships includes:
and inputting the ship motion state parameters and the natural environment parameters into a fuzzy logic reasoning model, and determining the collision risk between the ships according to a fuzzy rule in the fuzzy logic reasoning model.
In some embodiments, the determining a risk of collision for each vessel within the vessel risk area from the risk of collision between the vessels comprises:
constructing a ship collision risk judgment matrix;
and determining the collision risk of each ship in the ship risk area according to the ship collision risk judgment matrix.
In some embodiments, the determining the collision risk of each ship in the ship risk area according to the ship collision risk judgment matrix includes:
normalizing the ship collision risk judgment matrix according to columns;
adding the normalized ship collision risk judgment matrixes in rows to obtain a sum vector;
normalizing the sum vector to obtain a weight vector;
calculating collision risk vectors of a target ship and other ships in the ship risk area, wherein the target ship is any one ship in the ship risk area, and the rest ships in the ship risk area are used as other ships;
and determining the total collision risk of the target ship according to the weight vector and the collision risk vector.
In some embodiments, the determining a ship risk area comprises:
and determining a ship risk area according to a density clustering algorithm.
On the other hand, the embodiment of the invention provides a regional ship collision risk processing system based on fuzzy logic, which comprises:
the first determining module is used for determining a ship risk area;
the acquisition module is used for acquiring ship motion state parameters and natural environment parameters in the ship risk area, wherein the ship motion state parameters comprise a nearest meeting distance, a nearest meeting time and a collision position;
the reasoning module is used for inputting the ship motion state parameters and the natural environment parameters into a fuzzy logic reasoning model to obtain collision risks among ships;
a second determining module, configured to determine a collision risk of each ship in the ship risk area according to collision risks among the ships;
and the generating module is used for generating a ship collision risk thermodynamic diagram according to the collision risk of each ship.
On the other hand, the embodiment of the invention provides a regional ship collision risk processing system based on fuzzy logic, which comprises:
at least one memory for storing a program;
at least one processor for loading the program to execute the fuzzy logic-based regional ship collision risk processing method.
In another aspect, an embodiment of the present invention provides a storage medium, in which a computer-executable program is stored, and the computer-executable program is executed by a processor to implement the fuzzy logic-based regional ship collision risk processing method.
The method for processing the regional ship collision risk based on the fuzzy logic has the following beneficial effects that:
according to the method and the device, after the ship risk area is determined, the ship motion state parameters and the natural environment parameters in the ship risk area are obtained, then the ship motion state parameters and the natural environment parameters are input into the fuzzy logic reasoning model to obtain more accurate collision risks between the ships, then the collision risk of each ship in the ship risk area is determined according to the collision risks between the ships, and then a ship collision risk thermodynamic diagram is generated according to the collision risk of each ship, so that a crew or a manager can more accurately master the ship risk state, and the safety of the ship running process is improved.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The invention is further described with reference to the following figures and examples, in which:
FIG. 1 is a schematic diagram illustrating mapping of fuzzy Inputs in a fuzzy inference model according to an embodiment of the present invention;
FIG. 2 is a diagram of an Apply Fuzzy operator in a Fuzzy inference model according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating an application method in a fuzzy inference model according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating an application method in a fuzzy inference model according to an embodiment of the present invention;
FIG. 5 is a flowchart of a method for processing a regional ship collision risk based on fuzzy logic according to an embodiment of the present invention;
FIG. 6 is a schematic view of a risk area of a ship according to an embodiment of the present invention;
FIG. 7 is a schematic view of another risk area of a vessel according to an embodiment of the present invention;
FIG. 8 is a graph of membership functions of DCPA in accordance with an embodiment of the present invention;
FIG. 9 is a graph of membership functions for a TCPA in accordance with an embodiment of the present invention;
FIG. 10 is a schematic view of the relative positions of two vessels according to an embodiment of the present invention;
FIG. 11 is a diagram of a typical marine encounter situation in accordance with an embodiment of the present invention;
FIG. 12 is a graph of a membership function for collision location according to an embodiment of the present invention;
FIG. 13 is a schematic structural diagram of a multi-layer fuzzy inference model according to an embodiment of the present invention;
FIG. 14 is a graph of fuzzy inference based on vessel motion state parameters according to an embodiment of the present invention;
FIG. 15 is a graph of another fuzzy inference based on vessel motion state parameters according to an embodiment of the present invention;
FIG. 16 is a graph of fuzzy inference based on natural environment parameters, in accordance with an embodiment of the present invention;
FIG. 17 is a graph of another fuzzy inference based on natural environment parameters according to an embodiment of the present invention;
FIG. 18 is a graph of another fuzzy inference based on collision risk according to an embodiment of the present invention;
FIG. 19 is a data processing diagram of a fuzzy inference model according to an embodiment of the present invention;
FIG. 20 is a schematic illustration of a vessel in accordance with an embodiment of the invention;
fig. 21 is a ship risk thermodynamic diagram according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality is one or more, the meaning of a plurality is two or more, and the above, below, exceeding, etc. are understood as excluding the present numbers, and the above, below, within, etc. are understood as including the present numbers. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, reference to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "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 present invention. In this specification, the schematic representations of the terms used above do not necessarily 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.
