Fodder storage dynamic decision-making method and system based on comprehensive storage system cooperation

Abstract

The invention relates to the technical field of feed storage management, in particular to a feed storage dynamic decision-making method and system based on comprehensive storage system collaboration, and the method comprises the steps: obtaining the storage bin attribute data of a feed storage center, the feed supply time sequence data of suppliers, and the breeding cycle data, and carrying out the preprocessing; predicting feed demand fluctuation based on the breeding cycle data, and generating an initial decision scheme including a plurality of feed plan storage moments in combination with feed storage capacity constraints; dynamically adjusting the planned storage moment through compatibility verification and a preset cooperation mechanism based on feed supply time sequence data; and constructing a decision-making model taking the decision-making comprehensive cost minimization as a target, and solving an optimal decision-making scheme of the feed storage center in combination with a preset constraint condition. The objective of the invention is to realize dynamic decision management of multiple types of feeds in a large-scale feed storage center and improve the decision efficiency and accuracy of multiple types of feed storage in the large-scale feed storage center.

Description

Technical Field

[0001] The present invention relates to the technical field of feed warehousing management, and specifically relates to a dynamic decision-making method and system for feed warehousing based on the collaboration of an integrated warehousing system. Background Art

[0002] In the field of feed warehousing management, as a core node of the supply chain, large warehousing centers usually also serve as the core hub connecting suppliers and breeding enterprises. With the development of the livestock industry towards large-scale and intensive operations, feed categories show a highly segmented trend. Different types of feeds have significant differences in shelf life, temperature and humidity sensitivity, physical properties, etc., resulting in the difficulty of the traditional static rule-based warehousing decision-making mode to meet the dynamic and diversified management requirements.

[0003] Currently, the warehousing decision-making methods commonly used in the industry mainly rely on the intelligent decision-making based on a single warehousing capacity index and manual experience judgment to determine the storage locations and quantities of various feeds. Since this method fails to fully consider the actual needs of multiple parties such as warehousing centers, feed suppliers, and breeding enterprises, such as the real-time changes in the warehousing capacity of the warehousing center, the supply changes of the supply side, and the demand changes of the breeding side, the decisions of the warehousing center, suppliers, and breeding enterprises are isolated from each other, and it is difficult to achieve coordinated adjustment. Eventually, the decision-making efficiency of large feed warehousing centers is low and the scheduling accuracy is insufficient, restricting the dynamic management requirements of large feed warehousing centers for multi-category feeds. Summary of the Invention

[0004] In order to achieve the dynamic decision-making management of multi-category feeds in large feed warehousing centers and improve the decision-making efficiency and accuracy of multi-category feed warehousing in large feed warehousing centers, the present invention provides a dynamic decision-making method and system for feed warehousing based on the collaboration of an integrated warehousing system. The specific technical solutions adopted are as follows: The technical solution of the first aspect of the present invention provides a dynamic decision-making method for feed warehousing based on the collaboration of an integrated warehousing system. The method includes: Obtain the storage bin attribute data of the feed warehousing center, the feed supply time series data of the supplier, and the breeding cycle data, and perform preprocessing; Predict the feed demand fluctuations based on the breeding cycle data, and generate an initial decision-making plan including multiple feed planned storage times in combination with the feed warehousing capacity constraint; Based on the feed supply time series data, dynamically adjust the planned storage time through compatibility verification and a preset collaboration mechanism; Construct a decision-making model with the goal of minimizing the comprehensive decision-making cost, and solve the optimal decision-making plan for the feed warehousing center in combination with the preset constraint conditions.

[0005] Further, predicting the feed demand fluctuations based on the breeding cycle data includes: Based on the preprocessed breeding cycle data, extract the time series of the actual demand for various feeds within at least two complete livestock farming cycles; Adjust the periodic attenuation factor according to the fluctuation intensity of the actual demand time series, and set the benchmark demand offset according to the global mean of the actual demand time series; Assign weight coefficients to multiple periodic fluctuation components according to the historical influence ratio, and calculate the fluctuation values of each component decaying over time based on the adjusted periodic attenuation factor; Superimpose the fluctuation components and sum them with the benchmark offset to generate a demand prediction curve, and extract the predicted feed demand at each time point from the demand prediction curve according to the preset time granularity.

