CN108984820A - A kind of particle based on Nash Equilibrium throws drift path prediction technique again - Google Patents
A kind of particle based on Nash Equilibrium throws drift path prediction technique again Download PDFInfo
- Publication number
- CN108984820A CN108984820A CN201810509493.XA CN201810509493A CN108984820A CN 108984820 A CN108984820 A CN 108984820A CN 201810509493 A CN201810509493 A CN 201810509493A CN 108984820 A CN108984820 A CN 108984820A
- Authority
- CN
- China
- Prior art keywords
- drift
- particle
- ship
- nash equilibrium
- path
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention is to provide a kind of particles based on Nash Equilibrium to throw drift path prediction technique again.(1) Nash Equilibrium processing is carried out to the factor for influencing ship drift；(2) the processed information of Nash Equilibrium for passing through step (1) is inputted in three-dimensional visualization software Unity3D；(3) drift object initial probability distribution figure is obtained using monte carlo method；(4) drift velocity in Nash Equilibrium state is sought；(5) it is based on drift velocity, method is thrown again using particle in conjunction with drift time, is calculated by model, find out the 2D drift path of ship；(6) the 2D drift path of ship is converted to drift orbit and the display of 3D.The present invention cleverly combines Nash Equilibrium Theory and particle throws method again, has not only considered multiple influence factors because timely updating for information can make drift orbit be more nearly true drift path, has then effectively improved the degree of fitting of ship drift orbit.The present invention can export more accurate drift path.
Description
Technical field
The present invention relates to a kind of methods of marine ships drift path prediction, and in particular to one kind is based on Nash Equilibrium
Particle throw the prediction technique of drift path again.
Background technique
With flourishing for Chinese society economy, marine transportation becomes further busy, this also results in marine accident
Probability of happening greatly increases.Therefore establishing a reasonable maritime search and rescue target can ensure that quickly searching and rescuing marine accident loses
The cargo of track personnel and loss ensure seaborne safety conscientiously.Realize that maritime search and rescue rationally mainly seek to accomplish
The utilization of the region true and accurate of maritime search, maritime search and rescue resource is rationally efficient, therefore, finds and realizes fast and accurately
Maritime search and rescue method is the matter of utmost importance for ensureing marine transportation and facing.Calculating for shipwreck position and drift orbit and pre-
It surveys, conventional method is to carry out paper calculating by sea chart, experience, under efficiency is relatively low.
Research for the factor and ship drift path that influence ship drift is all the basis for establishing ship drift model,
Domestic existing drift model is mainly theoretical model, that is, establishes model and then verified, can using VB and MATLAB implementation
Depending on changing, but the difficulty for being applied to reality is quite big.
Summary of the invention
The purpose of the present invention is to provide a kind of particle weights based on Nash Equilibrium of efficiency that can be improved maritime search and rescue
Throw drift path prediction technique
The object of the present invention is achieved like this:
(1) Nash Equilibrium processing is carried out to the factor for influencing ship drift, ship drift is made to reach Nash Equilibrium state, institute
It includes wind, stream, wave, turbulent flow and ship self attributes that stating, which influences the factor of ship drift,；
(2) the processed information of Nash Equilibrium for passing through step (1) is inputted in three-dimensional visualization software Unity3D；
(3) drift object initial probability distribution figure is obtained using monte carlo method；
(4) drift velocity in Nash Equilibrium state is soughtHere v is referred in Nash Equilibrium shape
The drift velocity of the ship drift model of state, a' are the acceleration in Nash Equilibrium state, v0For the initial velocity of ship；
(5) it is based on drift velocity, method is thrown again using particle in conjunction with drift time, is calculated by model, find out ship
2D drift path；
(6) the 2D drift path of ship is converted to the drift orbit of 3D, more vivid display.