In order to reduce the collision accident of the ship, many researchers carry out a great deal of research on the collision risk of the ship from various angles, and obtain better research results, and according to the research content and the adopted method, the existing research can be divided into three categories:
first-class historical accident data-based ship collision risk identification: the ship collision risk research based on historical accident data mainly uses the historical marine accident data and the collision factors of ships to analyze and obtain the probability of occurrence of risks. And obtaining the probability of ship collision by counting historical accident data. In some embodiments, two months of data are used, ship encounter, wind speed and visibility are selected as control variables, and a Probit model is used to fit a ship collision risk state equation. In some embodiments, using collision accident data of nearly ten years, an ordered probit model of the collision severity of two ships is established, and it is concluded that lookout errors play a decisive role in increasing collision risk. In some embodiments, the vessel risk is calculated quantitatively using the probit regression model calculation using the three month AIS data. In some embodiments, using statistical analysis of marine accident data and AIS data, conditions associated with vessel risk are identified and a multivariate Logistic regression model is used to predict which factors the vessel risk is associated with. In some embodiments, a Bayesian network is used with a large amount of historical data to assess risk of collision of a vessel with an SOI in different voyage environments. This type of study requires high quality data and sufficient crash event data to support the accuracy of the study results. Meanwhile, the ship collision risk research method cannot monitor the ship collision risk in real time, and only can evaluate the ship collision risk of the marine area with historical data.
Second, ship domain based risk identification: the method based on the ship field is mainly characterized in that a circle of regular or irregular warning lines are arranged on the periphery of a ship as a center and used for identifying whether the ship threatens the ship. In some embodiments, it is still possible to cause a ship collision to occur if only the ship domain is used as a warning limit, and the Arena concept is proposed as a risk warning range. In some embodiments, the ship collision candidate model is detected by using a fuzzy quaternary ship field theory, and screening is performed by judging whether a ship enters a ship warning area and has a convergence trend. In some embodiments, a model of a cooperative ship domain is provided, and a collision risk model under the condition that two ships meet is constructed to identify the ship collision risk in real time. In some embodiments, a fuzzy quaternary ship domain of ship bridge collisions is established to describe the risk conditions near the bridge region. In some embodiments, how risk assessment and identification is performed in the field of ships is described. The research method mainly considers the ship collision risk from the perspective of a single ship, the model in the ship field is closely related to the dynamic and static characteristics of the ship, the dynamic and static information of all monitored ships cannot be acquired in some scenes, and the accurate ship field model cannot be established, so that the method cannot be well suitable for the regional collision risk research among multiple ships in ports and coastal water areas.
A third category of collision avoidance parameter-based methods:
the collision prevention parameter method is mainly used for establishing a mathematical model of ship collision. Such studies have data that is readily available and real-time for collision risk detection, as compared to historical data-based analysis. In some embodiments, the euler norm is used to calculate the risk of a vessel collision and to introduce safe time and safe distance factors. In some embodiments, the collision risk is also calculated using the form of an euler norm, into which distances and the ship domain are introduced in addition to the influencing factors of the time-of-encounter DCPA and the distance-of-encounter TCPA. In some embodiments, the vessel encounter clusters are first obtained by clustering the AIS data, and the relationship between DCPA, TCPA and collision risk is represented by using a negative exponential function. In some embodiments, the collision risk index is calculated using a fuzzy-based comprehensive evaluation method, wherein the parameters considered are DCPA, TCPA and distance, relative heading and speed ratio. Since ships have various uncertain factors when sailing at sea, some researchers use probabilistic methods to model and study the collision risks of ships. The method is mainly characterized in that the uncertainty of the ship motion is assumed to obey Gaussian distribution or the distribution condition of the ship is fitted by using historical data, and then the probability of collision of the ship is calculated. In some embodiments, AIS data is used to quantify uncertainty of ship tracks, and density functions of ship track distribution are determined, so that ship collision risks are predicted. Other modeling methods such as evidence reasoning theory, fuzzy logic, analytic hierarchy process, velocity barrier process, etc. belong to indirect modeling using DCAP or TCPA. In some embodiments, a time-varying collision risk is proposed, based on a velocity barrier method, to simultaneously consider multiple vessel encounters. In some embodiments, using the velocity barrier method and optimizing the velocity factors of previous researchers, the collision risk identification accuracy is more accurately improved. Such studies take into account dynamic information of the vessel, enabling real-time reaction of vessel collision risks, which is also a recently popular method of risk calculation and identification. However, the shortcomings of these studies are that the impact of the natural environment on the collision risk of the ship and the collision consequences of the ship are not considered at the same time, and some studies only study the collision risk of a single ship without considering the multiple ship risks. When the environment is harsh, the interference effect of multiple vessels may run away resulting in a rapid increase in risk, but existing models do not address this.
Fuzzy logic has a mode of simulating uncertainty judgment and reasoning of human brain, obtains results by using human experience, and is widely used for marine risk assessment and collision risk research. Therefore, the present embodiment proposes a method for processing a collision risk of a regional ship based on fuzzy logic. The fuzzy logic processes the fuzzy relation by means of the membership function concept, and simulates the human brain to implement regular reasoning. The risk of the ship is mostly caused by human factors, and the more abundant the experience of driving the ship, the more freely the risk of the ship is judged and processed. Therefore, the early warning of the collision risk of the ship can be carried out by using fuzzy logic which can simulate human brain to implement rule-type reasoning. The fuzzy logic model of the regional ship collision risk considering the environmental influence is provided by considering that the fuzzy logic method has a strong advantage for quantifying the ship collision risk from the natural environment and combining the ship collision risk into the single ship collision risk by using the analytic hierarchy process AHP, and can be effectively integrated into the navigation environment to model the regional ship collision risk with accuracy and effectiveness.
