Guiding method and system for entry and exit of warehouse of freshly cured tobacco truck in tobacco warehouse

Abstract

The embodiment of the specification provides a primary curing tobacco yard truck warehouse-in and warehouse-out guidance method and system, wherein the method comprises the following steps: collecting primary curing tobacco warehouse-in and warehouse-out historical data, training and optimizing a warehouse space demand prediction model based on the primary curing tobacco warehouse-in and warehouse-out historical data to obtain a warehouse space demand prediction result; adopting an ant colony search algorithm, classifying warehouse spaces of a yard based on the location and destination of primary curing tobacco raw materials and the distance between the warehouse spaces, establishing a warehouse space allocation model to obtain a warehouse space allocation result; and establishing a warehouse space path selection model based on the warehouse space demand prediction result and the warehouse space allocation result to realize optimal path selection of a vehicle warehouse-in and warehouse-out link. The application effectively guides the primary curing tobacco truck warehouse-in and warehouse-out process, can effectively utilize yard resources and improve raw material response speed.

Description

Technical Field

[0001] This document relates to the field of warehousing and logistics technology, and in particular to a method and system for guiding the entry and exit of tobacco trucks in a primary tobacco curing yard. Background Technology

[0002] The initial curing of tobacco is a crucial step in the tobacco industry's raw material storage process. It primarily involves transporting the initially cured tobacco leaves from tobacco stations to the initial curing yard via tobacco transport vehicles for in-storage management. Afterward, the initial curing is fed into the tobacco processing plant and cured according to the requirements of the leaf blend formula. During this process, the following problems may arise:

[0003] 1. Limited cargo yard resources

[0004] Taking Yunnan Tobacco Leaf Company as an example, the annual initial flue-cured tobacco storage volume is approximately 2.6 million dan (a unit of weight), and the open-air storage volume is approximately 600,000 dan. After the tobacco trucks arrive, the tobacco leaves are moved to one or more storage locations according to the requirements of the storage location management personnel until the storage location resources are used up. During this process, the storage location carries out the corresponding re-drying and feeding according to the company's relevant requirements for leaf threshing and re-drying, which frees up storage locations. If the existing storage location resources are not fully utilized, it will lead to the waste of storage location resources. That is, the storage location will contain tobacco leaves that are not needed in the short term for leaf threshing and re-drying, and a large amount of initial flue-cured tobacco leaves will be stored at the tobacco stations, which cannot be supplied, resulting in the tobacco leaves becoming moldy and causing huge economic losses.

[0005] 2. Delayed response to raw material demand

[0006] When raw materials are received into the warehouse, the allocation is randomized. This results in priority being given to storage locations closer to the re-drying workshop that meet the leaf group formula requirements. Consequently, storage locations farther from the re-drying workshop, but meeting the leaf group formula requirements, cannot be effectively released for re-drying. Because the raw materials for the leaf group formula tend to accumulate, if they are not re-dryed promptly, they will remain in the warehouse for a longer period. This will occupy storage space resources, affecting the receipt of other raw materials, and will also increase the pressure on raw material management and maintenance, significantly increasing the risk of mold. In summary, this leads to a delayed response in the warehouse to the feeding of raw materials for leaf re-drying. Summary of the Invention

[0007] This specification provides one or more embodiments of a method for guiding the entry and exit of tobacco carts at a primary tobacco curing yard, including:

[0008] Collect historical data on the entry and exit of primary flue-cured tobacco in the warehouse, and train and optimize the storage space demand prediction model based on the historical data to obtain the storage space demand prediction results.

[0009] An ant colony search algorithm is used to classify the storage locations in the storage yard based on the location and destination of the initial flue-cured tobacco raw materials and the distance between storage locations, and a storage location allocation model is established to obtain the storage location allocation results.

[0010] Based on the predicted demand and allocation results for storage locations, a storage location route selection model is established to achieve optimal route selection for vehicle entry and exit.

