CN-121998302-A - Maritime search and rescue resource scheduling method based on improved A-Star algorithm

CN121998302ACN 121998302 ACN121998302 ACN 121998302ACN-121998302-A

Abstract

The invention provides a maritime search and rescue resource scheduling method based on an improved A-Star algorithm, which comprises the following steps of 1, collecting related data of a maritime search and rescue target area, 2, rasterizing the maritime search and rescue target area to obtain nodes and node data, 3, generating a search and rescue route by adopting the improved A-Star algorithm according to the nodes and the node data, and issuing in real time, and 4, updating the related data of the maritime search and rescue target area according to a preset period, re-executing the step 3, and updating the search and rescue route.

Inventors

SUN RUI
HE YULIN
SHANG RUI
ZHOU YI
YE HONGJUN
PAN YUANJIN
TANG XU
Pang Bobo

Assignees

南京航空航天大学

Dates

Publication Date: 20260508
Application Date: 20251226

Claims (10)

1. The maritime search and rescue resource scheduling method based on the improved A-Star algorithm is characterized by comprising the following steps of: step 1, collecting relevant data of a maritime search and rescue target area; Step 2, rasterizing the target area for maritime search and rescue to obtain nodes and node data; Step 3, generating a search and rescue route by adopting an improved A-Star algorithm according to the nodes and the node data, and issuing in real time; and step 4, updating the relevant data of the maritime search and rescue target area according to a preset period, and re-executing the step 3 to update the search and rescue route.
2. The method for scheduling maritime search and rescue resources based on the improved a-Star algorithm according to claim 1, wherein the step 1 of collecting related data of the maritime search and rescue target area comprises the following steps: weather condition information, rescue vessel status information, ocean current information, search and rescue areas and operation risk levels.
3. The method for scheduling maritime search and rescue resources based on the improved a-Star algorithm according to claim 2, wherein the step 2 of rasterizing the maritime search and rescue target area comprises the following steps: Step 2-1, setting the warp resolution Sum weft resolution And rasterizing the target area accordingly; step 2-2, taking the grid point as a node The attribute of the node is set as the job risk level ; Step 2-3, constructing an adjacent matrix, namely establishing a communication relation between each node and other adjacent nodes, and calculating basic movement cost according to the range distance, the rescue ship speed and the external environment influence vector 。
4. The method for scheduling maritime search and rescue resources based on the improved a-Star algorithm as set forth in claim 3, wherein the generating the search and rescue route by using the improved a-Star algorithm in step3 includes: Step 3-1, setting an Open table as a node list to be expanded, wherein the Open table is used for storing all the nodes which are found but not processed, and carrying out priority ordering according to the size of the expected cost function value of the nodes; Step 3-2, setting a Close table as an extended node list, taking out the node with the smallest predicted cost function value from the Open table, expanding the adjacent nodes of the node, and putting the node into the Close table; and 3-3, finally, sorting according to the connection sequence according to the nodes in the Close table to obtain the search and rescue route.
5. The improved a-Star algorithm-based marine search and rescue resource scheduling method as claimed in claim 4, wherein the estimated cost function value of the node in step 3-1 is calculated as follows: according to the navigation time, designing a predicted cost function of the node, and calculating the total cost The method is characterized by comprising the following steps: ; Wherein the actual cost Is from the start point to the node Estimated cost of travel time of (2) Is a node Time of flight to the target point.
6. The maritime search and rescue resource scheduling method based on the improved A-Star algorithm as claimed in claim 5, wherein the estimated cost is And predicting the historical sea state data through a random forest model.
7. The improved a-Star algorithm-based marine search and rescue resource scheduling method as defined in claim 6, wherein expanding the neighboring nodes of the node in step 3-2 comprises: Step 3-2-1, calculating the total cost of all nodes adjacent to the current node, and expanding the node with the minimum total cost into adjacent nodes; Step 3-2-2, when the node number with the minimum total cost is more than 1, selecting a dynamic weight factor Minimum node, wherein dynamic weighting factors And calculating according to the wind wave data.
8. The improved A-Star algorithm-based maritime search and rescue resource scheduling method according to claim 7, wherein the sea condition affects cost The specific prediction method is as follows: constructing a training data set, wherein a data source comprises a historical meteorological record, real-time meteorological elements, ocean current distribution characteristics and wind wave fluctuation parameters; Calculating the deviation between the actual sailing speed and the theoretical speed of the ship under the conditions of different weather, ocean currents and wind and wave intensities by counting massive historical sailing tracks, and taking the speed deviation as a training label for supervised learning; training the random forest model by using the training data set and the training label to obtain a prediction model; The weather, ocean current and wind wave intensity collected in real time are used as input characteristics and are input into a pre-trained prediction model, and the sea condition influence cost in the current environment is obtained 。
9. The method for scheduling maritime search and rescue resources based on the improved a-Star algorithm according to claim 8, wherein the real-time issuing in step 3 comprises the following steps: And (3) sending the search and rescue route acquired in the step (3) and the predicted time consumption and risk level information to a ship terminal for executing the rescue task through a satellite communication link.
10. The method for scheduling maritime search and rescue resources based on the improved a-Star algorithm according to claim 9, wherein updating the related data of the maritime search and rescue target area in step 4 comprises: step 4-1, receiving weather condition information, rescue ship state information, ocean current information, search and rescue areas and operation risk levels updated in real time; step 4-2, updating the node attribute according to the update data received in the step 4-1; And 4-3, taking the current position of the ship as a new starting point, re-executing the step3 to obtain a new search and rescue route, and if the total cost of the new search and rescue route is reduced to exceed a set threshold delta C, replacing the current search and rescue route and issuing in real time.

Description

Maritime search and rescue resource scheduling method based on improved A-Star algorithm Technical Field The invention relates to a maritime search and rescue resource scheduling method, in particular to a maritime search and rescue resource scheduling method based on an improved A-Star algorithm. Background This section provides merely background information related to the present disclosure and is not necessarily prior art. With the increasing frequency of marine economic activities and the ever-expanding scale of marine transportation, marine safety has become an important issue in the field of shipping. The maritime search and rescue is used as a key task for guaranteeing the life and property safety of the sea, and has high complexity and timeliness requirements. The traditional scheduling method can provide effective support for command decision in open sea or simple scenes, however, under the condition of bad sea conditions, poor visibility or remarkable target drift, the integrity and reliability of available information are seriously reduced due to the dynamic change of environmental elements, so that the resource scheduling scheme deviates from the actual requirement. In addition, due to the fact that real constraints such as weather variation and sea condition complexity are adopted, unbalance of resource allocation, response delay or insufficient coverage are more prone to being caused, and the finally formed scheduling scheme is difficult to meet the actual requirements of efficient search and rescue. At present, aiming at a maritime search and rescue resource scheduling method, the following defects exist in the prior art: a) Maritime hazards such as ship capsizing and the like are often associated with severe weather conditions, and the existing method considers such conditions less and difficult to meet search and rescue resource scheduling work under the severe weather conditions. B) The existing methods are mostly based on heuristic learning methods, and the calculation efficiency of the methods is usually related to parameters, so that a group of optimal parameters are difficult to determine under the complex sea conditions and meteorological scenes of actual rescue. The wrong parameter setting can cause the algorithm to have low convergence speed, the result is in local optimum, and the problem of the rescue path with highest efficiency is eliminated. It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the present disclosure and thus may include information that does not constitute prior art known to those of ordinary skill in the art. Disclosure of Invention The invention aims to solve the technical problem of providing a maritime search and rescue resource scheduling method based on an improved A-Star algorithm aiming at the defects of the prior art. In order to solve the technical problems, the invention discloses a maritime search and rescue resource scheduling method based on an improved A-Star algorithm, which comprises the following steps: step 1, collecting relevant data of a maritime search and rescue target area; Step 2, rasterizing the target area for maritime search and rescue to obtain nodes and node data; Step 3, generating a search and rescue route by adopting an improved A-Star algorithm according to the nodes and the node data, and issuing in real time; and step 4, updating the relevant data of the maritime search and rescue target area according to a preset period, and re-executing the step 3 to update the search and rescue route. Further, the collecting relevant data of the maritime search and rescue target area in the step 1 includes: weather condition information, rescue vessel status information, ocean current information, search and rescue areas and operation risk levels. Further, the step 2 of rasterizing the target area for maritime search and rescue includes: Step 2-1, setting the warp resolution Sum weft resolutionAnd rasterizing the target area accordingly; step 2-2, taking the grid point as a node The attribute of the node is set as the job risk level; Step 2-3, constructing an adjacent matrix, namely establishing a communication relation between each node and other adjacent nodes, and calculating basic movement cost according to the range distance, the rescue ship speed and the external environment influence vectorThe concrete representation is as follows: Wherein, the The representation number isIs a node of (2)And number isIs a node of (2)The basic movement cost between the two,Is the range distance between two nodes,In order to rescue the speed of the ship,The external environment influence vector includes ocean current velocity and wind speed. Further, the generating a search and rescue route in the step 3 by adopting the improved A-Star algorithm comprises the following steps: Step 3-1, setting an Open table as a node list to be expanded, wherein the Open table is us