In particular, fuzzy inference models are processes that use fuzzy logic to formulate a mapping from inputs to outputs. The fuzzy inference model has two types Mamdani and Sugeno. The Mamdani fuzzy inference has the advantages of intuition, suitability for human input, interpretable rules and the like. Mamdani fuzzy reasoning can be introduced from a method where skilled workers obtain linguistic control rules to create a control system. The Fuzzy inference process involves five steps, Fuzzy Inputs, appliance Fuzzy operator, appliance inference method, Aggregate All Outputs, and Outputs Defuzzify. Specifically, the specific operation of each step is as follows:
fuzzify Inputs: and inputting an accurate value by the fuzzy inference model, and mapping the input accurate value to 0-1 by a fuzzy membership function. The mapping principle is shown in fig. 1.
Appliance Fuzzy operator: the fuzzy inference model inputs two variables into each layer, and the two variables determine an output result. After each input variable is fuzzified, the weight of each rule needs to be obtained by using logical operators (local operations) combination. This embodiment uses an AND operator to combine two input variables, AND the AND operator has two methods: min and prod. The Min method is chosen here, such as variable 1 with a fuzzy value of 0.7 AND variable 2 with a fuzzy value of 0.5, AND the fuzzy AND operator chooses the minimum of the two values of 0.5, i.e. the weight of this rule is 0.5, as shown in fig. 2.
Application method: and obtaining a fuzzy set by the input weight through a Min or prod method. In this embodiment, a min method is selected for implication, that is, the output fuzzy set is truncated, as shown in fig. 3.
Aggregate All Outputs: since fuzzy inference is based on the conclusions drawn from all rules, an inference operation is performed on each rule. Therefore, a plurality of fuzzy output sets are obtained, and the fuzzy output sets are aggregated to synthesize one output fuzzy set. The synthetic methods include maximum, probabilistic OR, sum of the rule output sets. In this embodiment, a maximum method is selected, and the method selects the corresponding maximum fuzzy set, as shown in fig. 4.
Outputs Defuzzify: defuzzification is the defuzzification of the combined fuzzy set to obtain an accurate value. Examples of defuzzification methods include centroid, bisector, middle of maximum (the ave)range of the maximum value of the output set), larget of maximum, and smalllest of maximum. The present embodiment uses a centroid method, which is based on the x-axis value corresponding to the barycentric position of the synthetic blur set. The defuzzification is shown in the formula (1), u (x)i) Is in the universe of discourse xiDegree of membership of:
based on the above problems and the fuzzification principle, referring to fig. 5, an embodiment of the present invention provides a regional ship collision risk processing method based on fuzzy logic. The embodiment can be applied to a server or a processor of a ship navigation management platform. The server or the processor can perform data interaction with each mobile terminal device and acquire related data from other websites.
In the application process, the present embodiment includes, but is not limited to, the following steps:
and step 55, generating a ship collision risk thermodynamic diagram according to the collision risk of each ship.
It is understood that the risk of the ship risk area is influenced by complicated intersection waters of coastal and harbor, harbor waters, or according to the difference of traffic environment. The risk of a zone collision is constituted by the risk of collision of the vessels encountered. Determining the ship risk area is to identify and classify the meeting ships. Ship encounters are the processes in which ships approach from various different directions and meet, and in the process, the encountered ships sometimes can safely drive through without taking any action, and can also cause that one or two ships have to take avoidance action, namely a ship meeting condition forming a collision risk. Thus, it is determined whether or not the vessels meet the need to determine the distance between the vessels and at least two vessels. The DBSCAN algorithm in the clustering algorithm can fully consider two factors encountered by ships. The DBSCAN is a density-based clustering algorithm, and has two parameters, namely a distance parameter and a density parameter, where the density parameter may be the number of ships in a meeting (i.e., there are at least two ships in a region), and the distance parameter is the farthest distance of the meeting of the two ships. The regions are obtained through clustering, and direct or indirect risk relation among all ships in the regions can be guaranteed. Due to the movement of the ship, the area can change along with the time change, and compared with an explicit and unchangeable research area, the clustered research area can accurately and efficiently show the ship collision risk condition. As shown in fig. 6, the part enclosed by the dotted line is the ship risk area, and after a period of time, the ship risk area reaches the range shown in fig. 7 from the range shown in fig. 6.
After the ship risk area is determined, the ship motion state parameters and the natural environment parameters in the ship risk area can be obtained. The latest meeting time DCPA and the latest meeting distance TCPA are parameters commonly used for quantifying the risk of ship collision, and collision must occur when both parameters are zero. When two ships collide, the collision positions are different, and casualties and economic losses are different. There are also objective factors that influence the impact of the vessel, for example, environmental factors of sea travel are also important for the impact between vessels. Therefore, the present embodiment takes the six factors of DCPA, TCPA, ship collision position, sea state, wind speed, and visibility as the factors of the ship collision risk.
In the embodiment, five fuzzy linguistic variables are selected for quantification, and the ship collision risk is described by very small (vs), small(s), medium (m), high (b) and very high (vb).
For the DCPA and TCPA calculation and the fuzzification of the ship motion state parameters, it can be understood that, in the fuzzification process, the two ships are assumed to have a relatively small nearest meeting time, and when the nearest meeting distance is smaller, the probability of collision between the two ships is higher. Also, assuming that the two ships meet at a relatively small distance in the near future, the smaller the time of meeting in the near future, the greater the risk of collision. By defining five fuzzy linguistic values for DCPA: fig. 8 shows membership functions of vs ═ 0,0,0.3,0.6, s ═ 0.3,0.6,0.9, m ═ 0.6,0.9,1.2, b ═ 0.9,1.2,1.5, and vb ═ 1.2,1.5, ∞ respectively. Five fuzzy linguistic values for TCPA: fig. 9 shows a membership function of vs (0,0,2,4), s (2,4,6), m (4,6,8), b (6,8,10), and vb (8,10, ∞). In the calculation process, the motion condition between the ships can be represented by the latest meeting time (DCPA), the latest meeting distance (TCPA) and the meeting angle of the two ships. In order to meet the real-time performance of risk prediction, the motion situation between two ships is obtained through AIS data processing. Figure 10 shows the motion of the two vessels and the parameters in between.
