Agricultural machinery scheduling method and system based on multi-objective optimization

Abstract

The invention discloses an agricultural machinery scheduling method and system based on multi-objective optimization, and relates to the technical field of intelligent agriculture, and the method comprises the steps: collecting the multi-dimensional data of agricultural machinery in a preset range, and determining the comprehensive score of the agricultural machinery according to the multi-dimensional data, according to the comprehensive score, selecting a target agricultural machine with the comprehensive score higher than a score threshold from the agricultural machines; clustering the target agricultural machinery by using a preset clustering algorithm to obtain a preset number of corresponding agricultural machinery clusters; establishing a comprehensive objective function composed of a transfer distance objective function and a scheduling cost objective function, obtaining the number of agricultural machines needing to be scheduled, and selecting a corresponding number of agricultural machines from the agricultural machine cluster as an agricultural machine combination according to the number of the agricultural machines needing to be scheduled; and determining a final agricultural machinery combination from the agricultural machinery combinations by using a preset optimization algorithm according to the comprehensive objective function, and scheduling the agricultural machinery according to the final agricultural machinery combination. According to the invention, the problem of poor scheduling effect of the agricultural machinery scheduling mode in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of smart agriculture technology, and in particular to an agricultural machinery scheduling method and system based on multi-objective optimization. Background Art

[0002] Agricultural machinery scheduling involves the rational arrangement and dispatch of agricultural machinery based on production needs, equipment, and operating environment conditions to ensure efficient and smooth agricultural operations. In some regions, the allocation of agricultural machinery resources is uneven, with some areas facing insufficient machinery while others face idle machinery. Managing resources rationally and avoiding waste across the board remains a challenge.

[0003] Currently, several agricultural machinery information service platforms exist that offer unified management platforms for machinery users and farmers, providing various supply and demand information and scheduling during machinery scheduling operations. However, traditional agricultural machinery information service platforms primarily randomly dispatch machinery to meet specific job requirements. This can lead to centralized dispatch of machinery without considering the impact of post-dispatching operations, resulting in poor dispatch results. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an agricultural machinery scheduling method and system based on multi-objective optimization, aiming to solve the problem of poor scheduling effect of agricultural machinery scheduling methods in the existing technology.

[0005] The embodiment of the present invention is implemented as follows: A method for dispatching agricultural machinery based on multi-objective optimization, the method comprising: collecting multidimensional data of agricultural machinery within a preset range, determining comprehensive scores of the agricultural machinery based on the multidimensional data, and selecting target agricultural machinery having a comprehensive score higher than a score threshold from among the agricultural machinery based on the comprehensive score; Clustering the target agricultural machinery using a preset clustering algorithm to obtain a corresponding preset number of agricultural machinery clusters with different characteristics, each agricultural machinery cluster containing a preset number of agricultural machinery with the same characteristics; Establish a comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function to obtain the number of agricultural machinery that needs to be scheduled. According to the number of agricultural machinery that needs to be scheduled, a corresponding number of agricultural machinery are selected from the agricultural machinery cluster as an agricultural machinery combination. According to the comprehensive objective function, the preset optimization algorithm is used to determine the final agricultural machinery combination from the agricultural machinery combinations, and the agricultural machinery is dispatched according to the final agricultural machinery combination.

[0006] Furthermore, in the above-mentioned agricultural machinery scheduling method based on multi-objective optimization, wherein the multi-dimensional data includes equipment age, equipment health index, remaining fuel amount, progress of current operation task, historical operation efficiency, failure rate, and maintenance record, the step of collecting the multi-dimensional data of agricultural machinery within a preset range and determining the comprehensive score of the agricultural machinery based on the multi-dimensional data includes: The formula for calculating the comprehensive score is: S = W 1* E + W 2* F + W 3* H ; in, E For basic ability scoring, F Rate the status, H Score historical performance, W 1. W 2. W 3 are the weights of basic ability score, status score, and historical performance score respectively; The calculation formula for basic ability score is: E =Equipment Age Rating* E 1+Device Health Index Score* E 2; The formula for calculating the status score is: F =Remaining fuel score* F 1 + Progress score of the current assignment* F 2; The formula for calculating the historical performance score is: H =Historical Operation Efficiency Rating* H 1+Failure Rate Score* H 2+ Maintenance Record Score* H 3; in, E 1. E 2. F 1. F 2. H 1. H 2. H 3 are the weighted proportions of the equipment age score, equipment health index score, remaining fuel score, current task progress score, historical operation efficiency score, failure rate score, and maintenance record score.

[0007] Furthermore, in the above-mentioned agricultural machinery scheduling method based on multi-objective optimization, the step of clustering the target agricultural machinery using a preset clustering algorithm to obtain a corresponding preset number of agricultural machinery clusters with different characteristics includes: Perform feature vectorization on the multidimensional data of the target agricultural machinery to obtain the multidimensional feature vector of the target agricultural machinery; Obtain the number of target agricultural machinery, determine the corresponding number of clusters according to the number of target agricultural machinery, and randomly select the same number of multidimensional feature vectors as the number of clusters as the initial cluster centers; Calculate the Euclidean distances of other multidimensional feature vectors to all initial cluster centers to assign the multidimensional feature vectors to the group where the nearest initial cluster center is located; For each group of initial cluster centers, calculate the mean of all multidimensional feature vectors within the group of initial cluster centers as the new initial cluster center; The steps of allocating the multidimensional feature vector and updating the initial cluster center are repeated until a preset number of iterations is reached, and agricultural machinery clusters with different characteristics, the number of which is the same as the number of clusters, are obtained.

