CN113159459B - Multi-forest-area air route scheduling planning method based on fusion algorithm - Google Patents
Multi-forest-area air route scheduling planning method based on fusion algorithm Download PDFInfo
- Publication number
- CN113159459B CN113159459B CN202110555185.2A CN202110555185A CN113159459B CN 113159459 B CN113159459 B CN 113159459B CN 202110555185 A CN202110555185 A CN 202110555185A CN 113159459 B CN113159459 B CN 113159459B
- Authority
- CN
- China
- Prior art keywords
- population
- algorithm
- forest
- particles
- scheduling
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 230000004927 fusion Effects 0.000 title claims abstract description 18
- 239000002245 particle Substances 0.000 claims abstract description 89
- 239000000575 pesticide Substances 0.000 claims abstract description 29
- 230000002068 genetic effect Effects 0.000 claims abstract description 22
- 238000005507 spraying Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000035772 mutation Effects 0.000 abstract description 7
- 230000007423 decrease Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 2
- 210000000349 chromosome Anatomy 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Biophysics (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Biodiversity & Conservation Biology (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a multi-forest area route scheduling planning method based on a fusion algorithm, which comprises the following steps of: s1, setting the number of evolutionary times Nmax and the number of individuals of a mixed particle swarm algorithm according to the number of forest areas needing to be sprayed with pesticide, and initializing particle positions; s2, calculating a particle fitness value; s3, updating the individual optimal particles and the group optimal particles according to the particle fitness value; s4, optimally crossing individuals; s5, optimal crossing of the groups; s6, carrying out particle variation; s7, checking iteration times; s8, outputting a working sequence path solution set; s9, setting the size, the cross probability and the mutation probability of a genetic algorithm population; s10, initializing a population Chrom2 by a genetic algorithm, and adopting a binary coding mode; s11, calculating a fitness value of a second-layer algorithm; s12, selecting, crossing and mutating the Chrom2 population; then reinserting to obtain an updated population Chrom2; s13, detecting iteration times; and S14, outputting the shortest global inter-area scheduling path.
Description
Technical Field
The invention relates to the technical field of forestry management, in particular to a multi-forest area route scheduling planning method based on a fusion algorithm.
Background
The forest region terrain in China is very complex, and large-area forest regions and scattered small-area forest lands exist at the same time. The northern areas of China mostly take large-area forest lands as the main parts, while the eastern areas take protective forests of roads, villages, farmlands and other areas as the main parts and are often small forest areas with scattered areas, so that the air route scheduling planning of the forest areas is particularly important. When the plant protection aircraft works, after the pesticide application of each small forest area is completed, the next forest area is entered until the pesticide application work of all the forest areas is completed, and then the plant protection aircraft returns to the aircraft take-off and landing point. Different operation sequences and areas entering and exiting points cause great difference in non-pesticide application range of the airplane. The non-pesticide application range of the airplane is reduced, the aviation fuel consumption and the operation time are reduced, the airplane plant protection operation efficiency is improved, and the method has important significance for realizing accurate agriculture and forestry operation. However, the solution of the shortest path between the global areas of the access points of each section of the airplane is very complex, and especially when the number of sections is large, the reasonable scheduling scheme is difficult to solve by the traditional greedy method, the deep search, the breadth search and the branch limit search. Therefore, the method has important significance in rapidly solving a reasonable route scheduling planning scheme among all the forest zones by using an advanced artificial intelligence algorithm. At present, the planning research on the scheduling route of the aerial pesticide application operation of the large-scale plant protection aircraft is less, the use requirement of the aerial pesticide application in multiple forest zones is difficult to meet, and some troubles are brought to the pesticide application operation in the multiple forest zones.