In order to make the distance parameter have practical significance in clustering, the embodiment uses the mercator distance in the distance between two ships, and the specific calculation process is shown in formula (2), formula (3), formula (4) and formula (5):
DMP＝MPt-MPoformula (3)
S ═ Dlat · sec (c) formula (5)
Wherein, MP represents the dimension growing rate, lat represents the dimension of the ship, Long represents the precision of the ship, and S represents the distance of the mercator.
The calculation process of the latest meeting distance TCPA and the latest meeting time DCPA is shown in formula (6), formula (7), formula (8) and formula (9):
TCPA＝DCPA/vrformula (9)
Wherein v isrIs the relative velocity, v, of the ship and the target shipoAnd vtThe speed of the ship and the speed of the target ship, cog respectivelyoAnd cogtRespectively the course of the ship and the course of the target ship,
theta is the azimuth of the target vessel for relative heading.
For the collision position in the ship motion state parameter, because the collision position is not easy to calculate and predict, the embodiment establishes the position relationship between the bow included angle and the collision in the meeting, and indirectly deduces the collision position by using the meeting included angle. In some embodiments, the most serious part of the collision result is a stern engine room section, the second is a cargo hold section in the ship, and the least harmful part is a bow bulb section through finite element simulation and risk assessment. The present embodiment uses a typical ship encounter situation map as shown in fig. 11 as the boundary of the collision region. The collision angle is assumed to be between 112.5 degrees and 180 degrees and between-112.5 degrees and-180 degrees to collide with the tail of the ship, between +/-67.5 degrees and +/-112.5 degrees and between +/-6 degrees and +/-67.5 degrees to collide with the middle of the ship, and between-6 degrees and 6 degrees to collide with the bow of the ship. Defining a collision angle fuzzy language value: s (-37,6,6,37), M (-0, ± 37, ± 67.5), B (-37, ± 90, ± 112.5), VB (-90, ± 112.5, ± 180, ± 180), and the membership functions are shown in fig. 12.
For natural environment parameters, the research on the current collision risk at sea is compared with the self experience of the crew, so that the natural environment condition in theoretical research is not considered completely, but the natural environment is very important for true navigation conditions. For the regional collision risk, except the risk condition of the ship inside the region, the storm condition and visibility condition of different regions are considered at the same time. Therefore, the present embodiment takes into account the effects of sea state, wind speed, and visibility when calculating the risk of ship collision.
Wherein, the wind speed is defined to be in the range of 0-9, and the Purper wind level is adopted. The present embodiment uses five language values for obfuscation, min wind, mid wind, max wind, and max wind. Rectangular membership functions are used for minimum wind and maximum wind, and triangular membership functions are used for others. The greater the wind level, the higher the probability of the ship being at risk. When the wind level reaches more than 7 grades, the fishing boat needs to shelter from wind in the harbor, and when the wind level reaches more than 9 grades, the boat is very dangerous in sailing, so the wind level corresponds to the risk. It is specified that VS ═ is (0,0,1,2), S ═ is (1,2,4), M ═ is (2,4,6), B ═ is (4,6,8), and VB ═ is (6,8,9, 9).
Sea state definition is in the range of 0-9, and the Dow wave level is adopted. This example uses five language values for obfuscation, Calm, Smooth, Moderate, Rough and Very High. Calm and Very High use trapezoidal membership functions, others use trigonometric membership functions. To simplify the model, the present embodiment assumes that sea state and wind speed work equally well on each vessel. The larger the wave level, the higher the impact on the vessel. The wave level size corresponds to the risk size. Provision is made that VS ═ 0,0,1,2, S ═ 1,2,3.5, M ═ 2,4,6, B ═ 4.5,6,7, and VB ═ 6,8,9, 9.
Sea fog is the primary factor affecting visibility at sea, and whether in the sea or in ports, visibility is very poor when dense fog occurs, which brings a lot of difficulty and risk to navigation. Even if the ship is provided with modern navigation instruments such as an electronic radar, the ship still has serious accidents such as collision. Therefore, visibility is critical to the safety of navigation. Fog can give horizontal visibility of less than 1km or 0.5 nautical miles, when the vessel is at high risk. International rules for collision avoidance at sea point out that vehicles should be prepared and the ship should be carefully driven when the visibility is less than 5 nautical miles, so that the ship should be at medium risk. In practice, when visibility drops to 2 or 3 seas, the ship can enter first-level fog voyage abstinence, and the risk is further increased. Therefore, in the present embodiment, VS ═ 5,6.5,7, S ═ 3.5,5,6.5, M ═ 2,3.5,5, B ═ 0.5,2,3.5, and VB ═ 0,0,0.5,2 are specified.
After the ship motion state parameters and the natural environment parameters are obtained, the collision risk between ships can be predicted according to the ship motion state parameters and the natural environment parameters, and the prediction can be performed through a fuzzy logic reasoning model. Wherein, fuzzy rules are arranged in the fuzzy logic reasoning model and are stored in a fuzzy rule base. Therefore, the present embodiment needs to build a fuzzy rule base before application.
Specifically, the input variables and the output variables need to be determined first before the fuzzy rules are determined. Because the research factors of the embodiment are numerous, a huge rule base is generated by using a fuzzy inference opportunity, and therefore the factors which directly interact with each other are used as a group of input variables to establish a multi-layer fuzzy inference system. The final output variable is the risk of collision between the vessels. The multi-layer fuzzy inference model is shown in fig. 13. The fuzzy rule is the core of the fuzzy inference model, and various influencing factors are connected through the rule to determine an output result. The fuzzy rule is expressed in the form of "IF … THEN …". In this way, the present embodiment sets fuzzy rules, such as if (dcpa is vs) and (tcpa is vs) the (shipcondition is vb), and some of the rules are shown in tables 1 and 2. FIG. 14, FIG. 15, FIG. 16, FIG. 17 and FIG. 18 are graphs of fuzzy inference >
TABLE 1
TABLE 2
After the fuzzy rule is built, the ship collision risk is predicted by using the built fuzzy rule. It will be appreciated that the vessel may be constructed by first constructing the vesselAnd determining the collision risk of each ship in the ship risk area according to the ship collision risk judgment matrix. Specifically, a ship collision risk judgment matrix is normalized according to columns, the normalized ship collision risk judgment matrices are added according to rows to obtain sum vectors, then the sum vectors are normalized to obtain weight vectors, and then collision risk vectors of a target ship and other ships in a ship risk area are calculated, wherein the target ship is any ship in the ship risk area, and the rest ships in the ship risk area are used as other ships; and finally, determining the total collision risk of the target ship according to the weight vector and the collision risk vector. In implementation, the present embodiment may use an analytic hierarchy process AHP to calculate the ship weight. Specifically, according to the principle of a hierarchical analysis method, a judgment matrix a ═ a is constructedij]n×n. The risk of ship collision after deblurring ranges between 0 and 1. Wherein, aijFor the importance of the risk of the ith ship to the own ship to the risk of the jth ship to the own ship, and aij>0,aij＝1,aji＝1/aij. Defining the collision wind after the deblurring as CRxyRepresenting the risk of ship collision for x and y ships, then aij＝CRxi/CRxj。
The decision matrix a is normalized by the column by equation (10):
the sum vector W is obtained by adding the following lines by the formula (11)i：
Normalizing the sum vector by formula (12) to obtain a weight vector
Calculating collision risk vectors CR of the ship x and other ships after the in-cluster deblurring through formula (13)xy：
CRxy＝(CRxy1,CRxy2,…,CRxyn) Formula (13)
Calculating the overall collision risk CRI for vessel x by equation (14)x：
According to a secondary rule, the total collision risk of any ship in the ship risk area can be obtained, and a ship collision risk thermodynamic diagram is generated according to the total collision risk of each ship, so that a driver or a manager can master the ship collision risk condition in time, and corresponding measures can be taken in time to improve the safety of the ship in the driving process.
In summary, as shown in fig. 19, in the embodiment, a ship risk area is obtained by using a clustering method, then, relevant parameters and natural environment parameters between ships in the ship risk area are calculated, the parameters are brought into a fuzzy inference model to obtain collision risks of the ships, then, the collision risks of each ship are synthesized by using an AHP method, and finally, the risks of each ship are displayed in a thermodynamic diagram manner, so that the collision risks in the area are intuitively known.
In order to verify the effect of the embodiment, the embodiment analyzes by selecting the ship AIS data of the preset actual strait. Specifically, a ship risk area at a certain moment is obtained as a research area by using DBSCAN cluster analysis, and two parameters Eps and Minpts are needed for DBSCAN clustering. The selection of the parameters determines the quality of the clustering result, thereby indirectly influencing the accuracy of risk identification. The EPS parameters adopted in this embodiment are 1.5nm, and the Minpts parameters are 3. Because research areas are different at different moments, the ship collision risk area is researched by researching the same parameters at different moments, so that the early warning of the ship collision risk area can be more accurate.
Specifically, the ship motion state parameters shown in table 3, the natural environment parameters shown in table 4, and the collision risk of the ship pair shown in table 5 are selected from one cluster of ship data in the research area:
TABLE 3
| Ship | Sog | | Long | Lat | |
| 1 | 7.7 | 230.2 | 117.8668 | 23.96726 | |
| 2 | 6.8 | 44.7 | 117.8695 | 23.974 | |
| 3 | 8.2 | 48.5 | 117.9032 | 24.00462 | |
| 4 | 10.1 | 45.7 | 117.9002 | 23.9801 | |
| 5 | 6.9 | 53.5 | 117.8778 | 23.98089 |
TABLE 4
| Ship with a detachable cover | Wind power | | Visibility | |
| 1 | 8.3 | 1.4 | 20 | |
| 2 | 8.0 | 1.3 | 20 | |
| 3 | 7.9 | 1.3 | 20 | |
| 4 | 8.5 | 1.4 | 20 | |
| 5 | 8.0 | 1.3 | 20 |
TABLE 5
From the above table, the risk weight matrix shown in formula (15) can be obtained by formula (6) to formula (10):
the final collision risk for each vessel is: 0.25, 0.702, 0.701, 0.504, 0.712.
When the TCPAs of the two ships are negative, the two ships pass through the nearest meeting point, so that the risk caused by the self condition of the ships does not need to be calculated, and only the risk caused by the environmental factors at the moment is considered. As shown in table 4, when calculating risks caused by natural environments, parameters of the worst environments of the two ships are selected for calculation. Table 5 shows the collision risks of the ship pairs, and in order to more clearly show the total risk of the ship collision, the ship pair risks are combined into the ship collision risk, and the risk weight is shown as (15).