The present invention may also include:
1, the method for throwing specifically includes particle again,
Input: drift particle initial information, drift time, drift particle initial information include wind field, flow field and ship from
Body attribute；
Output: drift path；
Step 5.1: drift particle initial information is read in input, obtains particle initial probability distribution figure；
Step 5.2: the input particle drift time analyzes particle drift state；
Step 5.3: Nash Equilibrium processing is carried out to particle drift state；
Step 5.4: judging whether particle is in Nash Equilibrium state, if it is execution step 5.5；It is no to then follow the steps
5.3；
Step 5.5: judging whether to need to be split the particle drift time, if it is execution step 5.6；If not
Execute step 5.9；
Step 5.6: n parts will be divided into drift time, information update sequentially is carried out to the particle in these periods；
Step 5.7: by the drift path Sequential output in every part of period；
Step 5.8: judging whether the ageing of output is complete, if it is step 5.9 is executed, if it is straight to be unsatisfactory for condition
It connects and executes step 5.10；
Step 5.9: exporting complete drift path；
Step 5.10: algorithm terminates.
2, in calculating by model, the drift final mask for the object that drifts about:
Wherein ε is wind pressure disturbance and flow field wind disturbance and t1,t2...,tnWhat is represented is the drift time to be divided into n parts,
When indicating n-th time, particle relies on Nash Equilibrium state stress condition after having updated information new in (n-1)th time
The drift path obtained with initial probability distribution figure.
The present invention provides the prediction techniques that a kind of particle based on Nash Equilibrium throws drift path again.The present invention adopts for the first time
Influence factor is handled with Nash Equilibrium method, and proposes that particle throws method again to generate drift path.
Therefore prediction that the computer simulation technique of highly effective and safe is introduced to drift path, can not only improve maritime search and rescue
Efficiency, while also adding wrecked ship and a possibility that personnel are rescued.Therefore sea is solved using computer simulation technique
Upper search and rescue problem will improve the maritime search and rescue ability in China, play a significant role for the development of China's marine cause.
The invention proposes a kind of three-dimensional visualization models, then complete one using Unity language on the basis of this model
Two-dimentional track picture, which can be showed, can also show the available system of three-dimensional Actual path, to enhance the availability of drift model.
For the ship drift after marine accident, the analysis and processing and for predicting drift of the factor of ship drift are influenced
The foundation for the drift model for moving path is all vital, but existing mould relatively more for the factor for influencing ship drift
The fewer problem of the factor of type processing, the present invention will introduce Nash Equilibrium method, be handled using Nash Equilibrium method more
Complex relationship between a factor, and then obtain the optimal solution of the unbalanced problem of influence factor；Ship is floated for conventional method
The initial information undertreatment of shifting, causes the prediction of drift path to differ greatly with true path, and as time increases,
The problem of degree of fitting of ship drift path reduces rapidly, the invention proposes particles to throw simulation method again.By entire drift time
Be divided into multistage, each section predicted after carry out information update, then proceed to predict, continue entire Drift Process.
The present invention cleverly combines Nash Equilibrium Theory and particle throws method again, not only considered multiple influence factors but also because
Drift orbit can be made to be more nearly true drift path for timely updating for information, then effectively improve ship drift orbit
Degree of fitting.
Present invention has an advantage that Nash Equilibrium Theory is applied to the prediction of drift orbit by (1) for the first time, it is assorted equal using receiving
The theoretical Multiple factors to handle influence ship drift of weighing apparatus, including the irrespective tide of usual method, wave, the factors such as turbulent flow,
The speed optimal solution (2) for obtaining ship drift proposes that particle throws method again and generates drift path for the first time, by drift total time point
It for multistage, all timely updates to information in per a period of time, avoids the increase with drift time, prediction result and reality
The degree of fitting of border result reduces.The present invention makes full use of the advantage of two methods, exports last more accurate drift path.
Detailed description of the invention
Fig. 1 is the frame diagram of the method for the present invention.
Fig. 2 is that 1 distinct methods of experiment generate path comparison diagram.
Fig. 3 is that 2 distinct methods of experiment generate path comparison diagram.
Fig. 4 is that particle throws method flow diagram again.
Specific embodiment
It illustrates below and the present invention is described in more detail.