[0008] Furthermore, in the above-mentioned agricultural machinery scheduling method based on multi-objective optimization, the step of establishing a comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function includes: The expression of the comprehensive objective function is: ; in, is the transfer distance objective function, is the scheduling cost objective function, A is the weight coefficient of the transfer distance objective function, B is the weight coefficient of the scheduling cost objective function; The objective function of the transfer distance objective function is: = ; in, Indicates agricultural machinery i To the plot j The transfer distance, Indicates agricultural machinery i Whether to dispatch to the plot j , 1 means scheduling, 0 means no scheduling, n Indicates the number of agricultural machinery, m Indicates the number of plots; The objective function of the scheduling cost objective function is: = ; in, Indicates agricultural machineryi Whether to dispatch to the plot j , 1 means scheduling, 0 means no scheduling, n Indicates the number of agricultural machinery, m Indicates the number of plots, Indicates agricultural machinery i To the plot j fuel costs, Indicates agricultural machinery i To the plot j time cost, Indicates agricultural machinery i To the plot j equipment loss costs.

[0009] Furthermore, in the above-mentioned agricultural machinery scheduling method based on multi-objective optimization, the step of determining the final agricultural machinery combination from the agricultural machinery combinations using a preset optimization algorithm according to the comprehensive objective function includes: generating an initial population according to the agricultural machinery combination, and calculating the fitness value of each agricultural machinery combination in the initial population using a comprehensive objective function; When the fitness value does not meet the optimization stopping condition, the initial population is sequentially subjected to selection, crossover and mutation operations to obtain an optimized population; The optimized population is used as the initial position of the particle swarm, the speed and position of the particles are updated, and the fitness value is calculated using the comprehensive objective function to perform iterative optimization until the optimization stop condition is met; The optimization stopping condition is that the number of iterative optimization times reaches a preset number or the fitness value reaches a preset threshold.

[0010] Furthermore, the above-mentioned agricultural machinery scheduling method based on multi-objective optimization, wherein the step of determining the final agricultural machinery combination from the agricultural machinery combinations using a preset optimization algorithm according to the comprehensive objective function and scheduling the agricultural machinery according to the final agricultural machinery combination, further includes: When an agricultural machine in the final agricultural machine combination needs to be replaced, the agricultural machine cluster where the replacement agricultural machine is located is obtained, and an agricultural machine is selected from the agricultural machine cluster for replacement; Among them, the conditions for changing the scheduling are that the agricultural machinery fails or the progress of the agricultural machinery operation on the field lags behind the threshold.

[0011] Furthermore, in the above-mentioned agricultural machinery scheduling method based on multi-objective optimization, the steps of obtaining the number of agricultural machinery to be scheduled and selecting a corresponding number of agricultural machinery from the agricultural machinery cluster as an agricultural machinery combination according to the number of agricultural machinery to be scheduled include: Obtain the required operation area and the corresponding operation time, and determine the operation efficiency based on the operation area and the corresponding operation time; The number of agricultural machines required to be selected in each cluster with different operating efficiencies is determined based on the required number of agricultural machines and their operating efficiency, so that a corresponding number of agricultural machines are selected from the agricultural machine clusters as an agricultural machine combination.

[0012] Another object of the present invention is to provide an agricultural machinery scheduling system based on multi-objective optimization, the system comprising: a collection module for collecting multidimensional data of agricultural machinery within a preset range, determining a comprehensive score of the agricultural machinery based on the multidimensional data, and selecting target agricultural machinery having a comprehensive score higher than a score threshold from among the agricultural machinery based on the comprehensive score; a clustering module, configured to cluster the target agricultural machinery using a preset clustering algorithm to obtain a corresponding preset number of agricultural machinery clusters with different characteristics, each agricultural machinery cluster containing a preset number of agricultural machinery with the same characteristics; Establish a module for establishing a comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function, obtain the number of agricultural machines that need to be scheduled, and select a corresponding number of agricultural machines from the agricultural machine cluster as an agricultural machine combination according to the number of agricultural machines that need to be scheduled; The scheduling module is used to determine the final agricultural machinery combination from the agricultural machinery combination based on the comprehensive objective function using a preset optimization algorithm, and to schedule the agricultural machinery based on the final agricultural machinery combination.

[0013] Another object of the present invention is to provide a readable storage medium having a computer program stored thereon, wherein the program implements the steps of the above method when executed by a processor.

[0014] Another object of the present invention is to provide an electronic device comprising a memory, a processor and a computer program stored in the memory and running on the processor, wherein the steps of the above method are implemented when the processor executes the program.