[0011] Furthermore, the specific method for collecting historical data on the entry and exit of primary flue-cured tobacco from the storage yard, training and optimizing the storage space demand prediction model based on the historical data, and obtaining the storage space demand prediction result is as follows:

[0012] The collected historical data on the entry and exit of flue-cured tobacco in the warehouse were divided into training set and test set;

[0013] The recurrent neural network (RNN) model is trained using a training set to capture the time dependencies in the sequence data of the training set. Based on the time dependencies, the demand for cargo space is predicted to obtain an initial model for predicting cargo space demand.

[0014] The prediction accuracy of the initial warehouse demand prediction model is tested using a test set. The model parameters are optimized based on the test results. When the prediction accuracy of the model is greater than a preset threshold, the final warehouse demand prediction model is output. The current warehouse demand prediction result is obtained through the warehouse demand prediction model.

[0015] Furthermore, the method of using the ant colony search algorithm to classify the storage locations in the yard based on the location and destination of the initial flue-cured tobacco raw materials and the distance between storage locations, and establishing a storage location allocation model to obtain the storage location allocation results is as follows:

[0016] Based on the current demand forecast for cargo space, the method for calculating the probability of each path selection using the ant colony search algorithm is as follows:

[0017]

[0018] Where i and j represent the storage of the initial flue-cured tobacco raw materials and the next destination, respectively, k represents the selection of different paths, the pheromone factor α reflects the relative importance of the amount of pheromone accumulated on the path during the ant movement in guiding the ant colony search; the heuristic function factor β reflects the relative importance of heuristic information in guiding the ant colony search.

[0019] Based on the optimized and unoptimized cargo collection distances, the cargo collection distance reduction ratio is calculated as follows:

[0020]

[0021] Among them, S ij Indicates the distance from one storage location to another; A nmThis represents the raw material requirement for each stack, X represents the number of cross-regions per unit quantity of each raw material before optimization, Y represents the number of regions after optimization, and P represents the SLP-GA layout planning method.

[0022] Construct a storage location allocation model to assign corresponding raw materials to each storage location in the storage yard.

[0023] Furthermore, the specific method for establishing a storage location route selection model based on the storage location demand forecast and storage location allocation results to achieve optimal route selection for vehicle entry and exit is as follows:

[0024] Based on the number of collection points, DBSCAN cluster analysis is used to classify the collection points and generate initial routes;

[0025] The initial path is deconstructed using destruction, repair, and insertion operators, and a better neighborhood is selected through an adaptive algorithm. After multiple iterations, the optimal path is obtained.

[0026] Furthermore, when the model's prediction accuracy is ≥85%, the final cargo space demand prediction model is output.

[0027] Furthermore, the allocation of corresponding raw materials to each storage location in the warehouse includes:

[0028] Determine the raw material storage area in the warehouse based on the raw material's place of origin;

[0029] The corresponding storage locations are allocated according to the different varieties and parts of the raw materials from the corresponding production areas within different regions.

[0030] Furthermore, the method specifically includes:

[0031] The DBSCAN algorithm is used to cluster cargo locations;

[0032] The initial path is generated based on the grouping of cargo locations after clustering. The initial T value and number of iterations in the TA criterion are set, and the operator scores and weights are reset.

[0033] A new path S* is generated by selecting a set of destruction and repair operators using a roulette wheel method.

[0034] The Metropolis acceptance criterion is adopted, which means that the new path S* is first compared with the current path S. If the new path S* is better than the current path S, the current path S is updated. Then, it is further compared with the optimal path Sbest. If it is better than the optimal path Sbest, the optimal path Sbest is updated; otherwise, it remains unchanged. When the new path S* is greater than the current path S, but the difference is less than the initial T value, the path is also accepted to avoid getting trapped in local optima. The T value gradually decreases at a certain rate.