The present invention is a kind of prediction technique of marine ships drift path, respectively to the influence factor of ship drift model and
Drift orbit technology is analyzed and is studied, and the factor for influencing ship drift firstly, for previous research is very few, leads to foundation
The false problem of ship drift model prediction result, the present invention, which proposes to be handled with Nash Equilibrium method, influences ship drift
Multiple factors.The factor that previous research influences ship drift often only has wind field and two kinds of flow field factor, the present invention basic herein
Upper utilization Nash Equilibrium method also studies wave, turbulent flow, the factors such as itself material and submergence ratio, and ship is made to drift about
Reach Nash Equilibrium state in the process, and then improves the accuracy of ship drift model prediction.Secondly, for existing method to ship
Oceangoing ship drift path predicts the low problem of degree of fitting, throws method again from the angle of piecewise prediction proposition particle to predict the drift of ship
Path.It can cause what degree of fitting reduced rapidly to ask as time increases for prediction of the existing model to ship drift orbit
Topic proposes that particle throws method again to predict the drift path of ship.Particle throws method again and entire drift time is divided into multistage, often
One section predicted after carry out information update, then proceed to predict, continue entire Drift Process, and then obtain whole section of drift road
Diameter.Timely updating for information can make drift orbit be more nearly true drift path, effective raising ship drift orbit
Degree of fitting.
1, the processing based on Nash Equilibrium method to ship drift effect factor
Nash Equilibrium method is one of the multifactor participation of processing or the most widely used method of problem of game, but in ship
Be not applied also in the foundation of oceangoing ship drift model, the present invention by use Nash Equilibrium method to influence ship drift about factor into
Row processing.
A kind of optimization method for the problem of Nash Equilibrium method is multiple participants while making a policy, what is only participated in is each
When side all makes one to oneself best strategy, it can just reach Nash Equilibrium.Therefore Nash Equilibrium is to the maximum extent
Consider each side's influence factor and the optimal balanced state of an each side realizing.N represents the number of participant, indicates N number of ginseng
With the decision variable of person, x=(x is remembered1, x2..., xv..., xN).Use xvThe decision for indicating v-th of participant, uses x-vIndicate x1,
x2...xNThe decision of other participants, wherein x-v=(x1,x2,...,xv-1,xv+1,...,xN)。
If xvDimension be nv, so the dimension of x can be expressed asThen other available participants
Decision dimension be n-nv.F can be usedv(xv,x-v) indicating the cost function of Nash Equilibrium, Solving Nash Equilibrium problem is just
It is to seek x*=(x*,1,x*,2,...,x*,N), so working as x for each participant v ∈ { 1 ..., N }-vTake x*,-vWhen, xvIt is
The decision set of v participant, x*,vIt is exactly the solution of following formula:
And in the present invention, the drift motion of ship will receive the influence of very Multiple factors, in the process of ship drift
In, influence factor collective effect is drifted about in ship, but the effect of each factor is different, and the purpose is to allow ship to drift about
Speed optimizes.In order to make being optimal of drift velocity, a controller is arranged in we, its effect is that each factor is allowed to beat
To Nash Equilibrium, the influence that the decision that each factor is made under the decision of controller can make oneself drift about ship reaches most
It is excellent.
Entire Drift Process is described underneath with abstract language,
N: the decision set of each influence factor；
A∈N×N；
Starting force size of v-th of influence factor in i-th decision；
Initial mass of v-th of influence factor in i-th decision；
Pi: receive the size of power of the assorted function in i-th decision；
Qi: receive the quality of ship drift model of the assorted function in i-th decision；
eij: the loss of power when being transformed into jth item decision from i-th decision；
CAPi v: the size of v-th of influence factor power in i-th decision；
V-th of influence factor is from i-th decision to the quality of ship drift model when making jth item decision；
V-th of influence factor is from i-th decision to the size of ship stress when making jth item decision；
Sj: all influence factors are from i-th decision to acceleration total when making jth item decision；
Then
pj: the drift acceleration of ship when all influence factors make jth item decision；
Then
The optimal solution of following formula is translated into for the optimal acceleration of ship drift in this way:
According to formula above, in available Nash Equilibrium state ship Drift Process each factor optimal solution, still
For marine environment complicated and changeable, some unexpected factors can lead to the destruction of Nash Equilibrium state.Therefore in order to more
Add each influence factor of comprehensive processing ship drift, while the time for also making ship as long as possible in Drift Process keeps
Nash Equilibrium state, the present invention introduce enchancement factor ξ in Nash Equilibrium model, and the optimal solution to make is more nearly ship
The real conditions of drift.