Specifically, fig. 20 is an intention of the ship when the ship is underway, and fig. 21 is an intention of showing the risk level of the ship on a map in the form of thermodynamic diagram. Each region forms a range of thermodynamic diagrams, and then the risk condition of the region is obtained, wherein the higher the risk level is, the more prominent the color of the region is. Finally, VTS person on duty, unmanned ship bank base control and person on duty on the ship can zoom the chart thermodynamic of chart that is generated, judge the risk grade of the area that the boats and ships are located and the risk situation of boats and ships self according to the color situation by oneself.
Therefore, in the embodiment, a research area with relatively high collision risk is obtained through DBSCAN clustering, influences among ships and influences of natural environments can be comprehensively considered through analyzing ship collision conditions, ship collision risk factors are quantized by introducing a fuzzy logic method, then the overall collision risk of the ship is obtained through calculating risk weight through an analytic hierarchy process, and finally the ship risk is displayed in a risk thermodynamic diagram mode, so that VTS (vessel traffic system) operators, unmanned ship-shore base monitoring and ship operators can judge collision risks of the ship and the area conveniently. In order to verify the validity of the model, the embodiment verifies the model by using the actual strait ship navigation data, and the verification result is approved by a specified expert. The model of this embodiment can provide important basis for the monitoring of marine supervision department and the driver of the ship perception risk as the early warning effect of ship collision risk.
The embodiment of the invention provides a regional ship collision risk processing system based on fuzzy logic, which comprises:
the first determining module is used for determining a ship risk area;
the acquisition module is used for acquiring ship motion state parameters and natural environment parameters in the ship risk area, wherein the ship motion state parameters comprise a nearest meeting distance, a nearest meeting time and a collision position;
the reasoning module is used for inputting the ship motion state parameters and the natural environment parameters into a fuzzy logic reasoning model to obtain collision risks among ships;
a second determining module, configured to determine a collision risk of each ship in the ship risk area according to collision risks among the ships;
and the generating module is used for generating a ship collision risk thermodynamic diagram according to the collision risk of each ship.
The content of the embodiment of the method of the invention is all applicable to the embodiment of the system, the function of the embodiment of the system is the same as the embodiment of the method, and the beneficial effect achieved by the embodiment of the system is the same as the beneficial effect achieved by the method.
The embodiment of the invention provides a regional ship collision risk processing system based on fuzzy logic, which comprises:
at least one memory for storing a program;
at least one processor for loading the program to execute the fuzzy logic-based regional ship collision risk processing method shown in fig. 5.
The content of the embodiment of the method of the invention is all applicable to the embodiment of the system, the function of the embodiment of the system is the same as the embodiment of the method, and the beneficial effect achieved by the embodiment of the system is the same as the beneficial effect achieved by the method.
An embodiment of the present invention provides a storage medium, in which a computer-executable program is stored, and the computer-executable program is executed by a processor to implement the fuzzy logic-based regional ship collision risk processing method shown in fig. 5.
Embodiments of the present invention also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and executed by the processor, to cause the computer device to perform the fuzzy logic based regional ship collision risk processing illustrated in fig. 5.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention. Furthermore, the embodiments of the present invention and the features of the embodiments may be combined with each other without conflict.
Claims (10)
1. A regional ship collision risk processing method based on fuzzy logic is characterized by comprising the following steps:
determining a ship risk area;
acquiring ship motion state parameters and natural environment parameters in the ship risk area, wherein the ship motion state parameters comprise a nearest meeting distance, a nearest meeting time and a collision position;
inputting the ship motion state parameters and the natural environment parameters into a fuzzy logic reasoning model to obtain collision risks among ships;
determining a collision risk for each vessel within the vessel risk area according to the collision risk between the vessels;
and generating a ship collision risk thermodynamic diagram according to the collision risk of each ship.
2. The fuzzy logic-based regional ship collision risk processing method according to claim 1, wherein the obtaining of the ship motion state parameters in the ship risk region comprises:
and determining ship motion state parameters according to AIS data in the ship risk area, wherein the nearest meeting distance comprises an ink card support distance, and the collision position is determined through a meeting included angle.
3. The fuzzy logic-based regional ship collision risk processing method according to claim 1, wherein the natural environment parameters comprise sea state, wind speed and visibility;
the wind speed comprises five fuzzified language values representing wind speed grades, the wind speed grades at two ends adopt rectangular membership functions, and the wind speed grades in the middle three adopt triangular membership functions;
the sea condition comprises five fuzzified language values representing risk levels, the risk levels at two ends adopt trapezoidal membership functions, and the three wind speed levels in the middle adopt triangular membership functions;
the visibility includes a sea fog state.
4. The fuzzy logic-based regional ship collision risk processing method according to claim 1, wherein the step of inputting the ship motion state parameters and the natural environment parameters into a fuzzy logic reasoning model to obtain collision risks between ships comprises the steps of:
and inputting the ship motion state parameters and the natural environment parameters into a fuzzy logic reasoning model, and determining the collision risk between the ships according to a fuzzy rule in the fuzzy logic reasoning model.
5. The fuzzy logic-based regional ship collision risk processing method according to claim 1, wherein the determining the collision risk of each ship in the ship risk region according to the collision risk between the ships comprises:
constructing a ship collision risk judgment matrix;
and determining the collision risk of each ship in the ship risk area according to the ship collision risk judgment matrix.