[0015] The present invention collects multidimensional data of agricultural machinery within a preset range, determines a comprehensive score for the agricultural machinery based on the multidimensional data, and selects target agricultural machinery with a comprehensive score above a score threshold from the agricultural machinery based on the comprehensive score. A preset clustering algorithm is used to cluster the target agricultural machinery to obtain a preset number of agricultural machinery clusters with different characteristics, each agricultural machinery cluster containing a preset number of agricultural machinery with the same characteristics. A comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function is established to obtain the number of agricultural machinery to be scheduled. A corresponding number of agricultural machinery is selected from the agricultural machinery clusters as an agricultural machinery combination based on the number of agricultural machinery to be scheduled. A preset optimization algorithm is used to determine a final agricultural machinery combination from the agricultural machinery combination based on the comprehensive objective function, and the agricultural machinery is scheduled based on the final agricultural machinery combination. The agricultural machinery is initially screened based on the multidimensional data of the agricultural machinery, and then the target agricultural machinery is clustered to obtain agricultural machinery clusters with different characteristics. During scheduling, agricultural machinery is selected from the agricultural machinery clusters for scheduling, thereby avoiding the situation where agricultural machinery is overly centralized and improving the scheduling effect. This solves the problem of poor scheduling effect in the agricultural machinery scheduling method in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of an agricultural machinery scheduling method based on multi-objective optimization provided by the first embodiment of the present invention; Figure 2 This is a structural block diagram of an agricultural machinery scheduling system based on multi-objective optimization in the third embodiment of the present invention.

[0017] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0018] To facilitate understanding of the present invention, the present invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate several embodiments of the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the present invention.

[0019] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be an intermediate element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or there may be an intermediate element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The terms used in this specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0021] Example 1 See also Figure 1 , which shows an agricultural machinery scheduling method based on multi-objective optimization in a first embodiment of the present invention, and the method includes steps S10 to S13.

[0022] Step S10 , collecting multidimensional data of agricultural machinery within a preset range, determining comprehensive scores of the agricultural machinery based on the multidimensional data, and selecting target agricultural machinery having a comprehensive score higher than a score threshold from the agricultural machinery based on the comprehensive score.

[0023] Among them, various types of data of various agricultural machinery are collected in a specific area or under certain conditions. These "multidimensional data" may include but are not limited to information on the working efficiency, maintenance records, failure rates and other aspects of the agricultural machinery. Specifically, in the embodiment of the present invention, the multidimensional data include equipment age, equipment health index, remaining fuel volume, progress of the current task, historical work efficiency, failure rate, and maintenance records. The "preset range" may refer to a specific geographical location or a specific type of agricultural machinery, etc. The collected multidimensional data is cleaned and standardized to ensure the accuracy and consistency of the data, and a comprehensive score is determined based on the multidimensional data. This score is a quantitative assessment of the overall performance and condition of the agricultural machinery, reflecting the comprehensive performance of the agricultural machinery in multiple dimensions; after obtaining the comprehensive score of each agricultural machinery, a score threshold is set as a screening criterion. The score threshold can be set according to actual needs and evaluation objectives to screen out the required target agricultural machinery.

[0024] Specifically, the calculation formula for the comprehensive score is: S = W 1* E + W 2* F + W 3* H ; in, E For basic ability scoring, F Rate the status, H Score historical performance, W 1. W 2. W 3 are the weights of basic ability score, status score, and historical performance score respectively; The calculation formula for basic ability score is: E =Equipment Age Rating* E 1+Device Health Index Score* E 2; The formula for calculating the status score is: F =Remaining fuel score* F 1 + Progress score of the current assignment* F 2; The formula for calculating the historical performance score is: H =Historical Operation Efficiency Rating* H 1+Failure Rate Score* H 2+ Maintenance Record Score* H 3; in, E 1. E 2. F 1. F 2. H 1. H 2. H 3 are the weighted proportions of the equipment age score, equipment health index score, remaining fuel score, current task progress score, historical operation efficiency score, failure rate score, and maintenance record score.

[0025] The equipment age score can be quantified based on information such as the equipment's purchase date and service life. For example, new equipment receives a high score, while older equipment receives a low score. The equipment health index score can be quantified through professional evaluation. The health index reflects the equipment's wear and tear, performance, and other factors. The remaining fuel score can be quantified based on the equipment's fuel tank capacity and the current remaining fuel level. For example, a full tank receives a high score, while a low tank receives a low score. The progress score for the current task can be quantified based on the equipment's completion performance indicators. The historical operating efficiency score can be quantified by analyzing the equipment's operating efficiency data over a period of time. The failure rate score can be quantified based on the equipment's failure rate over a period of time. A low failure rate may receive a high score. The maintenance record score can be quantified based on the number of maintenance visits, with well-maintained equipment likely receiving a high score. The corresponding weights can be determined based on a comprehensive consideration of factors such as the actual application scenario, evaluation objectives, and expert opinion. It should be noted that in this embodiment of the present invention, the comprehensive scoring system is designed to accurately assess the overall performance of agricultural machinery, thereby selecting the desired target agricultural machinery. The data required for scoring (such as equipment age, health index, remaining fuel, task progress, historical operating efficiency, failure rate, and maintenance records) is readily available and recorded by those skilled in the art in their daily work. Specific quantitative details, such as the calculation method for each data point, scoring criteria, and weighting, are well-known expertise and experience to those skilled in the art and will not be elaborated upon here.

[0026] In step S11 , the target agricultural machinery is clustered using a preset clustering algorithm to obtain a corresponding preset number of agricultural machinery clusters with different characteristics, each agricultural machinery cluster containing a preset number of agricultural machinery with the same characteristics.

[0027] Specifically, the target agricultural machinery has different characteristics. Agricultural machinery with the same characteristics can be clustered into one cluster through preset clustering algorithms such as K-means, hierarchical clustering, DBSCAN, etc., wherein the target agricultural machinery is divided into a preset number of clusters. The agricultural machinery in each cluster is relatively similar in characteristics, while the agricultural machinery between different clusters has more obvious differences.