During the entire process of ship drift, the speed of ship drift we can use inverse velocity function p (t, ξ (ω))
Description, p (t, ξ (ω)) here refer to acceleration function, and t refers to Drift Process total time here, while we are also
Know the quality m of ship and the decision set N of each influence factor.Wherein ξ: Ω → R is a continuous random variable, and wherein ξ is used
To describe some random uncertain factors.
Influence factor i, i=1,2..., n oneself can influence the time of ship drift with decision oneself in Drift Process
ti, then velocity function can indicate are as follows: Ri(ti,T-i)=Ε [tip(T,ξ)-Ci(ti)], T here-iIt refers to other than i
Other influence factor decisions oneself influence the time of ship drift, T=T in Drift Process-i+tiIt is all influence factors pair
Total time of ship drift effect.If the acceleration of ship drift is p (T, ξ), then tiP (T, ξ) is influence factor i, i=
1,2..., n assigns ship and obtains speed in Drift Process.Ci(ti) indicate influence factor i in ship Drift Process because of resistance
Power and lead to the speed to slow down.In view of the speed of ship drift is influenced by some random uncertain factors, such as typhoon,
Tsunami, submarine volcano outburst etc., therefore each influence factor i, i=1,2..., the decision set of n have shared constraint g (ti)=
Ε[G(ti,ξ)≤0。
Since the influence time t that the speed of ship drift drifts about to ship with influence factoriIt is related, therefore influence factor will
It can decision one suitable time tiTo make velocity function RiReach maximum.When the decision of all influence factors made can allow
None influence factor can make oneself to increase the influence power of ship drift by changing the decision of oneself, at this moment
Say that each factor has reached Nash Equilibrium.
2, the path generating method thrown again based on particle
Particle again the method for throwing be Monte Carlo forecast method advanced method, it is (main according to drift particle initial information first
It is wind field, flow field, the information such as stress condition and floating material material), the probability point of particle is obtained using monte carlo method
Cloth；Then the drift time Δ t for selecting particle, analyzes the stress condition and oneself state of the particle within the Δ t time, according to these
The drift velocity of information acquisition particle and direction can obtain the Δ t time if the drift time of particle is enough short
Interior drift path, the length of this Δ t can oneself setting Δ t is divided for n Δ t' if the time of Δ t is long,
Then it repeats the above process；It finally needs to determine at the end of each Δ t that more new particle initial information need to not be needed, obtains new
Then particle probabilities distribution map re-starts particle drift analysis.
In the case where drift velocity under known Nash Equilibrium state, it is easy to acquire drift path:Wherein when t=Δ t and Δ t sufficiently small, so that it may form t-y integral curve, this is bent
Line is exactly drift path.This method is possible the prediction of short-range drift path, but for drifting about for a long time
Prediction can generate very big error, and drift is divided into n sections total time by the present invention in response to this, then all to per a period of time
Particle is carried out to throw again, that is to say, that each period can more new particle initial probability distribution figure and at this time particle receive it is assorted equal
Weighing apparatus state can make drift path closer to time of day in this way:
WhereinWhen indicating n-th time, particle information new with new (n-1)th time relies on Nash Equilibrium shape later
The drift path that state stress condition and initial probability distribution figure obtain.
Particle throws simulation method algorithm again:
Input: drift particle initial information (including wind field, the information such as flow field and self attributes)；Drift time；
Output: drift path.
Step1: drift particle initial information is read in input, obtains particle initial probability distribution figure；
Step2: the input particle drift time analyzes particle drift state；
Step3: Nash Equilibrium processing is carried out to particle drift state；
Step4: judging whether particle is in Nash Equilibrium state, if it is execution Step5；Otherwise Step3 is executed；
Step5: judging whether to need to be split the particle drift time, if it is execution Step6；If not execution
Step9；
Step6: n parts will be divided into drift time, sequence carries out information update to the particle in these periods；
Step7: by the drift path Sequential output in every part of period；
Step8: judging whether the ageing of output is complete, if it is Step9 is executed, directly holds if being unsatisfactory for condition
Row Step10 terminates algorithm.
