Corn harvester and bundling machine cooperative scheduling method for soil mechanical compaction and reduction

Abstract

The invention discloses a corn harvester and bundling machine cooperative scheduling method for soil mechanical compaction and reduction, and relates to the field of agricultural machinery scheduling. The invention aims to solve the problems of unreasonable scheduling, resource waste and low efficiency of the existing corn combine harvester and straw bundling machine. The method comprises the following steps: establishing an objective function and corresponding constraint conditions by taking the lowest total scheduling cost, the maximization of total field piece compaction satisfaction and the minimization of total working time as objectives according to the position, area and compaction degree requirements of each field piece in a to-be-operated area and starting warehouses and ending warehouses of all corn combine harvesters and straw balers; solving the objective function under the constraint condition by adopting a cuckoo algorithm; and motion paths and motion time of all corn combine harvesters and straw balers in different fields are obtained. The method is suitable for cooperative scheduling of the corn harvester and the bundling machine.

Description

Technical Field

[0001] The present invention relates to the field of agricultural machinery scheduling. Background Art

[0002] Smart agriculture refers to the perception, transmission, storage, processing, and control of the entire agricultural production process with the support of digital, networked, and intelligent technologies, so as to achieve visualization of the agricultural production process, intelligence of decision-making, precision of operation, and informatization of management. The black soil is a high-quality and scarce cultivated land resource, playing an irreplaceable role in maintaining national food security and the stable development of the economy and society. However, due to long-term high-intensity development and utilization and unreasonable tillage methods, the black soil in Northeast China faces serious degradation problems. Although relevant departments have implemented relevant policies and regulations to promote the application of smart agriculture in black soil protection, the coverage of conservation tillage has not been fully achieved, and the trend of soil erosion has not been fundamentally curbed. The situation of black soil protection remains severe. Reducing the soil compaction degree of black soil can improve soil structure, increase soil fertility, and enhance the soil's water and fertilizer retention capacity. Using a corn combine harvester and a straw baler that meet the soil compaction degree to complete the harvesting and straw baling operations can achieve the sustainable utilization and protection of black soil. However, when the existing corn combine harvester and straw baler are operating, there are often unreasonable scheduling problems between the corn combine harvester and the straw baler, resulting in resource waste and low efficiency. Summary of the Invention

[0003] The present invention is to solve the problems of unreasonable scheduling between the existing corn combine harvester and straw baler, resulting in resource waste and low efficiency. Now, a collaborative scheduling method for a corn harvester and a baler for reducing soil mechanical compaction is provided.

[0004] The collaborative scheduling method for a corn harvester and a baler for reducing soil mechanical compaction according to the present invention includes:

[0005] According to the position, area, compaction degree requirements of each field block in the area to be operated, the starting warehouse O and the ending warehouse D of all corn combine harvesters and straw balers, with the goal of minimizing the total scheduling cost, maximizing the total field block compaction satisfaction, and minimizing the total working time, establish the objective function for the optimal path of the corn combine harvester and the straw baler and its corresponding constraint conditions;

[0006] Adopt the cuckoo algorithm to solve the objective function under the constraint conditions; obtain the movement paths and movement times of all corn combine harvesters and straw balers between different field blocks.

[0007] Further, in the present invention, the objective function is:

[0008]

[0009] Among them: β1 is the objective weight of the total scheduling cost in the objective function, β2 is the objective weight of the total working time in the objective function, β3 is the objective weight of the overall field compaction satisfaction in the objective function, c ij The moving cost from field i to field j; x ijv Indicates whether the corn combine harvester v travels from field i to field j. If so, x ijv = 1, otherwise x ijv = 0; y ijk Indicates whether the straw baler k travels from field i to field j. If so, y ijk = 1. Otherwise y ijk = 0; t Dk Is the time when the straw baler k arrives at the terminal warehouse D; t iD Is the moving time from field i to the termination warehouse; η i Is the compaction satisfaction of field i. S represents the set of fields, V represents the set of corn combine harvesters, v represents the vth corn combine harvester; K represents the set of straw balers, k represents the kth straw baler, and i and j respectively represent the ith and jth fields; y iDk Indicates whether the straw baler k travels from field i to the termination warehouse D. If so, y iDk = 1, otherwise y iDk = 0.