[0028] Exemplarily, in an embodiment of the present invention, an improved K-means is used to cluster the target agricultural machinery, wherein the multidimensional data of the target agricultural machinery are respectively feature vectorized to obtain the multidimensional feature vectors of the target agricultural machinery; the number of target agricultural machinery is obtained, the corresponding number of clusters is determined according to the number of target agricultural machinery, and the multidimensional feature vectors with the same number as the number of clusters are randomly selected as the initial cluster centers; the Euclidean distances of other multidimensional feature vectors to all initial cluster centers are calculated to assign the multidimensional feature vectors to the group where the nearest initial cluster center is located; for each group of initial cluster centers, the mean of all multidimensional feature vectors in the group of initial cluster centers is calculated as the new initial cluster center; the steps of allocating multidimensional feature vectors and updating the initial cluster centers are repeated until a preset number of iterations is reached, and a number of agricultural machinery clusters with different characteristics that is the same as the number of clusters is obtained.

[0029] First, the multidimensional data are eigenvectorized separately to convert the complex, multidimensional data into a feature vector form that is easy to calculate and compare for subsequent analysis. Next, the number of clusters to be formed is determined based on the total number of target agricultural machinery, that is, the number of agricultural machinery clusters with different characteristics that are ultimately obtained. The same number of multidimensional feature vectors as the number of clusters are randomly selected as the initial cluster centers. These centers will serve as the starting point of the clustering algorithm to guide the subsequent clustering process.

[0030] During the clustering process, the Euclidean distances of all other multidimensional feature vectors to all initial cluster centers are calculated. Each multidimensional feature vector is then assigned to the cluster containing the initial cluster center closest to it. This way, each initial cluster center forms a preliminary cluster. Subsequently, for each cluster of initial cluster centers, the mean of all multidimensional feature vectors within that cluster is calculated, and this mean is used as the new cluster center. This step is crucial for the iterative process, as it allows the cluster center to gradually move to the center of the data within the cluster, thereby more accurately reflecting the characteristics of the cluster. The multidimensional feature vector assignment and cluster center update steps are repeated until the preset number of iterations is reached. In each iteration, data points within the cluster are reallocated based on their distance to the new cluster center, and the cluster center is continuously updated based on the position of the data points within the cluster. This process gradually converges until a stable agricultural machinery cluster with distinct characteristics is formed.

[0031] Specifically, the calculation formula for the number of clusters is: K = ; Where n is the number of agricultural machinery to be clustered. Since the number of clusters is a positive integer, the final number of clusters can be obtained by rounding up after determining the K value.

[0032] Step S12: Establish a comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function, obtain the number of agricultural machinery that needs to be scheduled, and select a corresponding number of agricultural machinery from the agricultural machinery cluster as an agricultural machinery combination according to the number of agricultural machinery that needs to be scheduled.

[0033] A comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function is established. The purpose of this comprehensive function is to minimize both distance and scheduling costs. The number of agricultural machinery to be dispatched is determined. Specifically, based on the specific agricultural operation requirements, the number of machines required to complete the task is determined. This number may be based on various factors, such as the operating area, operating efficiency, and time requirements. After determining the number of machines to be dispatched, the next step is to select an appropriate number of machines from existing agricultural machinery clusters to form a scheduling plan. To avoid centralized scheduling, an appropriate number of machines can be selected from clusters with different characteristics to form a machinery combination.

[0034] Specifically, the operation area and the corresponding operation time are obtained, and the operation efficiency is determined according to the operation area and the corresponding operation time; According to the required number of agricultural machinery and the operating efficiency, the number of agricultural machinery that needs to be selected in each cluster with different operating efficiency is determined, so that the corresponding number of agricultural machinery is selected from the agricultural machinery cluster as an agricultural machinery combination; wherein, after obtaining the required operating area and the corresponding operating time, the operating efficiency is first calculated based on these area and time data, that is, the operating area that can be completed per unit time. According to the required number of agricultural machinery and the determined operating efficiency, the number of agricultural machinery that needs to be selected in the clusters with different operating efficiency can be calculated.

[0035] Specifically, the expression of the comprehensive objective function is: ; in, is the transfer distance objective function, is the scheduling cost objective function, A is the weight coefficient of the transfer distance objective function, B is the weight coefficient of the scheduling cost objective function; The objective function of the transfer distance objective function is: = ; in, Indicates agricultural machinery i To the plot j The transfer distance, Indicates agricultural machinery i Whether to dispatch to the plot j , 1 means scheduling, 0 means no scheduling, n Indicates the number of agricultural machinery,m Indicates the number of plots; The objective function of the scheduling cost objective function is: = ; in, Indicates agricultural machinery i Whether to dispatch to the plot j , 1 means scheduling, 0 means no scheduling, n Indicates the number of agricultural machinery, m Indicates the number of plots, Indicates agricultural machinery i To the plot j fuel costs, Indicates agricultural machinery i To the plot j time cost, Indicates agricultural machinery i To the plot j equipment loss costs.

[0036] Step S13: Determine the final agricultural machinery combination from the agricultural machinery combinations using a preset optimization algorithm according to the comprehensive objective function, and dispatch the agricultural machinery according to the final agricultural machinery combination.