Step9: complete drift path is exported；
Step10: algorithm terminates.
Wherein particle information more new technological process:
Step1: drift particle initial information is read in input, obtains particle initial probability distribution figure；
Step2: the input particle drift time analyzes particle drift state；
Step3: Nash Equilibrium processing is carried out to particle drift state；
Step4: judging whether particle is in Nash Equilibrium state, if it is execution Step5；Otherwise Step3 is executed；
Step5: judging whether to need to be split the particle drift time, if it is execution Step6；If not execution
Step8；
Step6: n parts will be divided into drift time, sequence carries out information update to the particle in these periods；
Step7: by the drift path Sequential output in every part of period；
Step8: algorithm terminates.
The process that particle updates in fact is equivalent to the embedded circulation that particle throws method again, in order to realize drift time
Limitless defense right (according to the size of n in experiment, general cycle-index is no more than 5 times).Make the information update of particle so more
Refinement, so path prediction will be more accurate.
Method disclosed by the invention handles the Multiple factors for influencing ship drift using Nash Equilibrium, and further for the first time
It proposes that particle throws method again to generate drift path, total drift time is divided into n segment, in the drift for generating a segment
The new drifting state of horse back more new particle, new drift path is generated according to the particle information of new state, this makes after path
In entire Drift Process, information constantly updates, and error constantly reduces, so that the prediction of entire drift path becomes closer to
True drift path, to obtain good result.
(1) specific step is as follows for ship drift path prediction technique proposed by the invention:
Step 1: the factor bigger to ship drift effect to wind, stream, wave, turbulent flow and self attributes etc. receive assorted
Equilibrium treatment makes ship drift reach Nash Equilibrium state；
Step 2: the processed information of previous step Nash Equilibrium is inputted in three-dimensional visualization software Unity3D；
Step 3: obtaining drift object initial probability distribution figure using monte carlo method；
Step 4: seeking the drift velocity in Nash Equilibrium stateHere v refers to assorted equal in receiving
The drift velocity of the ship drift model of weighing apparatus state, a' are the acceleration in Nash Equilibrium state, v0For the initial speed of ship
Degree.
Step 5: being based on drift velocity, throw method again using particle in conjunction with drift time, in wind pressure disturbance and wind field flow field
Under disturbance, removes in wind pressure and flow field experiment because of error caused by experimental data and random error, calculate, ask by model
The 2D drift path of ship out；
Step 6: the 2D drift path of ship is converted to the drift orbit of 3D, more vivid display.
From above-mentioned steps as can be seen that proposed by the present invention handle influence factor with Nash Equilibrium method, fully consider
The influence that multiple influence factors drift about to ship, the decision that each factor reaches Nash Equilibrium, and makes can all make oneself
Influence to ship drift is optimal, and particle throws method again and very long drift is divided into n stage, thus very good solution
The problem of causing qualified rates of fitting to reduce because of drift time increase.
(2) analysis of simulation result
The effect of method is thrown again in order to verify Nash Equilibrium method proposed by the present invention and particle, has done two to having a competition
It tests.
Experiment 1 is that the influence factor for influencing ship drift is handled with vector splitting method, on this basis using Lagrange
Back tracking method, Monte Carlo forecast method, the method for throwing respectively obtains the drift orbit of ship to particle again, then compares each drift
Degree of fitting of the track with original drift path.Wherein, A line segment is original drift orbit, and B line segment is vector splitting method and particle weight
What throwing method combined, D line segment is that vector splitting method and Lagrangian back tracking method combine, and C line segment is vector splitting method and Meng Teka
The method that Lip river predicted method combines.2 are tested by Nash Equilibrium method and Lagrangian back tracking method, Monte Carlo forecast method, particle weight
Throwing method is respectively combined, and the influence factor for influencing ship drift is handled with Nash Equilibrium method, on this basis using on other kinds
Method respectively obtains the drift orbit of ship, for comparing effect of the Nash Equilibrium method on ship drift orbit.Wherein,
E line segment is original drift orbit, the method that F line segment Nash Equilibrium method and particle throw method combination again, G line segment Nash Equilibrium method and
The method that Lagrangian back tracking method combines, H line segment are the methods that Nash Equilibrium method and Monte Carlo forecast method combine.Experimental result
As shown in Fig. 2 and 3.