6. The fuzzy logic-based regional ship collision risk processing method according to claim 5, wherein the determining the collision risk of each ship in the ship risk region according to the ship collision risk judgment matrix comprises:
normalizing the ship collision risk judgment matrix according to columns;
adding the normalized ship collision risk judgment matrixes in rows to obtain a sum vector;
normalizing the sum vector to obtain a weight vector;
calculating collision risk vectors of a target ship and other ships in the ship risk area, wherein the target ship is any one ship in the ship risk area, and the rest ships in the ship risk area are used as other ships;
and determining the total collision risk of the target ship according to the weight vector and the collision risk vector.
7. The fuzzy logic-based regional ship collision risk processing method according to claim 1, wherein the determining the ship risk region comprises:
and determining a ship risk area according to a density clustering algorithm.
8. A fuzzy logic based regional vessel collision risk handling system, comprising:
the first determining module is used for determining a ship risk area;
the acquisition module is used for acquiring ship motion state parameters and natural environment parameters in the ship risk area, wherein the ship motion state parameters comprise a nearest meeting distance, a nearest meeting time and a collision position;
the reasoning module is used for inputting the ship motion state parameters and the natural environment parameters into a fuzzy logic reasoning model to obtain collision risks among ships;
a second determining module, configured to determine a collision risk of each ship in the ship risk area according to collision risks among the ships;
and the generating module is used for generating a ship collision risk thermodynamic diagram according to the collision risk of each ship.
9. A fuzzy logic based regional vessel collision risk handling system, comprising:
at least one memory for storing a program;
at least one processor configured to load the program to perform the fuzzy logic based regional vessel collision risk processing method of any of claims 1-7.
10. A storage medium having stored therein a computer-executable program for implementing the fuzzy logic based regional vessel collision risk processing method of any one of claims 1-7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210007235.8A CN114464014A (en) | 2022-01-05 | 2022-01-05 | Fuzzy logic based regional ship collision risk processing method, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210007235.8A CN114464014A (en) | 2022-01-05 | 2022-01-05 | Fuzzy logic based regional ship collision risk processing method, system and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114464014A true CN114464014A (en) | 2022-05-10 |
Family
ID=81409941
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210007235.8A Pending CN114464014A (en) | 2022-01-05 | 2022-01-05 | Fuzzy logic based regional ship collision risk processing method, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114464014A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115331486A (en) * | 2022-08-12 | 2022-11-11 | 河海大学 | Ship collision risk assessment and prediction method and device |
| CN117315995A (en) * | 2023-09-28 | 2023-12-29 | 大连海事大学 | Water area collision danger quantification and spatial distribution characterization method based on close-range missing |
| CN117521815A (en) * | 2024-01-04 | 2024-02-06 | 交通运输部水运科学研究所 | Assessment method for safe distance between route and platform and electronic equipment |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890875A (en) * | 2012-10-15 | 2013-01-23 | 浙江大学 | Method for acquiring system collision risk of maritime intelligent transportation network |
| CN103207937A (en) * | 2013-04-15 | 2013-07-17 | 大连海事大学 | Quaternion ship security domain model and ship collision avoidance method |
| CN104050329A (en) * | 2014-06-25 | 2014-09-17 | 哈尔滨工程大学 | Method for detecting degree of risk of ship collision |
| CN105185162A (en) * | 2015-10-26 | 2015-12-23 | 中国电子科技集团公司第二十八研究所 | AIS information-based multi-target anti-collision warning method |
| CN105390029A (en) * | 2015-11-06 | 2016-03-09 | 武汉理工大学 | Ship collision avoidance assisted decision-making method and system based on track fusion and track prediction |
| CN109887339A (en) * | 2019-03-20 | 2019-06-14 | 集美大学 | A kind of ship collision danger and risk assessment method being associated with evacuation behavior |
| CN109932929A (en) * | 2019-03-15 | 2019-06-25 | 中科恒运股份有限公司 | Ship cruise analog simulation method, computer readable storage medium and terminal device |
| CN110009937A (en) * | 2019-03-21 | 2019-07-12 | 武汉理工大学 | A kind of ship collision risk analysis method based on AIS data |
| CN111721321A (en) * | 2020-05-19 | 2020-09-29 | 交通运输部东海航海保障中心上海航标处 | Intelligent collision avoidance method and system for navigation mark |
| CN112036007A (en) * | 2020-07-22 | 2020-12-04 | 海洋石油工程股份有限公司 | Risk assessment method for structural failure of underwater claw connector |
| CN112102361A (en) * | 2020-09-04 | 2020-12-18 | 珠海大横琴科技发展有限公司 | Multi-ship operation collision detection method and device and computer equipment |
| CN112967527A (en) * | 2021-02-05 | 2021-06-15 | 武汉理工大学 | Ferry collision risk assessment method, system, device and medium |
| CN113762367A (en) * | 2021-08-26 | 2021-12-07 | 集美大学 | Self-adaptive multi-ship meeting identification method based on optimal meeting distance in complex water area |
-
2022
- 2022-01-05 CN CN202210007235.8A patent/CN114464014A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102890875A (en) * | 2012-10-15 | 2013-01-23 | 浙江大学 | Method for acquiring system collision risk of maritime intelligent transportation network |
| CN103207937A (en) * | 2013-04-15 | 2013-07-17 | 大连海事大学 | Quaternion ship security domain model and ship collision avoidance method |