[0006] Furthermore, generate an initial decision-making scheme including multiple feed planned storage times in combination with the feed storage capacity constraint, including: Divide the decision-making cycle into continuous time windows based on the proportional relationship between the predicted demand and the total storage capacity; Dynamically adjust the length of the time window according to the shortest shelf life requirement of the feed category; Generate a set of planned storage times according to the central moment of the time window.

[0007] Furthermore, the compatibility check includes: Locate the moment point closest to the supplier's supply time in the set of planned storage times; Calculate the absolute time deviation between the supply time and the located time, and check whether the current remaining storage capacity supports the supply quantity; If the check passes, replace the supply time with the planned storage time; if the check fails, trigger a preset coordination mechanism.

[0008] Furthermore, the preset coordination mechanism includes: Dynamically calculate the supply quantity range of the feed storage center, including the lower limit value of the received quantity and the upper limit value of the received quantity; Generate a coordination request for the adjustable range of the time window and the supply quantity range according to the supply quantity range, and send it to the supplier; Update the supply time series data according to the adjustment response of the supplier.

[0009] Furthermore, based on the feed supply time series data, dynamically adjust the planned storage time through the compatibility check and the preset coordination mechanism, and also include: Calculate the storage priority based on the ratio of the remaining shelf life duration, the demand urgency decay index, and the storage critical state, and dynamically allocate the storage time period and storage bin resources for the conflicting batches according to the storage priority.

[0010] Furthermore, construct a decision-making model with the goal of minimizing the comprehensive decision-making cost, including: Define three-dimensional decision variables, including feed categories, storage times, and silo allocation relationships; Calculate the storage delay cost based on the delay duration and the unit time cost coefficient; Calculate the supply deviation cost based on the linear function of the absolute deviation between the storage time and the supply time; Calculate the feed loss cost based on the temperature response function of the Arrhenius equation.

[0011] Furthermore, the mathematical expression of the objective function of the decision-making model with the goal of minimizing the comprehensive decision-making cost is:

[0012] In the formula, indicates whether the feed of category is allocated to silo at the th target storage time; indicates the storage delay cost coefficient; indicates the supply deviation cost coefficient; indicates the feed loss cost coefficient; indicates the original planned storage time of the feed; indicates the feed supply time of the supplier; indicates the temperature of under the feed loss rate.

[0013] Furthermore, the preset constraint conditions include: Silo capacity constraint, configured such that the total amount of feed stored in a single silo does not exceed its capacity; Time mutual exclusion constraint, configured such that a single silo stores only one type of feed at the same target storage time; Compatibility constraint, configured such that the feed can only be allocated to silos that support its type; Demand satisfaction constraint, configured such that the total amount of feed allocated for each category is equal to the predicted demand; Supply window constraint, configured such that the feed storage time is not earlier than the supply start time.

[0014] The technical solution of the second aspect of the present invention provides a feed storage dynamic decision-making system based on the coordination of an integrated storage system, which adopts the feed storage dynamic decision-making method based on the coordination of an integrated storage system described in the technical solution of the first aspect of the present invention. The system includes: Data acquisition and preprocessing module, configured to acquire the silo attribute data of the feed storage center, the feed supply time series data of the supplier, and the breeding cycle data, and perform preprocessing; An initial decision-making module, configured to predict feed demand fluctuations based on the breeding cycle data, and generate an initial decision-making plan including multiple feed planned storage times in combination with feed storage capacity constraints; A feed storage time adjustment module, configured to dynamically adjust the planned storage time based on feed supply time series data through compatibility verification and a preset coordination mechanism; A decision-making module, configured to construct a decision-making model with the goal of minimizing the comprehensive decision-making cost, and solve the optimal decision-making plan for the feed storage center in combination with preset constraint conditions.