From experimental result picture it is found that the particle proposed by the present invention based on Nash Equilibrium throws method compared to its in experiment again
His five kinds of methods, not only drift orbit meets the stress rule of offshore drift but also is highest with the degree of fitting of original drift orbit
, so, method proposed by the present invention is to handle the relatively good method of ship drift model.
Claims (3)
1. a kind of particle based on Nash Equilibrium throws drift path prediction technique again, it is characterized in that:
(1) Nash Equilibrium processing is carried out to the factor for influencing ship drift, ship drift is made to reach Nash Equilibrium state, the shadow
The factor for ringing ship drift includes wind, stream, wave, turbulent flow and ship self attributes；
(2) the processed information of Nash Equilibrium for passing through step (1) is inputted in three-dimensional visualization software Unity3D；
(3) drift object initial probability distribution figure is obtained using monte carlo method；
(4) drift velocity in Nash Equilibrium state is soughtHere v is referred in Nash Equilibrium state
The drift velocity of ship drift model, a' are the acceleration in Nash Equilibrium state, v0For the initial velocity of ship；
(5) it is based on drift velocity, method is thrown again using particle in conjunction with drift time, is calculated by model, finds out the 2D drift of ship
Move path；
(6) the 2D drift path of ship is converted to the drift orbit of 3D, more vivid display.
2. the particle according to claim 1 based on Nash Equilibrium throws drift path prediction technique, it is characterized in that particle again
Method is thrown again to specifically include,
Input: drift particle initial information, drift time, drift particle initial information include that wind field, flow field and ship itself belong to
Property；
Output: drift path；
Step 5.1: drift particle initial information is read in input, obtains particle initial probability distribution figure；
Step 5.2: the input particle drift time analyzes particle drift state；
Step 5.3: Nash Equilibrium processing is carried out to particle drift state；
Step 5.4: judging whether particle is in Nash Equilibrium state, if it is execution step 5.5；It is no to then follow the steps 5.3；
Step 5.5: judging whether to need to be split the particle drift time, if it is execution step 5.6；If not execution
Step 5.9；
Step 5.6: n parts will be divided into drift time, information update sequentially is carried out to the particle in these periods；
Step 5.7: by the drift path Sequential output in every part of period；
Step 5.8: judging whether the ageing of output is complete, if it is step 5.9 is executed, directly held if being unsatisfactory for condition
Row step 5.10；
Step 5.9: exporting complete drift path；
Step 5.10: algorithm terminates.
3. the particle according to claim 2 based on Nash Equilibrium throws drift path prediction technique again, it is characterized in that by
During model calculates, the drift final mask for the object that drifts about:Wherein ε
It is wind pressure disturbance and flow field wind disturbance and t1,t2...,tnWhat is represented is the drift time to be divided into n parts,Indicate the
When n time, particle is after having updated information new in (n-1)th time by Nash Equilibrium state stress condition and initial
The drift path that probability distribution graph obtains.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2018103186231 | 2018-04-11 | ||
| CN201810318623 | 2018-04-11 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108984820A true CN108984820A (en) | 2018-12-11 |
Family
ID=64542644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810509493.XA Pending CN108984820A (en) | 2018-04-11 | 2018-05-24 | A kind of particle based on Nash Equilibrium throws drift path prediction technique again |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108984820A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111159924A (en) * | 2020-04-02 | 2020-05-15 | 上海彩虹鱼海洋科技股份有限公司 | Method and apparatus for predicting drift trajectory |
| CN111914462A (en) * | 2020-07-22 | 2020-11-10 | 中国地质大学深圳研究院 | Method and device for predicting target drift of maritime search and rescue |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009085610A (en) * | 2007-09-27 | 2009-04-23 | Oki Electric Ind Co Ltd | Method and device for analyzing motion of target object |
