CN116678409B - North polar ice area ship path planning method based on improved wolf algorithm - Google Patents
North polar ice area ship path planning method based on improved wolf algorithm Download PDFInfo
- Publication number
- CN116678409B CN116678409B CN202310448494.9A CN202310448494A CN116678409B CN 116678409 B CN116678409 B CN 116678409B CN 202310448494 A CN202310448494 A CN 202310448494A CN 116678409 B CN116678409 B CN 116678409B
- Authority
- CN
- China
- Prior art keywords
- wolf
- position information
- wolves
- value
- ship
- 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.)
- Active
Links
- 241000282461 Canis lupus Species 0.000 title claims abstract description 116
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000000739 chaotic effect Effects 0.000 claims abstract description 12
- 238000013507 mapping Methods 0.000 claims abstract description 8
- 241000282421 Canidae Species 0.000 claims description 46
- 238000005295 random walk Methods 0.000 claims description 15
- 230000007246 mechanism Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 abstract description 18
- 230000000694 effects Effects 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 14
- 238000005457 optimization Methods 0.000 description 8
- 239000013598 vector Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000002068 genetic effect Effects 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000011160 research Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 230000013016 learning Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002028 premature Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000009326 social learning Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/203—Specially adapted for sailing ships
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a north pole ice region ship path planning method based on an improved gray wolf algorithm, which comprises the steps of obtaining a ship type, a navigation area and sea ice data of the navigation area, carrying out rasterization on the navigation area, and establishing a ship navigation objective function; constructing a wolf algorithm model, initializing position information of a wolf population through Tent chaotic mapping, updating the position information of the wolf population through hunting behaviors and predation behaviors, calculating the value of an objective function according to the position information, judging whether the value of the objective function meets a threshold or whether the current iteration number is equal to the maximum iteration number, acquiring the position information of the wolf population as a path of a ship if the current iteration number is equal to the threshold, otherwise optimizing the position information of the wolf population, and recalculating the value of the objective function according to the optimized position information. The invention ensures that the planned path is better, and improves the efficiency, the convergence speed and the obstacle avoidance effect of the path planning of the ship in the ice area.
Description
Technical Field
The invention relates to the technical field of arctic ice region ship path planning, in particular to an arctic ice region ship path planning method based on an improved gray wolf algorithm.
Background
In recent years, as global climate gradually warms, the area of arctic sea ice is reduced year by year, and the ship realizes commercial navigation in arctic ice areas, but due to the influence of complex ice conditions, the ship is easy to collide, ice is trapped and other accidents caused by sea ice invasion in the navigation process. The arctic navigation ships are mostly PC 7-level ships, so that the navigation practice and the navigation safety are considered, a scientifically planned ice area route is required to be generated and integrated in the ships, and navigation is carried out on the navigation process of the PC 7-level ships according to the integrated ice area route. Conventional route (path) planning algorithms include Genetic (GA) algorithms, fast extended random tree (RRT) algorithms, artificial potential field methods (APF), a-algorithms, and the like. Wherein: the GA algorithm has the problems of low searching efficiency, easy generation of premature convergence and the like when applied to the problem of path planning; the APF method has the problems of easy sinking into local optimum, difficult processing of gravitation function and repulsive force, and the like; the RRT algorithm has the problems of slow speed in the later search period, low search efficiency and the like; the algorithm A has the problems of more search points, large search range, low efficiency and the like.
Many intelligent optimization algorithms such as Particle Swarm Optimization (PSO), ant swarm optimization (ACO), and the Grey wolf algorithm (GWO) are currently applied to the path planning problem, and the effect is superior to that of the traditional path planning algorithm. The GWO algorithm has the advantages of high search instantaneity and high search capability, but is easy to fall into local optimum, and can jump out of the local optimum solution without any measure, so that the distribution of the path nodes is not diversified, and an ideal path planning effect is often not achieved.
Disclosure of Invention
The invention provides a arctic ice region ship path planning method based on an improved gray wolf algorithm, which aims to overcome the technical problems.
A arctic ice region ship path planning method based on an improved wolf algorithm comprises the following steps of,
step one, acquiring sea ice data of a ship type, a sailing area and the sailing area, carrying out rasterization processing on the sailing area, calculating a risk index of each grid through a polar operation limit assessment risk index system and the sea ice data of the sailing area, marking whether the area where the grid is positioned can be sailed according to the value of the risk index of the grid, establishing an objective function of ship sailing according to the marked sailing area,
step two, constructing a wolf algorithm model, setting the maximum iteration times, initializing the position information of the wolf population through Tent chaotic mapping, calculating the fitness value of the wolf population according to the position information, carrying out descending sequencing on the fitness value to obtain three wolves serving as head wolves in the first three sequences,
step three, when the current iteration times are smaller than the maximum iteration times, the wolf group updates the position information through the hunting behavior and the predation behavior, calculates the fitness value of the wolf group according to the updated position information, updates the parameters required by the hunting behavior and the predation behavior,
step four, calculating the fitness value of the head wolves according to the fitness value of the wolf clusters, judging whether the fitness value of the head wolves changes, if so, increasing the current iteration times by 1, entering step five, if not, optimizing the position information of the wolf clusters, calculating the fitness value according to the optimized position information, re-calculating the fitness value of the head wolves, judging whether the fitness value of the head wolves changes,
and fifthly, calculating the value of the objective function according to the fitness value of the wolf clusters, stopping iteration when the value of the objective function meets a threshold value or the current iteration number is equal to the maximum iteration number, taking the position information of the wolf clusters as the path of the ship, and otherwise, returning to the step three.
Preferably, the calculating the risk index of each grid by polar operating the limit assessment risk index system and sea ice data of the voyage area includes calculating the risk index according to formula (1),
wherein z is the type of sea ice, D Z Is the concentration of the z-type ice; RIVs z Is the risk index value for class z ice.
Preferably, the initializing the position information of the wolf population through the Tent chaotic map comprises obtaining the initial position information of the wolf population according to a formula (2),
wherein,the number of the wolves is K, the number of the wolves is I is the current iteration number, and the number of the wolves is>Respectively->Maximum and minimum of columns, wherein +.>Obtained according to the formula (3),
wherein u is a random number in the [0,1] interval.
Preferably, the optimizing the position information of the wolf group comprises generating a random step length according to the Lewy flight strategy to globally optimize the position information of the wolf group, or locally optimize the position information of the wolf group according to the random walk strategy and a greedy mechanism.
Preferably, the generating random step sizes according to the Lewy flight strategy to globally optimize the position information of the wolf group comprises generating random step sizes according to formulas (4) and (5), globally optimizing the position information of all the wolf individuals in the wolf group according to formulas (6) and (7),
wherein s is a random step size, mu and v are both subjected to normal distribution,σ v =1, Γ is a gamma function, ψ is a random value in the (0, 2) interval, R is a random quantity, aε [ -1, 1)]As a proportion of molecules, Q b For the global optimal solution of the current iteration, +.>Is the position information of the ith gray wolf at the t-th iteration.
Preferably, the local optimization of the position information of the wolf clusters according to the random walk strategy and the greedy mechanism comprises generating new position information Q 'of the ith wolf only according to a formula (8)' i (t) and judging whether to take the new position information as the position information of the ith gray wolf according to the formula (9),
wherein Q is j (t) and Q k (t) is the position information of the j-th and k-th wolves in the t-th iteration;is a scaling factor->fit is a greedy function.
The invention provides a north pole ice region ship path planning method based on an improved wolf algorithm, which enables the wolf algorithm to avoid a local optimal solution in operation through Tent chaotic mapping, thereby maintaining population diversity and improving global searching capability; and a Levy flight stagnation disturbance strategy and a random walk strategy are adopted, global searching and local optimizing capability are respectively enhanced, a greedy mechanism is added to keep a solution with better fitness, a planned path is finally made to be better, and the efficiency, convergence speed and obstacle avoidance effect of ship path planning are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it will be obvious that the drawings in the following description are some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a view of the north latitude 74.86 sea area of the present invention;
FIG. 3 is a grid view of the present invention for a north latitude 74.86 sea area;
FIG. 4 is a 72.05 North latitude sea area diagram of the present invention;
FIG. 5 is a grid view of a 72.05 North latitude sea area of the present invention;
FIG. 6 is a diagram of the results of the sea area 1 path planning of the present invention;
FIG. 7 is a chart of the optimal planned path length for sea area 1 of the present invention;
FIG. 8 is a diagram of the results of the sea area 2 path planning of the present invention;
fig. 9 is a diagram of the optimal planned path length for sea area 2 of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
FIG. 1 is a flowchart of the method of the present invention, as shown in FIG. 1, the method of the present embodiment may include:
step one, acquiring sea ice data of a ship type, a sailing area and the sailing area, carrying out rasterization processing on the sailing area, calculating a risk index of each grid through a polar operation limit assessment risk index system and the sea ice data of the sailing area, marking whether the area where the grid is positioned can be sailed according to the value of the risk index of the grid, establishing an objective function of ship sailing according to the marked sailing area,
step two, constructing a wolf algorithm model, setting the maximum iteration times, initializing the position information of the wolf population through Tent chaotic mapping, calculating the fitness value of the wolf population according to the position information, carrying out descending sequencing on the fitness value to obtain three wolves serving as head wolves in the first three sequences,
step three, when the current iteration times are smaller than the maximum iteration times, the wolf group updates the position information through the hunting behavior and the predation behavior, calculates the fitness value of the wolf group according to the updated position information, updates the parameters required by the hunting behavior and the predation behavior,
step four, calculating the fitness value of the head wolves according to the fitness value of the wolf clusters, judging whether the fitness value of the head wolves changes, if so, increasing the current iteration times by 1, entering step five, if not, optimizing the position information of the wolf clusters, calculating the fitness value according to the optimized position information, re-calculating the fitness value of the head wolves, judging whether the fitness value of the head wolves changes,
and fifthly, calculating the value of the objective function according to the fitness value of the wolf clusters, stopping iteration when the value of the objective function meets a threshold value or the current iteration number is equal to the maximum iteration number, taking the position information of the wolf clusters as the path of the ship, and otherwise, returning to the step three.
Based on the scheme, the Tent chaotic mapping is adopted to enable the gray wolf algorithm to avoid a local optimal solution in operation, so that the diversity of the population is maintained, and the global searching capability is improved; and a Levy flight stagnation disturbance strategy and a random walk strategy are adopted, global searching and local optimizing capability are respectively enhanced, a greedy mechanism is added to keep a solution with better fitness, a planned path is finally made to be better, and the efficiency, convergence speed and obstacle avoidance effect of ship path planning are improved.
Step one, acquiring sea ice data of a ship type, a sailing area and the sailing area, carrying out rasterization processing on the sailing area, calculating a risk index of each grid through a polar operation limit assessment risk index system and the sea ice data of the sailing area, marking whether the area where the grid is positioned can be sailed according to the value of the grid risk index, establishing an objective function of ship sailing according to the marked sailing area,
specifically, the polar operation limit assessment risk index system (Polar Operational Limit Assessment Risk Indexing System, POLARIS) is a system proposed by the International Maritime Organization (IMO) and adopted by the chinese classification society as a reference for ice navigation and ship operation. The system provides a quantization model aiming at ship ice navigation risk: by using ice condition data, combining the ice level of the ship and different growth stages (ice thickness and ice age) of each type of ice in a sailing water area, defining ship sailing risk index values (Risk Index Values, RIVs), and calculating risk index results (Risk Index Outcome, RIO) according to the corresponding RIVs and the densities of the corresponding types of ice, wherein the risk index results are used for evaluating the ship sailing risk in the ice area.