[0037] A preset optimization algorithm is used to determine the final combination of agricultural machinery from a multitude of possible combinations. This algorithm is then used to iteratively optimize the overall objective function, continuously trying different combinations to find the optimal combination that minimizes the overall objective function. Once the final combination is determined, the machinery can be dispatched accordingly.

[0038] In summary, the agricultural machinery scheduling method based on multi-objective optimization in the above embodiment of the present invention collects multi-dimensional data of agricultural machinery within a preset range, determines the comprehensive score of the agricultural machinery based on the multi-dimensional data, and selects target agricultural machinery with the comprehensive score higher than the score threshold from the agricultural machinery based on the comprehensive score; clusters the target agricultural machinery using a preset clustering algorithm to obtain a corresponding preset number of agricultural machinery clusters with different characteristics, each agricultural machinery cluster contains a preset number of agricultural machinery with the same characteristics; establishes a comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function, obtains the number of agricultural machinery to be scheduled, and selects a corresponding number of agricultural machinery from the agricultural machinery cluster as an agricultural machinery combination according to the number of agricultural machinery to be scheduled; determines the final agricultural machinery combination from the agricultural machinery combination using a preset optimization algorithm based on the comprehensive objective function, and schedules the agricultural machinery based on the final agricultural machinery combination; performs preliminary screening on the agricultural machinery based on the multi-dimensional data of the agricultural machinery, and then clusters the target agricultural machinery to obtain agricultural machinery clusters with different characteristics. When scheduling, agricultural machinery is selected from the agricultural machinery clusters for scheduling, thereby avoiding the situation of over-centralized scheduling of agricultural machinery and improving the scheduling effect. The invention solves the problem of poor dispatching effect of the agricultural machinery dispatching method in the prior art.

[0039] Example 2 This embodiment also proposes an agricultural machinery scheduling method based on multi-objective optimization. The difference between the agricultural machinery scheduling method based on multi-objective optimization in this embodiment and the agricultural machinery scheduling method based on multi-objective optimization in Example 1 is that: The step of determining the final agricultural machinery combination from the agricultural machinery combinations using a preset optimization algorithm according to the comprehensive objective function includes: generating an initial population according to the agricultural machinery combination, and calculating the fitness value of each agricultural machinery combination in the initial population using a comprehensive objective function; When the fitness value does not meet the optimization stopping condition, the initial population is sequentially subjected to selection, crossover and mutation operations to obtain an optimized population; The optimized population is used as the initial position of the particle swarm, the speed and position of the particles are updated, and the fitness value is calculated using the comprehensive objective function to perform iterative optimization until the optimization stop condition is met; The optimization stopping condition is that the number of iterative optimization times reaches a preset number or the fitness value reaches a preset threshold.

[0040] An initial population is generated based on the combination of agricultural machinery. This population contains multiple possible combinations. A comprehensive objective function (which takes into account multiple factors such as transfer distance and scheduling cost) is then used to calculate the fitness of each combination within the initial population. This fitness value reflects how well the combination meets the operational requirements and optimization objectives. If the calculated fitness value does not meet the optimization termination criteria (i.e., the current optimization result has not reached a predetermined level of satisfaction), a series of operations are performed on the initial population to generate a more optimized population. These operations include selection (selecting excellent individuals from the current population as parents for subsequent operations), crossover (exchanging partial genes between two parent individuals to produce new individuals), and mutation (randomly changing the genes of new individuals with a small probability to increase population diversity). After these selection, crossover, and mutation operations, an optimized population is obtained. This optimized population is then used as the initial position for the particle swarm optimization algorithm, which then undergoes further iterative optimization. In the particle swarm algorithm, each particle represents a possible combination of agricultural machinery and has a corresponding speed and position. By continuously updating the particle's speed and position and calculating a new fitness value using a comprehensive objective function, the algorithm gradually approaches the optimal solution until a stopping condition is met. This can be when the number of iterations reaches a preset number or when the fitness value reaches a preset threshold. When either of these conditions is met, the algorithm is considered to have found a sufficiently good combination of agricultural machinery and is used as the final combination for scheduling.

[0041] In addition, in some optional embodiments of the present invention, after the step of determining a final agricultural machinery combination from the agricultural machinery combinations using a preset optimization algorithm according to the comprehensive objective function and scheduling the agricultural machinery according to the final agricultural machinery combination, the following steps are further included: When an agricultural machine in the final agricultural machine combination needs to be replaced, the agricultural machine cluster where the replacement agricultural machine is located is obtained, and an agricultural machine is selected from the agricultural machine cluster for replacement; Among them, the conditions for changing the scheduling are that the agricultural machinery fails or the progress of the agricultural machinery operation on the field lags behind the threshold.

[0042] When the finalized agricultural machinery combination encounters certain circumstances during its operation that require replacement, specifically when a machine fails and cannot continue operating, or when a machine's progress on its assigned plot falls significantly behind schedule, exceeding a preset threshold, the replacement scheduling process is triggered. The machine that needs replacement is identified, and its cluster is determined. After the machine and its cluster are determined, a suitable machine is selected from the cluster for replacement. This ensures the timeliness and accuracy of scheduling decisions.

[0043] In summary, the agricultural machinery scheduling method based on multi-objective optimization in the above embodiment of the present invention collects multi-dimensional data of agricultural machinery within a preset range, determines the comprehensive score of the agricultural machinery based on the multi-dimensional data, and selects target agricultural machinery with the comprehensive score higher than the score threshold from the agricultural machinery based on the comprehensive score; clusters the target agricultural machinery using a preset clustering algorithm to obtain a corresponding preset number of agricultural machinery clusters with different characteristics, each agricultural machinery cluster contains a preset number of agricultural machinery with the same characteristics; establishes a comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function, obtains the number of agricultural machinery to be scheduled, and selects a corresponding number of agricultural machinery from the agricultural machinery cluster as an agricultural machinery combination according to the number of agricultural machinery to be scheduled; determines the final agricultural machinery combination from the agricultural machinery combination using a preset optimization algorithm based on the comprehensive objective function, and schedules the agricultural machinery based on the final agricultural machinery combination; performs preliminary screening on the agricultural machinery based on the multi-dimensional data of the agricultural machinery, and then clusters the target agricultural machinery to obtain agricultural machinery clusters with different characteristics. When scheduling, agricultural machinery is selected from the agricultural machinery clusters for scheduling, thereby avoiding the situation of over-centralized scheduling of agricultural machinery and improving the scheduling effect. The invention solves the problem of poor dispatching effect of the agricultural machinery dispatching method in the prior art.

[0044] Example 3 See also Figure 2 , which shows an agricultural machinery scheduling system based on multi-objective optimization proposed in the third embodiment of the present invention, the system includes: The collection module 100 is configured to collect multidimensional data of agricultural machinery within a preset range, determine a comprehensive score of the agricultural machinery based on the multidimensional data, and select target agricultural machinery having a comprehensive score higher than a score threshold from among the agricultural machinery based on the comprehensive score; The clustering module 200 is configured to cluster the target agricultural machinery using a preset clustering algorithm to obtain a preset number of agricultural machinery clusters with different characteristics, each agricultural machinery cluster containing a preset number of agricultural machinery with the same characteristics; Establishing module 300, for establishing a comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function, obtaining the number of agricultural machines to be scheduled, and selecting a corresponding number of agricultural machines from the agricultural machine cluster as an agricultural machine combination according to the number of agricultural machines to be scheduled; The scheduling module 400 is used to determine the final agricultural machinery combination from the agricultural machinery combinations based on the comprehensive objective function using a preset optimization algorithm, and to schedule the agricultural machinery based on the final agricultural machinery combination.

[0045] Furthermore, in the above-mentioned agricultural machinery scheduling system based on multi-objective optimization, wherein the multi-dimensional data includes equipment age, equipment health index, remaining fuel, progress of current operation tasks, historical operation efficiency, failure rate, and maintenance records, the step of collecting the multi-dimensional data of agricultural machinery within a preset range and determining the comprehensive score of the agricultural machinery based on the multi-dimensional data includes: The formula for calculating the comprehensive score is: S = W 1* E + W 2* F + W 3* H ; in, E For basic ability scoring, F Rate the status, H Score historical performance, W 1. W 2. W 3 are the weights of basic ability score, status score, and historical performance score respectively; The calculation formula for basic ability score is: E =Equipment Age Rating* E 1+Device Health Index Score* E 2; The formula for calculating the status score is: F =Remaining fuel score* F 1 + Progress score of the current assignment* F 2; The formula for calculating the historical performance score is: H =Historical Operation Efficiency Rating* H 1+Failure Rate Score* H 2+ Maintenance Record Score* H 3; in, E 1. E 2. F 1. F 2. H 1. H 2. H 3 are the weighted proportions of the equipment age score, equipment health index score, remaining fuel score, current task progress score, historical operation efficiency score, failure rate score, and maintenance record score.

[0046] Furthermore, in the above-mentioned agricultural machinery scheduling system based on multi-objective optimization, the step of clustering the target agricultural machinery using a preset clustering algorithm to obtain a corresponding preset number of agricultural machinery clusters with different characteristics includes: Perform feature vectorization on the multidimensional data of the target agricultural machinery to obtain the multidimensional feature vector of the target agricultural machinery; Obtain the number of target agricultural machinery, determine the corresponding number of clusters according to the number of target agricultural machinery, and randomly select the same number of multidimensional feature vectors as the number of clusters as the initial cluster centers; Calculate the Euclidean distances of other multidimensional feature vectors to all initial cluster centers to assign the multidimensional feature vectors to the group where the nearest initial cluster center is located; For each group of initial cluster centers, calculate the mean of all multidimensional feature vectors within the group of initial cluster centers as the new initial cluster center; The steps of allocating the multidimensional feature vector and updating the initial cluster center are repeated until a preset number of iterations is reached, and agricultural machinery clusters with different characteristics, the number of which is the same as the number of clusters, are obtained.

[0047] Furthermore, in the above-mentioned agricultural machinery scheduling system based on multi-objective optimization, the step of establishing a comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function includes: The expression of the comprehensive objective function is: ; in, is the transfer distance objective function, is the scheduling cost objective function, A is the weight coefficient of the transfer distance objective function, B is the weight coefficient of the scheduling cost objective function; The objective function of the transfer distance objective function is: = ; in, Indicates agricultural machinery i To the plot j The transfer distance, Indicates agricultural machinery i Whether to dispatch to the plot j , 1 means scheduling, 0 means no scheduling, n Indicates the number of agricultural machinery, m Indicates the number of plots; The objective function of the scheduling cost objective function is: = ; in, Indicates agricultural machineryi Whether to dispatch to the plot j , 1 means scheduling, 0 means no scheduling, n Indicates the number of agricultural machinery, m Indicates the number of plots, Indicates agricultural machinery i To the plot j fuel costs, Indicates agricultural machinery i To the plot j time cost, Indicates agricultural machinery i To the plot j equipment loss costs.