| CN102221448A (en) * | 2011-05-20 | 2011-10-19 | 大连海事大学 | Method and system for determining maritime SAR (search and rescue) region, and SAR simulator |
| CN106204706A (en) * | 2016-07-07 | 2016-12-07 | 哈尔滨工程大学 | A kind of sea three-dimension visible sysem of drift model |
-
2018
- 2018-05-24 CN CN201810509493.XA patent/CN108984820A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009085610A (en) * | 2007-09-27 | 2009-04-23 | Oki Electric Ind Co Ltd | Method and device for analyzing motion of target object |
| CN102221448A (en) * | 2011-05-20 | 2011-10-19 | 大连海事大学 | Method and system for determining maritime SAR (search and rescue) region, and SAR simulator |
| CN106204706A (en) * | 2016-07-07 | 2016-12-07 | 哈尔滨工程大学 | A kind of sea three-dimension visible sysem of drift model |
Non-Patent Citations (2)
| Title |
|---|
| 余谦 等: "《基于粒子群优化求解纳什均衡的演化算法》", 《武汉大学学报（理学版）》 * |
| 刘海峥 等: "《基于Monte Carlo方法的搜救区域预测算法》", 《船海工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111159924A (en) * | 2020-04-02 | 2020-05-15 | 上海彩虹鱼海洋科技股份有限公司 | Method and apparatus for predicting drift trajectory |
| CN111914462A (en) * | 2020-07-22 | 2020-11-10 | 中国地质大学深圳研究院 | Method and device for predicting target drift of maritime search and rescue |
| CN111914462B (en) * | 2020-07-22 | 2021-05-14 | 中国地质大学深圳研究院 | Method and device for predicting target drift of maritime search and rescue |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110703752B (en) | Unmanned ship double-layer path planning method based on immune heredity-artificial potential field method | |
| Lawrance et al. | Autonomous exploration of a wind field with a gliding aircraft | |
| CN108764298B (en) | Electric power image environment influence identification method based on single classifier | |
| CN108416152A (en) | The optimal global path planning method of unmanned boat ant colony energy consumption based on electronic chart | |
| CN110222769A (en) | A kind of Further aim detection method based on YOLOV3-tiny | |
| CN102221448B (en) | Method and system for determining maritime SAR (search and rescue) region, and SAR simulator | |
| CN110472738A (en) | A kind of unmanned boat Real Time Obstacle Avoiding algorithm based on deeply study | |
| CN110209152A (en) | The deeply learning control method that Intelligent Underwater Robot vertical plane path follows | |
| CN113190037A (en) | Unmanned aerial vehicle optimal path searching method based on improved fluid disturbance and sparrow algorithm | |
| CN108984820A (en) | A kind of particle based on Nash Equilibrium throws drift path prediction technique again | |
| Cai et al. | A meta-heuristic assisted underwater glider path planning method | |
| CN108909964A (en) | A kind of ship stabilization controller method for handover control to navigate under state more | |
| Zhou et al. | LSSVM and hybrid particle swarm optimization for ship motion prediction | |
| CN115657689A (en) | Autonomous underwater vehicle target tracking control method based on track prediction | |
| Zhang et al. | A path planning method for the autonomous ship in restricted bridge area based on anisotropic fast marching algorithm | |
| CN107194155A (en) | A kind of threat assessment modeling method based on small data set and Bayesian network | |
| CN107219525A (en) | SAR seas emulation mode and device | |
| CN114330828A (en) | Method for forecasting movement rest period of ship | |
| CN104360306B (en) | A kind of target boats and ships direction estimation method based on differential evolution mechanism | |
| Wu et al. | Efficient Identification of water conveyance tunnels siltation based on ensemble deep learning | |
| Bandyopadhyay | Swimming and flying in nature—The route toward applications: The Freeman scholar lecture | |
| CN107621637A (en) | Slipped region Wind-field Retrieval method based on single-Doppler radar | |
| CN104122530B (en) | A kind of shell target identification method based on normal radar | |
| Wang et al. | Multi-step Prediction AR Model of Ship Motion Based On Constructing and Correcting Error | |
| CN109002860B (en) | Intelligent adaptive matching prediction method for sudden change wind speed along high-speed railway |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181211 |
|
| RJ01 | Rejection of invention patent application after publication |