[0015] The present invention has the following beneficial effects: The feed storage dynamic decision-making method based on the coordination of the integrated storage system provided by the present invention preprocesses by obtaining silo attributes, supply time series, and breeding cycle data, predicts demand fluctuations based on the breeding cycle to generate an initial planned storage time plan in combination with storage capacity, and then dynamically adjusts the planned storage time according to the supply time series data through compatibility verification and a coordination mechanism. Finally, a decision-making model with the goal of minimizing the comprehensive cost is constructed and the optimal plan is solved in combination with constraint conditions; realizing the collaborative decision-making of the three parties of the storage center, the supplier, and the breeding enterprise, coordinating the storage time and location allocation of multiple types of feed, improving the storage decision-making efficiency, and at the same time optimizing the feed resource utilization rate by minimizing the decision-making cost and matching the supply and storage capabilities. Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative work.

[0017] Figure 1 It is a method flow chart of the feed storage dynamic decision-making method based on the coordination of the integrated storage system provided by an embodiment of the present invention; Figure 2 It is a structural schematic diagram of the feed storage dynamic decision-making system based on the coordination of the integrated storage system provided by an embodiment of the present invention. Detailed Embodiments

[0018] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, with reference to the accompanying drawings and preferred embodiments, a feed storage dynamic decision-making method and system based on the coordination of an integrated storage system, including its specific implementation manner, structure, features, and effects. In the following description, different "embodiments" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0020] The following specifically describes the specific solution of a feed storage dynamic decision-making method and system based on the coordination of an integrated storage system provided by the present invention with reference to the accompanying drawings.

[0021] Taking a large feed storage center as an example, the present invention is configured with several feed storage bins for storing different types of feed; the goal is to achieve dynamic decision-making management of multiple types of feed in the large feed storage center and collaborative decision-making among the large feed storage center, suppliers, and breeding enterprises; improve the efficiency and accuracy of feed storage decision-making in the large feed storage center; finally, input data such as the planned storage time of feed, the supply time of suppliers, the feed demand, and the storage capacity into the decision optimization model, and combine the above preset constraints, and use tools such as a mixed integer programming solver to solve, to obtain the dynamic decision-making results of multiple types of feed in the large feed storage center under the condition of meeting the actual situation and the lowest comprehensive cost of storage decision-making.

[0022] Please refer to Figure 1 , which shows the method flow chart of a feed storage dynamic decision-making method based on the coordination of an integrated storage system provided by an embodiment of the present invention. The method includes: Step S100: Obtain the storage bin attribute data of the feed storage center, the feed supply time series data of the supplier, and the breeding cycle data, and perform preprocessing; Step S100 specifically includes: Step S110: Obtain the storage bin-related data, feed supply data, and feed breeding data of the feed storage center; define the storage bin set as , is the total number of storage bins; the storage bin-related data includes the storage bin capacity , indicating the maximum capacity of storage bin , with the unit of ton; the storage bin coordinate , indicating the planar coordinate position of storage bin , and the storage bin compatible feed type vector , indicating storage bin It can store feeds of the category , and is a set of feed categories; meanwhile, temperature data of each storage bin is collected; the feed supply data includes the feed supply time , indicating the time when the feed provided by the supplier arrives at the feed storage center, and the feed supply quantity provided by the supplier ; the breeding data includes the livestock breeding cycle data of the breeding enterprise, which is used to predict the feed demand fluctuation of the breeding enterprise; Step S120: Perform spatio-temporal alignment preprocessing on the storage bin related data, feed supply data, and feed breeding data; the spatio-temporal alignment preprocessing includes unified processing of the spatio-temporal dimensions of the storage bin related data, feed supply data, and breeding data; for the time dimension, the timestamps of data from different sources are calibrated to a unified time coordinate system to ensure the consistency of the supply time, breeding cycle time points, and storage bin status time records; for the space dimension, the storage bin coordinate data is matched with the feed storage location requirements, and at the same time, combined with the feed supply source and the geographical location of the breeding enterprise, a spatial association matrix is constructed.

[0023] Step S200: Predict the feed demand fluctuation based on the breeding cycle data, and generate an initial decision plan including multiple feed planned storage times in combination with the feed storage capacity constraint; Step S200 specifically includes: Step S210: Based on the preprocessed breeding cycle data, extract the actual demand quantity time series of various feeds in at least two complete livestock breeding cycles; the actual demand quantity time series can be expressed as , indicating the actual demand quantity of the feed , represents the historical time point; Step S211: Adjust the periodic attenuation factor according to the fluctuation intensity of the actual demand quantity time series, and set the benchmark demand offset according to the global mean of the actual demand quantity time series; specifically, calculate the variance of the demand quantity time series to characterize the fluctuation intensity, , the greater the variance, the faster its attenuation; the benchmark demand offset can be expressed as:

[0024] In the formula, is the benchmark demand offset; is the total number of time points; Step S212: Allocate weight coefficients to multiple periodic fluctuation components according to the historical influence ratio, and calculate the fluctuation values of each component decaying with time based on the adjusted periodic attenuation factor; specifically, decompose the historical demand quantity time series through the EM algorithm to obtain A Gaussian component, and the historical average proportion of each component is its contribution coefficient to the demand for the category of feed , reflecting the influence weight of this periodic fluctuation component in the historical demand; for each Gaussian component, its central moment corresponds to a key time point in the livestock farming cycle, such as the conversion point of the livestock growth stage. Using the adjusted decay factor , calculate the fluctuation value of this component. The predicted demand can finally be expressed as:

[0025] In the formula, represents the predicted demand for feed at time ; represents the th Gaussian component's contribution coefficient to the demand for the category of feed; represents the decay factor of the demand fluctuation of the feed of category , controlling the width of the Gaussian function; represents the central moment of the kth Gaussian component, corresponding to a key time point in the livestock farming cycle; represents the number of Gaussian components, which can be determined according to the complexity of the livestock farming cycle; Step S213: Superimpose the fluctuation components and sum them with the reference offset to generate a demand prediction curve, and extract the predicted feed demand at each time point from the demand prediction curve according to the preset time granularity; in this embodiment, by extracting the actual demand time series of at least two complete livestock farming cycles, adjusting the decay factor based on the fluctuation intensity, setting the reference offset by the global mean, allocating the Gaussian component weights according to the historical influence proportion and calculating the fluctuation value, and finally superimposing to generate a demand prediction curve, the dynamic modeling of the demand fluctuations of multiple categories of feed is realized. Through this method, the periodic change law of demand in the breeding cycle can be accurately captured. Combining with the initial planned storage time scheme generated by the storage capacity constraint, it not only considers the dynamic fluctuation characteristics of feed demand but also meets the storage space limit conditions, thus ensuring that the initial decision-making scheme can fit the real demand fluctuations of breeding enterprises and improving the foresight and rationality of storage decisions.

[0026] Step S220: Divide the decision-making cycle into continuous time windows based on the proportional relationship between the predicted demand and the total storage capacity; determine the length of each time window , ensuring that the total amount of feed stored within this window does not exceed the total capacity of the storage center. The storage capacity constraint can be expressed as:

[0027] This formula is used to constrain within the window Within, the total feed demand is less than or equal to the total effective storage capacity; Denotes the storage bin The maximum capacity of; Step S221: Dynamically adjust the time window length according to the shortest shelf life requirement of the feed category; Specifically, the shortest shelf life of the feed category can be expressed as , that is, the feed The shortest shelf life of; If , then shrink the window; Step S222: Generate a set of planned storage times according to the central time of the time window; For each time window, select the central time as the planned storage time to form a set of planned storage times, which can be expressed as: , Is the number of planned storage times; In this embodiment, by dynamically calculating the time window length Ensure that the total demand integral within the window does not exceed the effective storage capacity, shrink the window according to the shortest shelf life constraint to avoid feed expiration, and finally construct a set of planned storage times based on the central time of the window, realizing a feasible initial decision-making scheme under the dual constraints of storage capacity and shelf life.

[0028] Step S300: Dynamically adjust the planned storage time based on the feed supply timing data through compatibility verification and a preset coordination mechanism; Step S300 specifically includes: Step S310: Locate the time point closest to the supplier's supply time in the set of planned storage times; Step S320: Calculate the absolute time deviation between the supply time and the located time, and verify whether the current remaining storage capacity supports the supply quantity; Calculate the supplier's supply time And the planned storage time The time difference, and find the planned storage time with the smallest time difference, which can be expressed as:

[0029] In the formula, Represents the planned storage time with the smallest absolute time difference from ; If the time difference , Is the time window threshold, with a value of , then it is considered that the supply time is within the time window of the planned storage time; The storage capacity verification includes calculating the available capacity of each storage bin at the supply time; If the supply time is within the time window and the storage capacity allows, directly adopt the supply time As the target storage time; otherwise, trigger the collaboration mechanism and feedback an adjustment request to the supplier, including: the adjustment range of the supply time: ; the adjustment interval of the supply quantity: , ; Step S330: If the verification passes, replace the supply time with the planned storage time; if the verification fails, trigger the preset collaboration mechanism; among them, the preset collaboration mechanism includes: dynamically calculating the supply quantity interval of the feed storage center , including the lower limit value of the receiving quantity and the upper limit value of the receiving quantity; generating an adjustable range of the time window and a collaboration request for the supply quantity interval, and sending them to the supplier; then update the supply timing data according to the adjustment response of the supplier; if the supplier's response processing is to agree to the adjustment, update the supply plan, and then return to step S310 for re-verification; if the supplier cannot adjust, initiate emergency procurement, and include the supply time of the new supplier in the data set of step S100 for re-processing.

[0030] Among them, when the warehouse is overloaded due to multi-batch conflicts, step S300 further includes: Step S340: Calculate the storage priority based on the remaining shelf life ratio, the demand urgency decay index, and the warehouse critical state, and dynamically allocate the storage time period and warehouse resources for the conflicting batches according to the storage priority; in this embodiment, if the supply times are concentrated and cause the warehouse to be overloaded, the storage time period is dynamically allocated according to the feed priority; the priority calculation can be expressed as:

[0031] In the formula, represents the storage priority of the feed of category ; , , are weight coefficients, corresponding to the importance of the shelf life, demand urgency, and warehouse critical state respectively; represents the shelf life of the feed of category ; represents the currently stored time; Category of the feed's effective use period, indicating the maximum allowable storage duration from production to the start of deterioration; represents the warehouse critical state indicator function, which takes the value of 1 when the warehouse capacity is close to the upper limit, otherwise 0; is the remaining ratio of the shelf life, and the larger its value, the higher the priority; is the demand urgency, and the urgency index decays as the storage time increases; is the warehouse capacity critical state, and the priority is forced to be increased when full; According to Sort in descending order, and preferentially allocate storage time periods and silo resources to high-priority feeds to ensure that feeds with short shelf lives, urgent demands, or critical storage capacities are stored first; In summary, in this embodiment, the dual verification of the time window threshold and the storage capacity is used to quickly adapt to the supply time. For those who fail the verification, a collaborative mechanism is triggered to dynamically generate an acceptable supply quantity range and a time adjustment window, and the plan is flexibly updated in combination with the supplier's response; for multi-batch conflicts, resources are allocated based on the priority model, which improves the supply deviation absorption ability and the emergency efficiency of warehouse overloading, ensures that high-priority feeds obtain storage guarantees, solves the resource allocation problem during multi-batch conflicts, and realizes the dynamic robust optimization of tripartite collaboration.

[0032] Step S400: Construct a decision-making model with the goal of minimizing the comprehensive decision-making cost, and solve the optimal decision-making plan for the feed storage center in combination with the preset constraint conditions; Step S400 specifically includes: Step S410: Define three-dimensional decision variables, including feed category, storage time, and silo allocation relationship; Define three-dimensional decision variables , indicating whether the feed of tonnage category is allocated to silo at the th target storage time; , is the set of adjusted planned storage times; Through this variable, the silo allocation relationship of each type of feed at different times can be accurately described, avoiding storage conflicts; In this embodiment, the comprehensive cost includes: calculating the storage delay cost according to the delay duration and the unit time cost coefficient; calculating the supply deviation cost according to the linear function of the absolute deviation between the storage time and the supply time; calculating the feed loss cost according to the temperature response function of the Arrhenius equation; The mathematical expression of the objective function of the decision-making model with the goal of minimizing the comprehensive decision-making cost is:

[0033] In the formula, indicates whether the feed of tonnage category is allocated to silo at the th target storage time; represents the storage delay cost coefficient, which is used to measure the unit cost of the feed storage time being later than the planned time; represents the supply deviation cost coefficient, which is used to measure the unit cost of the deviation between the target storage time and the supplier's supply time; represents the feed loss cost coefficient, which is used to measure the unit cost of the characteristic loss of the feed during storage; Indicates the originally planned storage time of the feed, and cost is incurred only when the actual storage time is later than ; Indicates the supply time of the supplier of the feed ; Indicates the feed loss rate at a temperature of , which can be calculated based on the Arrhenius equation; The preset constraint conditions include: Warehouse capacity constraint, configured such that the total amount of feed stored in a single warehouse does not exceed its capacity, which can be expressed as:

[0034] In the formula, represents any warehouse; Time mutual exclusion constraint, configured such that a single warehouse stores only one type of feed at the same target storage time, which can be expressed as:

[0035] Compatibility constraint, configured such that the feed can only be allocated to a warehouse that supports its type, which can be expressed as:

[0036] In the formula, represents whether the warehouse supports the feed ; Demand satisfaction constraint, configured such that the total amount of each type of feed allocated is equal to the predicted demand, which can be expressed as:

[0037] Supply window constraint, configured such that the feed storage time is not earlier than the start time of supply, which can be expressed as:

[0038] In the formula, is the starting moment of the supply window promised by the supplier; based on the above constraints, a mixed-integer programming solver is used to solve the above integer programming model, and an optimization algorithm is used to search for the combination of decision variable values that satisfy all constraints to minimize the objective function value; the optimal decision plan is presented in the form of a set of five-tuples, including feed category, original planned moment, adjusted moment, allocated storage bin, and adjustment reason, along with the supply moment deviation, details of the delay cost and loss cost for each feed category, and a heat map of the storage bin utilization rate, providing a visual decision-making basis for warehouse management. In this embodiment, the distribution relationship among feed, moment, and storage bin is accurately depicted by defining three-dimensional decision variables, a comprehensive optimization objective function including storage delay cost, supply deviation cost, and feed loss cost is constructed, and combined with multiple constraints such as storage bin capacity and time mutual exclusion, a mixed-integer programming solver is used to obtain the optimal decision plan, realizing the cost optimization and precise resource scheduling of feed warehouse decision-making. The delay loss, time deviation between supply and storage, and the impact of temperature on feed loss are quantified in the objective function respectively; this step transforms the warehouse decision-making into a quantifiable optimization problem through mathematical modeling, and the final output five-tuple plan decision result not only minimizes the comprehensive decision-making cost, but also ensures the efficient utilization of storage bin resources, and at the same time provides data support for the tripartite collaboration among the warehouse center, supplier, and breeding enterprise, significantly improving the scientificity and accuracy of multi-category feed warehouse decision-making.

[0039] In summary, the dynamic decision-making method for feed warehouse based on the collaboration of the comprehensive warehouse system predicts the feed demand fluctuation based on the breeding cycle data and generates an initial decision plan in combination with the warehouse capacity, which can prospectively match the needs of the breeding enterprise with the warehouse capacity and avoid storage chaos caused by unclear demand. Furthermore, through compatibility verification and a preset collaboration mechanism, the planned storage moment is dynamically adjusted, realizing the two-way interaction between the warehouse center and the supplier, effectively solving the deviation problem between the supply moment and the planned storage moment, and enhancing the adaptability of the warehouse system to dynamic supply. Finally, by constructing a decision-making model with the goal of minimizing the comprehensive decision-making cost and combining the preset constraints to solve the optimal plan, the allocation and utilization of feed resources are optimized from the cost perspective, and at the same time, various constraints ensure the feasibility and rationality of the decision plan. This method realizes the collaborative decision-making among the warehouse center, supplier, and breeding enterprise. In the process of coordinating the storage time and location allocation of multi-category feed, it not only improves the efficiency of warehouse decision-making, but also matches the supply with the warehouse capacity through cost optimization and reasonable resource allocation, meeting the needs of dynamic management of multi-category feed in large feed warehouse centers.

[0040] Please refer to Figure 2 , which shows a schematic structural diagram of a dynamic decision-making system for feed warehouse based on the collaboration of the comprehensive warehouse system provided by an embodiment of the present invention. The system includes: A data acquisition and preprocessing module, configured to acquire the storage bin attribute data of the feed storage center, the feed supply time series data of the supplier, and the breeding cycle data, and perform preprocessing; An initial decision-making module, configured to predict the feed demand fluctuation based on the breeding cycle data, and generate an initial decision-making scheme including multiple feed planned storage times in combination with the feed storage capacity constraint; A feed storage time adjustment module, configured to dynamically adjust the planned storage time based on the feed supply time series data through compatibility verification and a preset coordination mechanism; A decision-making module, configured to construct a decision-making model with the goal of minimizing the comprehensive decision-making cost, and solve the optimal decision-making scheme of the feed storage center in combination with preset constraint conditions.

[0041] It should be noted that: the above sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0042] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other, and the focus of each embodiment is to illustrate the differences from other embodiments.

Claims

1. A dynamic decision-making method for feed warehousing based on the collaboration of an integrated warehousing system, characterized in that, The method includes: Obtaining the storage bin attribute data of the feed storage center, the feed supply time series data of the supplier, and the breeding cycle data, and performing preprocessing; Predicting the feed demand fluctuation based on the breeding cycle data, and generating an initial decision-making scheme including multiple feed planned storage times in combination with the feed storage capacity constraint; Based on the feed supply time series data, dynamically adjusting the planned storage time through compatibility verification and a preset coordination mechanism; Constructing a decision-making model with the goal of minimizing the comprehensive decision-making cost, and solving the optimal decision-making scheme of the feed storage center in combination with the preset constraint conditions.

2. The dynamic decision-making method for feed warehousing based on the collaboration of an integrated warehousing system according to claim 1, wherein, Predicting the feed demand fluctuation based on the breeding cycle data includes: Based on the preprocessed breeding cycle data, extracting the actual demand time series of various feeds in at least two complete livestock breeding cycles; Adjusting the periodic attenuation factor according to the fluctuation intensity of the actual demand time series, and setting the benchmark demand offset according to the global mean of the actual demand time series; Allocating weight coefficients to multiple periodic fluctuation components according to the historical influence ratio, and calculating the fluctuation values of each component decaying with time based on the adjusted periodic attenuation factor; Superposing the fluctuation components and summing them with the benchmark offset to generate a demand prediction curve, and extracting the predicted feed demand at each time point from the demand prediction curve according to the preset time granularity.

3. The dynamic decision-making method for feed warehousing based on the collaboration of an integrated warehousing system according to claim 2, wherein Generating an initial decision-making scheme including multiple feed planned storage times in combination with the feed storage capacity constraint includes: Dividing the decision-making cycle into continuous time windows based on the relationship between the predicted demand and the total storage capacity ratio; Dynamically adjusting the time window length according to the shortest shelf life requirement of the feed category; Generating a set of planned storage times according to the central moment of the time window.