| CN104050329A (en) * | 2014-06-25 | 2014-09-17 | 哈尔滨工程大学 | Method for detecting degree of risk of ship collision |
| CN105185162A (en) * | 2015-10-26 | 2015-12-23 | 中国电子科技集团公司第二十八研究所 | AIS information-based multi-target anti-collision warning method |
| CN105390029A (en) * | 2015-11-06 | 2016-03-09 | 武汉理工大学 | Ship collision avoidance assisted decision-making method and system based on track fusion and track prediction |
| CN109932929A (en) * | 2019-03-15 | 2019-06-25 | 中科恒运股份有限公司 | Ship cruise analog simulation method, computer readable storage medium and terminal device |
| CN109887339A (en) * | 2019-03-20 | 2019-06-14 | 集美大学 | A kind of ship collision danger and risk assessment method being associated with evacuation behavior |
| CN110009937A (en) * | 2019-03-21 | 2019-07-12 | 武汉理工大学 | A kind of ship collision risk analysis method based on AIS data |
| CN111721321A (en) * | 2020-05-19 | 2020-09-29 | 交通运输部东海航海保障中心上海航标处 | Intelligent collision avoidance method and system for navigation mark |
| CN112036007A (en) * | 2020-07-22 | 2020-12-04 | 海洋石油工程股份有限公司 | Risk assessment method for structural failure of underwater claw connector |
| CN112102361A (en) * | 2020-09-04 | 2020-12-18 | 珠海大横琴科技发展有限公司 | Multi-ship operation collision detection method and device and computer equipment |
| CN112967527A (en) * | 2021-02-05 | 2021-06-15 | 武汉理工大学 | Ferry collision risk assessment method, system, device and medium |
| CN113762367A (en) * | 2021-08-26 | 2021-12-07 | 集美大学 | Self-adaptive multi-ship meeting identification method based on optimal meeting distance in complex water area |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115331486A (en) * | 2022-08-12 | 2022-11-11 | 河海大学 | Ship collision risk assessment and prediction method and device |
| CN115331486B (en) * | 2022-08-12 | 2023-06-13 | 河海大学 | Ship collision risk assessment and prediction method and device |
| CN117315995A (en) * | 2023-09-28 | 2023-12-29 | 大连海事大学 | Water area collision danger quantification and spatial distribution characterization method based on close-range missing |
| CN117315995B (en) * | 2023-09-28 | 2024-05-07 | 大连海事大学 | Water area collision danger quantification and spatial distribution characterization method based on close-range missing |
| CN117521815A (en) * | 2024-01-04 | 2024-02-06 | 交通运输部水运科学研究所 | Assessment method for safe distance between route and platform and electronic equipment |
| CN117521815B (en) * | 2024-01-04 | 2024-04-02 | 交通运输部水运科学研究所 | Assessment method for safe distance between route and platform and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114464014A (en) | Fuzzy logic based regional ship collision risk processing method, system and medium | |
| CN110083155B (en) | Machine learning method for realizing ship anthropomorphic intelligent collision avoidance decision | |
| Bukhari et al. | An intelligent real-time multi-vessel collision risk assessment system from VTS view point based on fuzzy inference system | |
| Xu et al. | A survey on ship collision risk evaluation | |
| Tran | Effect of ship loading on marine diesel engine fuel consumption for bulk carriers based on the fuzzy clustering method | |
| Shi et al. | Fuzzy logic-based modeling method for regional multi-ship collision risk assessment considering impacts of ship crossing angle and navigational environment | |
| CN111353222B (en) | Simulation test system and method for automatic berthing capability of intelligent ship | |
| CN113012472B (en) | Ship early warning method and equipment suitable for VTS system and storage medium | |
| Li et al. | AIS data-based decision model for navigation risk in sea areas | |
| CN112560286B (en) | Ship collision risk determination method based on digital ship field model | |
| CN111613094A (en) | Port water area ship traffic risk early warning method | |
| CN111815120A (en) | Water traffic risk assessment method, device, computer equipment and storage medium | |
| CN112561232A (en) | Method for measuring traffic conflict risk of ship in busy water area | |
| Trincas et al. | Risk-based system to control safety level of flooded passenger ships | |
| Li et al. | Towards real-time ship collision risk analysis: An improved R-TCR model considering target ship motion uncertainty | |
| CN111240229B (en) | Fault information processing system based on intelligent ship berthing-off simulation test | |
| Zhou et al. | Navigation safety domain and collision risk index for decision support of collision avoidance of USVs | |
| Vagale et al. | Evaluation of path planning algorithms of autonomous surface vehicles based on safety and collision risk assessment | |
| Zhang et al. | A method of performing real-time ship conflict probability ranking in open waters based on AIS data | |
| Cheng et al. | Traffic-conflict and fuzzy-logic-based collision risk assessment for constrained crossing scenarios of a ship | |
| Zhao et al. | A method for correcting the closest point of approach index during vessel encounters based on dimension data from AIS | |
| CN110826891B (en) | Relative collision risk degree obtaining method based on ship cluster situation | |
| CN115410419B (en) | Ship mooring early warning method, system, electronic equipment and storage medium | |
| CN115330167A (en) | Ship navigation safety assessment method and device, electronic equipment and medium | |
| Song et al. | Interference intention classification of moving obstacles used for USV collision avoidance |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Fang Qionglin Inventor after: Zhen Rong Inventor after: Shi Ziqiang Inventor after: Shao Zheping Inventor after: Pan Jiacai Inventor before: Zhen Rong Inventor before: Shi Ziqiang Inventor before: Shao Zheping Inventor before: Pan Jiacai Inventor before: Fang Qionglin |
|
| CB03 | Change of inventor or designer information |