A multi-forest area route scheduling planning method based on double-layer fusion intelligent algorithm

Abstract

The invention discloses a multi-forest area route scheduling planning method based on a double-layer fusion intelligent algorithm, S1, setting the population of the first-layer genetic algorithm; S2-S6, using decimal coding to initialize the population, calculating fitness, performing selection, crossover, mutation, and reversal operations, reinserting into the population and checking the number of iterations; S7, initializing the pheromone of the ant colony algorithm; S8-S20, setting the number of ants m, randomly placing them on the nodes of the multi-area forest area to be planned, ant k traverses all areas without repetition, and updates local pheromones in time; checking whether the ant index number k is greater than the number of ants m; global pheromone update. Check the number of iterations; output the job sequence path solution set; set the second-layer genetic algorithm population; use the binary coding population Chrom2; calculate the fitness value; perform selection, crossover, and mutation operations; reinsert to obtain the updated population; detect the number of iterations; output the best route scheduling plan.

Description

Technical Field

[0001] The present invention relates to the field of forestry management, and in particular to a multi-forest area route scheduling planning method based on a double-layer fusion intelligent algorithm. Background Art

[0002] The terrain of my country's forest areas is very complex, with both large concentrated forest areas and small scattered forest areas. The forest land in the eastern region of my country is mainly protective forests in areas such as roads, villages and farmlands, and most of them are small forests. In the process of aerial spraying, the spraying area often appears to be multiple small forest areas. Therefore, the scheduling route planning of multiple forest areas is particularly important. In the planning of small single forest areas, the number of U-turns of quality assurance aircraft should be reduced; in the scheduling planning of multiple forest areas, it is of great significance to consider the entry and exit points of the area and plan the global inter-regional scheduling routes with shorter routes. At present, there is little research on the scheduling route during aerial spraying operations in multiple forest areas, which is difficult to meet the use needs of aerial spraying operations in multiple forest areas, and has brought certain troubles to the spraying operations in multiple forest areas. Summary of the invention

[0003] The purpose of the present invention is to provide a multi-forest area route scheduling planning method based on a double-layer fusion intelligent algorithm which is simple to operate and has improved efficiency in order to solve the above problems.

[0004] In order to achieve the above object, the technical solution of the present invention is:

[0005] A multi-forest area route scheduling planning method based on a double-layer fusion intelligent algorithm includes the following steps:

[0006] S1. Set the population size and length, crossover probability, and mutation probability of the first-layer genetic algorithm according to the number of forest areas that need to be sprayed;

[0007] S2, using decimal coding and randomly generating populations to obtain the initial population Chrom1;

[0008] S3, calculate the fitness of the initial population Chrom1, the fitness value is the reciprocal of the length of the job sequence path corresponding to each chromosome;

[0009] S4, performing selection, crossover, mutation, and reversal operations on the initial population Chrom1;

[0010] S5, reinsert into the initial population Chrom1 to obtain the updated updated population Chrom1;

[0011] S6, check whether the number of iterations reaches the maximum value, if it reaches the maximum value, execute S7, otherwise execute S3;

[0012] S7. Initialize the ant colony algorithm pheromone according to the result in the updated population Chrom1; if the updated population Chrom1 contains the path from area 1 to area 2, increase the pheromone of the path from area 1 to area 2 when setting the ant colony algorithm pheromone; the pheromone increase value is the fitness value of the chromosome with the largest fitness value in the updated population Chrom1;

[0013] S8. Set the number of ants m, information heuristic factor, expected heuristic factor, pheromone volatilization factor, pheromone enhancement coefficient, and the maximum number of iterations of the ant colony algorithm. Set the initial value of the number of iterations Nc to 0;

[0014] S9, the iteration counter is increased by 1, and m ants are randomly placed on the nodes of the multi-area forest area to be planned;

[0015] S10, the ant taboo table index number k=1, the ant selects the next area according to the state transition probability, updates the local pheromone, that is, when passing through the area, the pheromone of the path between the area and the previous area is appropriately increased, and the area taboo table is modified, that is, the area that has been passed is removed from the set of areas to be traversed, until the ant has traversed all areas without repetition; the ant updates the local pheromone once every time it arrives at an area;

[0016] S11, check whether the ant index number k is greater than the number of ants m. If k ≥ m, execute S12, otherwise set the ant taboo table k = k + 1 and execute S10;

[0017] S12. m ants traverse all areas and perform global pheromone updates.