4. The dynamic decision-making method for feed warehousing based on the collaboration of an integrated warehousing system according to claim 1, wherein The compatibility verification includes: Locating the moment point closest to the supplier's supply moment in the set of planned storage times; Calculating the absolute time deviation between the supply moment and the located moment, and verifying whether the current remaining storage capacity supports the supply quantity; If the verification passes, replacing the supply moment with the planned storage moment, and if the verification fails, triggering the preset coordination mechanism.

5. The dynamic decision-making method for feed warehousing based on the collaboration of an integrated warehousing system according to claim 4, characterized in that The preset coordination mechanism includes: Dynamically calculating the supply quantity range of the feed storage center, including the lower limit value of the received quantity and the upper limit value of the received quantity; Generating a coordination request for the adjustable range of the time window and the supply quantity range according to the supply quantity range, and sending it to the supplier; Updating the supply time series data according to the adjustment response of the supplier.

6. The dynamic decision-making method for feed warehousing based on the collaboration of an integrated warehousing system as claimed in claim 5, wherein Based on the feed supply time series data, dynamically adjusting the planned storage time through compatibility verification and a preset coordination mechanism further includes: Calculating the storage priority based on the ratio of the remaining shelf life duration, the demand urgency decay index, and the storage critical state, and dynamically allocating the storage time period and storage bin resources of the conflict batches according to the storage priority.

7. The dynamic decision-making method for feed warehousing based on the collaboration of an integrated warehousing system according to any one of claims 1 to 6, characterized in that, Constructing a decision-making model with the goal of minimizing the comprehensive decision-making cost includes: Defining three-dimensional decision variables, including feed category, storage time, and storage bin allocation relationship; Calculating the storage delay cost according to the delay duration and the unit time cost coefficient; Calculating the supply deviation cost according to the linear function of the absolute deviation between the storage time and the supply time; Calculating the feed loss cost according to the temperature response function of the Arrhenius equation.

8. The dynamic decision-making method for feed warehousing based on the collaboration of an integrated warehousing system as claimed in claim 7, wherein The mathematical expression of the objective function for constructing a decision-making model with the goal of minimizing the comprehensive decision-making cost is as follows: In the formula, represents whether the feed of tonnage category is allocated to the storage bin at the th target storage moment ; represents the storage delay cost coefficient; represents the supply deviation cost coefficient; represents the feed loss cost coefficient; represents the original planned storage moment of the feed; represents the supply moment of the supplier of the feed represents the feed loss rate at a temperature of ; 9. The dynamic decision-making method for feed warehousing based on the coordination of an integrated warehousing system according to claim 8, wherein The preset constraint conditions include: Bin capacity constraint, configured such that the total amount of feed stored in a single bin does not exceed its capacity; Time mutual exclusion constraint, configured such that a single bin stores only one type of feed at the same target storage time; Compatibility constraint, configured such that feed can only be allocated to bins that support its type; Demand satisfaction constraint, configured such that the total amount of feed allocated for each category is equal to the predicted demand; Supply window constraint, configured such that the feed storage time is not earlier than the start time of supply.

10. A feed storage dynamic decision-making system based on the collaboration of an integrated warehousing system, characterized in that, Adopt the feed storage dynamic decision-making method based on the coordination of the integrated warehousing system according to any one of claims 1 to 9, wherein the system includes: Data acquisition and preprocessing module, configured to acquire the bin attribute data of the feed storage center, the feed supply time series data of the supplier, and the breeding cycle data, and perform preprocessing; Initial decision-making module, configured to predict the feed demand fluctuation based on the breeding cycle data, and generate an initial decision-making plan including multiple feed planned storage times in combination with the feed storage capacity constraint; Feed storage time adjustment module, configured to dynamically adjust the planned storage time based on the feed supply time series data through compatibility verification and a preset coordination mechanism; Decision-making module, configured to construct a decision-making model with the goal of minimizing the comprehensive decision-making cost, and solve the optimal decision-making plan for the feed storage center in combination with the preset constraint conditions.

Images