[0048] Furthermore, in the above-mentioned agricultural machinery scheduling system based on multi-objective optimization, the step of determining the final agricultural machinery combination from the agricultural machinery combinations using a preset optimization algorithm according to the comprehensive objective function includes: generating an initial population according to the agricultural machinery combination, and calculating the fitness value of each agricultural machinery combination in the initial population using a comprehensive objective function; When the fitness value does not meet the optimization stopping condition, the initial population is sequentially subjected to selection, crossover and mutation operations to obtain an optimized population; The optimized population is used as the initial position of the particle swarm, the speed and position of the particles are updated, and the fitness value is calculated using the comprehensive objective function to perform iterative optimization until the optimization stop condition is met; The optimization stopping condition is that the number of iterative optimization times reaches a preset number or the fitness value reaches a preset threshold.

[0049] Furthermore, the above-mentioned agricultural machinery scheduling system based on multi-objective optimization, wherein the step of determining the final agricultural machinery combination from the agricultural machinery combinations using a preset optimization algorithm according to the comprehensive objective function and scheduling the agricultural machinery according to the final agricultural machinery combination further includes: When an agricultural machine in the final agricultural machine combination needs to be replaced, the agricultural machine cluster where the replacement agricultural machine is located is obtained, and an agricultural machine is selected from the agricultural machine cluster for replacement; Among them, the conditions for changing the scheduling are that the agricultural machinery fails or the progress of the agricultural machinery operation on the field lags behind the threshold.

[0050] Furthermore, in the above-mentioned agricultural machinery scheduling system based on multi-objective optimization, the steps of obtaining the number of agricultural machinery to be scheduled and selecting a corresponding number of agricultural machinery from the agricultural machinery cluster as an agricultural machinery combination according to the number of agricultural machinery to be scheduled include: Obtain the required operation area and the corresponding operation time, and determine the operation efficiency based on the operation area and the corresponding operation time; The number of agricultural machines required to be selected in each cluster with different operating efficiencies is determined based on the required number of agricultural machines and their operating efficiency, so that a corresponding number of agricultural machines are selected from the agricultural machine clusters as an agricultural machine combination.

[0051] The functions or operation steps implemented when the above modules are executed are substantially the same as those in the above method embodiments and will not be repeated here.

[0052] Example 4 Another aspect of the present invention further provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the above-mentioned embodiments 1 to 2.

[0053] Example 5 On the other hand, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the program, the steps of the method described in any one of the above-mentioned embodiments 1 to 2 are implemented.

[0054] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0055] Those skilled in the art will appreciate that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable storage medium for use by an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device), or for use in conjunction with such instruction execution system, apparatus, or device. For purposes of this specification, a "computer-readable storage medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by an instruction execution system, apparatus, or device, or in conjunction with such instruction execution system, apparatus, or device.

[0056] More specific examples (a non-exhaustive list) of computer-readable storage media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable storage medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0057] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0058] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0059] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

Claims

1. A method for agricultural machinery scheduling based on multi-objective optimization, characterized in that: The method comprises: collecting multidimensional data of agricultural machinery within a preset range, determining comprehensive scores of the agricultural machinery based on the multidimensional data, and selecting target agricultural machinery having a comprehensive score higher than a score threshold from among the agricultural machinery based on the comprehensive score; Clustering the target agricultural machinery using a preset clustering algorithm to obtain a corresponding preset number of agricultural machinery clusters with different characteristics, each agricultural machinery cluster containing a preset number of agricultural machinery with the same characteristics; Establish a comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function to obtain the number of agricultural machinery that needs to be scheduled. According to the number of agricultural machinery that needs to be scheduled, a corresponding number of agricultural machinery are selected from the agricultural machinery cluster as an agricultural machinery combination. According to the comprehensive objective function, the preset optimization algorithm is used to determine the final agricultural machinery combination from the agricultural machinery combinations, and the agricultural machinery is dispatched according to the final agricultural machinery combination.

2. The agricultural machinery scheduling method based on multi-objective optimization according to claim 1 is characterized in that: The multidimensional data includes equipment age, equipment health index, remaining fuel, progress of current operation tasks, historical operation efficiency, failure rate, and maintenance records. The steps of collecting the multidimensional data of agricultural machinery within a preset range and determining a comprehensive score of the agricultural machinery based on the multidimensional data include: The formula for calculating the comprehensive score is: S = W 1* E + W 2* F + W 3* H ； in, E For basic ability scoring, F Rate the status, H Score historical performance, W 1. W 2. W 3 are the weights of basic ability score, status score, and historical performance score respectively; The calculation formula for basic ability score is: E =Equipment Age Rating* E 1+Device Health Index Score* E 2; The formula for calculating the status score is: F =Remaining fuel score* F 1 + Progress score of the current assignment* F 2; The formula for calculating the historical performance score is: H =Historical Operation Efficiency Rating* H 1+Failure Rate Score* H 2+ Maintenance Record Score* H 3; in, E 1. E 2. F 1. F 2. H 1. H 2. H 3 are the weighted proportions of the equipment age score, equipment health index score, remaining fuel score, current task progress score, historical operation efficiency score, failure rate score, and maintenance record score.

3. The agricultural machinery scheduling method based on multi-objective optimization according to claim 1 is characterized in that: The step of clustering the target agricultural machinery using a preset clustering algorithm to obtain a corresponding preset number of agricultural machinery clusters with different characteristics includes: Perform feature vectorization on the multidimensional data of the target agricultural machinery to obtain the multidimensional feature vector of the target agricultural machinery; Obtain the number of target agricultural machinery, determine the corresponding number of clusters according to the number of target agricultural machinery, and randomly select the same number of multidimensional feature vectors as the number of clusters as the initial cluster centers; Calculate the Euclidean distances of other multidimensional feature vectors to all initial cluster centers to assign the multidimensional feature vectors to the group where the nearest initial cluster center is located; For each group of initial cluster centers, calculate the mean of all multidimensional feature vectors within the group of initial cluster centers as the new initial cluster center; The steps of allocating the multidimensional feature vector and updating the initial cluster center are repeated until a preset number of iterations is reached, and agricultural machinery clusters with different characteristics, the number of which is the same as the number of clusters, are obtained.

4. The agricultural machinery scheduling method based on multi-objective optimization according to claim 1 is characterized in that: The step of establishing a comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function comprises: The expression of the comprehensive objective function is: ； in, is the transfer distance objective function, is the scheduling cost objective function, A is the weight coefficient of the transfer distance objective function, B is the weight coefficient of the scheduling cost objective function; The objective function of the transfer distance objective function is: = ； in, Indicates agricultural machinery i To the plot j The transfer distance, Indicates agricultural machinery i Whether to dispatch to the plot j , 1 means scheduling, 0 means no scheduling, n Indicates the number of agricultural machinery, m Indicates the number of plots; The objective function of the scheduling cost objective function is: = ； in, Indicates agricultural machinery i Whether to dispatch to the plot j , 1 means scheduling, 0 means no scheduling, n Indicates the number of agricultural machinery, m Indicates the number of plots, Indicates agricultural machinery i To the plot j fuel costs, Indicates agricultural machinery i To the plot j time cost, Indicates agricultural machinery i To the plot j equipment loss costs.

5. The agricultural machinery scheduling method based on multi-objective optimization according to claim 1 is characterized in that: The step of determining the final agricultural machinery combination from the agricultural machinery combinations using a preset optimization algorithm according to the comprehensive objective function includes: generating an initial population according to the agricultural machinery combination, and calculating the fitness value of each agricultural machinery combination in the initial population using a comprehensive objective function; When the fitness value does not meet the optimization stopping condition, the initial population is sequentially subjected to selection, crossover and mutation operations to obtain an optimized population; The optimized population is used as the initial position of the particle swarm, the speed and position of the particles are updated, and the fitness value is calculated using the comprehensive objective function to perform iterative optimization until the optimization stop condition is met; The optimization stopping condition is that the number of iterative optimization times reaches a preset number or the fitness value reaches a preset threshold.

6. The agricultural machinery scheduling method based on multi-objective optimization according to claim 1 is characterized in that: After the steps of determining the final agricultural machinery combination from the agricultural machinery combinations using a preset optimization algorithm according to the comprehensive objective function and dispatching the agricultural machinery according to the final agricultural machinery combination, the following steps are further included: When an agricultural machine in the final agricultural machine combination needs to be replaced, the agricultural machine cluster where the replacement agricultural machine is located is obtained, and an agricultural machine is selected from the agricultural machine cluster for replacement; Among them, the conditions for changing the scheduling are that the agricultural machinery fails or the progress of the agricultural machinery operation on the field lags behind the threshold.

7. The agricultural machinery scheduling method based on multi-objective optimization according to claim 1 is characterized in that: The steps of obtaining the number of agricultural machines to be dispatched and selecting a corresponding number of agricultural machines from the agricultural machine cluster as an agricultural machine combination according to the number of agricultural machines to be dispatched include: Obtain the required operation area and the corresponding operation time, and determine the operation efficiency based on the operation area and the corresponding operation time; The number of agricultural machines required to be selected in each cluster with different operating efficiencies is determined based on the required number of agricultural machines and their operating efficiency, so that a corresponding number of agricultural machines are selected from the agricultural machine clusters as an agricultural machine combination.

8. An agricultural machinery scheduling system based on multi-objective optimization, characterized in that: The system comprises: a collection module for collecting multidimensional data of agricultural machinery within a preset range, determining a comprehensive score of the agricultural machinery based on the multidimensional data, and selecting target agricultural machinery having a comprehensive score higher than a score threshold from among the agricultural machinery based on the comprehensive score; a clustering module, configured to cluster the target agricultural machinery using a preset clustering algorithm to obtain a corresponding preset number of agricultural machinery clusters with different characteristics, each agricultural machinery cluster containing a preset number of agricultural machinery with the same characteristics; Establish a module for establishing a comprehensive objective function consisting of a transfer distance objective function and a scheduling cost objective function, obtain the number of agricultural machines that need to be scheduled, and select a corresponding number of agricultural machines from the agricultural machine cluster as an agricultural machine combination according to the number of agricultural machines that need to be scheduled; The scheduling module is used to determine the final agricultural machinery combination from the agricultural machinery combination based on the comprehensive objective function using a preset optimization algorithm, and to schedule the agricultural machinery based on the final agricultural machinery combination.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the steps of the method according to any one of claims 1 to 7 are implemented when the processor executes the program.

Images