[0035] Adjust the operator score based on the path update and update the corresponding weights;

[0036] Continue using the roulette wheel method to select a set of destruction and repair operators, repeat the above steps until the number of iterations is reached, and obtain the final optimal path Sbest.

[0037] This specification provides one or more embodiments of a system for guiding the entry and exit of tobacco carts at a primary tobacco curing yard, including:

[0038] Storage space demand forecasting module: used to collect historical data on the entry and exit of primary flue-cured tobacco in the storage yard, train and optimize the storage space demand forecasting model based on the historical data on the entry and exit of primary flue-cured tobacco in the storage yard, and obtain the storage space demand forecasting results;

[0039] The storage location allocation module is used to classify the storage locations in the storage yard based on the location and destination of the raw materials for initial flue-cured tobacco and the distance between storage locations using an ant colony search algorithm, establish a storage location allocation model, and obtain the storage location allocation results.

[0040] Route selection module: used to establish a cargo location route selection model based on the cargo location demand forecast results and cargo location allocation results, so as to realize the optimal route selection for vehicle entry and exit from the warehouse.

[0041] This specification provides one or more embodiments of an electronic device, including:

[0042] Processor; and,

[0043] A memory is configured to store computer-executable instructions, which, when executed, cause the processor to implement the steps of the above-described method for guiding the entry and exit of tobacco carts at the initial tobacco curing yard.

[0044] This specification provides one or more embodiments of a storage medium for storing computer-executable instructions that, when executed, implement the steps of the above-described method for guiding the entry and exit of tobacco carts at the initial tobacco curing yard.

[0045] The embodiments of the present invention effectively guide the process of initial curing tobacco trucks entering and leaving the warehouse, effectively utilize warehouse resources, and improve the response speed of raw materials.

[0046] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in one or more embodiments of this specification or in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 A flowchart illustrating a method for guiding the entry and exit of tobacco carts at a primary tobacco curing yard, provided for one or more embodiments of this specification;

[0049] Figure 2 A schematic diagram illustrating the implementation of a method for guiding the entry and exit of tobacco carts in a primary tobacco curing yard, provided for one or more embodiments of this specification;

[0050] Figure 3 A schematic diagram illustrating the composition of a primary tobacco curing yard truck entry and exit guidance system provided for one or more embodiments of this specification;

[0051] Figure 4 This is a schematic diagram of the structure of an electronic device provided for one or more embodiments of this specification. Detailed Implementation

[0052] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0053] Method Implementation Examples

[0054] According to an embodiment of the present invention, a method for guiding the entry and exit of tobacco carts in a primary tobacco curing yard is provided. Figure 1 A flowchart illustrating a method for guiding the entry and exit of tobacco carts at a primary tobacco curing yard, provided for one or more embodiments of this specification. Figure 2 This specification provides a flowchart illustrating the implementation of a method for guiding the entry and exit of tobacco carts at a primary tobacco curing yard, as illustrated in one or more embodiments. Figure 1 , Figure 2 As shown, the method for guiding the entry and exit of tobacco carts at the initial curing tobacco yard according to an embodiment of the present invention specifically includes:

[0055] S1. Collect historical data on the entry and exit of primary flue-cured tobacco in the warehouse, train and optimize the storage space demand prediction model based on the historical data on the entry and exit of primary flue-cured tobacco, and obtain the storage space demand prediction result.

[0056] Historical data on the entry and exit of primary flue-cured tobacco from the freight yard over the years were collected and divided into a training set and a test set. In this embodiment, historical data from 2018 to 2021 was collected as the training set, and data from 2022 to 2023 was collected as the test set.

[0057] A recurrent neural network (RNN) model is trained using a training set to capture the temporal dependencies in the training set's sequence data. Based on these temporal dependencies, the demand for cargo space is predicted, resulting in an initial model for cargo space demand prediction. Using a self-learning approach, the RNN algorithm autonomously learns patterns and rules from the demand data and generates accurate predictions based on this information, achieving an accurate response in demand forecasting. Its mathematical expression is as follows:

[0058] (h_t=\sigma(W_{xh}x_t+W_{hh}h_{t-1}+b_h));

[0059] (y_t=W_{hy}h_t+b_y);

[0060] Where (h_t) represents the output of the hidden layer, (x_t) represents the input data, (y_t) represents the prediction result, (W_{xh}), (W_{hh}) and (W_{hy}) are weight matrices, (b_h) and (b_y) are bias terms, and (\sigma) is the activation function.

[0061] The prediction accuracy of the initial warehouse space demand prediction model is tested using a test set. The model parameters are optimized based on the test results. When the prediction accuracy of the model is greater than a preset threshold, the final warehouse space demand prediction model is output. The current warehouse space demand prediction result is obtained through the warehouse space demand prediction model. In this embodiment, when the prediction accuracy of the model is ≥85%, the final warehouse space demand prediction model is output, and warehouse space allocation modeling analysis is carried out.

[0062] S2. Using the ant colony search algorithm, based on the location and destination of the initial flue-cured tobacco raw materials and the distance between storage locations, the storage locations in the yard are classified, a storage location allocation model is established, and the storage location allocation results are obtained.

[0063] Based on the current demand forecast for cargo space, the method for calculating the probability of each path selection using the ant colony search algorithm is as follows:

[0064]

[0065] Where i and j represent the storage of the initial flue-cured tobacco raw materials and the next destination, respectively, k represents the selection of different paths, the pheromone factor α reflects the relative importance of the amount of pheromone accumulated on the path during the ant movement in guiding the ant colony search; the heuristic function factor β reflects the relative importance of heuristic information in guiding the ant colony search.

[0066] The collection distance mainly refers to the actual travel distance of each tobacco truck in the yard. When a tobacco truck cannot place all its tobacco leaves in the same storage location, unloading needs to be done between multiple storage locations. This distance is the reduction ratio of the total unloading path distance for each tobacco truck. The collection distance reduction ratio is calculated based on the optimized collection distance and the unoptimized collection distance, as shown below:

[0067]

[0068] Among them, S ij Indicates the distance from one storage location to another; A nm This represents the raw material requirement for each stack, X represents the number of cross-regions per unit quantity of each raw material before optimization, Y represents the number of regions after optimization, and P represents the SLP-GA layout planning method.

[0069] Construct a storage location allocation model to assign corresponding raw materials to each storage location in the storage yard. Specifically: determine the raw material storage area in the storage yard based on the origin of the raw materials; allocate corresponding storage locations in different areas according to the different varieties and parts of the raw materials from the corresponding origin.

[0070] S3. Based on the predicted demand and allocation results of the storage locations, establish a storage location route selection model to achieve optimal route selection for vehicle entry and exit.

[0071] The number of collection points represents the centralized storage points where virgin tobacco needs to be unloaded. The principle for unloading virgin tobacco in open-air yards is to unload directly when a storage location is empty. If the location has raw materials, the unloaded raw materials must be of the same grade as the raw materials in that location; mixing is not allowed. For example, if a tobacco truck is carrying C3F raw materials, and there are currently no empty C3F storage locations, but 5-6, or even 7-8 locations that meet the C3F unloading requirements, the specific location for unloading depends primarily on the actual situation of different storage locations in the yard and the situation of incoming tobacco trucks. The principle is to prioritize full stacks, and another principle is to facilitate unloading. Therefore, based on the number of collection points, DBSCAN cluster analysis is used to classify the collection points so that the tobacco trucks know where to unload. The specific method is as follows:

[0072] Based on the number of collection points, DBSCAN clustering analysis is used to classify the collection points and generate high-quality initial paths. Subsequently, the initial paths are deconstructed using destruction, repair, and insertion operators, and an adaptive algorithm is used to select better neighborhoods. After multiple iterations, the optimal path is obtained. The corresponding algorithm implementation steps for the initial flue-cured tobacco inbound and outbound processes are as follows:

[0073] The DBSCAN algorithm is used to cluster cargo locations;

[0074] The initial path is generated based on the grouping of cargo locations after clustering. The initial T value and number of iterations in the TA criterion are set, and the operator scores and weights are reset.

[0075] A new path S* is generated by selecting a set of destruction and repair operators using a roulette wheel method.

[0076] The Metropolis acceptance criterion is adopted, which means that the new path S* is first compared with the current path S. If the new path S* is better than the current path S, the current path S is updated. Then, it is further compared with the optimal path Sbest. If it is better than the optimal path Sbest, the optimal path Sbest is updated; otherwise, it remains unchanged. When the new path S* is greater than the current path S, but the difference is less than the initial T value, the path is also accepted to avoid getting trapped in local optima. The T value gradually decreases at a certain rate.

[0077] Adjust the operator score based on the path update and update the corresponding weights;

[0078] Continue using the roulette wheel method to select a set of destruction and repair operators, repeat the above steps until the number of iterations is reached, and obtain the final optimal path Sbest.

[0079] The beneficial effects of this invention are as follows:

[0080] This invention guides the tobacco trucks in the warehousing process by specifying the exact location to be placed and the quantity of raw tobacco materials to be placed in each location during the warehousing phase, and by specifying the location from which the trucks should exit and the quantity of raw tobacco materials to be removed during the outbound phase, thus satisfying the "first-in, first-out" principle. This effectively guides the inbound and outbound processes of raw tobacco trucks, making efficient use of yard resources and improving the response speed of raw materials.

[0081] System Implementation Examples

[0082] According to embodiments of the present invention, a system for guiding the entry and exit of tobacco carts in a primary tobacco curing yard is provided. Figure 3 This specification provides a schematic diagram illustrating the composition of a primary tobacco curing yard truck entry and exit guidance system, as shown in one or more embodiments. Figure 3 As shown, the initial curing tobacco yard tobacco truck entry and exit guidance system according to an embodiment of the present invention specifically includes:

[0083] Storage space demand forecasting module 30: used to collect historical data on the entry and exit of primary flue-cured tobacco in the storage yard, train and optimize the storage space demand forecasting model based on the historical data on the entry and exit of primary flue-cured tobacco, and obtain the storage space demand forecasting result;

[0084] Storage location allocation module 32: It is used to classify the storage locations in the storage yard based on the location and destination of the raw materials for initial curing of tobacco and the distance between storage locations using the ant colony search algorithm, establish a storage location allocation model, and obtain the storage location allocation results.

[0085] Path selection module 34: Used to establish a path selection model for the storage location based on the storage location demand forecast and storage location allocation results, so as to achieve the optimal path selection for vehicle entry and exit from the warehouse.

[0086] The embodiments of the present invention are system embodiments corresponding to the above method embodiments. The specific operation of each module can be understood by referring to the description of the method embodiments, and will not be repeated here.

[0087] Device Example 1

[0088] This invention provides an electronic device, such as... Figure 4 As shown, it includes: a memory 40, a processor 42, and a computer program stored in the memory 40 and executable on the processor 42. When the computer program is executed by the processor 42, it performs the following method steps:

[0089] S1. Collect historical data on the entry and exit of primary flue-cured tobacco in the warehouse, and train and optimize the storage space demand prediction model based on the historical data on the entry and exit of primary flue-cured tobacco to obtain the storage space demand prediction result;

[0090] S2. Using the ant colony search algorithm, based on the location and destination of the initial flue-cured tobacco raw materials and the distance between storage locations, the storage locations in the storage yard are classified, a storage location allocation model is established, and the storage location allocation results are obtained;

[0091] S3. Based on the predicted demand and allocation results of the storage locations, establish a storage location route selection model to achieve optimal route selection for vehicle entry and exit.

[0092] Device Example 2

[0093] This invention provides a computer-readable storage medium storing an information transmission implementation program. When executed by a processor 42, the program performs the following method steps:

[0094] S1. Collect historical data on the entry and exit of primary flue-cured tobacco in the warehouse, and train and optimize the storage space demand prediction model based on the historical data on the entry and exit of primary flue-cured tobacco to obtain the storage space demand prediction result;

[0095] S2. Using the ant colony search algorithm, based on the location and destination of the initial flue-cured tobacco raw materials and the distance between storage locations, the storage locations in the storage yard are classified, a storage location allocation model is established, and the storage location allocation results are obtained;

[0096] S3. Based on the predicted demand and allocation results of the storage locations, establish a storage location route selection model to achieve optimal route selection for vehicle entry and exit.

[0097] The computer-readable storage media described in this embodiment include, but are not limited to, ROM, RAM, disk, or optical disk.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for guiding the entry and exit of tobacco carts in a primary flue-cured tobacco yard, characterized in that, include: Collect historical data on the entry and exit of primary flue-cured tobacco in the warehouse, and train and optimize the storage space demand prediction model based on the historical data to obtain the storage space demand prediction results. An ant colony search algorithm is used to classify the storage locations in the storage yard based on the location and destination of the initial flue-cured tobacco raw materials and the distance between storage locations, and a storage location allocation model is established to obtain the storage location allocation results. The method employs an ant colony search algorithm to classify storage locations in the yard based on the location and destination of the initial flue-cured tobacco raw materials and the distance between storage locations, establishing a storage location allocation model to obtain the storage location allocation results. Based on the current demand forecast for cargo space, the method for calculating the probability of each path selection using the ant colony search algorithm is as follows: ； Where i and j represent the storage of the initial flue-cured tobacco raw materials and the next destination, respectively, k represents the selection of different paths, the pheromone factor α reflects the relative importance of the amount of pheromone accumulated on the path during the ant movement in guiding the ant colony search; the heuristic function factor β reflects the relative importance of heuristic information in guiding the ant colony search. Based on the optimized and unoptimized cargo collection distances, the cargo collection distance reduction ratio is calculated as follows: ； Among them, S ij Indicates the distance from one storage location to another; A nm This represents the raw material requirement for each stack, X represents the number of cross-regions per unit quantity of each raw material before optimization, Y represents the number of regions after optimization, and P represents the SLP-GA layout planning method. Construct a storage location allocation model to assign corresponding raw materials to each storage location in the storage yard; Based on the predicted demand and allocation results for storage locations, a storage location route selection model is established to achieve optimal route selection for vehicle entry and exit.

2. The method according to claim 1, characterized in that, The specific method for collecting historical data on the entry and exit of primary flue-cured tobacco from the storage yard, and training and optimizing the storage space demand prediction model based on this historical data to obtain the storage space demand prediction results is as follows: The collected historical data on the entry and exit of flue-cured tobacco in the warehouse were divided into training set and test set; The recurrent neural network (RNN) model is trained using a training set to capture the time dependencies in the sequence data of the training set. Based on the time dependencies, the demand for cargo space is predicted to obtain an initial model for predicting cargo space demand. The prediction accuracy of the initial warehouse demand prediction model is tested using a test set. The model parameters are optimized based on the test results. When the prediction accuracy of the model is greater than a preset threshold, the final warehouse demand prediction model is output. The current warehouse demand prediction result is obtained through the warehouse demand prediction model.

3. The method according to claim 1, characterized in that, The specific method for establishing a storage location route selection model based on the storage location demand forecast and storage location allocation results to achieve optimal route selection for vehicle entry and exit is as follows: Based on the number of collection points, DBSCAN cluster analysis is used to classify the collection points and generate initial routes; The initial path is deconstructed using destruction, repair, and insertion operators, and a better neighborhood is selected through an adaptive algorithm. After multiple iterations, the optimal path is obtained.

4. The method according to claim 2, characterized in that, When the model's prediction accuracy is ≥85%, the final cargo space demand prediction model is output.

5. The method according to claim 1, characterized in that, The allocation of raw materials to each storage location in the warehouse includes: Determine the raw material storage area in the warehouse based on the raw material's place of origin; The corresponding storage locations are allocated according to the different varieties and parts of the raw materials from the corresponding production areas within different regions.

6. The method according to claim 3, characterized in that, The method specifically includes: The DBSCAN algorithm is used to cluster cargo locations; The initial path is generated based on the grouping of cargo locations after clustering. The initial T value and number of iterations in the TA criterion are set, and the operator scores and weights are reset. A new path S* is generated by selecting a set of destruction and repair operators using a roulette wheel method. The Metropolis acceptance criterion is adopted, which means that the new path S* is first compared with the current path S. If the new path S* is better than the current path S, the current path S is updated. Then, it is further compared with the optimal path Sbest. If it is better than the optimal path Sbest, the optimal path Sbest is updated; otherwise, it remains unchanged. When the new path S* is greater than the current path S, but the difference is less than the initial T value, the path is also accepted to avoid getting trapped in local optima. The T value gradually decreases at a certain rate. Adjust the operator score based on the path update and update the corresponding weights; Continue using the roulette wheel method to select a set of destruction and repair operators, repeat the above steps until the number of iterations is reached, and obtain the final optimal path Sbest.

7. A system for guiding the entry and exit of tobacco carts in a primary flue-cured tobacco yard, characterized in that, include: Storage space demand forecasting module: used to collect historical data on the entry and exit of primary flue-cured tobacco in the storage yard, train and optimize the storage space demand forecasting model based on the historical data on the entry and exit of primary flue-cured tobacco in the storage yard, and obtain the storage space demand forecasting results; The storage location allocation module is used to classify the storage locations in the storage yard based on the location and destination of the raw materials for initial flue-cured tobacco and the distance between storage locations using an ant colony search algorithm, establish a storage location allocation model, and obtain the storage location allocation results. The method employs an ant colony search algorithm to classify storage locations in the yard based on the location and destination of the initial flue-cured tobacco raw materials and the distance between storage locations, establishing a storage location allocation model to obtain the storage location allocation results. Based on the current demand forecast for cargo space, the method for calculating the probability of each path selection using the ant colony search algorithm is as follows: ； Where i and j represent the storage of the initial flue-cured tobacco raw materials and the next destination, respectively, k represents the selection of different paths, the pheromone factor α reflects the relative importance of the amount of pheromone accumulated on the path during the ant movement in guiding the ant colony search; the heuristic function factor β reflects the relative importance of heuristic information in guiding the ant colony search. Based on the optimized and unoptimized cargo collection distances, the cargo collection distance reduction ratio is calculated as follows: ； Among them, S ij Indicates the distance from one storage location to another; A nm This represents the raw material requirement for each stack, X represents the number of cross-regions per unit quantity of each raw material before optimization, Y represents the number of regions after optimization, and P represents the SLP-GA layout planning method. Construct a storage location allocation model to assign corresponding raw materials to each storage location in the storage yard; Route selection module: used to establish a cargo location route selection model based on the cargo location demand forecast results and cargo location allocation results, so as to realize the optimal route selection for vehicle entry and exit from the warehouse.

8. An electronic device, characterized in that, include: processor; as well as, A memory configured to store computer-executable instructions, which, when executed, cause the processor to implement the steps of the method for guiding the entry and exit of tobacco carts at the initial curing tobacco yard as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, Used to store computer-executable instructions, which, when executed, implement the steps of the method for guiding the entry and exit of tobacco carts in a primary tobacco storage yard as described in any one of claims 1 to 6.

Images