[0018] S13, check whether the number of iterations Nc is greater than the maximum number of iterations of the ant colony algorithm. If Nc ≥ Ncmax, execute step S14, otherwise execute step S9;

[0019] S14, outputting the job sequence path solution set;

[0020] S15, setting the second-layer genetic algorithm population size, crossover probability, mutation probability, the second-layer algorithm maximum number of iterations GENMAX2, and setting the initial value of the number of iterations to 1, that is, gen2 = 1;

[0021] S16. The second-level genetic algorithm initializes the population Chrom2 using binary coding.

[0022] S17. Calculate the fitness value of the second-layer algorithm. Consider the take-off and landing points of the aircraft as two points, which can represent the global inter-regional scheduling routes starting from the take-off and landing points of the aircraft and considering the entry and exit points of each area. Assuming that there are n types of global inter-regional scheduling routes obtained by the first layer of the algorithm, the fitness calculation formula is:

[0023]

[0024] S18, performing selection, crossover, and mutation operations on population Chrom2; and then reinserting to obtain updated population Chrom2;

[0025] S19, checking whether the number of iterations exceeds the maximum number of iterations GENMAX2, when the number of iterations does not exceed the maximum number of iterations, returning to step S17, otherwise proceeding to step S20;

[0026] S20, outputting the shortest global inter-regional scheduling path, where the shortest scheduling path is the optimal scheduling solution for multi-forest area route scheduling planning.

[0027] Furthermore, the population size in the first-layer genetic algorithm population in step S1 is set to 4 to 6 times the sum of the number of forest areas and the aircraft take-off and landing points, and the number of iterations, crossover probability, mutation probability, and generation gap are all set to constants; the crossover probability is set to 0.6 to 0.9, the mutation probability is set to 0.0001 to 0.1, and the generation gap is set to 0.9 to 0.95.

[0028] Furthermore, in step S8, the number of ants, information heuristic factor, expected heuristic factor, pheromone volatilization factor, and pheromone enhancement coefficient of the ant colony algorithm are all set to constants; the number of ants m is set to 2 / 3 times the number of patches, the information heuristic factor is set between 1 and 5, the expected heuristic factor is set between 2 and 5, the pheromone volatilization factor is set between 0.1 and 0.5, and the pheromone enhancement coefficient is set between 100 and 1000.

[0029] Furthermore, in step S15, the population size in the second-layer genetic algorithm population is set to 4 to 6 times the sum of the number of forest areas and the aircraft take-off and landing points, and the crossover probability, mutation probability, and generation gap are all set to constants; the crossover probability is set to 0.6 to 0.9, the mutation probability is set to between 0.0001 and 0.1, and the generation gap is set to 0.9 to 0.95.

[0030] Compared with the prior art, the present invention has the following advantages and positive effects:

[0031] The present invention plans the route scheduling path for multiple forest areas by adopting a double-layer fusion intelligent algorithm, especially for aerial spraying of pesticides by manned large-scale plant protection aircraft. The first layer adopts a combination of genetic algorithm and ant colony algorithm, and uses the optimized result of genetic algorithm to initialize the pheromone of ant colony algorithm, avoiding the blindness of the initial search stage of ant colony algorithm, thereby improving the search speed and obtaining a better solution set of operation sequence path more quickly; the second layer algorithm adopts genetic algorithm, combined with the solution set obtained by the first layer, considering the entry and exit points of each area, so as to obtain the shortest global inter-regional scheduling path, which avoids the local optimal solution of the global inter-regional scheduling path that only obtains the shortest operation sequence path in the first layer program, and has high calculation efficiency, thereby improving the path planning efficiency of spraying pesticides in multiple forest areas. The present invention can shorten the number of turns for spraying pesticides by plant protection aircraft in a single forest area, shorten the inter-regional dispatching path range for spraying pesticides in multiple forest areas, save the working time of spraying pesticides in multiple forest areas, improve the spraying efficiency of forest areas, and effectively reduce the use of aviation fuel, save the economic cost of spraying pesticides in forest areas, and bring convenience to spraying pesticides in multiple forest areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0033] Figure 1 It is a flow chart of the double-layer fusion intelligent algorithm in the present invention;

[0034] Figure 2 Plan mission charts for multi-forest routes;

[0035] Figure 3 This is a schematic diagram of route planning within a single area;

[0036] Figure 4 This is a schematic diagram of the global route scheduling planning results for Duolin District. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work, any modifications, equivalent substitutions, improvements, etc., should be included in the protection scope of the present invention.

[0038] like Figures 1 to 4As shown, this embodiment discloses a multi-forest route scheduling planning method based on a double-layer fusion intelligent algorithm, and its route planning tasks are as follows: Figure 2 The aircraft starts from the take-off and landing point H, then passes through the entry and exit points of each area, traverses each area, and then returns to H. The route for scheduling between areas is required to be the shortest. Figure 3 The full coverage route planning algorithm shown in the figure is to draw a parallel line from the longest side of the boundary according to the width of the aircraft spray. When it reaches the intersection of other boundaries, the aircraft turns around and flies until all areas of the area are traversed. Therefore, each area must have an entry point and an exit point. When scheduling, it must enter and exit from two points, but it is not specific which point. For example, from Figure 2 After entering from A1, you must exit from A2, or after entering from A2, you must exit from A1. Figure 3 The route plan shown. Figure 1 The double-layer fusion intelligent algorithm shown in the figure is used for route planning, and the following is obtained: Figure 4 The better results shown.

[0039] The process of the dual-layer fusion intelligent algorithm is as follows: Figure 1 As shown:

[0040] The following is the algorithm implementation process:

[0041] Step 1: There are 18 forest areas that need to be treated, so the length of the population is set to 18+1=19. The reason is that each forest area is represented by the midpoint of the line connecting the entry and exit points, such as Figure 2 As shown in A0 in Figure 2 The aircraft take-off and landing points in the is also regarded as a point and placed at the last position of the population length. Then the scheduling task of 18 forest areas is regarded as the scheduling task of 19 forest areas. The number of populations is set to 4-6 times the number of cities. For example, if the scheduling task of 19 areas is to be considered, the number of populations can be set between 76-114. Set the number of iterations of the first-layer algorithm GEN1 to a constant, such as 500; the crossover probability, mutation probability, and generation gap are all set to constants. The crossover probability is set between 0.6-0.9, the mutation probability is set between 0.0001-0.1, and the generation gap is set to 0.9-0.95.

[0042] Step 2: Use decimal encoding and random population generation to obtain the initial population Chrom1. For the sake of example, assume that there are five forest areas and an aircraft take-off and landing point in the population, then 123456, 213465, and 345216 can all be a chromosome in the population, and the numbers must not be repeated. If the population number is set to 30 in the first step, there are 30 randomly generated chromosomes in the initial population.

[0043] Step 3: Calculate the fitness of the genetic algorithm in the first layer of the algorithm. To facilitate quick calculation, the algorithm fitness calculation is based on the neighborhood table generated by the midpoints of the entry and exit points of the area. Figure 2 Taking the scheduling task in as an example, the coordinates of its 18 areas and aircraft take-off and landing points are shown in Table 1. The neighborhood table generated by the midpoints of its entry and exit points is shown in Table 2. According to Table 2, the fitness of the chromosome in the genetic algorithm at this level can be quickly calculated.

[0044] Table 1 Coordinates of each forest area

[0045]

[0046] The midpoint coordinates of the entry and exit points of each area are used as reference points to calculate the distance of the operation sequence path of each forest area. The distance neighborhood table is generated using the midpoint coordinates of the 18 areas and the coordinates of the aircraft take-off and landing points.

[0047] Table 2 Distance neighborhood table generated by the midpoints of each area's entry and exit points

[0048]

[0049]

[0050] Step 4: Perform selection, crossover, mutation, and reversal operations. Choose to use the roulette method. Using the reversal operation can enhance the ability of global search. If the chromosome is 123456, and breaks occur at 2 and 3, 4 and 5 and then reverse insertion, the new code string is 12-43-56.

[0051] Step 5: Re-insert to generate updated population Chrom1.

[0052] Step 6: Check whether the number of iterations exceeds the maximum number of iterations GENmin. When the number of iterations ≥ GENmin, return to step 3, otherwise proceed to step 7.

[0053] Step 7: Initialize the ant colony algorithm pheromone according to the results in Chrom1. If Chrom1 contains the path from area 1 to area 2, increase the pheromone of the path from area 1 to area 2 when setting the ant colony algorithm pheromone. The pheromone increase value is the fitness value of the chromosome with the largest fitness value in Chrom1.

[0054] Step 8: Set the number of ants m, information heuristic factor, expected heuristic factor, pheromone volatilization factor, pheromone enhancement coefficient, and the maximum number of iterations of the ant colony algorithm. The number of ants m is set to 2 / 3 times the number of patches, the information heuristic factor is set between 1 and 5, the expected heuristic factor is set between 2 and 5, the pheromone volatilization factor is set between 0.1 and 0.5, and the pheromone enhancement coefficient is set between 100 and 1000. Set the initial number of iterations Nc to 0.

[0055] Step 9: The iteration counter is increased by 1, and m ants are randomly placed on the nodes of the multi-area forest area to be planned.

[0056] Step 10, the ant taboo table index number k = 1, the ant selects the next area according to the probability calculated by the ant colony algorithm state transition probability formula, updates the local pheromone, that is, when passing through the area, the pheromone of the path between the area and the previous area is appropriately increased, and the area taboo table is modified, that is, the area that has been passed is removed from the set of areas to be traversed, until the ant traverses all areas without repetition.

[0057] Step 11: Check whether the ant index number k is greater than the number of ants m. If k≥m, execute step 12, otherwise set the ant taboo table k=k+1 and execute step 10;

[0058] Step 12: After all m ants have traversed all the areas, global pheromone updates are performed.

[0059] Step 13: Check whether the number of iterations Nc is greater than the maximum number of iterations of the ant colony algorithm. If Nc≥Ncmax, execute step 14, otherwise execute step 9;

[0060] Step 14: Output the job sequence path solution set;

[0061] Step 15, set the second-layer genetic algorithm population size, crossover probability, and mutation probability. If the population size is set to 4 to 6 times the sum of the number of forest areas and aircraft take-off and landing points, such as 18 areas, then set the population size to 100; the crossover probability, mutation probability, and generation gap are all set to constants; the crossover probability is set to 0.6 to 0.9, such as 0.8, the mutation probability is set to between 0.0001 and 0.1, such as 0.1, and the generation gap is set to 0.9 to 0.95, such as 0.9. The maximum number of iterations of the second-layer algorithm is GENMAX2, such as 2000. And the initial value of the iteration number is set to 1, that is, gen2 = 1;

[0062] Step 16, the second-layer genetic algorithm initializes the population Chrom2, using binary coding. The coding method uses binary coding. Taking four areas as an example, the operation sequence is assumed to be ABCD, where A represents the aircraft take-off and landing point. The operation start and end points of area B can be B1 and B2 or B2 and B1, respectively, and the two states are represented by 0 and 1 respectively. Then the state code of A1A2B1B2C1C2D1D2 is 0000. In particular, the coordinates of the aircraft take-off and landing points A1 and A2 are exactly the same, indicating that the operation sequence is starting from A, B2 in, B1 out, C1 in, C2 out, D2 in, D1 out, and then back to A. Then the state code of A1A2B2B1C1C2D2D1 is 0101. In this way, the operation scheduling path between each area considering the entry and exit points of each area starting from the aircraft take-off and landing point can be represented.

[0063] Step 17, calculate the fitness value of the second-layer algorithm. To facilitate the calculation of the fitness of the second-layer genetic algorithm, the neighborhood table is also used. The neighborhood table is a neighborhood table generated by the horizontal and vertical coordinates of the entry and exit points of each area in Table 1. Because the neighborhood table considering the entry and exit points of 18 areas is too large, the domain distance matrix of 4 areas and 1 aircraft take-off and landing point is displayed here. The four areas are A, B, C, and D, and the entry and exit points of each area are represented by two codes, such as the entry and exit points of area A are represented by A1 and A2. The coordinates of the aircraft take-off and landing points are represented by H. The fitness f2 is designed to be the inverse of the shortest distance of all global inter-regional scheduling routes obtained by the first-layer algorithm for each entry and exit state. Taking state code 10010 as an example, the optimal path solution set obtained by the first-layer algorithm is corrected according to the 10010 state.

[0064] Assuming that there are n types of global inter-regional scheduling routes obtained in the first layer of the algorithm, the fitness calculation formula is formula (8).

[0065]

[0066] Step 18, perform selection, crossover, and mutation operations on population Chrom2; then reinsert to obtain updated population Chrom2;

[0067] Step 19, check whether the number of iterations exceeds the maximum number of iterations GENMAX2, when the number of iterations does not exceed the maximum number of iterations, return to step 17, otherwise proceed to step 20;

[0068] Step 20: output the shortest global inter-regional scheduling path, which is the optimal scheduling solution for multi-forest area route scheduling planning.

[0069] The present invention plans the route scheduling paths for multiple forest areas by adopting a double-layer fusion intelligent algorithm, especially for aerial spraying of manned large-scale plant protection aircraft. Considering the safety and the flight distance without spraying in the dispatching between forest areas, the parameters of the plant protection spray operation endurance range, drug load, and plant protection spray operation endurance time are set to be smaller than the aircraft's own performance parameters. The spraying area is calculated based on the endurance mileage, load capacity, and endurance time, and the final determined operation area is the minimum value of the above three.

[0070] The double-layer fusion intelligent algorithm of the present invention adopts a serial fusion method, and the number of iterations is the sum of the number of iterations of the two algorithms, which is faster than the nested fusion. The first layer adopts a combination algorithm of genetic algorithm and ant colony algorithm, which takes advantage of the fast initial search speed of genetic algorithm, and uses the optimized results of genetic algorithm to initialize the pheromone of ant colony algorithm, avoiding the blindness of the initial search stage of ant colony algorithm, thereby improving the search speed of ant colony algorithm, and quickly obtaining a better job sequence path solution set; the second layer algorithm adopts genetic algorithm, combined with the job sequence path solution set obtained by the first layer, considering the entry and exit points of each area, so as to obtain the shortest global inter-regional scheduling path, which avoids the local optimal solution of the global inter-regional scheduling path that only seeks the shortest job sequence path in the first layer program, and has high calculation efficiency, thereby improving the path planning efficiency of spraying in multiple forest areas.

[0071] The present invention can shorten the number of turns of the plant protection aircraft in a single forest area, shorten the inter-regional dispatching path distance of the pesticide application operation in multiple forest areas, save the working time of the pesticide application operation in multiple forest areas, improve the pesticide application efficiency in the forest area, and effectively reduce the use of aviation fuel, save the economic cost of the pesticide application operation in the forest area, and bring convenience to the pesticide application operation in multiple forest areas.

Claims

1. A multi-forest route scheduling and planning method based on a double-layer fusion intelligent algorithm, characterized by: The steps include: S1. Set the population size, length, crossover probability, and mutation probability of the first-layer genetic algorithm according to the number of forest areas that need to be sprayed; A full coverage route planning algorithm is used inside each forest area, that is, a parallel line is drawn from the longest side of the boundary according to the width of the aircraft spray. When it reaches the intersection of other boundaries, the aircraft turns around and flies until all areas of the area are traversed. Therefore, each area must have an entry point and an exit point. During scheduling planning, it must enter and exit from two points, but which point is not specific. Each forest area is represented by the midpoint of the line connecting the entry and exit points. The aircraft take-off and landing point is regarded as a point and placed at the end of the population length. The length of the population is the number of forest areas + 1. S2, using decimal coding and randomly generating populations to obtain the initial population Chrom1; S3, calculate the fitness of the initial population Chrom1, the fitness value is the reciprocal of the length of the job sequence path corresponding to each chromosome; S4, performing selection, crossover, mutation, and reversal operations on the initial population Chrom1; S5, reinsert into the initial population Chrom1 to obtain the updated updated population Chrom1; S6, check whether the number of iterations reaches the maximum value, if it reaches the maximum value, execute S7, otherwise execute S3; S7. Initialize the ant colony algorithm pheromone according to the result in the updated population Chrom1; if the updated population Chrom1 contains the path from area 1 to area 2, increase the pheromone of the path from area 1 to area 2 when setting the ant colony algorithm pheromone; the pheromone increase value is the fitness value of the chromosome with the largest fitness value in the updated population Chrom1; S8, set the number of ants m, information heuristic factor, expected heuristic factor, pheromone volatilization factor, pheromone enhancement coefficient, and maximum number of iterations of the ant colony algorithm; set the initial value of the initial number of iterations Nc=0; S9, the iteration counter is increased by 1, and m ants are randomly placed on the nodes of the multi-area forest area to be planned; S10, the ant taboo table index number k=1, the ant selects the next area according to the state transition probability, updates the local pheromone, that is, when passing through the area, the pheromone of the path between the area and the previous area is appropriately increased, and the area taboo table is modified, that is, the area that has been passed is removed from the set of areas to be traversed, until the ant has traversed all areas without repetition; the ant updates the local pheromone once every time it arrives at an area; S11, check whether the ant index number k is greater than the number of ants m; when k≥m, execute S12, otherwise set the ant taboo table k=k+1 and execute S10; S12, m ants traverse all patches and perform global pheromone updates; S13, check whether the number of iterations Nc is greater than the maximum number of iterations of the ant colony algorithm; when Nc≥Ncmax, execute step S14, otherwise execute step S9; S14, outputting the job sequence path solution set; S15, setting the second-layer genetic algorithm population size, crossover probability, mutation probability, the second-layer algorithm maximum number of iterations GENMAX2, and setting the initial value of the number of iterations to 1, that is, gen2 = 1; S16, the second-level genetic algorithm initializes the population Chrom2, using binary coding; S17, calculate the fitness value of the second-layer algorithm, regard the aircraft take-off and landing points as two points, representing the global inter-regional scheduling routes starting from the aircraft take-off and landing points considering the entry and exit points of each area. The first layer of the algorithm obtains n types of global inter-regional scheduling routes, so the fitness calculation formula is The fitness f2 is the inverse of the shortest distance of all global inter-regional scheduling routes obtained by the first-layer algorithm under each entry and exit state; S18, performing selection, crossover, and mutation operations on population Chrom2; and then reinserting to obtain updated population Chrom2; S19, checking whether the number of iterations exceeds the maximum number of iterations GENMAX2, when the number of iterations does not exceed the maximum number of iterations, returning to step S17, otherwise proceeding to step S20; S20, outputting the shortest global inter-regional scheduling path, where the shortest scheduling path is the optimal scheduling solution for multi-forest area route scheduling planning.

2. The multi-forest route scheduling and planning method based on a double-layer fusion intelligent algorithm as claimed in claim 1 is characterized by: In step S1, the population size in the first-layer genetic algorithm population is set to 4 to 6 times the sum of the number of forest areas and the number of aircraft take-off and landing points, and the number of iterations, crossover probability, mutation probability, and generation gap are all set to constants.

3. The multi-forest route scheduling and planning method based on a double-layer fusion intelligent algorithm as claimed in claim 2 is characterized by: The crossover probability is set to 0.6-0.9, the mutation probability is set to 0.0001-0.1, and the generation gap is set to 0.9-0.

95.

4. The multi-forest route scheduling and planning method based on a double-layer fusion intelligent algorithm as claimed in claim 1 is characterized by: In step S8, the number of ants, information heuristic factor, expected heuristic factor, pheromone volatilization factor, and pheromone enhancement coefficient of the ant colony algorithm are all set as constants.

5. The multi-forest area route scheduling and planning method based on a double-layer fusion intelligent algorithm as claimed in claim 4 is characterized by: The number of ants m is set to 2 / 3 times the number of patches, the information heuristic factor is set between 1 and 5, the expectation heuristic factor is set between 2 and 5, the pheromone volatility factor is set between 0.1 and 0.5, and the pheromone enhancement coefficient is set between 100 and 1000.

6. The multi-forest route scheduling and planning method based on a double-layer fusion intelligent algorithm as claimed in claim 1 is characterized by: In step S15, the population size of the second-layer genetic algorithm population is set to 4 to 6 times the sum of the number of forest areas and the aircraft take-off and landing points, and the crossover probability, mutation probability, and generation gap are all set to constants.

7. The multi-forest area route scheduling and planning method based on a double-layer fusion intelligent algorithm as claimed in claim 6 is characterized by: The crossover probability was set between 0.6 and 0.9, the mutation probability was set between 0.0001 and 0.1, and the generation gap was set between 0.9 and 0.95.

Images