Disclosure of Invention
The invention aims to provide a multi-forest area route scheduling and planning method based on a fusion algorithm, which is simple to operate and high in efficiency aiming at the defects of the prior art.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a multi-forest area air route scheduling planning method based on a fusion algorithm comprises the following steps:
s1, setting the number of evolutionary times Nmax, the number of individuals and the position of initialized particles of a hybrid particle swarm algorithm according to the number of forest areas needing to be sprayed with pesticide;
the length of the population is added with 1 by the number of individuals, a single spraying area adopts a full coverage route planning algorithm, parallel lines are made according to the spraying width of the airplane from the longest edge of the boundary, when the boundary is crossed with other boundaries, the airplane turns around to fly until all areas of the single spraying area are traversed, the single spraying area is provided with an entry point and an exit point, the single spraying area is represented by the middle point of the line connecting the entry point and the exit point, and the airplane take-off and landing point is used as a point and is placed at the last position of the length of the population;
s2, calculating a particle fitness value according to a neighborhood table generated by the midpoints of the in-out points of the regions, and calculating the distance of each forest region operation sequence path by taking the midpoint coordinates of the in-out points of each region as a reference point;
s3, updating particles, and updating the individual optimal particles and the group optimal particles according to the particle fitness value;
s4, carrying out optimal crossing on the individuals, and crossing the individuals and the optimal particles of the individuals to obtain new particles;
s5, carrying out optimal crossing on the groups, and crossing the individual particles and the optimal particles of the groups to obtain new particles;
s6, carrying out particle variation, wherein the particles are subjected to self variation to obtain new particles;
s7, checking whether the iteration times reach the maximum evolution times; when N is larger than or equal to Nmax, executing the step S8, otherwise executing the step S2;
s8, outputting a working sequence path solution set;
s9, setting the population size, the cross probability, the variation probability and the maximum iteration number GENMAX of the second-layer genetic algorithm, and setting the initial value of the iteration number to 1, namely gen =1;
s10, initializing a population Chrom2 by a second-layer genetic algorithm, wherein a coding mode adopts binary coding;
s11, calculating a fitness value of a second-layer algorithm; taking the airplane take-off and landing points as 2 points by using a neighborhood table generated by the abscissa and the ordinate of the point of each pesticide spraying area, and setting the coordinates as the same numerical value so as to conveniently and quickly calculate the fitness value by using the neighborhood table; the fitness f2 is designed to be the reciprocal of the shortest distance of the scheduling air route among all the global areas obtained by the first-layer algorithm under each in-out state;
s12, selecting, crossing and mutating the Chrom2 population; then reinserting to obtain an updated population Chrom2;
s13, detecting whether the iteration number exceeds the maximum iteration number GENMAX, returning to the step S11 when the iteration number does not exceed the maximum iteration number, and otherwise, performing the step S14;
and S14, outputting the shortest global inter-area scheduling path, wherein the shortest scheduling path is the optimal scheduling scheme of the multi-forest area air route scheduling planning.
As an improvement to the above technical solution, in step S9, the population size in the genetic algorithm population is set to be 4 to 6 times of the sum of the forest area number and the aircraft take-off and landing point, the surrogate ditches are set to be constants, and the surrogate ditches are set to be 0.9 to 0.95; the cross probability Pc and the variation probability Pm are both designed as dynamic variation probabilities; the calculation formula is as follows:
Pm：
as an improvement to the above technical solution, pcmin =0.6, pcmax =0.9, pm0=0.1.
Compared with the prior art, the invention has the advantages and positive effects that:
the invention discloses a multi-forest area route scheduling planning method based on a fusion algorithm. A mixed particle swarm algorithm and a genetic algorithm are fused to plan a plurality of forest area route scheduling paths, and aerial pesticide application is particularly carried out on manned large-scale plant protection airplanes. The first layer adopts a hybrid particle swarm algorithm to solve a better operation sequence path, and the algorithm adopts three modes of individual-individual optimal intersection, individual-group optimal intersection and individual self variation to obtain new particles, so that compared with the traditional hybrid particle swarm algorithm and the genetic algorithm, the solving speed and the global searching capacity are improved; the second layer algorithm adopts a genetic algorithm, combines the solution set obtained by the first layer, considers the access points of each block, and thus obtains the shortest global inter-area scheduling path, avoids the situation that the local optimal solution of the global inter-area scheduling path is trapped due to the shortest operation sequence path obtained by the first layer program, has higher calculation efficiency, and thus improves the path planning efficiency of pesticide application in multiple forest zones. The genetic algorithm adopts dynamic cross probability and mutation probability, the cross probability and the mutation probability are both reduced along with the increase of the iteration times, the algorithm convergence speed is improved on the premise of taking care of the global search capability, the search time is saved, and the algorithm efficiency is improved. The invention can shorten the pesticide application turning times of the plant protection operation aircraft in the single-chip area forest region, and reduce the driving operation difficulty of pilots; the scheduling route voyage between the global areas of the pesticide application operation in the multiple forest areas can be shortened, the working time of the aerial pesticide application in the multiple forest areas is saved, the usage amount of aerial fuel oil is effectively reduced, the economic cost of the pesticide application operation in the forest areas is saved, convenience is brought to the pesticide application operation in the multiple forest areas, and the aerial pesticide application efficiency in the forest areas is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a task diagram for planning routes in multiple forest zones;
FIG. 3 is a schematic view of a route plan within a single block;
FIG. 4 is a diagram illustrating a result of a global route scheduling planning in a plurality of forest zones.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments of the present invention, should be included in the protection scope of the present invention.
As shown in fig. 1 to 4, the present embodiment discloses a multi-forest area route scheduling and planning method based on a fusion algorithm, and the route planning task is as follows: the helicopter starts at the airplane takeoff and landing point H in fig. 2, then passes through the entry and exit points of each patch, traverses each patch, and then returns to H. The shortest route is required for inter-area dispatch. The inside of the area adopts a full-coverage route planning algorithm shown in fig. 3, namely, parallel lines are made from the longest edge of the boundary according to the spraying width of the airplane, and when the boundary of other boundaries is reached, the airplane turns around to fly until all areas of the area are traversed. Each patch must have an entry point and an exit point. Scheduling must be done from two points in and out, but not specifically at which point. E.g., from A1 in fig. 2, must exit from A2, or from A1 after entering from A2. The interior of the area is planned according to the route shown in fig. 3. The route planning is performed according to the fusion algorithm shown in fig. 1, and the better result shown in fig. 4 is obtained.
The fusion algorithm flow is shown in fig. 1, and the following is the algorithm implementation process:
step 1: the algorithm starts, the number of times of evolution Nmax and the number of individuals of the mixed particle swarm algorithm are set according to the number of forest areas needing to be sprayed with the pesticide, and the particle positions are initialized. For example, if 18 forest regions need to be applied, the length of the population is 18+1=19. The reason is that each forest zone is represented by the midpoint of the in-out point connection line, as shown by A0 in fig. 2, the aircraft take-off and landing point in fig. 2 is also considered as a point, and the last position in the population length is the point where the scheduling tasks for 18 forest zones are considered to be 19 forest zone scheduling tasks. The initial positions of the particles are generated by random initialization, for example, if a population has five forest regions and one airplane take-off and landing point, 123456, 213465 and 345216 may be one particle in the particle population, and the number is required not to be repeated.
And 2, step: a particle fitness value is calculated. In order to facilitate and rapidly calculate, the algorithm fitness calculation is calculated according to a neighborhood table generated by the middle points of the in and out points of the film area. Taking the scheduling task in fig. 2 as an example, the coordinates of the 18 slices and the aircraft take-off and landing points are shown in table 1. The neighborhood table generated by its in and out points midpoints is shown in table 2. According to the table 2, the fitness of each particle in the layer of mixed particle swarm optimization can be rapidly calculated.
TABLE 1 coordinate table of various forest zones
Unit: m is a unit of
And calculating the distance of the operation sequence path of each forest region by taking the midpoint coordinates of the in-out points of each forest region as reference points. And generating a distance neighborhood table by using the point coordinates in the 18 areas and the coordinates of the take-off and landing points of the airplane.
TABLE 2 distance neighborhood table generated by the midpoint of the in-out point of each segment
And step 3: and updating the particles. The module updates the individual optimal particles and the population optimal particles according to the particle fitness value. The algorithm sets an individual optimal memory and a population optimal memory. For each generation of optimal particles, there is a population-optimal memory.
And 4, step 4: the particles are crossed with the particles in the particle group in the cycle, and the particles are accepted only when the particle fitness value after the crossing is higher than the particle fitness value before the crossing and then are replaced into the particle group.
And 5: the particles are interleaved with the population-optimal memory-optimal particles. Only if the particle fitness value after the intersection is higher than the particle fitness value before the intersection, the particle is accepted and then replaced into the particle population.
Step 6: and (4) particle variation. Only if the fitness value of the particle after the variation is higher than the fitness value of the particle before the variation, the particle is accepted and then replaced into the particle group.
And 7: checking whether the iteration number reaches the maximum evolution number. When N is larger than or equal to Nmax, executing the step S8, otherwise executing the step S2;
step 8, outputting a working sequence path solution set;
and 9, setting the population size, the cross probability and the mutation probability of the genetic algorithm. If the population size is set to be 4-6 times of the sum of the forest zone number and the airplane take-off and landing point, if 18 zones exist, the population number is set to be 100; the ditch is set as constant; the substitution groove is set to be 0.9-0.95, such as 0.9. Both the cross probability Pc and the variation probability Pm are designed as dynamic variation probabilities. The cross probability decreases with increasing iteration number, and the mutation probability decreases with increasing iteration number. The calculation formula is as follows:
Pm：/>
wherein P is cmin ＝0.6，P cmax =0.9, initial mutation probability P m0 =0.1. The maximum iteration number GENMAX of the genetic algorithm is 2000. Setting the initial value of the iteration times to be 1, namely gen =1;
and step 10, initializing the population Chrom2 by a second-layer genetic algorithm, and adopting a binary coding mode. The encoding mode adopts binary encoding, and takes a four-chip area as an example, the operation sequence is assumed to be ABCD, wherein A represents the aircraft take-off and landing point. The starting point of the operation in the B region can be B1 and B2 or B2 and B1, respectively, and the two states are represented by 0 and 1, respectively. The status code of A1A2B1B2C1C2D1D2 is 0000, and it is specifically noted that the coordinates of the aircraft take-off and landing points A1 and A2 are identical, indicating that the operation sequence is from a, B1 in, B2 out, C1 in, C2 out, D1 in, D2 out, and then back to a. Then the state encoding of A1A2B 1C2D1 is 0101. The situation of the operation scheduling path among the districts considering the entrance and exit points of the districts from the departure and landing points of the airplane can be represented.
And 11, calculating the fitness value of the second layer algorithm. In order to facilitate the calculation of the fitness of the second layer genetic algorithm, a neighborhood table is also utilized, and the neighborhood table is generated by using the abscissa and the ordinate of the inlet and outlet points of each region in the table 1, as shown in table 3. Since the neighborhood table for the 18 patches to consider access points is too large, a neighborhood distance matrix of 4 patches and 1 aircraft take-off and landing point is shown.
The job order is assumed to be ABCD. The starting point of the operation in the B region can be B1 and B2 or B2 and B1, respectively, and the two states are represented by 0 and 1, respectively. The state encoding of A1A2B1B2C1C2D1D2 is 0000. The operation sequence is shown as starting from A1, entering the A area, going out from A2, B1 in, B2 out, C1 in, C2 out, D1 in, D2 out and returning to A1. Then the state encoding of A1A2B 1C2D1 is 0101. Five areas A, B, C and D respectively, the access point of each area is respectively expressed as two codes, and if the access point of the area A is expressed as A 1 And A 2 . The aircraft takeoff and landing point coordinates are represented by H. The 18 zones of the domain distance matrix considering the entry and exit points and the aircraft take-off and landing points can be referred to the method.
Fitness f 2 The design is the reciprocal of the shortest distance of all global area scheduling routes obtained by the first layer algorithm under each access state. Taking the state coding 10010 as an example, the better path solution set obtained by the first layer algorithm is corrected according to the 10010 state, and the correction method is shown in table 4. Assuming that n types of scheduling routes between global areas are obtained in the first layer of the algorithm, the fitness calculation formula is a formula (8).
TABLE 3 Domain distance matrix considering patch in and out points and aircraft landing points
TABLE 4 example of modifying first-tier algorithmic work order Path based on State Table Chrom2
Note that 7 in table 4 corresponds to point A2 in table 3, and 1 corresponds to point A1 in the table. And so on. Reference is made specifically to step 16.
Step 12, selecting, crossing and mutating the population Chrom2; then reinserting to obtain an updated population Chrom2;
step 13, detecting whether the iteration number exceeds the maximum iteration number GENMAX, returning to the step 11 when the iteration number does not exceed the maximum iteration number, and otherwise, performing the step 14;
and 14, outputting the shortest global inter-area scheduling path, wherein the shortest scheduling path is the optimal scheduling scheme for the multi-forest area air route scheduling planning.
The steps S1-S8 represent the first layer of the fusion algorithm, the layer adopts a mixed particle swarm algorithm to solve the operation sequence path, the algorithm abandons the traditional particle swarm algorithm method of updating particles by tracking extreme values, but uses the ideas of intersection and variation in the genetic algorithm for reference, and the improvement is made on the basis. The particles are crossed through the current individual and the historical optimal value of the individual, and if the fitness is better, new particles after the individual is crossed are received; the particles are crossed with the optimal particles of the current population, and if the fitness is better, the new particles after the crossing are received; the particle itself generates a variation, and if the fitness value is better after the variation, a new particle is accepted. The three methods are used for generating new particles, and the particles have the capabilities of self evolution, self learning and group learning.
Steps S9-S14 represent the second layer of the fusion algorithm, which is a practical genetic algorithm for further considering the entry point mechanism based on the job sequence path. In the step S11, depending on the solution result of the first layer of hybrid particle swarm algorithm, the second layer of genetic algorithm fitness value calculation adopts an expansion operation on all the operation path sequences obtained by the first layer of algorithm for each chromosome in Chrom2, and adopts an expansion domain table to calculate the scheduling distance length between the global areas, where the length does not include the distance inside the parcel, and the obtained reciprocal of the shortest distance is used as the fitness value of the chromosome.
The population size in the genetic algorithm population in the step S9 is set to be 4-6 times of the sum of the forest area number and the airplane take-off and landing point, the alternative ditches are set to be a constant, and the alternative ditches are set to be 0.9-0.95; both the cross probability Pc and the variation probability Pm are designed as dynamic variation probabilities. The crossover probability decreases with increasing iteration number, and the mutation probability decreases with increasing iteration number. The calculation formula is as follows:
Pm：/>
wherein Pcmin =0.6, pcmax =0.9, pm0=0.1.
The invention plans the multi-forest area air route scheduling paths by adopting a fusion algorithm of combining a hybrid particle swarm algorithm and a genetic algorithm, and particularly aims at aerial pesticide application of manned large-scale plant protection airplanes. Considering safety and scheduling non-spraying flight distance among all forest zones, the setting of the endurance range, the drug loading capacity and the endurance time parameter of the plant protection spraying operation is smaller than the performance parameter of the airplane.
The fusion algorithm adopts a serial fusion method, the iteration times are the sum of the addition of the iteration times of the two algorithms, and the speed is higher than that of the nested fusion. Both layers of algorithms converge. The first layer adopts a hybrid particle swarm algorithm, abandons a method for updating the positions of particles by tracking extreme values, and adopts a method for generating new particles by adopting three modes of individual-individual optimal intersection, individual-group optimal intersection and individual variation, so that the search speed and the global search capability of the hybrid particle swarm algorithm are improved, and a better operation sequence path solution set can be obtained quickly; the second layer algorithm adopts a genetic algorithm, combines the operation sequence path solution set obtained by the first layer, and considers the entrance and exit points of each block, so that the shortest global inter-area scheduling path is obtained, the local optimal solution of the global inter-area scheduling path, which is trapped by the shortest operation sequence path obtained by the first layer program, is avoided, the calculation efficiency is higher, and the path planning efficiency of pesticide application in multiple forest zones is improved.
The invention can shorten the pesticide application turning times of the plant protection operation airplane in the single forest area, shorten the inter-area scheduling path voyage of pesticide application operation in multiple forest areas, save the working time of pesticide application operation in the multiple forest areas, improve the pesticide application efficiency of the forest areas, effectively reduce the usage amount of aviation fuel, save the economic cost of pesticide application operation in the forest areas and bring convenience to pesticide application operation in the multiple forest areas.
Claims (3)
1. A multi-forest region route scheduling and planning method based on a fusion algorithm is characterized in that: the method comprises the following steps:
s1, setting the number of evolutionary times Nmax, the number of individuals and the position of initialized particles of a hybrid particle swarm algorithm according to the number of forest areas needing to be sprayed with pesticide;
the length of the population is 1 added to the number of individuals, a single spraying area adopts a full coverage route planning algorithm, parallel lines are made according to the width of the spraying amplitude of the airplane from the longest edge of the boundary, when the boundary of other boundaries is reached, the airplane turns around to fly until all areas of the single spraying area are traversed, the single spraying area is provided with an entry point and an exit point, the single spraying area is represented by the middle point of the line connecting the entry point and the exit point, and the airplane take-off and landing point is used as a point and is placed at the last position of the length of the population;
s2, calculating a particle fitness value according to a neighborhood table generated by the midpoints of the in-out points of the regions, and calculating the distance of each forest region operation sequence path by taking the midpoint coordinates of the in-out points of each region as a reference point;
s3, updating particles, and updating the individual optimal particles and the group optimal particles according to the particle fitness value;
s4, carrying out optimal crossing on the individuals, and crossing the individuals and the optimal particles of the individuals to obtain new particles;
s5, carrying out optimal population crossing, and crossing the individual and the optimal population particles to obtain new particles;
s6, carrying out particle variation, wherein the particles are subjected to self variation to obtain new particles;
s7, checking whether the iteration times reach the maximum evolution times or not; when N is larger than or equal to Nmax, executing the step S8, otherwise executing the step S2;
s8, outputting a working sequence path solution set;
s9, setting the population size, the cross probability, the variation probability and the maximum iteration number GENMAX of the second-layer genetic algorithm, and setting the initial value of the iteration number to 1, namely gen =1;
s10, initializing a population Chrom2 by a second-layer genetic algorithm, wherein a coding mode adopts binary coding;
s11, calculating a fitness value of a second-layer algorithm; taking the airplane take-off and landing points as 2 points by using a neighborhood table generated by the abscissa and the ordinate of the point of each pesticide spraying area, and setting the coordinates as the same numerical value so as to conveniently and quickly calculate the fitness value by using the neighborhood table; the fitness f2 is designed to be the reciprocal of the shortest distance of all global area scheduling routes obtained by the first-layer algorithm under each access state;
s12, selecting, crossing and mutating the Chrom2 population; then reinserting to obtain an updated population Chrom2;
s13, detecting whether the iteration number exceeds the maximum iteration number GENMAX, returning to the step S11 when the iteration number does not exceed the maximum iteration number, and otherwise, performing the step S14;
and S14, outputting the shortest global inter-area scheduling path, wherein the shortest scheduling path is the optimal scheduling scheme of the multi-forest area air route scheduling planning.
2. The fusion algorithm based multi-forest area route scheduling planning method of claim 1, wherein: in the step S9, the population size in the genetic algorithm population is set to be 4-6 times of the sum of the forest region number and the airplane take-off and landing point, the surrogate ditches are set to be constants, and the surrogate ditches are set to be 0.9-0.95; the cross probability Pc and the variation probability Pm are both designed as dynamic variation probabilities; the calculation formula is as follows:
3. the fusion algorithm based multi-forest region route scheduling planning method of claim 1, wherein: wherein Pcmin =0.6, pcmax =0.9, pm0=0.1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110555185.2A CN113159459B (en) | 2021-05-21 | 2021-05-21 | Multi-forest-area air route scheduling planning method based on fusion algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110555185.2A CN113159459B (en) | 2021-05-21 | 2021-05-21 | Multi-forest-area air route scheduling planning method based on fusion algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113159459A CN113159459A (en) | 2021-07-23 |
| CN113159459B true CN113159459B (en) | 2023-04-18 |
Family
ID=76876895
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110555185.2A Active CN113159459B (en) | 2021-05-21 | 2021-05-21 | Multi-forest-area air route scheduling planning method based on fusion algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113159459B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114467900B (en) * | 2022-02-17 | 2022-12-27 | 南京林业大学 | Accurate spraying method of lawn herbicide |
| CN116415480B (en) * | 2022-09-06 | 2024-01-19 | 中国人民解放军海军航空大学 | IPSO-based off-road planning method for aircraft offshore platform |
| CN117235558B (en) * | 2023-11-14 | 2024-03-19 | 江苏宁翔通用航空有限公司 | Multi-field block route scheduling planning method for large-area hilly and mountainous areas |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503464A (en) * | 2014-12-30 | 2015-04-08 | 中南大学 | Computer-based convex polygon field unmanned aerial vehicle spraying operation route planning method |
| CN106557844A (en) * | 2016-11-23 | 2017-04-05 | 华东理工大学 | A kind of welding robot paths planning method |
| JP2017201936A (en) * | 2016-05-12 | 2017-11-16 | 学校法人早稲田大学 | Line network route-designing apparatus and program thereof, and system for generating and displaying line network route |
| CN108846472A (en) * | 2018-06-05 | 2018-11-20 | 北京航空航天大学 | A kind of optimization method of Adaptive Genetic Particle Swarm Mixed Algorithm |
| CN110930182A (en) * | 2019-11-08 | 2020-03-27 | 中国农业大学 | Improved particle swarm optimization algorithm-based client classification method and device |
| CN111860957A (en) * | 2020-06-18 | 2020-10-30 | 浙江工业大学 | Multi-vehicle type vehicle path planning method considering secondary distribution and balance time |
| CN112082552A (en) * | 2020-07-11 | 2020-12-15 | 西北工业大学太仓长三角研究院 | Unmanned aerial vehicle flight path planning method based on improved hybrid particle swarm optimization algorithm |
-
2021
- 2021-05-21 CN CN202110555185.2A patent/CN113159459B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104503464A (en) * | 2014-12-30 | 2015-04-08 | 中南大学 | Computer-based convex polygon field unmanned aerial vehicle spraying operation route planning method |
| JP2017201936A (en) * | 2016-05-12 | 2017-11-16 | 学校法人早稲田大学 | Line network route-designing apparatus and program thereof, and system for generating and displaying line network route |
| CN106557844A (en) * | 2016-11-23 | 2017-04-05 | 华东理工大学 | A kind of welding robot paths planning method |
| CN108846472A (en) * | 2018-06-05 | 2018-11-20 | 北京航空航天大学 | A kind of optimization method of Adaptive Genetic Particle Swarm Mixed Algorithm |
| CN110930182A (en) * | 2019-11-08 | 2020-03-27 | 中国农业大学 | Improved particle swarm optimization algorithm-based client classification method and device |
| CN111860957A (en) * | 2020-06-18 | 2020-10-30 | 浙江工业大学 | Multi-vehicle type vehicle path planning method considering secondary distribution and balance time |
| CN112082552A (en) * | 2020-07-11 | 2020-12-15 | 西北工业大学太仓长三角研究院 | Unmanned aerial vehicle flight path planning method based on improved hybrid particle swarm optimization algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 徐博等.多作业区域植保无人机航线规划算法.农业机械学报.2017,(第02期),75-81. * |
| 武锦龙等.基于粒子群算法的植保无人机航线规划.山西电子技术.2018,(第02期),3-5. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113159459A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113159459B (en) | Multi-forest-area air route scheduling planning method based on fusion algorithm | |
| CN112016812B (en) | Multi-unmanned aerial vehicle task scheduling method, system and storage medium | |
| US6266610B1 (en) | Multi-dimensional route optimizer | |
| CN111047087B (en) | Intelligent optimization method and device for path under cooperation of unmanned aerial vehicle and vehicle | |
| CN110597286B (en) | Method for realizing unmanned aerial vehicle autonomous inspection of power transmission line by using smart hangar | |
| CN108871335B (en) | Unmanned aerial vehicle spraying operation air route and load planning method | |
| CN109357678A (en) | A kind of multiple no-manned plane paths planning method based on heterogeneousization dove colony optimization algorithm | |
| Shao et al. | Bipartite cooperative coevolution for energy-aware coverage path planning of uavs | |
| CN106060896B (en) | Method and system for obtaining formation communication topology of unmanned aerial vehicle based on minimum arborescence | |
| Tang et al. | A novel cooperative path planning for multirobot persistent coverage in complex environments | |
| CN115938162A (en) | Conflict minimization track collaborative planning method considering high-altitude wind time variability | |
| CN112735188B (en) | Air traffic network vulnerability analysis system based on complex network theory | |
| CN108592928A (en) | Construction method and device for double-layer path of vehicle-mounted unmanned aerial vehicle | |
| ElSayed et al. | Autonomous drone charging station planning through solar energy harnessing for zero-emission operations | |
| Huang et al. | Supply distribution center planning in UAV-based logistics networks for post-disaster supply delivery | |
| CN106127335A (en) | The battery altering station layout method of electronic many rotor wing unmanned aerial vehicles overlength distance flight | |
| CN109917810B (en) | Unmanned aerial vehicle cluster energy management method | |
| CN113703488A (en) | Multi-operation plant protection unmanned aerial vehicle path planning method based on improved ant colony algorithm | |
| Ghorpade | Airspace configuration model using swarm intelligence based graph partitioning | |
| Katsanikas et al. | Chains of rotational tori and filamentary structures close to high multiplicity periodic orbits in a 3D galactic potential | |
| CN113326990B (en) | Helicopter scheduling route planning method based on dynamic genetic algorithm serial fusion | |
| CN113222264B (en) | Multi-forest-area air route scheduling planning method based on coupling algorithm | |
| CN113191567A (en) | Multi-forest-area air route scheduling planning method based on double-layer fusion intelligent algorithm | |
| Zhou et al. | Crossover recombination-based global-best brain storm optimization algorithm for uav path planning | |
| Li et al. | A bi-level planning approach of logistics unmanned aerial vehicle route network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |