Agricultural machinery operation plan decision-making method based on weather forecast information

Abstract

The invention relates to the technical field of agricultural intelligence, discloses an agricultural machinery operation plan decision-making method based on weather forecast information, and aims to solve the problem of agricultural time delay caused by influence of weather factors during agricultural machinery scheduling operation in the prior art. In combination with the information of each machine and tool in the machine and tool cluster and the information of each field piece, the weather suitability of each machine and tool in each working time period of each field piece is calculated according to the weather information, the most suitable operation time period of each machine and tool in each field piece is distinguished, and the weather condition is integrated into the intelligent agricultural operation. The calculated weather suitability degree is input into the agricultural machinery scheduling model to solve a scheduling scheme when the machine cluster meets the maximum working efficiency, by adopting the technical scheme, scheduling of the machine cluster is achieved according to the weather condition, the influence of weather factors on agricultural machinery operation is reduced, and more efficient and faster agricultural machinery operation is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of agricultural intelligence, in particular to a farm machine operation plan decision method. BACKGROUND

[0002] With the development of modern science and technology, science and technology has been widely applied in various fields, and smart agriculture has emerged as the times require. Under the basic support of Internet, Internet of Things and sensor technology hardware, smart agriculture has brought qualitative improvement to agricultural production activities.

[0003] In order to seize the time, smart agriculture allocates and sets the operation path and access field of each machine tool through scheduling machine tool cluster, so as to realize efficient and rapid operation of the production field. However, since the farm machine operation is an outdoor operation, it is often affected by weather factors, and different weather conditions will affect the working efficiency of the machine tool, and the influence degree of different types of machine tools is also different.

[0004] Therefore, how to realize the scheduling of machine tool cluster according to weather conditions, reduce the influence of weather factors on farm machine operation, and realize more efficient and rapid farm machine operation is a problem to be solved by those skilled in the art. SUMMARY

[0005] The purpose of the present application is to solve the problem that the current technology is often affected by weather factors when scheduling farm machines, resulting in delayed time. Therefore, the present application provides a farm machine operation plan decision method based on weather forecast information, which realizes the scheduling of machine tool cluster according to weather conditions, reduces the influence of weather factors on farm machine operation, and realizes more efficient and rapid farm machine operation.

[0006] In order to solve the above technical problems, the present application provides a farm machine operation plan decision method based on weather forecast information, comprising:

[0007] According to the pre-divided multiple working time periods, the weather suitability of each machine tool in each field in each working time period is calculated in combination with weather information, machine tool information and field information.

[0008] The farm machine scheduling model is called, and the scheduling scheme of the machine tool cluster when the maximum working efficiency is met is solved according to the weather suitability; the working efficiency is a value calculated according to the operation time of the machine tool, the moving time and the weather suitability of the operation field.

[0009] Preferably, the calling of the farm machine scheduling model and the solving of the scheduling scheme of the machine tool cluster when the maximum working efficiency is met according to the weather suitability is:

[0010] According to the objective function of the farm machine scheduling model, a multi-particle swarm optimization algorithm is called to solve the farm machine scheduling model.

[0011] The objective function of the agricultural machine scheduling model is:

[0012]

[0013] wherein,

[0014] is a pre-set constant, is a set of machine tools, and the element is is a set of farmland, and the element is is a set of working time periods, and the element is , the element corresponding continuous time interval is a set of nodes, and the element is and is a starting point, is a terminal point, is the moving time of the node to the node , is the working time of the agricultural machine in the farmland block , is the weather suitability of the agricultural machine in the farmland block in the time period , is whether the time of the agricultural machine arriving at the farmland block belongs to the time period , is whether the agricultural machine works in the farmland block in the time period , is whether the agricultural machine moves from to .

[0015] Preferably, the calling of the multi-particle swarm optimization algorithm to solve the agricultural machine scheduling model comprises:

[0016] ​​​​​​​​​​​Based on field information and machinery information, a scheduling plan for the machinery cluster is generated, and each scheduling plan of the machinery cluster is transformed into a searchable particle structure through particle position encoding; the structure of each particle contains the operation path information of each machinery, the matching relationship between machinery and field, and the calculation logic information of operation time.

[0017] Each particle is decoded to obtain the operation path information of each machine, and the time for each machine to arrive at each matching field is estimated according to the operation time estimation logic information.

[0018] Particles that meet preset conditions are selected based on the arrival time of each machine in each matched field and the weather suitability of each machine in each working time period in each field. The preset conditions are: the sum of the arrival time of each machine in the matched field and the working time in the matched field is within a time period corresponding to a weather suitability of the matched field.

[0019] Based on the objective function of the agricultural machinery scheduling model, the fitness of each particle that meets the preset conditions is calculated.

[0020] The operation path information of each particle is iterated by the time when each machine visits the field, and the best fitness that satisfies the objective function of the agricultural machinery scheduling model is selected during the iteration process.

[0021] The scheme corresponding to the best fitness is used as the scheduling scheme.

[0022] Preferably, the formula for calculating the fitness includes:

[0023] ;

[0024] in, For fitness, The penalty value is calculated based on the number of penalty terms satisfied by the particle's behavior.

[0025] Preferably, after selecting particles that meet the preset conditions, the method further includes selecting particles whose weather suitability is not less than the weather suitability threshold when the machinery is operating in the matched field.

[0026] Preferably, the penalty items include: the starting point and / or the ending point is not visited; a field is visited multiple times; the time increment relationship of the machine visiting the field in sequence is not satisfied; there are unvisited, repeatedly visited, or unconnected fields in the path; and particles whose weather suitability is less than the suitability threshold when the machine is matching the field for operation.

[0027] Preferably, it also includes: correcting particles that satisfy the penalty term during the iteration process.

[0028] Preferably, the constraints of the agricultural machinery scheduling model include:

[0029] ;

[0030] ;

[0031] ;

[0032] ;

[0033] ;

[0034] ;

[0035] ;

[0036] ;

[0037] ;

[0038] in, For agricultural machinery Reaching the node Continuous working time, For a pre-set constant, , For fields The weather suitability threshold.

[0039] Preferably, the step of selecting the optimal fitness that satisfies the objective function of the agricultural machinery scheduling model during the particle iteration process includes:

[0040] Record the current fitness of all particles as the optimal solution, and select the swarm optimal solution;

[0041] During the iteration process, when the fitness of the current particle is better than the corresponding historical best solution, the best solution corresponding to the particle in the record is updated, and the population best solution is also updated.

[0042] After satisfying the required number of iterations, the optimal solution for the population is taken as the best fitness.

[0043] Preferably, the particle velocity iteration update formula is:

[0044] ;

[0045] The formula for iteratively updating the particle's position is:

[0046] ;

[0047] in, It is a constant. For the updated particle velocity, The particle velocity before the update. For the preset individual influence weights, The pre-defined group influence weight, For random disturbance coefficients, This is the historical optimal solution for the particle. This is the optimal solution for the population. For the updated particle positions, The position of the particle before the update.

[0048] This invention provides a method for agricultural machinery operation planning and decision-making based on weather forecast information. Compared to current technologies where weather factors can cause delays in agricultural machinery scheduling, this method pre-divides the operation time into multiple working periods, calculates the weather suitability for each period, and combines information on each machine in the machinery cluster and each field. Based on the weather information, it calculates the weather suitability for each machine in each field for each working period, identifying the most suitable working time for each machine in each field. This integrates weather conditions into smart agriculture operations. The calculated weather suitability is input into the agricultural machinery scheduling model to solve for the scheduling scheme that maximizes the efficiency of the machinery cluster. Using this technical solution, scheduling of the machinery cluster based on weather conditions is achieved, reducing the impact of weather factors on agricultural machinery operations and realizing more efficient and faster agricultural machinery operations. Attached Figure Description

[0049] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart illustrating a method for agricultural machinery operation planning decision-making based on weather forecast information, provided in an embodiment of the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of the present invention.

[0052] The core of this invention is to provide a method for agricultural machinery operation planning decision-making based on weather forecast information, which can be used to schedule machinery clusters according to weather conditions, reduce the impact of weather factors on agricultural machinery operations, and achieve more efficient and faster agricultural machinery operations.

[0053] To enable those skilled in the art to better understand the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0054] Figure 1 A flowchart illustrating a method for agricultural machinery operation planning decision-making based on weather forecast information provided in an embodiment of the present invention is shown below. Figure 1 As shown, the method includes:

[0055] S10: Based on the pre-defined multiple working time periods, combined with weather information, equipment information and field information, calculate the weather suitability of each machine in each working time period in each field;

[0056] S11: Call the agricultural machinery scheduling model to solve the scheduling scheme of the machinery cluster to meet the maximum working efficiency based on the weather suitability; the working efficiency is the value calculated based on the working time, movement time of the machinery, and the weather suitability of the working field.

[0057] The agricultural machinery operation planning decision-making method based on weather forecast information provided in this application is applied to the operation scheduling of machinery clusters, enabling the machinery clusters to flexibly adjust their operation paths according to weather changes, thereby improving operation efficiency and seizing agricultural opportunities. In specific implementations, the executing entity of this method can be an agricultural machinery operation planning decision-making device based on weather forecast information. This device may specifically include a memory and a processor, wherein the memory is used to store computer programs, and the processor is used to execute the computer programs to implement the steps of the agricultural machinery operation planning decision-making method based on weather forecast information provided in the above embodiments. In some embodiments, the agricultural machinery operation planning decision-making device based on weather forecast information may also include human-computer interaction devices such as displays and touch screens. In specific implementations, the agricultural machinery operation planning decision-making device based on weather forecast information provided in this embodiment may include, but is not limited to, smartphones, tablets, laptops, or desktop computers. After obtaining the scheduling scheme through this application, parameters such as the operation path and operation time of each machinery in the scheme can be input into each machinery to realize the operation settings.

[0058] Of course, it is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the technical solutions of this application can be embodied in the form of a software product, which is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application.

[0059] Agricultural machinery operation, as an outdoor operation, is affected by weather factors. During seasons with high temperatures and heavy rain, it is often necessary to adjust operating times to seize the opportune time for farming. Therefore, step S10 of this application considers the impact of weather factors and calculates the weather suitability of machinery for each field at each working time. The weather suitability for a time period refers to an index indicating whether the machinery is suitable for operation in the field during that time period. A higher weather suitability indicates that the machinery is more suitable for field operation during that time period, resulting in higher operating efficiency. It should be noted that the agricultural machinery operation planning decision-making method based on weather forecast information provided in this application can be applied to irregular machinery clusters and fields. That is, the models, types, operating speeds, and other parameters of the machinery in the machinery cluster can be different, and the size, hardness, and other parameters of each field can be different. In step S10, the calculation of weather suitability is based on time periods. Multiple time periods can be divided according to the overall size of the field to be operated, the working efficiency of the machinery, the total required operating time, and the available operating time. The length of each time period can also be different. Based on weather forecasts, equipment information, and field information for each time period, the weather suitability for each piece of equipment in each field at each working time period is calculated. Weather forecast information includes, but is not limited to, wind speed and rainfall; equipment information includes, but is not limited to, the movement speed and operating speed of each piece of equipment; and field information includes, but is not limited to, the size of each field and soil hardness. Because the information for each piece of equipment and each field within the equipment cluster differs, the weather suitability for each piece of equipment operating on each field at different times also varies. Therefore, it is necessary to calculate the weather suitability for each piece of equipment in each field at each working time period.

[0060] After calculating the weather suitability, in actual production, the weather suitability for each time period can be input into the agricultural machinery scheduling model. By solving the agricultural machinery scheduling model, the scheduling scheme for each machine that maximizes work efficiency can be obtained. Work efficiency is a value calculated based on the machine's operating time, movement time, and the weather suitability of the field. The agricultural machinery scheduling model in this application is established based on the correspondence between weather suitability and machinery cluster scheduling schemes. It uses maximizing work efficiency as the objective function and finds the scheduling scheme that maximizes the efficiency of machinery cluster operations by calculating the operating paths and operating times of each machine. The pathfinding rules can be roughly understood as follows: Calculate the predicted time period required for the current machine to move from the starting point to the target field and perform its work actions. Determine if the predicted time period falls within a full working time period corresponding to the weather suitability index of the target field. If not, repeat this step until the target field is found. If it is, include the target field in the work path and calculate if the time period required for the current machine to move from the target field to the next field and perform its work actions falls within a full working time period corresponding to a weather suitability index of the corresponding field. Repeat this step until no target field that meets the judgment conditions can be found. Then, include the path of the current machine from its current position to the destination in the recorded work path. Repeat the above steps. Due to the number of fields and the number of weather suitability indices, each machine may have multiple work paths, and the entire machine cluster may have multiple scheduling schemes. After each machine completes its work path arrangement, paths that do not meet production requirements, such as paths to fields that have been visited multiple times or paths to fields that have not been visited, are eliminated based on pre-set constraints. The scheme with the highest work efficiency for the entire machine cluster is selected as the final scheduling scheme generated by the agricultural machinery scheduling model.

[0061] The agricultural machinery operation planning decision-making method based on weather forecast information provided in this application addresses the problem of weather-related delays in agricultural machinery scheduling in current technologies. This application pre-divides the operation time into multiple working periods, calculates the weather suitability for each period, and combines information on each machine in the machinery cluster and each field. Based on the weather information, it calculates the weather suitability for each machine in each field for each working period, identifying the most suitable working time for each machine in each field, thus integrating weather conditions into smart agriculture operations. The calculated weather suitability is input into the agricultural machinery scheduling model to solve for the scheduling scheme that maximizes the working efficiency of the machinery cluster. Using this technical solution, scheduling of the machinery cluster based on weather conditions is achieved, reducing the impact of weather factors on agricultural machinery operations and realizing more efficient and faster agricultural machinery operations.

[0062] The above embodiments illustrate that the scheduling scheme of the machinery cluster can be obtained by solving the agricultural machinery scheduling model to meet the maximum working efficiency. This application provides a specific solution method. This application calls the multi-particle swarm optimization algorithm to solve the agricultural machinery scheduling model based on the objective function of the agricultural machinery scheduling model. The objective function of the agricultural machinery scheduling model is:

[0063] ;

[0064] in, , , , , , ;

[0065] For a pre-set constant, A collection of machinery and equipment, with elements as follows: , For farmland collection, the elements are , This is a set of working time periods, with elements as follows: ,element The corresponding continuous time interval ; A set of nodes, with elements as and , Starting point As the endpoint, For nodes arrive The travel time, For agricultural machinery Work plots Homework time, For agricultural machinery In time period Work plots The weather suitability For agricultural machinery Arrival at the field Does the time belong to a time period? , For agricultural machinery Is it within a time period? Work plots , For agricultural machinery Whether from arrive move.

[0066] It can be seen that the objective function consists of two parts: the first part is the sum of the equipment movement time and the operation time, and the second part is the weather suitability. In order to maximize the working efficiency of the equipment cluster, the sum of the equipment movement time and the operation time should be as small as possible, and the weather suitability should be as large as possible.

[0067] Based on the above embodiments, this embodiment provides a specific application method of the multi-particle swarm optimization algorithm. Before starting, initialization settings are first performed, setting the basic parameters of particle swarm optimization, including: population size N, maximum number of iterations, individual optimal weight coefficient, global optimal weight coefficient, inertia weight, and velocity boundary. Then, a scheduling scheme for the machinery cluster is generated based on field information and machinery information, and each scheduling scheme of the machinery cluster is transformed into a searchable particle structure through particle position encoding. The structure of each particle contains the operation path information of each machinery, the matching relationship between machinery and field, and the calculation logic information of operation time. Each particle represents a complete agricultural machinery scheduling scheme. The position vector of each particle represents the agricultural machinery number assigned to each field and the access order, and its velocity vector controls the direction and magnitude of particle search updates.

[0068] Then, each particle is decoded to obtain the operation path information of each machine, and the time for each machine to arrive at each matching field is estimated according to the operation time estimation logic information.

[0069] Each particle corresponds to a complete agricultural machinery operation path and time plan. During the decoding process, the order in which each agricultural machine visits the fields is first determined based on the encoding, and the arrival time of each machine in each field is calculated sequentially. The arrival time is mapped to the working time period, thereby filtering particles that meet preset conditions based on the arrival time of each machine in each matched field and the weather suitability of each machine in each working time period in each field. The preset conditions are: the sum of the arrival time of each machine in the matched field and its working time in the matched field must fall within the time period corresponding to a certain weather suitability of the matched field. After filtering particles that meet the preset conditions, the process also includes filtering particles whose weather suitability during the operation of the matched field is not less than a weather suitability threshold. The weather suitability threshold represents the minimum acceptable weather suitability value in the scheduling plan; that is, agricultural machinery operations with a weather suitability greater than this index are acceptable during the scheduling process. When the weather suitability is lower than this value, it indicates that the machine is not suitable for operation during this time period and therefore cannot operate.

[0070] After decoding, the current particle scheduling scheme needs to be evaluated. Therefore, based on the objective function of the agricultural machinery scheduling model, the fitness of each particle that meets the preset conditions is calculated; the fitness calculation formula includes:

[0071] ;

[0072] in, For fitness, This is the penalty value; the penalty value is calculated based on the number of penalty items that the particle behavior satisfies. Penalty items include: the starting point and / or ending point is not visited; a field is visited multiple times; the time increment relationship of the machine visiting fields sequentially is not satisfied; there are unvisited, repeatedly visited, or unconnected fields in the path; and particles whose weather suitability is less than the suitability threshold when the machine is matching fields.

[0073] Finally, the operation path information of each particle is iterated by the time when each machine visits the field. Particles that meet the penalty term during the iteration process are corrected, and the optimal fitness that meets the objective function of the agricultural machinery scheduling model is selected during the particle iteration process. The scheme corresponding to the optimal fitness is taken as the scheduling scheme.

[0074] During the iteration process, the formula for updating the particle's velocity is:

[0075] ;

[0076] The formula for iteratively updating the particle's position is:

[0077] ;

[0078] in, It is a constant. For the updated particle velocity, The particle velocity before the update. For the preset individual influence weights, The pre-defined group influence weight, For random disturbance coefficients, This is the historical optimal solution for the particle. This is the optimal solution for the population. For the updated particle positions, The position of the particle before the update.

[0079] In the solution based on the multi-particle swarm optimization algorithm, each particle in the particle swarm maintains a historical best solution. And record the current global optimal solution through group update. If the current particle's fitness is better than its historical best solution... Then update it. If the particle's fitness is better than that of all individuals in the population... Then update .

[0080] Therefore, the process of selecting the optimal fitness that satisfies the objective function of the agricultural machinery scheduling model during the particle iteration includes: recording the fitness of all current particles as the optimal solution and selecting the swarm optimal solution; during the iteration process, when the fitness of the current particle is better than the corresponding historical optimal solution, updating the optimal solution corresponding to the particle in the record and updating the swarm optimal solution; after satisfying the number of iterations, using the swarm optimal solution as the best fitness.

[0081] When solving the agricultural machinery scheduling model based on the multi-particle swarm optimization algorithm, the constraints of the agricultural machinery scheduling model include:

[0082] ; ;

[0083] The above formula realizes the constraint of the closed operation path of the machinery, which stipulates that each machine starts from the starting point, completes the assigned task, and returns to the ending point;

[0084] ;

[0085] The above formula constrains the flow balance at the nodes, stipulating that the number of inflows and outflows is the same for all fields;

[0086] ;

[0087] The above formula enables access to all fields, stipulating that the needs of all fields must be met;

[0088] ;

[0089] The above formula is a constraint on the increasing operation time, which stipulates that the operation time of each machine is increasing.

[0090] ;

[0091] ;

[0092] ;

[0093] The above formula establishes a relationship between the time of accessing a certain field and the working time period;

[0094] ;

[0095] The above formula stipulates that the weather suitability of a field must be greater than the weather suitability threshold of that field when machinery visits it;

[0096] in, For agricultural machinery Reaching the node Continuous working time, This is a pre-defined constant, which in practice is a sufficiently large constant used to linearize Boolean variables. Logical relationships with continuous variables , For fields The weather suitability threshold.

[0097] The above provides a detailed description of the agricultural machinery operation planning decision-making method based on weather forecast information provided by this invention. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. It should be noted that those skilled in the art can make various improvements and modifications to this invention without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this invention.

Claims

1. A method for agricultural machinery operation planning decision-making based on weather forecast information, characterized in that, include: Based on multiple pre-defined working time periods, combined with weather information, equipment information, and field information, the weather suitability of each machine in each working time period in each field is calculated. The agricultural machinery scheduling model is invoked to solve the scheduling scheme of the machinery cluster to meet the maximum working efficiency based on the weather suitability. The work efficiency is a value calculated based on the machine's operating time, travel time, and the weather suitability of the field.

2. The agricultural machinery operation planning decision-making method based on weather forecast information according to claim 1, characterized in that, The agricultural machinery scheduling model is invoked, and the scheduling scheme for the machinery cluster to achieve maximum working efficiency is determined based on the weather suitability. Based on the objective function of the agricultural machinery scheduling model, the multi-particle swarm optimization algorithm is called to solve the agricultural machinery scheduling model; The objective function of the agricultural machinery scheduling model is: ； in, , , , , , ; For a pre-set constant, A collection of machinery and equipment, with elements as follows: , For farmland collection, the elements are , This is a set of working time periods, with elements as follows: ,element The corresponding continuous time interval ; A set of nodes, with elements as and , Starting point As the endpoint, For nodes arrive The travel time, For agricultural machinery Work plots Homework time, For agricultural machinery In time period Work plots The weather suitability For agricultural machinery Arrival at the field Does the time belong to a time period? , For agricultural machinery Is it within a time period? Work plots , For agricultural machinery Whether from arrive move.

3. The agricultural machinery operation planning decision-making method based on weather forecast information according to claim 2, characterized in that, The step of using the multi-particle swarm optimization algorithm to solve the agricultural machinery scheduling model includes: Based on field information and machinery information, a scheduling plan for the machinery cluster is generated, and each scheduling plan of the machinery cluster is transformed into a searchable particle structure through particle position encoding; the structure of each particle contains the operation path information of each machinery, the matching relationship between machinery and field, and the calculation logic information of operation time. Each particle is decoded to obtain the operation path information of each machine, and the time for each machine to arrive at each matching field is estimated according to the operation time estimation logic information. Particles that meet preset conditions are selected based on the arrival time of each machine in each matched field and the weather suitability of each machine in each working time period in each field. The preset conditions are: the sum of the arrival time of each machine in the matched field and the working time in the matched field is within a time period corresponding to a weather suitability of the matched field. Based on the objective function of the agricultural machinery scheduling model, calculate the fitness of each particle that meets the preset conditions; The operation path information of each particle is iterated by the time when each machine visits the field, and the best fitness that satisfies the objective function of the agricultural machinery scheduling model is selected during the iteration process. The scheme corresponding to the best fitness is used as the scheduling scheme.

4. The agricultural machinery operation planning decision-making method based on weather forecast information according to claim 3, characterized in that, The formula for calculating fitness includes: ； in, For fitness, The penalty value is calculated based on the number of penalty terms satisfied by the particle's behavior.

5. The agricultural machinery operation planning decision-making method based on weather forecast information according to claim 4, characterized in that, After selecting particles that meet the preset conditions, the process also includes selecting particles whose weather suitability is not less than the weather suitability threshold when the equipment is operating in the matched field.

6. The agricultural machinery operation planning decision-making method based on weather forecast information according to claim 5, characterized in that, The penalty items include: the starting point and / or the ending point is not visited; a field is visited multiple times; the time increment relationship of the machine visiting the field in sequence is not satisfied; there are unvisited, repeatedly visited, or unconnected fields in the path; and particles whose weather suitability is less than the suitability threshold when the machine is matching the field for operation.

7. The agricultural machinery operation planning decision-making method based on weather forecast information according to claim 6, characterized in that, Also includes: Correct the particles that satisfy the penalty term during the iteration process.

8. The agricultural machinery operation planning decision-making method based on weather forecast information according to claim 2, characterized in that, The constraints of the agricultural machinery scheduling model include: ； ； ； ； ； ； ； ； ； in, For agricultural machinery Reaching the node Continuous working time, For a pre-set constant, , For fields The weather suitability threshold.

9. The agricultural machinery operation planning decision-making method based on weather forecast information according to claim 3, characterized in that, The process of selecting the optimal fitness that satisfies the objective function of the agricultural machinery scheduling model during the particle iteration includes: Record the current fitness of all particles as the optimal solution, and select the swarm optimal solution; During the iteration process, when the fitness of the current particle is better than the corresponding historical best solution, the best solution corresponding to the particle in the record is updated, and the population best solution is also updated. After satisfying the required number of iterations, the optimal solution for the population is taken as the best fitness.

10. The agricultural machinery operation planning decision-making method based on weather forecast information according to claim 9, characterized in that, The formula for iteratively updating the particle's velocity is: ； The formula for iteratively updating the particle's position is: ； in, It is a constant. For the updated particle velocity, The particle velocity before the update. For the preset individual influence weights, The pre-defined group influence weight, For random disturbance coefficients, This is the historical optimal solution for the particle. This is the optimal solution for the population. For the updated particle positions, The position of the particle before the update.

Images