POLARIS uses an equivalent combination of polar ice level from international classification society (International Association ofClassification Societies, IACS) and ice level rules in swedish, finland. IACS specifies a sea ice specific term for ice comprising 7 polar ship ice grades from PC1-PC7, describing ice conditions in world meteorological organization (World Meteorological Organization, WMO). POLARIS calculates and determines ship navigation RIO based on RIVs and sea ice density information provided by ice types at different growth stages in different ice level ship navigation waters. The larger the RIO value, the lighter the ice conditions in the selected sea area, and the smaller the risk of vessel navigation.
The calculating the risk index of each grid by polar operating limit assessment risk index system and sea ice data of the voyage area includes calculating the risk index according to formula (1),
wherein z is the type of sea ice, D Z Is the concentration of the z-type ice; RIVs z Is the risk index value for class z ice.
In recent years, since north pole navigation ships are mostly PC 7-class ships, route planning research is performed on PC 7-class ships in consideration of navigation practice. The table of sea ice growth stage and sea ice thickness is shown in table 1, and the table of sea ice type and PC7 ice-level ship RIVs value is shown in table 2.
TABLE 1 sea ice growth stage versus sea ice thickness correspondence table
TABLE 2 sea ice type and PC7 ice level Ship RIVs value correspondence table
And constructing a grid environment according to North sea ice data provided by the Goinby website (www.copernicus.eu), carrying out path planning research on the IA-class ship by combining POLARIS, and carrying out RIO calculation by selecting the North latitude 74.86 degree sea area of 2022, 6 months and 30 days of the karla sea as a first sea area (shown in figure 2) and the North latitude 72.05 degree sea area as a second sea area (shown in figure 3) in consideration of sailing practice. If RIO > =0, determine that the area is navigable, as a blank grid; if RIO <0, it is determined that the area is not navigable, defined as an obstacle, as a black grid. The first sea area after rasterization is shown in fig. 4, and the second sea area after rasterization is shown in fig. 5.
Step two, constructing a wolf algorithm model, and initializing parameters of the wolf algorithm, wherein the parameters comprise the number m of the wolf population and the maximum iteration number I M Initializing the position information of the wolf population through the Tent chaotic map according to the fitness values of alpha, beta and theta of the wolf individuals, wherein the initializing the position information of the wolf population through the Tent chaotic map comprises obtaining the initial position information of the wolf population according to a formula (2),
wherein,the number of the wolves is K, the number of the wolves is I is the current iteration number, and the number of the wolves is>Respectively->Maximum and minimum of columns, wherein +.>Obtained according to the formula (3),
wherein u is a random number in the [0,1] interval.
Calculating the fitness value of the wolf group according to the position information, carrying out descending sequencing on the fitness value, obtaining three wolves in the front three of the sequences as head wolves, respectively representing alpha, beta and theta, and recording the position information as Q α ，Q β ，Q θ ；
Step three, when the current iteration number is smaller than the maximum iteration number, updating position information of the wolf group through hunting behaviors and predation behaviors, calculating fitness values of the wolf group according to the updated position information, and updating parameters required by the hunting behaviors and predation behaviors, wherein the parameters comprise coefficient vectorsAnd a decay factor b, specifically, a Hunting behavior of the Hunting wolf group by the formulas (4), (5),
wherein t is the iteration number,representing the distance vector between the individual gray wolf and the prey,/->Representing the current prey location vector,/->Representing individual gray wolf position vectors, +.>And->Is a coefficient vector, defined according to formulas (6), (7):
where the attenuation factor b decreases linearly from 2 to 0 as t increases, b=2-2 (t×maxt), max t For the maximum number of iterations to be performed,and->Is [0,1]Random vector between.
The predation behavior of the wolf group is implemented through formulas (8) and (9), and the final position of the wolf is obtained according to formula (10),
in the method, in the process of the invention,respectively represent three head wolves in the wolf groupIs a position of (2); />Respectively represent the advancing direction and the advancing step length of the wolf omega to the three head wolves.
And step four, calculating the fitness value of the head wolves according to the fitness value of the wolves, judging whether the fitness value of the head wolves changes, if so, increasing the current iteration times by 1, entering step five, and if not, optimizing the position information of the wolves, wherein the optimizing the position information of the wolves comprises global optimization of the position information of the wolves according to random step length generated according to a Lewy flight strategy, or local optimization of the position information of the wolves according to a random walk strategy and a greedy mechanism.
Levy flight is a walking mode with alternate long and short distance searching, and is characterized in that small step length time random walk, occasional large step length abrupt jump and good global searching capability. When the Levy flight strategy is used for global detection, wolves are widely distributed in the search space, and the global optimizing capability is good. The generation of random step length according to the Lewy flight strategy to globally optimize the position information of the wolf group comprises the generation of random step length according to formulas (11) and (12), the global optimization of the position information of all the wolf individuals in the wolf group according to formulas (13) and (14),
wherein s is a random step size, mu and v are both subjected to normal distribution,σ v =1, Γ is a gamma function, ψ is a random value in the (0, 2) interval, R is a random quantity, aε [ -1, 1)]As a proportion of molecules, Q b For the global optimal solution of the current iteration, +.>Is the position information of the ith gray wolf at the t-th iteration.
The random walk generates a new solution by utilizing the mixed variation and the cross strategy, so that population diversity is enhanced, the local searching capability of an algorithm is improved, and the optimizing speed can be increased by applying the random walk to the gray wolf algorithm. The random walk strategy enables the wolf clusters to search in the concentrated area, and the local optimizing capability is greatly improved. And comparing the adaptability of the new solution and the original solution by using a greedy mechanism, and reserving the solution with better adaptability. The local optimization of the position information of the wolf clusters according to the random walk strategy and the greedy mechanism comprises the generation of the new position information Q 'of the ith wolf according to the formula (15)' i (t) and judging whether to take the new position information as the position information of the ith gray wolf according to the formula (16),
wherein Q is j (t) and Q k (t) is the position information of the j-th and k-th wolves in the t-th iteration;is a scaling factor->fit is a greedy function.
Calculating fitness value according to the optimized position information, re-calculating the fitness value of the head wolf and judging whether the fitness value of the head wolf changes or not,
and fifthly, calculating the value of the objective function according to the fitness value of the wolf clusters, stopping iteration when the value of the objective function meets a threshold value or the current iteration number is equal to the maximum iteration number, taking the position information of the wolf clusters as the path of the ship, and otherwise, returning to the step three.
The process of improving the wolf algorithm in this embodiment includes:
step1: initializing parameters of the wolf algorithm, including the number m of the wolf population and the maximum iteration number I M The fitness value of alpha, beta and theta of the individual gray wolves;
step2: performing Tent chaotic mapping treatment on the initial population, calculating the fitness value of the individual gray wolves, and screening and sorting;
step3: screening out alpha, beta and theta of the single gray wolf with the first three fitness values, and recording the position information as Q α ，Q β ，Q θ ；
Step4: wolves enter hunting behavior and initialize H, N respectively; H. n is a coefficient vector defined as follows:
step5: the current iteration times do not reach the maximum iteration times, and the wolves enter predation behaviors to update position information;
step6: updating parameters b, H and N; calculating corresponding fitness values, judging whether the alpha wolf fitness values and the beta wolf fitness values are updated or not, and adding 1 to the iteration times;
step7: when the fitness value is unchanged in the multiple iteration processes, performing global and local optimizing processing by using the Laiwei flight stagnation disturbance and the random walk strategy;
step8: the maximum iteration times are reached, the circulation is stopped, and the optimal solution Q is output; otherwise, loop execution Step4-Step7 is returned until the best path is found.
