Bundling machine in-field path planning method for soil mechanical compaction subduction

Abstract

The invention discloses a baler in-field path planning method for soil mechanical compaction and reduction, belongs to the field of agricultural machinery scheduling, and aims to solve the problem that an existing path planning method is difficult to adapt to the operation requirements of complex fields. The method comprises the following steps: step 1, acquiring in-field furrow information and boundary point information of an irregular field; 2, setting a path planning rule; and step 3, performing path planning on the harvester and the bundling machine on the irregular field by using an artificial bee colony algorithm, taking the minimization of the total compaction times as a target, taking the working area overlapping times and the treatment starting times of the bundling machine before the completion of the harvester as penalty terms, ending when a termination condition is reached, and outputting an optimal solution.

Description

Technical Field

[0001] The present invention relates to a method for planning the in-field path of a baler for reducing soil mechanical compaction, belonging to the field of agricultural machinery scheduling. Background Art

[0002] With the continuous development of agricultural modernization, the application of intelligent agricultural technologies has increasingly become an important way to improve agricultural production efficiency and promote sustainable development. Although traditional mechanized operations have significantly improved agricultural production efficiency, they are also accompanied by problems such as soil compaction and uneven distribution of crop residues, posing threats to land quality and long-term agricultural production. A baler is an important piece of equipment in agricultural production, and the reasonable planning of its operation path is of great significance for reducing soil compaction, optimizing operation efficiency, and realizing the resource utilization of straw.

[0003] At present, the operation paths of traditional balers are mostly designed based on fixed rules, ignoring the influence of factors such as field shape, soil conditions, and crop distribution, which easily lead to problems such as long mechanical driving paths, low operation efficiency, incomplete straw treatment, and serious soil compaction. In addition, with the advancement of large-scale farmland management, the number of irregular fields is gradually increasing, and the existing path planning methods are difficult to meet the operation requirements of complex fields. Therefore, how to dynamically optimize the operation path of the baler based on field characteristics and crop distribution, reduce soil compaction, and improve operation efficiency has become one of the important research directions in the development of agricultural mechanization. Summary of the Invention

[0004] Aiming at the problem that the existing path planning methods are difficult to meet the operation requirements of complex fields, the present invention provides a method for planning the in-field path of a baler for reducing soil mechanical compaction.

[0005] The method for planning the in-field path of a baler for reducing soil mechanical compaction according to the present invention includes the following steps:

[0006] Step 1: Obtain the in-field ridge ditch information and boundary point information of the irregular field;

[0007] Step 2: Set path planning rules;

[0008] Step 3: Use the artificial bee colony algorithm to plan the paths of the harvester and the baler on the irregular field. This step includes:

[0009] Step 1: Nectar source coding and initialization;

[0010] The nectar source coding represents a scheduling scheme, including the starting ridge sequences of the harvester and the baler, and initializes the path planning rules;

[0011] Step 2: The fitness function aims to minimize the total compaction times, while considering the number of times of work area overlap and the number of times the baler starts processing before the harvester finishes as penalty terms;

[0012] Step 3: The leading bee search adopts a neighborhood generation strategy of direction adjustment, path exchange, insertion or deletion. After generating a new solution, verify the constraints and retain the better solution;

[0013] Step 4: The follower bee search selects the nectar source according to probability and executes the neighborhood search strategy of the leading bee;

[0014] Step 5: In the scout bee stage, regenerate the nectar sources that have not been improved for a long time, randomly reset the paths of the harvester and the baler, ensure to start from the middle and meet the constraint conditions;

[0015] Step 6: Constraint handling and repair include spatial constraint adjustment, time constraint delay, and redundant operation deletion of compaction constraints;

[0016] Step 7: End when the termination condition is reached, and output the optimal solution. The termination condition is reaching the maximum number of iterations or fitness convergence.

[0017] Preferably, applying the GNSS technology in step one to obtain the in-field ridge ditch information and boundary point information of the irregular field includes: the total number of ridges n in the field, the length L of the i-th ridge i , the ridge spacing W and the total area A of the field. The total area A is calculated according to the formula to obtain.

[0018] Preferably, the path planning rules in step two include the settings of the starting ridge, working time sequence, constraint conditions, and turning paths:

[0019] Starting ridge: the initial position of the harvester ridge, the initial position of the baler ridge;

[0020] Working time sequence: The harvester starts from ridge and gradually expands to the left or right until all ridges are covered; the path of the baler lags behind the harvester. After the harvester completes the work of one ridge, the baler starts working; the time t b (i) when the baler completes the i-th ridge and the time t h (i) when the harvester completes the i-th ridge satisfy the condition t b (i) ≥ t h (i), Eh is the efficiency of the harvester, E b is the efficiency of the straw baler;

[0021] Constraint conditions: Meet the constraint condition that each ridge can be compacted at most once, Where T is the total time required to complete the harvesting and baling of the plot, and x i (t) = 1 indicates that the i-th ridge is compacted, i = 1, 2,..., n, and x i (t) = 0 indicates that it is not compacted, and t = {t p} ∪ {t q}; When the harvester and baler work simultaneously, they satisfy the non-overlapping working ridge constraint;

[0022] Turning path: Each time a job is completed and reaching the end of the field, a turn is required to start the next job. If there is sufficient space at the end of the field, an Ackermann turn is selected; if there is insufficient space at the end of the field: a in-place turn is selected.

[0023] Preferably, the nectar source coding in step 1 is: Each nectar source X x represents a path planning and scheduling scheme, x = 1, 2,..., NP, where NP is the number of nectar sources. The path planning and scheduling scheme includes the harvester starting ridge sequence S h = [s h (t1), s h (t2),..., s h (t h )] and the baler starting ridge sequence S b = [s b (t1), s b (t2),..., s b (t b )], where sh(tp), p = 1, 2,..., h represents the starting ridge of the p-th harvester operation, h represents the total number of harvester operations, and t p represents the starting time of the p-th harvester operation; s b (t q ), q = 1, 2,..., b represents the starting ridge of the q-th baler operation, b is the total number of baler operations, and t q represents the starting time of the q-th baler operation;

[0024] The working range of the harvester starting ridge sequence Sh each time is Work h (t p ) = {s h (t p ), s h (t p ) + 1,..., s h (t p ) + w h -1 ≤ n}, where w h is the number of ridges across which the harvester operates;

[0025] The working range of the baler starting ridge sequence Sb each time is Work b (t q) = {s b (t q ), s b (t q ) + 1,..., s b (t q ) + w b - 1 ≤ n}, w b is the number of ridges across which the baler operates;

[0026] And it satisfies

[0027] Preferably, for the nectar source initialization in step 1: The harvester starts from and gradually expands to the left or right to cover all ridges; The initial position of the baler The path lags behind the harvester and avoids overlap; A feasible solution is generated under the setting of rule constraints as the initial solution.

[0028] Preferably, the fitness function fitness(X x ) in step 2 is:

[0029]

[0030] In the formula,

[0031] Z is the objective function, In the formula, OverlapPenalty is the number of times of overlap in the working area; TimePenalty is the number of times the baler starts processing before the harvester finishes, α is the working area overlap penalty coefficient, and β is the penalty coefficient for the baler starting processing before the harvester finishes.

[0032] Preferably, for the onlooker bee search in step 3, a neighborhood generation strategy of direction adjustment, path exchange, insertion or deletion is adopted;

[0033] The direction adjustment is: Randomly select a certain time step t p or t q and modify the starting ridge of s h (t p ) or s b (t q ) to shift 1 ridge to the left or right to ensure the effectiveness of the working range;

[0034] The path exchange is: Exchange the starting ridge order of two time steps to optimize the coverage efficiency;

[0035] The insertion / deletion is: Add or remove time steps to shorten the total time.

[0036] Preferably, the nectar source is selected in step 4 according to the probability In the formula, p xis the selection probability for the x-th nectar source follower bee, fitness(X x ), fitness(X y ) represent the fitness values of the x-th nectar source and the y-th nectar source, where x, y = 1, 2, ..., NP, and x ≠ y.

[0037] Preferably, the constraint handling and repair in step 6 include spatial constraint, time constraint, and compaction constraint:

[0038] Spatial constraint: If Adjust s b (t q ) to the nearest non-overlapping position;

[0039] Time constraint. If t b (i) < t h (i), delay the processing time step of the baler;

[0040] Compaction constraint: If a certain ridge is compacted multiple times, delete redundant operations.

[0041] Preferably, the termination condition of step 7 is: reaching the maximum number of iterations H or fitness convergence, where the fitness convergence means that the optimal solution has not been improved for K consecutive times.

[0042] Advantages of the present invention: The present invention proposes a method for in-field path planning of a baler, which effectively reduces the impact of soil compaction while ensuring the operation efficiency and packing quality, and realizes the sustainable utilization of land resources. At the same time, the method of the present invention provides a new technical idea and application reference for the path planning of intelligent agricultural machinery, and provides technical support and innovation impetus for the development of smart agriculture.

[0043] The present invention conducts in-field path planning for maximizing the operation coverage area of a corn seeder under the premise of minimizing soil mechanical compaction, optimizes the in-field path planning of the corn seeder, reduces the impact of compaction on the soil, and realizes the operation goal of high efficiency and low loss. Brief Description of the Drawings

[0044] Figure 1 is the flow chart of the in-field path planning method of the baler for reducing soil mechanical compaction according to the present invention;

[0045] Figure 2 is the flow chart of the artificial bee colony algorithm. Detailed Embodiments

[0046] 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.

[0047] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0048] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but it is not limited to the present invention.

[0049] Specific Embodiment 1: The following will be described in conjunction with Figure 1 and Figure 2 to illustrate this embodiment. The method for in-field path planning of a baler for soil mechanical compaction reduction described in this embodiment includes the following steps:

[0050] Step 1: Obtain the in-field ridge and furrow information and boundary point information of the irregular field.

[0051] Step 2: Set the path planning rules.

[0052] Step 3: Use the artificial bee colony algorithm to perform path planning for the harvester and baler on the irregular field. This step includes:

[0053] Step 1: Nectar source coding and initialization;

[0054] The nectar source coding represents a scheduling scheme, including the starting ridge sequences of the harvester and the baler, and initializes the path planning rules.

[0055] Step 2: The fitness function aims to minimize the total compaction times, and at the same time considers the number of times of overlapping working areas and the number of times the baler starts processing before the harvester finishes as penalty terms.

[0056] Step 3: The leading bee search adopts neighborhood generation strategies such as direction adjustment, path exchange, insertion, or deletion, verifies the constraints after generating a new solution, and retains the better solution.

[0057] Step 4: The follower bee search selects the nectar source according to probability and executes the neighborhood search strategy of the leading bee.

[0058] Step 5: In the scout bee stage, the nectar sources that have not been improved for a long time are regenerated, and the paths of the harvester and the baler are randomly reset to ensure starting from the middle and meeting the constraint conditions.

[0059] Step 6: Constraint handling and repair include spatial constraint adjustment, time constraint delay, and redundant operation deletion of compaction constraints.

[0060] Step 7, end when the termination condition is reached, and output the optimal solution. The termination condition is reaching the maximum number of iterations or fitness convergence.

[0061] Step 1: Apply GNSS technology to obtain the in-field ridge and furrow information and boundary point information of the irregular field block, including: the total number of ridges n in the field block, the length Li of the i-th ridge, i , the ridge spacing W, and the total area A of the field block. The total area A is calculated according to the formula . The field block targeted by the present invention is irregular in shape, and the length of each ridge can be different.

[0062] The path planning rules in Step 2 include the settings of the starting ridge, working time sequence, constraint conditions, and turning paths:

[0063] Starting ridge: the initial position of the harvester ridge, the initial position of the baler ridge; both start from the middle ridge. The number of ridges crossed by the harvester and the baler can be the same or different.

[0064] Working time sequence: The harvester starts from ridge and gradually expands to the left or right until all ridges are covered; the path of the baler lags behind the harvester. After the harvester completes the work of one ridge, the baler starts to work; the time ti of the baler to complete the i-th ridge b (i) and the time ti of the harvester to complete the i-th ridge h (i) satisfy the condition ti b (i) ≥ ti h (i), Eh is the efficiency of the harvester, E b is the efficiency of the straw baler;

[0065] Constraint conditions: satisfy the constraint condition that each ridge can be compacted at most once. In the formula, T is the total time required to complete the harvesting and baling of the plot, xi i (t) = 1 indicates that the i-th ridge is compacted, i = 1, 2,..., n, xi i (t) = 0 indicates that it is not compacted, t = {ti p} ∪ {ti q}; when the harvester and the baler work simultaneously, they satisfy the non-overlapping working ridge constraint condition;

[0066] In order to minimize the number of compactions, it is limited that the number of compactions of the ridge within the entire operation range is less than or equal to 1. The moment when the harvester starts the p-th work at each field head is ti p , and the set of all operation start moments of the harvester is {ti p}, similarly, the set of all operation start moments of the baler is {ti q} The union of the two represents the starting moment when all machines start working in the field, and based on this, it is determined whether the i-th ridge is pressed.

[0067] Turning path: Every time a job is completed and the machine reaches the end of the field, it needs to turn to start the next job. If there is enough space at the end of the field, Ackermann turning is selected; if there is insufficient space at the end of the field: in-situ turning is selected.

[0068] Ackermann turning is a turning method with continuous curvature during driving. When the machine turns, the front and rear wheels travel along different arcs to ensure that the rear wheel is tangent to the front wheel's trajectory. It is applicable to relatively wide field end spaces: the steering center of the machine is O, and the turning radius of the left front wheel is R left , and the right side is R right , the wheelbase of the machine (the distance between the front and rear wheels) is L, the track width of the front wheels (the distance between the left and right wheels) is W, and the distances from the steering center to the two front wheels satisfy The turning radius of the rear wheel is Define the steering angle of the left front wheel as θ left , and the right side is θ right , satisfying The total path length of the turn is determined by the arc lengths of the left and right wheels L turn =R center ·Δθ, where Δθ is the turning angle, and the turning radius must be greater than the minimum turning radius R min , to avoid excessive turning of the vehicle body R center ≥R min . In-situ turning is applicable to the situation where there is insufficient space at the field head. The machine advances with one side's wheels and retreats with the other side's wheels, forming a turning method that rotates around its own center: the center of the machine is O, the left wheel advances at a speed of v left , and the right wheel advances at a speed of v right , the track width of the machine is W, and the speeds of the two sides' wheels during turning satisfy v left =-v right , that is, the speed directions of the two sides' wheels are opposite and the magnitudes are equal. The angular velocity ω of the machine around the center O is The time t required for the machine to complete a turn of Δθ is The path length is Turning method selection rule. If there is enough space at the end of the field, Ackermann turning is selected. The width D of the field head space field satisfies Advantages: low energy consumption and less compaction of the field. If there is insufficient space at the end of the field: in-situ turning is selected. The width D of the field head space field does not meet the Ackermann turning condition It is applicable to narrow field head spaces and has high flexibility.

[0069] Step 3: Use the artificial bee colony algorithm (ABC) to solve the regular path. Specifically, it includes:

[0070] Step 1, nectar source coding and initialization;

[0071] The nectar source coding is as follows: Each nectar source X x represents a path planning and scheduling scheme, where x = 1, 2,..., NP, and NP is the number of nectar sources. The path planning and scheduling scheme includes the harvester starting ridge sequence S h = [s h (t1), s h (t2),..., s h (t h )] and the baler starting ridge sequence S b = [s b (t1), s b (t2),..., s b (t b )], where sh(tp), p = 1, 2,..., h represents the starting ridge of the p-th harvester operation, h represents the total number of harvester operations, and t p represents the starting time of the p-th harvester operation; sb(tq), q = 1, 2,..., b represents the starting ridge of the q-th baler operation, and b is the total number of baler operations, and t q represents the starting time of the q-th baler operation;

[0072] The working range Work h (t p ) of the harvester starting ridge sequence Sh is {s h (t p ), s h (t p ) + 1,..., s h (t p ) + w h -1 ≤ n}, where w h is the number of ridges across which the harvester operates;

[0073] The working range Work b (t q ) of the baler starting ridge sequence Sb is {s b (t q ), s b (t q ) + 1,..., s b (t q ) + w b -1 ≤ n}, where w b is the number of ridges across which the baler operates;

[0074] And it satisfies

[0075] Nectar source initialization: The harvester starts from Start, gradually expand to the left or right to cover all ridges; the initial position of the baler The path lags behind the harvester and avoids overlap; generate a feasible solution under the setting rules as the initial solution.

[0076] Step 2: The fitness function aims to minimize the total number of compactions, and at the same time considers the number of overlaps in the working area and the number of times the baler starts processing before the harvester finishes as penalty terms;

[0077] The fitness function fitness(X x ) is:

[0078]

[0079] In the formula,

[0080] Z is the objective function, In the formula, OverlapPenalty is the number of overlaps in the working area; TimePenalty is the number of times the baler starts processing before the harvester finishes, α is the working area overlap penalty coefficient, and β is the penalty coefficient for the baler starting processing before the harvester finishes.

[0081] Step 3: The leading bee search adopts a neighborhood generation strategy of direction adjustment, path exchange, insertion or deletion. After generating a new solution, verify the constraints and retain the better solution;

[0082] The direction adjustment is: randomly select a certain time step t p or t q Modify s h (t p ) or s b (t q ) to shift the starting ridge 1 ridge to the left or right to ensure the effectiveness of the working range;

[0083] The path exchange is: exchange the starting ridge order of two time steps to optimize the coverage efficiency;

[0084] Insertion / deletion is: add or remove time steps to shorten the total time.

[0085] Step 4: The follower bee search selects the nectar source according to the probability and executes the neighborhood search strategy of the leading bee;

[0086] The nectar source is selected according to the probability for, in the formula, p x is the selection probability of the xth nectar source by the follower bee, fitness(X x ) and fitness(X y ) represent the fitness values of the xth nectar source and the yth nectar source, x, y = 1, 2,..., NP, and x ≠ y.

[0087] Step 5: During the scouting bee stage, the nectar sources that have not been improved for a long time are regenerated, and the paths of the harvester and baler are randomly reset to ensure starting from the middle and meeting the constraints.

[0088] Step 6: Constraint handling and repair include spatial constraint adjustment, time constraint delay, and redundant operation deletion for compaction constraints.

[0089] Constraint handling and repair include spatial constraints, time constraints, and compaction constraints:

[0090] Spatial constraint: If Adjust s b (t q ) to the nearest non-overlapping position;

[0091] Time constraint. If t b (i) < t h (i), delay the processing time step of the baler;

[0092] Compaction constraint: If a ridge is compacted multiple times, delete the redundant operations.

[0093] Step 7: End when the termination condition is reached, and output the optimal solution. The termination condition is reaching the maximum number of iterations or fitness convergence.

[0094] The termination condition is: reaching the maximum number of iterations H or fitness convergence, and the fitness convergence means that the optimal solution has not been improved for K consecutive times.

[0095] The optimal solution generated by using the method of the present invention is the final path, and the harvester and baler work according to this scheme to achieve the optimal effect.

[0096] 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 deviate 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 baler field path planning method for reducing soil mechanical compaction, characterized in that: The method comprises the following steps: Step 1: Obtain the ridge and ditch information and boundary point information of the irregular field; Step 2: Set path planning rules; Step 3: Use the artificial bee colony algorithm to plan the paths of harvesters and balers on irregular fields. This step includes: Step 1: Honey source encoding and initialization; The honey source code represents a scheduling scheme, including the starting ridge sequence of the harvester and baler, and the initialization path planning rules; Step 2: The fitness function aims to minimize the total number of compactions, while considering the number of overlapping working areas and the number of times the baler starts processing before the harvester finishes as penalty terms; Step 3: The leading bee search adopts a neighborhood generation strategy of direction adjustment, path exchange, insertion or deletion, verifies constraints after generating a new solution, and retains the better solution; Step 4: The follower bee search selects the nectar source according to probability and executes the neighborhood search strategy of the leader bee; Step 5: During the scout bee phase, the nectar sources that have not been improved for a long time are regenerated, and the paths of the harvester and baler are randomly reset to ensure that they start from the middle and meet the constraints; Step 6: Constraint processing and repair includes space constraint adjustment, time constraint delay, and compaction constraint deletion redundant operations; Step 7: When the termination condition is reached, the optimal solution is output. The termination condition is that the maximum number of iterations is reached or the fitness converges.

2. The method for baler field path planning for reducing soil mechanical compaction according to claim 1, characterized in that: Step 1: Use GNSS technology to obtain the ridge information and boundary point information of irregular fields, including the total number of ridges n, the length of the i-th ridge L i , ridge spacing W and the total area of ​​the field A, the total area A is calculated according to the formula To obtain.

3. The method for baler field path planning for reducing soil mechanical compaction according to claim 2, characterized in that: The path planning rules in step 2 include the setting of the starting ridge, working sequence, constraints and turning paths: Starting ridge: initial position of the harvester Ridge, initial position of baler ridge; Working sequence: harvester from The baler starts from the i-th ridge and gradually expands to the left or right until all ridges are covered. The baler path lags behind the harvester. The baler starts working after the harvester completes the work of a ridge. The time t for the baler to complete the i-th ridge is b (i) and the time t when the harvester completes the i-th ridge h (i) Satisfy the condition t b (i)≥t h (i) E h is the efficiency of the harvester, E b for the efficiency of straw balers; Constraints: Each ridge must be compacted at most once. Where T is the total time required to complete the harvesting and packaging of the plot, x i (t) = 1 means the ith ridge is compacted, i = 1, 2, ..., n, x i (t) = 0 means no compaction, t = {t p }∪{t q }; When the harvester and baler work at the same time, the working ridges do not overlap. Turning path: After completing each operation and reaching the end of the field, you need to turn to proceed to the next operation. If there is enough space at the end of the field, choose Ackerman turning; if there is insufficient space at the end of the field: choose turning on the spot.

4. The method for baler field path planning for reducing soil mechanical compaction according to claim 3, characterized in that: The nectar source code in step 1 is: each nectar source X x represents a path planning and scheduling scheme, x = 1, 2, ..., NP, NP is the number of nectar sources, and the path planning and scheduling scheme includes the starting ridge sequence S of the harvester h =[s h (t1),s h (t2),...,s h (t h )] and the baler starting ridge sequence S b =[s b (t1),s b (t2),...,s b (t b )], where s h (t p ), p=1,2,...,h represents the starting ridge of the pth harvester operation, h represents the total number of harvester operations, t p Indicates the starting time of the pth harvester operation; s b (t q ),q=1,2,...,b represents the starting ridge of the qth baler operation, b is the total number of baler operations, t q represents the starting time of the qth baler operation; Harvester starting ridge sequence S h Work scope each time h (t p )={s h (t p ),s h (t p )+1,...,s h (t p )+w h -1≤n}, w h The number of ridges across which the harvester operates; Baler starting ridge sequence S b Work scope each time b (t q )={s b (t q ),s b (t q )+1,...,s b (t q )+w b -1≤n}, w b The number of ridges across which the baler operates; And meet 5. The method for baler field path planning for reducing soil mechanical compaction according to claim 4, characterized in that: Step 1: Initialize the honey source: the harvester starts Start, gradually expand to the left or right to cover all ridges; baler initial position The path lags behind the harvester and avoids overlapping; a feasible solution is generated under the set rule constraints as the initial solution.

6. The method for baler field path planning for reducing soil mechanical compaction according to claim 5, characterized in that: The fitness function fitness(X x )for: In the formula, Z is the objective function, Where OverlapPenalty is the number of times the work area overlaps; TimePenalty is the number of times the baler starts processing before the harvester finishes, α is the penalty coefficient for work area overlap, and β is the penalty coefficient for the baler starting processing before the harvester finishes.

7. The method for baler field path planning for reducing soil mechanical compaction according to claim 4, characterized in that: The leader bee search in step 3 adopts a neighborhood generation strategy of direction adjustment, path exchange, insertion or deletion; The direction is adjusted to: randomly select a time step t p or q Modifications h (t p ) or s b (t q ) is offset by 1 ridge to the left or right to ensure that the working range is valid; The path exchange is: exchanging the starting ridge order of two time steps to optimize the coverage efficiency; Insertion / deletion is: adding or removing time steps to shorten the total time.

8. The method for baler field path planning for reducing soil mechanical compaction according to claim 6, characterized in that: In step 4, select the nectar source according to the probability Carry out, where p x is the probability of selecting the xth nectar source follower bee, fitness(X x )、fitness(X y ) represents the fitness value of the x-th nectar source and the y-th nectar source, x, y = 1, 2, ..., NP, and x ≠ y.

9. The method for baler field path planning for reducing soil mechanical compaction according to claim 7, characterized in that: The constraint processing and repair in step 6 includes space constraints, time constraints, and compaction constraints: Space constraints: If Adjustments b (t q ) to the nearest non-overlapping position; Time constraint. If t b (i)<t h (i),delay baler’s processing time step; Compaction constraint: If a ridge is compacted multiple times, delete the redundant operations.

10. The method for baler field path planning for reducing soil mechanical compaction according to claim 1, characterized in that: The termination condition of step 7 is: reaching the maximum number of iterations H or the fitness convergence, and the fitness convergence is that the optimal solution has not been improved for K consecutive times.

Images