[0010] Furthermore, in the present invention, the constraint condition formula:

[0011]

[0012]

[0013] x ijv , y ijk , r jv , u jk , σ v ∈ {0, 1} (17)

[0014] t iv , t ik , η i ≥ 0 (18)

[0015] Among them, x ojv Indicates whether the vth corn combine harvester travels from the starting warehouse O to field j. If so, x ojv = 1, otherwise x ojv = 0; x iDv Indicates whether the vth corn combine harvester travels from the ith field to the termination warehouse D. If so, x iDv = 1, otherwise x iDv = 0; x jsvIndicates whether the v-th corn combine harvester travels from the j-th field to the v-th field. If so, x jsv = 1. Otherwise, x jsv = 0; y jsk Indicates whether the straw baler k travels from the s-th field to the j-th field. If so, y jsk = 1. Otherwise, y jsk = 0; y sik Indicates whether the straw baler k travels from the s-th field to the i-th field. If so, y sik = 1. Otherwise, y sik = 0; y Ojk Indicates whether the straw baler k travels from the starting warehouse O to the field j. If so, y Ojk = 1. Otherwise, y Ojk = 0; S represents the set of fields, i, j, s respectively represent the i-th, j-th, s-th fields; V represents the set of corn combine harvesters, v represents the v-th corn combine harvester; K represents the set of straw balers, k represents the k-th straw baler, O represents the starting warehouse, {O} represents the set of starting warehouses, D represents the termination warehouse; {D} represents the set of termination warehouses, t ij Indicates the travel time from field i to field j, Indicates the setup time for the corn combine harvester v to travel from field s to field i, Indicates the setup time for the straw baler k to travel from field s to field i, Indicates the straw bale packing time for field i; δ represents the time dilation coefficient for the cooperation between a specific model of corn combine harvester and the straw baler; a i Indicates the area of field i, e v Indicates the working efficiency of the corn combine harvester v; e k Indicates the working efficiency of the straw baler k; Indicates the target compaction degree for field i; l v Indicates the compaction degree after the corn combine harvester v has operated; l k Indicates the compaction degree after the straw baler k has operated; M represents an infinitely large positive number; r jv Indicates whether the corn combine harvester v is working in field j. When the corn combine harvester v is working in field j, r jv = 1. Otherwise, r jv = 0; u jk Indicates whether the straw baler k is working inside field j. When the straw baler k is working in field j, u jk = 1. Otherwise, u jk = 0; t iv Indicates the time when the corn combine harvester v arrives at field i; t ik Indicates the time when the straw baler k arrives at field i; σ vIt is represented that if the corn combine harvester v is a model that requires the cooperation of a specific type of straw baler, then it is equal to 1, otherwise it is equal to 0.

[0016] Furthermore, in the present invention, the process of solving the objective function under the constraint conditions by using the cuckoo algorithm is as follows:

[0017] Step 1: Initialize the parameters and population of the cuckoo algorithm; each individual in the population represents a scheduling solution, each scheduling solution satisfies the constraint conditions, and each scheduling solution includes a pair of decision variables x ijv , y ijk and the corresponding objective function value;

[0018] Step 2: If the current iteration number reaches the set maximum iteration number or the objective function value reaches the optimal value, then the solution of the objective function is completed and the optimal solution is obtained; otherwise, execute Step 3;

[0019] Step 3: Generate a new scheduling solution by using the cuckoo's jumping strategy, and determine whether the new scheduling solution satisfies all the constraint conditions. If so, execute Step 4; otherwise, regenerate a new scheduling solution by using the cuckoo's jumping strategy until the new scheduling solution satisfies all the constraint conditions, and then execute Step 4;

[0020] Step 4: Take the objective function as the fitness function of the cuckoo algorithm, calculate the fitness function values of all the new scheduling solutions by using the cuckoo algorithm, screen the scheduling solutions with larger fitness function values according to the set ratio, retain the screened scheduling solutions, and take the remaining screened scheduling solutions as the individuals to be mutated, and then execute Step 5;

[0021] Step 5: Mutate the individuals to be mutated, and determine whether the mutated scheduling solution satisfies all the constraint conditions. If so, execute Step 6; otherwise, continue to mutate the mutated scheduling solution that does not satisfy the constraint conditions until the mutated scheduling solution satisfies all the constraint conditions; then execute Step 6;

[0022] Step 6: Calculate the fitness function value of the mutated scheduling solution. If the fitness value of the mutated scheduling solution is greater than the fitness value of the corresponding pre-mutated scheduling solution, then retain the mutated scheduling solution; otherwise, retain the corresponding pre-mutated scheduling solution;

[0023] Step 7: Calculate the fitness function values of the scheduling solutions retained in Step 6 and the scheduling solutions retained in Step 4 as the fitness function value of the current iteration scheduling solution. If the current iteration reaches the maximum iteration number or the fitness function value of the current iteration scheduling solution reaches the optimal value, obtain the optimal scheduling solution; otherwise, return to execute Step 3 until the solution of the objective function is completed and the optimal solution is obtained.

[0024] Further, in the present invention, in step three, the formula for generating a new scheduling solution by adopting the jumping strategy of cuckoos is as follows:

[0025] X n = X c + α·step

[0026] Where: X c represents an individual in the current population; step is used to simulate random jumps to enhance the global search ability, and α represents the jumping step length of cuckoos, which controls the jumping amplitude when generating a new solution.

[0027] Further, in the present invention, in step six, the formula for mutating the scheduling solution with a fitness greater than the threshold is as follows:

[0028] X m = X s + α m ·rand(-1, 1)

[0029] Where, X m is the mutated individual; X s is the selected inferior individual; rand(-1, 1) is a uniformly distributed random number used to control the perturbation direction; α m controls the mutation range and usually takes a value of 0.01 - 0.1.

[0030] The combined scheduling method of the corn combine harvester and the straw baler according to the present invention aims at each field operation point, comprehensively considers the position factor and the operation matching factor of the two types of machines. The corn combine harvester and the straw baler will start from the starting warehouse, complete the operations of the assigned fields, and then return to the terminal warehouse. The straw baling operation can only be carried out after the harvesting operation of the same field is completed. The movement of the corn combine harvester and the straw baler between the starting warehouse, the terminal warehouse and the fields will generate movement time and movement cost. The corn combine harvester and the straw baler will generate operation time and operation cost when operating in each field, and will also compact the soil. At the same time, the use of the cuckoo genetic algorithm effectively improves the accuracy of obtaining the optimal strategy, improves the operation efficiency, and reduces the waste of resources. Description of the Drawings

[0031] Figure 1 is a flowchart of solving the objective function under the constraint conditions by using the cuckoo algorithm in the present invention. Detailed Embodiments

[0032] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other.

[0033] Specific Embodiment 1: Refer to Figure 1 This specific embodiment will be specifically described. The collaborative scheduling method for a corn harvester and a baler for reducing soil mechanical compaction according to this embodiment includes:

[0034] Based on the location, area, compaction degree requirements of each field block in the area to be operated, and the starting warehouse O and the ending warehouse D of all corn combine harvesters and straw balers, with the goal of minimizing the total scheduling cost, maximizing the total field block compaction satisfaction, and minimizing the total working time, establish the objective function for the optimal path of the corn combine harvester and the straw baler and its corresponding constraints;

[0035] Adopt the cuckoo algorithm to solve the objective function under the above constraints; obtain the movement paths and movement times of all corn combine harvesters and straw balers among different field blocks.

[0036] Furthermore, in the present invention, the objective function is:

[0037]

[0038] Among them: β1 is the objective weight of the total scheduling cost in the objective function, β2 is the objective weight of the total working time in the objective function, β3 is the objective weight of the total field block compaction satisfaction in the objective function, c ij The moving cost from field block i to field block j; x ijv Indicates whether the corn combine harvester v sails from field block i to field block j. If so, x ijv =1, otherwise x ijv =0; y ijk Indicates whether the straw baler k goes from field block i to field block j. If so, y ijk =1. Otherwise, y ijk =0; t Dk Is the time when the straw baler k arrives at the terminal warehouse D; t iD Is the moving time from field block i to the ending warehouse; η iis the compaction satisfaction degree of field block i, S represents the set of field blocks, V represents the set of corn combine harvesters, v represents the v-th corn combine harvester; K represents the set of straw balers, k represents the k-th straw baler, and i, j respectively represent the i-th and j-th field blocks; y iDk represents whether the straw baler k goes from field block i to the terminal warehouse D. If so, y iDk = 1, otherwise y iDk = 0.

[0039] Furthermore, in the present invention, the constraint condition formula:

[0040]

[0041] x ijv , y ijk , r jv , u jk , σ v ∈ {0, 1}(17)

[0042] t iv , t ik , η i ≥ 0 (18)

[0043] Among them, x ojv represents whether the v-th corn combine harvester goes from the starting warehouse O to field block j. If so, x ojv = 1, otherwise x ojv = 0; x iDv represents whether the v-th corn combine harvester goes from the i-th field block to the terminal warehouse D. If so, x iDv = 1, otherwise x iDv = 0; x jsv represents whether the v-th corn combine harvester goes from the j-th field block to the v-th field block. If so, x jsv = 1. Otherwise x jsv = 0; y jsk represents whether the straw baler k goes from the s-th field block to the j-th field block. If so, y jsk = 1. Otherwise y jsk = 0; y sik represents whether the straw baler k goes from the s-th field block to the i-th field block. If so, y sik = 1. Otherwise y sik = 0; y Ojk represents whether the straw baler k goes from the starting warehouse O to field block j. If so, y Ojk = 1. Otherwise y Ojk= 0; S represents the set of fields, where i, j, and s represent the i-th, j-th, and s-th fields respectively; V represents the set of corn combine harvesters, and v represents the v-th corn combine harvester; K represents the set of straw balers, and k represents the k-th straw baler, O represents the starting warehouse, {O} represents the set of starting warehouses, D represents the ending warehouse; {D} represents the set of ending warehouses, t ij represents the moving time from field i to field j, represents the setup time for corn combine harvester v to move from field s to field i, represents the setup time for straw baler k to move from field s to field i, represents the straw bailing time of field i; δ represents the time dilation coefficient for the cooperation between a specific model of corn combine harvester and straw baler; a i represents the area of field i, e v represents the working efficiency of corn combine harvester v; e k represents the working efficiency of straw baler k; represents the target compaction degree of field i; l v represents the compaction degree after the operation of corn combine harvester v; l k represents the compaction degree after the operation of straw baler k; M represents an infinitely large positive number; r jv represents whether corn combine harvester v is working in field j. When corn combine harvester v is working in field j, r jv = 1, otherwise r jv = 0; u jk represents whether straw baler k is working in field j. When straw baler k is working in field j, u jk = 1, otherwise u jk = 0; t iv represents the time when corn combine harvester v arrives at field i; t ik represents the time when straw baler k arrives at field i; σ v represents that if corn combine harvester v is a model that requires cooperation with a specific model of straw baler, then = 1, otherwise = 0.

[0044] Furthermore, in the present invention, the process of solving the objective function under the above constraints by using the cuckoo algorithm is as follows:

[0045] Step 1: Initialize the parameters and population of the cuckoo algorithm; each individual in the population represents a scheduling solution, each scheduling solution satisfies the constraints, and each scheduling solution includes a pair of decision variables x ijv 、y ijk and the corresponding objective function value;

[0046] Step 2: If the current iteration number reaches the set maximum iteration number or the objective function value reaches the optimal value, then the solution of the objective function is completed and the optimal solution is obtained; otherwise, go to Step 3;

[0047] Step 3: Generate a new scheduling solution using the cuckoo's hopping strategy, and determine whether the new scheduling solution satisfies all the constraint conditions. If it does, go to Step 4; otherwise, regenerate a new scheduling solution using the cuckoo's hopping strategy until the new scheduling solution satisfies all the constraint conditions, and then go to Step 4;

[0048] Step 4: Take the objective function as the fitness function of the cuckoo algorithm, calculate the fitness function values of all the new scheduling solutions using the cuckoo algorithm, screen the scheduling solutions with larger fitness function values according to a set ratio, retain the screened scheduling solutions, and take the remaining screened scheduling solutions as the individuals to be mutated, then go to Step 5;

[0049] Step 5: Mutate the individuals to be mutated, and determine whether the mutated scheduling solution satisfies all the constraint conditions. If it does, go to Step 6; otherwise, continue to mutate the mutated scheduling solution that does not satisfy the constraint conditions until the mutated scheduling solution satisfies all the constraint conditions; then go to Step 6;

[0050] Step 6: Calculate the fitness function value of the mutated scheduling solution. If the fitness value of the mutated scheduling solution is greater than the fitness value of the corresponding scheduling solution before mutation, then retain the mutated scheduling solution; otherwise, retain the corresponding scheduling solution before mutation;

[0051] Step 7: Calculate the fitness function values of the scheduling solutions retained in Step 6 and the scheduling solutions retained in Step 4 as the fitness function value of the current iteration scheduling solution. If the current iteration reaches the maximum iteration number or the fitness function value of the current iteration scheduling solution reaches the optimal value, obtain the optimal scheduling solution; otherwise, return to Step 3 until the solution of the objective function is completed and the optimal solution is obtained.

[0052] Furthermore, in the present invention, in Step 3, the formula for generating a new scheduling solution using the cuckoo's hopping strategy is:

[0053] X n =X c +α·step

[0054] where: X c represents an individual in the current population; step is used to simulate random hopping to enhance the global search ability, and α represents the hopping step size of the cuckoo, which controls the hopping amplitude when generating a new solution.

[0055] Furthermore, in the present invention, in Step 6, the formula for mutating the scheduling solution with fitness greater than the threshold is:

[0056] X m = X s + α m ·rand(-1, 1)

[0057] where X m is the mutated individual; X s is the selected inferior individual; rand(-1, 1) is a uniformly distributed random number used to control the perturbation direction; α m is used to control the mutation range and usually takes values from 0.01 to 0.1.

[0058] Specific implementation process:

[0059] Construct a combined scheduling model for a corn combine harvester and a straw baler: The combined scheduling model for the corn combine harvester and the straw baler includes: a set of fields composed of multiple farmlands in the target area, a set of corn combine harvesters composed of multiple corn combine harvesters, a set of straw balers composed of multiple straw balers, a starting warehouse O, a terminating warehouse D, and preset relevant constraint conditions;

[0060] This method aims to solve the combined scheduling problem of a corn combine harvester and a straw baler considering the satisfaction of field compaction. Each field has certain requirements for soil compaction. The objectives of this method are to minimize the total scheduling cost, minimize the total working time, and maximize the satisfaction of field compaction.

[0061] For each field operation point, considering the location factor and the operation matching factor of the two types of machines, the corn combine harvester and the straw baler will start from the starting warehouse, return to the terminating warehouse after completing the operations on the assigned fields. The straw baling operation can only be carried out after the harvesting operation on the same field is completed. The movement of the corn combine harvester and the straw baler between the starting warehouse, the terminating warehouse and the fields will generate movement time and movement cost. The corn combine harvester and the straw baler will generate operation time and operation cost when operating on each field, and will also compact the soil.

[0062] Specifically, in the process of constructing the corresponding model according to the characteristics of this problem, the problem description is as follows: Starting from a garage with multiple corn combine harvesters and straw balers with different parameters, it is necessary to carry out harvesting and straw baling operations on multiple fields in the area with different compaction requirements. Each field can only be served once by the corn combine harvester and the straw baler respectively. The start time of the corn combine harvester should be later than the earliest allowable harvesting time, and the earliest allowable operation time of the straw baler on a certain field is later than the time when the corn combine harvester completes the operation.

[0063] Objective function: (1) Minimize the total scheduling cost. The total scheduling cost is the sum of the moving costs of the corn combine harvesters and the straw balers. The moving cost between each field block is a fixed value. (2) Maximize the overall field block compaction satisfaction. Each field block has a compaction requirement. The compaction degree after the operation of different models of corn combine harvesters and straw balers is a fixed value. The compaction degree after the operation of each field block is the sum of the compaction degrees after the operation of the corn combine harvesters and straw balers operating in that field block. The compaction satisfaction of each field block is calculated from the field block compaction requirement and the compaction degree after the operation. (3) Minimize the total working time. The total working time is obtained by calculating the time point when all straw balers complete the straw baling operation in the last field block.

[0064] Problem assumptions:

[0065] (1) At the start of the operation, all corn combine harvesters and straw balers need to depart from the starting warehouse O. Multiple corn combine harvesters and straw balers can flow out from the starting warehouse O.

[0066] (2) Each field block can only be visited once by a corn combine harvester and a straw baler respectively, and the demands of all field blocks need to be met;

[0067] (3) All corn combine harvesters and straw balers return to the terminal warehouse D after completing the operations on the assigned field blocks. All corn combine harvesters and straw balers must return to the end point after completing the operations.

[0068] (4) After a corn combine harvester and a straw baler arrive at each field block, there is a setup time before starting the operation, which is used to complete tasks such as refueling, lubricating, and repairing. This setup time is related to the previous node where the corn combine harvester and the straw baler arrived at this field block.

[0069] (5) For some specific models of corn combine harvesters, only specific straw balers can operate after the work, and at this time, an additional moving time is generated, which is represented by a fixed expansion coefficient.

[0070] (6) The working time of all field blocks is the same every day because the sunrise and sunset times are similar during the harvest season in the same city.

[0071] (7) Moving time and moving cost are generated when a corn combine harvester and a straw baler move between the starting warehouse, the terminal warehouse, and the field blocks, which are represented by fixed values.

[0072] (8) The time point when a straw baler conducts the straw baling operation in a certain field block is not earlier than the time point when the corn combine harvester completes the harvesting operation in that field block.

[0073] 1. The expression of the objective function is:

[0074]

[0075] The objective function (1) is the total objective function of the function, including minimizing the total scheduling cost, minimizing the total working time, and maximizing the satisfaction degree of field compaction. Among them:

[0076] β1: The objective weight of the total scheduling cost in the objective function; β2: The objective weight of the total working time in the objective function; β3: The objective weight of the total satisfaction degree of field compaction in the objective function; c ij : The moving cost from field i to field j; x ijv : If the corn combine harvester v drives from field i to field j, then = 1, otherwise = 0; y ijk : If the straw baler k goes from field i to field j, then = 1. Otherwise = 0; t Dk : The time when the straw returning machine k arrives at the terminal warehouse D; t iD : The moving time from field i to the termination warehouse; η i : The compaction satisfaction degree of field i;

[0077] 3. The constraint conditions include:

[0078]

[0079]

[0080] x ijv ,y ijk ,r jv ,u jk ,σ v ∈{0,1}(17)

[0081] t iv ,t ik ,η i ≥0 (18)

[0082] Among them, S: The set of fields, represented by i, j, s; V: The set of corn combine harvesters, represented by v; K: The set of straw balers, indexed by k; O: The starting warehouse; D: The termination warehouse; t ij : The moving time from field i to field j; The setup time for the corn combine harvester v to move from field s to field i; The setup time for the straw baler k to move from field s to field i; The straw bailing time of field i; δ: The time expansion coefficient for the cooperation between a specific model of corn combine harvester and straw baler; a i : The area of field i; e v : The working efficiency of the corn combine harvester v; e k: The working efficiency of the straw baler k; The target compaction degree of the field i; l v : The compaction degree after the corn combine harvester v operates; l k : The compaction degree after the straw baler k operates; M: An infinitely large positive number; r jv , if the corn combine harvester v works for the field j, then = 1, otherwise = 0; u jk : If the straw baler k works for the field j, then = 1, otherwise = 0; t iv : The time when the corn combine harvester v arrives at the field i; t ik : The time when the straw baler k arrives at the field i; σ v : If the corn combine harvester v is a model that requires the cooperation of a specific type of straw baler, then = 1, otherwise = 0;

[0083] Constraints (2) and (3) respectively stipulate that the corn combine harvester departs from the starting warehouse and returns to the terminal warehouse after completing the operation; Constraints (4) and (5) respectively stipulate that the straw baler departs from the starting warehouse and returns to the terminal warehouse after completing the operation; Constraints (6) and (7) stipulate that each field can only be served once by the corn combine harvester and the straw baler respectively; Constraints (8) and (9) illustrate the relationship between the decision variables; Constraints (10) and (11) stipulate that the number of inflows and outflows of the corn combine harvester and the straw baler in each field are equal; Constraint (12) determines the straw bale packing working time of each field; Constraints (13) and (14) are the time increment constraints for the corn combine harvester and the straw baler; Constraint (15) ensures that the straw bale packing operation starts after the corn harvesting operation is completed in the same field; Constraint (16) determines the compaction satisfaction degree of each field; Constraints (17) and (18) stipulate the value ranges of the relevant variables.

[0084] Solution steps based on the cuckoo algorithm:

[0085] Principle of using the cuckoo algorithm to solve the joint scheduling problem of the corn combine harvester and the straw baler:

[0086] (1) The cuckoo algorithm optimizes the problem by simulating the breeding behavior of cuckoos. It explores a broader solution space by simulating the behavior of cuckoos generating candidate solutions through random jumps and using random step sizes.

[0087] (2) The fitness function of the cuckoo algorithm is obtained from the objective function of this joint scheduling problem and is used to evaluate the quality of each generated solution. The objective function includes: I. The objective of minimizing the total scheduling cost: including the moving costs of the corn combine harvester and the straw baler; II. The objective of minimizing the total working time; III. The objective of maximizing the total compaction satisfaction: calculated through the compaction target of each field block and the compaction degree after operation.

[0088] (3) Each cuckoo generates a new solution through a leapfrog search. The formula for generating the new solution is based on the current optimal solution and the step size. The size of the step size is controlled by a distribution function, and a random step size is used to introduce diversity and perturbation in order to jump out of the current local optimal solution. After each new solution is generated, it is checked whether the generated solution satisfies all scheduling constraints. If the solution is infeasible, it is repaired or regenerated to ensure that each solution is feasible.

[0089] (4) The mutation operation of the cuckoo algorithm is realized by simulating the leapfrog search behavior of the cuckoo. In the joint scheduling problem, the purpose of mutation is to enhance the diversity of the population and avoid the algorithm falling into local optimality. Mutation explores a wider solution space by randomly perturbing the decision variables. The amplitude of mutation is controlled by the mutation step size (α m ), and this parameter affects the intensity of mutation.

[0090] Specific solution steps:

[0091] (1) Set parameters and initialize the population

[0092] Parameter setting: Population size popnum: representing the number of solutions explored simultaneously; Discovery probability P a : The probability that the inferior solution is replaced; Maximum number of iterations MaxN_iter: The maximum number of iterations when the algorithm stops; Step size α: controlling the jump amplitude when generating a new solution.

[0093] Population initialization:

[0094] I. Generate the initial population. Each individual represents a complete scheduling solution, including decision variables x ijv 、x ijk , and the corresponding objective function value. II. When initializing the population, ensure that the generated individuals meet the problem constraints.

[0095] (2) Judge whether the termination condition is satisfied

[0096] I. Check whether the maximum number of iterations MaxN_iter is reached, or a satisfactory objective value is found. II. If satisfied, the algorithm terminates and outputs the optimal solution in the current population. III. If not satisfied, continue to execute step (3).

[0097] (3) Generate candidate population operation

[0098] I. Generate new solutions using the cuckoo's hopping strategy:

[0099] X n = X c + α · step

[0100] where: X c represents an individual in the current population; step is used to simulate random hopping to enhance the global search ability;

[0101] II. Check the feasibility of the generated new solutions to ensure that all constraints are satisfied. For infeasible solutions, use penalty functions to repair them or directly regenerate the solutions.

[0102] (4) Execute the elitist selection operator

[0103] Strategy: Select individuals with higher fitness from the parent and candidate populations to enter the next generation.

[0104] Fitness function:

[0105]

[0106] where: β1: The objective weight of the total scheduling cost in the objective function; β2: The objective weight of the total working time in the objective function; β3: The objective weight of the overall field compaction satisfaction in the objective function; the total scheduling cost, total travel time, and compaction satisfaction respectively measure the quality of the solution.

[0107] (5) Execute the random migration operator

[0108] I. Randomly select a certain proportion (controlled by P a ) of inferior individuals for mutation according to the mutation formula.

[0109] X m = X s + α m · rand(-1, 1)

[0110] where: X m is the mutated individual; X s is the selected inferior individual; rand(-1, 1) is a uniformly distributed random number used to control the perturbation direction; α m controls the mutation range, usually taking values from 0.01 to 0.1;

[0111] II. The feasibility of the mutated solution needs to be rechecked. Infeasible solutions are also repaired or regenerated.

[0112] (6) Execute the elitist selection operator again

[0113] I. For the mutated individual, compare the fitness before and after mutation: If the fitness after mutation is higher, retain the mutated individual; otherwise, retain the individual before mutation. II. Update the population and use the high-quality individuals as the parents of the next generation.

[0114] (7) Iterative update and output results

[0115] I. Output results: If the algorithm meets the termination condition, output the optimal solution and the corresponding objective function value.

[0116] II. Iterative update: If the termination condition is not reached, return to step (3) and continue the iteration.

[0117] Although the present invention has been described herein with reference to specific embodiments, it should be understood that these embodiments are merely examples of the principles and applications of the present invention. Therefore, it should be understood that many modifications can be made to the exemplary embodiments, and other arrangements can be designed, as long as they do not depart from the spirit and scope of the present invention as defined by the appended claims. It should be understood that the different dependent claims and the features described herein can be combined in a manner different from that described in the original claims. It should also be understood that the features described in connection with a single embodiment can be used in other described embodiments.

Claims

1. A collaborative scheduling method for a corn harvester and a baler for reducing soil mechanical compaction, characterized in that, Including: Based on the location, area, compaction degree requirements of each field block in the area to be operated, and the starting warehouse O and the ending warehouse D of all corn combine harvesters and straw balers, with the goal of minimizing the total scheduling cost, maximizing the overall satisfaction of field block compaction, and minimizing the total working time, establish the objective function for the optimal path of corn combine harvesters and straw balers and its corresponding constraint conditions; Adopt the cuckoo algorithm to solve the objective function under the said constraint conditions; obtain the movement paths and movement times of all corn combine harvesters and straw balers between different field blocks.

2. The collaborative scheduling method of a corn harvester and a baler for reducing soil mechanical compaction according to claim 1, characterized in that, The objective function is: Among them: β1 is the objective weight of the total scheduling cost in the objective function, β2 is the objective weight of the total working time in the objective function, β3 is the objective weight of the overall field compaction satisfaction in the objective function, c ij The moving cost from field i to field j; x ijv Indicates whether the corn combine harvester v travels from field i to field j. If so, x ijv = 1, otherwise x ijv = 0; y ijk Indicates whether the straw baler k travels from field i to field j. If so, y ijk = 1. Otherwise y ijk = 0; t Dk Is the time when the straw baler k arrives at the terminal warehouse D; t iD Is the moving time from field i to the termination warehouse; η i Is the compaction satisfaction of field i. S represents the set of fields, V represents the set of corn combine harvesters, v represents the vth corn combine harvester; K represents the set of straw balers, k represents the kth straw baler, and i and j respectively represent the ith and jth fields; y iDk Indicates whether the straw baler k travels from field i to the termination warehouse D. If so, y iDk = 1, otherwise y iDk = 0.

3. The collaborative scheduling method for a corn harvester and a baler for reducing soil mechanical compaction according to claim 2, wherein The formula for the constraint conditions is: x ijv , y ijk , r jv , u jk , σ v ∈ {0, 1}(17) t iv , t ik , η i ≥0 (18) Among them, x ojv indicates whether the v-th corn combine harvester drives from the starting warehouse O to the field j. If so, x ojv = 1; otherwise, x ojv = 0; x iDv indicates whether the v-th corn combine harvester drives from the i-th field to the termination warehouse D. If so, x iDv = 1; otherwise, x iDv = 0; x jsv indicates whether the v-th corn combine harvester drives from the j-th field to the v-th field. If so, x jsv = 1; otherwise, x jsv = 0; y jsk indicates whether the straw baler k drives from the s-th field to the j-th field. If so, y jsk = 1; otherwise, y jsk = 0; y sik indicates whether the straw baler k drives from the s-th field to the i-th field. If so, y sik = 1; otherwise, y sik = 0; y Ojk indicates whether the straw baler k goes from the starting warehouse O to the field j. If so, y Ojk = 1; otherwise, y Ojk = 0; S represents the set of fields, and i, j, s represent the i-th, j-th, and s-th fields respectively; V represents the set of corn combine harvesters, and v represents the v-th corn combine harvester; K represents the set of straw balers, and k represents the k-th straw baler, O represents the starting warehouse, {O} represents the set of starting warehouses, D represents the termination warehouse; {D} represents the set of termination warehouses, t ij represents the moving time from field i to field j, represents the setup time for the corn combine harvester v to move from field s to field i, represents the setup time for the straw baler k to move from field s to field i, represents the straw bale packing time of field i; δ represents the time dilation coefficient for the cooperation between a specific model of corn combine harvester and straw baler; a i represents the area of field i, e v represents the working efficiency of the corn combine harvester v; e k represents the working efficiency of the straw baler k; represents the target compaction degree of field i; l v represents the compaction degree after the operation of the corn combine harvester v; l k represents the compaction degree after the operation of the straw baler k; M represents an infinitely large positive number; r jv indicates whether the corn combine harvester v is working in field j. When the corn combine harvester v is working in field j, r jv = 1; otherwise, r jv = 0; u jk Indicates whether the straw baler k is working in the field j. When the straw baler k is working in the field j, u jk = 1, otherwise u jk = 0; t iv Indicates the time when the corn combine harvester v arrives at the field i; t ik Indicates the time when the straw baler k arrives at the field i; σ v Indicates that if the corn combine harvester v is a model that requires a specific type of straw baler for coordinated operation, then = 1, otherwise = 0.

4. The collaborative scheduling method of the corn harvester and baler for reducing soil mechanical compaction according to claim 3, wherein The process of using the cuckoo algorithm to solve the objective function under the said constraint conditions is: Step 1: Initialize the parameters and population of the cuckoo algorithm; each individual in the population represents a scheduling solution, each scheduling solution satisfies the constraint conditions, and each scheduling solution includes a pair of decision variables x ijv , y ijk and the corresponding objective function value; Step 2: If the current iteration number reaches the set maximum iteration number or the objective function value reaches the optimal value, then complete the solution of the objective function to obtain the optimal solution; otherwise, execute Step 3; Step 3: Use the jumping strategy of the cuckoo to generate a new scheduling solution, and determine whether the new scheduling solution satisfies all constraint conditions. If so, execute Step 4; otherwise, re-use the jumping strategy of the cuckoo to generate a new scheduling solution until the new scheduling solution satisfies all constraint conditions, and then execute Step 4; Step 4: Take the objective function as the fitness function of the cuckoo algorithm, calculate the fitness function values of all new scheduling solutions using the cuckoo algorithm, screen the scheduling solutions with larger fitness function values according to the set ratio, retain the screened scheduling solutions, and use the remaining screened scheduling solutions as the individuals to be mutated, and then execute Step 5; Step 5: Mutate the individuals to be mutated, and determine whether the mutated scheduling solution satisfies all constraint conditions. If so, execute Step 6; otherwise, continue to mutate the mutated scheduling solution that does not satisfy the constraint conditions until the mutated scheduling solution satisfies all constraint conditions; then execute Step 6; Step 6: Calculate the fitness function value of the mutated scheduling solution. If the fitness value of the mutated scheduling solution is greater than the fitness value of the corresponding scheduling solution before mutation, then retain the mutated scheduling solution; otherwise, retain the corresponding scheduling solution before mutation; Step 7: Calculate the fitness function values of the scheduling solutions retained in Step 6 and the scheduling solutions retained in Step 4 as the fitness function value of the current iteration scheduling solution. If the current iteration reaches the maximum iteration number or the fitness function value of the current iteration scheduling solution reaches the optimal value, obtain the optimal scheduling solution; otherwise, return to execute Step 3 until the solution of the objective function is completed to obtain the optimal solution.

5. The collaborative scheduling method of the corn harvester and baler for reducing soil mechanical compaction according to claim 4, characterized in that, In Step 3, the formula for using the jumping strategy of the cuckoo to generate a new scheduling solution is: X n = X c + α·step Where: X c represents an individual in the current population; step is used to simulate random jumps to enhance the global search ability, α represents the jump step length of the cuckoo, and controls the jump amplitude when generating new solutions.

6. The collaborative scheduling method of the corn harvester and baler for soil mechanical compaction reduction according to claim 5, wherein In Step 6, the formula for mutating the scheduling solution with fitness greater than the threshold is: X m = X s + α m · rand(-1, 1) Among them, X m is the mutated individual; X s is the selected inferior individual; rand(-1, 1) is a uniformly distributed random number used to control the perturbation direction; α m is used to control the mutation range.

Images