To verify the feasibility and superiority of the improved gray wolf algorithm in ice area path planning, a grid map of 30×30 of two sea areas is constructed by using POLARIS and ice area sea ice dataThe two sea areas are respectively a sea area 1 with north latitude of 74.86 degrees and a sea area 2 with north latitude of 72.05 degrees in 6 months and 30 days in 2022 of karla sea, and a Gray Wolf (GWO) algorithm, a Genetic (GA) algorithm and a Particle Swarm (PSO) algorithm are compared and analyzed with an improved GWO algorithm. The specific parameters for the test are as follows: the population individual number is 50, the maximum iteration number is 50, and the crossover probability P in the genetic algorithm 1 =0.9, probability of variation P 2 =0.1; inertia weight w=0.9 and individual learning factor C in particle swarm algorithm 1 =1.2, social learning factor C 2 ＝1.2。
The path planning result of the sea area 1 is shown in fig. 6, the optimal planning path length of the four algorithms is shown in fig. 7, the comparison data of the four algorithms of the sea area 1 is shown in table 3, the path planning result of the sea area 2 is shown in fig. 8, the optimal planning path length of the four algorithms is shown in fig. 9, and the comparison data of the four algorithms of the sea area 2 is shown in table 4.
Table 3 sea area 1 four algorithms comparison data
| Algorithm | Optimal Path Length/nmile | Run time/s | Number of inflection points |
| GA | 44.5269 | 6.5741 | 19 |
| PSO | 44.5269 | 4.1594 | 19 |
| GWO | 42.7696 | 3.6658 | 9 |
| IGWO | 42.1838 | 1.7405 | 6 |
Table 4 sea area 2 four algorithms comparison data
As can be seen from the planned path results and the table data, compared with the GA algorithm, the GWO algorithm and the PSO algorithm, the IGWO algorithm provided by the invention has the following advantages in path planning: the final planned path length and directivity are better; the running time is greatly shortened, the inflection point of the path is few, and the path is smoother; the algorithm is easier to avoid sinking into local optimum to obtain global optimum after being integrated with the Levy flight strategy, the random walk strategy and the greedy strategy.
The whole beneficial effects are that:
the invention provides a north pole ice region ship path planning method based on an improved wolf algorithm, which enables the wolf algorithm to avoid a local optimal solution in operation through Tent chaotic mapping, thereby maintaining population diversity and improving global searching capability; and a Levy flight stagnation disturbance strategy and a random walk strategy are adopted, global searching and local optimizing capability are respectively enhanced, a greedy mechanism is added to keep a solution with better fitness, a planned path is finally made to be better, and the efficiency, convergence speed and obstacle avoidance effect of ship path planning are improved.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (5)
1. A arctic ice region ship path planning method based on an improved wolf algorithm is characterized by comprising the following steps of,
step one, acquiring sea ice data of a ship type, a sailing area and the sailing area, carrying out rasterization processing on the sailing area, calculating a risk index of each grid through a polar operation limit assessment risk index system and the sea ice data of the sailing area, calculating the risk index of each grid through the polar operation limit assessment risk index system and the sea ice data of the sailing area comprises calculating the risk index according to a formula (1),
wherein z is the type of sea ice, D Z Is the concentration of the z-type ice; RIVs z Is the risk index value for class z ice,
marking whether the area where the grid is positioned can navigate according to the value of the risk index of the grid, establishing an objective function of ship navigation according to the marked navigation area,
step two, constructing a wolf algorithm model, setting the maximum iteration times, initializing the position information of the wolf population through Tent chaotic mapping, calculating the fitness value of the wolf population according to the position information, carrying out descending sequencing on the fitness value to obtain three wolves serving as head wolves in the first three sequences,
step three, when the current iteration times are smaller than the maximum iteration times, the wolf group updates the position information through the hunting behavior and the predation behavior, calculates the fitness value of the wolf group according to the updated position information, updates the parameters required by the hunting behavior and the predation behavior,
step four, calculating the fitness value of the head wolves according to the fitness value of the wolf clusters, judging whether the fitness value of the head wolves changes, if so, increasing the current iteration times by 1, entering step five, if not, optimizing the position information of the wolf clusters, calculating the fitness value according to the optimized position information, re-calculating the fitness value of the head wolves, judging whether the fitness value of the head wolves changes,
and fifthly, calculating the value of the objective function according to the fitness value of the wolf clusters, stopping iteration when the value of the objective function meets a threshold value or the current iteration number is equal to the maximum iteration number, taking the position information of the wolf clusters as the path of the ship, and otherwise, returning to the step three.
2. The arctic-region ship path planning method based on the improved wolf algorithm of claim 1, wherein the initializing the position information of the wolf population through the Tent chaotic map comprises obtaining the initial position information of the wolf population according to a formula (2),
wherein,the number of the wolves is K, the number of the wolves is I is the current iteration number, and the number of the wolves is>Respectively->Maximum and minimum of columns, wherein +.>Obtained according to the formula (3),
wherein u is a random number in the [0,1] interval.
3. The arctic-region ship path planning method based on the improved wolf algorithm according to claim 1, wherein the optimizing the position information of the wolf group comprises global optimizing the position information of the wolf group by generating random step sizes according to a Lewy flight strategy or local optimizing the position information of the wolf group according to a random walk strategy and a greedy mechanism.
4. A arctic-region ship path planning method based on an improved wolf algorithm according to claim 3, wherein the generating random step sizes according to the Lewy flight strategy to globally optimize the position information of the wolf population comprises generating random step sizes according to formulas (4) and (5), globally optimizing the position information of all the wolf individuals in the wolf population according to formulas (6) and (7),
wherein s is a random step size, mu and v are both subjected to normal distribution,σ v =1, Γ is a gamma function, ψ is a random value in the (0, 2) interval, R is a random quantity, aε [ -1, 1)]As a proportion of molecules, Q b For the global optimal solution of the current iteration, +.>Is the position information of the ith gray wolf at the t-th iteration.
5. A arctic-region ship path planning method based on an improved wolf algorithm according to claim 3, wherein the locally optimizing the position information of the wolf clusters according to the random walk strategy and the greedy mechanism comprises generating new position information Q 'of the ith wolf according to formula (8)' i (t) and judging whether to take the new position information as the position information of the ith gray wolf according to the formula (9),
wherein Q is j (t) and Q k (t) is the position information of the j-th and k-th wolves in the t-th iteration;is a zoomFactor (F)>fit is a greedy function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310448494.9A CN116678409B (en) | 2023-04-24 | 2023-04-24 | North polar ice area ship path planning method based on improved wolf algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310448494.9A CN116678409B (en) | 2023-04-24 | 2023-04-24 | North polar ice area ship path planning method based on improved wolf algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116678409A CN116678409A (en) | 2023-09-01 |
| CN116678409B true CN116678409B (en) | 2024-03-12 |
Family
ID=87782565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310448494.9A Active CN116678409B (en) | 2023-04-24 | 2023-04-24 | North polar ice area ship path planning method based on improved wolf algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116678409B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794526A (en) * | 2015-05-13 | 2015-07-22 | 哈尔滨工程大学 | Automatic ship anti-collision method optimized by wolf colony search algorithm |
| WO2021022637A1 (en) * | 2019-08-06 | 2021-02-11 | 南京赛沃夫海洋科技有限公司 | Unmanned surface vehicle path planning method and system based on improved genetic algorithm |
| WO2021035911A1 (en) * | 2019-08-28 | 2021-03-04 | 青岛蓝海未来海洋科技有限责任公司 | Method and system for planning path of unmanned surface vehicle based on forward/reverse data-driven linear parameter-varying genetic algorithm |
| CN115469673A (en) * | 2022-11-02 | 2022-12-13 | 中国人民解放军陆军装甲兵学院 | Unmanned vehicle route planning method based on air-ground information cooperation |
| CN115550837A (en) * | 2022-09-22 | 2022-12-30 | 合肥工业大学 | DV-Hop positioning method based on chaos mapping and Husky algorithm optimization |
-
2023
- 2023-04-24 CN CN202310448494.9A patent/CN116678409B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794526A (en) * | 2015-05-13 | 2015-07-22 | 哈尔滨工程大学 | Automatic ship anti-collision method optimized by wolf colony search algorithm |
| WO2021022637A1 (en) * | 2019-08-06 | 2021-02-11 | 南京赛沃夫海洋科技有限公司 | Unmanned surface vehicle path planning method and system based on improved genetic algorithm |
| WO2021035911A1 (en) * | 2019-08-28 | 2021-03-04 | 青岛蓝海未来海洋科技有限责任公司 | Method and system for planning path of unmanned surface vehicle based on forward/reverse data-driven linear parameter-varying genetic algorithm |
| CN115550837A (en) * | 2022-09-22 | 2022-12-30 | 合肥工业大学 | DV-Hop positioning method based on chaos mapping and Husky algorithm optimization |
| CN115469673A (en) * | 2022-11-02 | 2022-12-13 | 中国人民解放军陆军装甲兵学院 | Unmanned vehicle route planning method based on air-ground information cooperation |
Non-Patent Citations (3)
| Title |
|---|
| Application of improved RRT algorithm in unmanned surface vehicle pathplanning;Yutong Lin 等;2022 34th Chinese Control and Decision Conference (CCDC);全文 * |
| 基于改进蚁群算法的船舶冰区航行路径规划;童帮裕等;中国航海;24-28 * |
| 混沌狼群围捕算法的车间机器人导航路径规划;周璟;机械设计与制造;251-255 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116678409A (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111176807A (en) | Multi-satellite cooperative task planning method | |
| CN110926477A (en) | Unmanned aerial vehicle route planning and obstacle avoidance method | |
| CN111199103B (en) | Full-flow automatic calculation navigational speed optimization method and system for full-electric propulsion ship | |
| CN107273912A (en) | A kind of Active Learning Method based on three decision theories | |
| CN113238232B (en) | Target searching method of autonomous underwater vehicle system for ocean static target | |
| CN111562786B (en) | Multi-stage optimized unmanned ship path planning method and device | |
| CN115063676A (en) | Ship target classification method based on AIS data | |
| CN112733251B (en) | Collaborative flight path planning method for multiple unmanned aerial vehicles | |
| CN113204417A (en) | Multi-satellite multi-point target observation task planning method based on improved genetic and firefly combined algorithm | |
| CN111612217A (en) | Improved GA-SA path planning method for water surface unmanned ship for offshore wind farm inspection | |
| Bai et al. | USV path planning algorithm based on plant growth | |
| CN111476082A (en) | Method and device for online batch normalization, online learning and continuous learning | |
| CN114819143A (en) | Model compression method suitable for communication network field maintenance | |
| CN117975128A (en) | Yolov5x forest fire identification method and system based on diffusion model | |
| CN116678409B (en) | North polar ice area ship path planning method based on improved wolf algorithm | |
| CN111639695A (en) | Method and system for classifying data based on improved drosophila optimization algorithm | |
| CN109976158B (en) | AUV energy optimization path searching method based on distance evolution N-PSO | |
| Azarbad et al. | Brain tissue segmentation using an unsupervised clustering technique based on PSO algorithm | |
| CN117806346A (en) | Unmanned plane path planning method based on self-adaptive dung beetle optimizer | |
| CN115542912B (en) | Mobile robot path planning method based on improved Q-learning algorithm | |
| CN114840016B (en) | Multi-ant colony search submarine target cooperative path optimization method based on rule heuristic method | |
| Qin et al. | U_EFF_NET: High-precision segmentation of offshore farms from high-resolution SAR remote sensing images | |
| CN113589810A (en) | Intelligent dynamic autonomous obstacle avoidance movement method and device, server and storage medium | |
| Thoma et al. | Potential of hybrid neural network local path planner for small UAV in urban environments | |
| CN105160436A (en) | N neighboring Lipschitz supporting surface-based generalized augmented group global optimization method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |