Incoming-factory logistics optimization method, electronic equipment and storage medium

Abstract

The invention relates to the technical field of logistics, particularly provides an in-factory logistics optimization method, electronic equipment and a storage medium, and aims to solve the technical problem of low management efficiency of a warehouse logistics management system due to the fact that the existing warehouse logistics management system is only suitable for a single delivery frequency and a single delivery source. In order to achieve the purpose, the in-factory logistics optimization method comprises the steps that an initial parameter set is obtained based on historical logistics data, and the initial parameter set comprises target function parameters, simulated annealing algorithm parameters and digital modeling parameters; constructing a composite objective function about the delivery frequency based on the objective function parameters; iterative optimization is carried out on the composite objective function based on simulated annealing algorithm parameters, and an optimal solution of the delivery frequency is obtained; and performing simulation verification on the optimal solution based on the digital modeling parameters so as to evaluate the optimal solution of the delivery frequency. Therefore, unnecessary inventory overstock is reduced, the inventory cost is reduced, and the logistics turnover efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of logistics technology, specifically providing an inbound logistics optimization method, electronic equipment, and storage medium. Background Technology

[0002] In the field of intelligent manufacturing, "logistics management" has become a crucial link supporting the entire production process. Especially under the new economic normal, predicting the optimal delivery frequency in advance based on the supplier's transportation distance using an "algorithm prediction-modeling verification" approach has become an ideal solution. Therefore, in the current era of digital and intelligent innovation and transformation, intelligent logistics and warehousing management has become an important strategic means for the manufacturing industry to improve quality, efficiency, and reduce costs.

[0003] Traditional warehouse logistics management systems often fail to achieve a dynamic balance between the frequency of incoming goods and the area of ​​temporary storage for raw materials within the factory, leading to the accumulation of raw materials within a certain period and affecting the balance of logistics rhythm. Most existing warehouse logistics management systems are designed based on manually selecting the shortest path, which is only suitable for situations with a single delivery frequency and a single source of goods, resulting in low management efficiency. Summary of the Invention

[0004] To overcome the aforementioned shortcomings, this application is proposed to provide a solution, or at least a partial solution, to the technical problem that existing warehouse logistics management systems are only applicable to a single shipping frequency and a single shipping source, resulting in low management efficiency. This application provides an inbound logistics optimization method, electronic equipment, and storage medium.

[0005] In a first aspect, this application provides an inbound logistics optimization method, the method comprising:

[0006] An initial parameter set is obtained based on historical logistics data. The initial parameter set includes objective function parameters, simulated annealing algorithm parameters, and digital modeling parameters.

[0007] Construct a composite objective function about shipping frequency based on the parameters of the objective function;

[0008] The composite objective function is iteratively optimized based on the parameters of the simulated annealing algorithm to obtain the optimal solution for the shipping frequency;

[0009] The optimal solution is simulated and verified based on the digital modeling parameters to evaluate the optimal solution for the shipping frequency.

[0010] In one embodiment of the inbound logistics optimization method of this application, the simulated annealing algorithm parameters include an initial solution, an initial temperature, and a maximum number of iterations; the iterative optimization of the objective function based on the simulated annealing algorithm parameters includes:

[0011] The initial solution is randomly perturbed to generate candidate solutions;

[0012] The objective function difference is determined based on the candidate solution and the initial solution;

[0013] Whether to accept the candidate solution is determined based on the difference in the objective function.

[0014] After accepting the candidate solution, the initial temperature is updated;

[0015] When the maximum number of iterations is reached, the optimal solution is output.

[0016] In one embodiment of the inbound logistics optimization method of this application, the initial solution is randomly perturbed, including: using a neighborhood search strategy to randomly perturb the current solution with a shipping frequency adjustment amount to generate the candidate solution, wherein the value range of the shipping frequency adjustment amount is a preset multiple of the standard deviation of historical shipping frequencies.

[0017] In one embodiment of the inbound logistics optimization method of this application, determining whether to accept the candidate solution based on the objective function difference includes:

[0018] Determine whether the difference in the objective function is less than or equal to zero;

[0019] If so, then the candidate solution is accepted directly;

[0020] Otherwise, calculate the acceptance probability of the candidate solution and generate a random number;

[0021] Whether to accept the candidate solution is determined based on the difference between the acceptance probability and the random number.

[0022] In one embodiment of the inbound logistics optimization method of this application, determining whether to accept the candidate solution based on the difference between the acceptance probability and the random number includes:

[0023] Determine whether the difference between the acceptance probability and the random number is greater than zero;

[0024] If so, then accept the candidate solution;

[0025] Otherwise, retain the current solution.

[0026] In one embodiment of the inbound logistics optimization method of this application, updating the initial temperature includes:

[0027] The cooling index is obtained based on the current iteration number;

[0028] The initial temperature is updated based on the product of the cooling index and the initial temperature.

[0029] In one embodiment of the inbound logistics optimization method of this application, an initial solution is obtained based on historical logistics data, including:

[0030] The historical average frequency of shipments for each material is obtained based on the historical logistics data.

[0031] The material vector is obtained based on the historical average shipping frequency of each material.

[0032] The material vector is used as the initial solution.

[0033] In one embodiment of the inbound logistics optimization method of this application, the optimal solution is verified by simulation based on the digital modeling parameters, including:

[0034] A logistics simulation model is constructed based on the digital modeling parameters and the optimal solution;

[0035] The logistics simulation model was used for simulation verification to obtain the actual performance value of the optimal solution.

[0036] The actual performance value of the optimal solution is compared with the simulation baseline value;

[0037] The optimal solution for the stated shipping frequency is evaluated based on the comparison results.

[0038] In a second aspect, an electronic device is provided, comprising:

[0039] At least one processor;

[0040] And, a memory communicatively connected to the at least one processor;

[0041] The memory stores a computer program, which, when executed by the at least one processor, is the aforementioned inbound logistics optimization method.

[0042] In a third aspect, a computer-readable storage medium is provided, wherein a plurality of program codes are stored therein, the program codes being adapted to be loaded and run by a processor to perform the inbound logistics optimization method described in any of the preceding claims.

[0043] The above-described technical solutions of this application have at least one or more of the following features. Beneficial effects:

[0044] The inbound logistics optimization method in this application includes: obtaining an initial parameter set based on historical logistics data, the initial parameter set including objective function parameters, simulated annealing algorithm parameters, and digital modeling parameters; constructing a composite objective function regarding shipping frequency based on the objective function parameters; iteratively optimizing the composite objective function based on the simulated annealing algorithm parameters to obtain the optimal solution for shipping frequency; and performing simulation verification on the optimal solution based on the digital modeling parameters to evaluate the optimal solution for shipping frequency. By analyzing historical logistics data and combining iterative optimization with the simulated annealing algorithm, the optimal shipping frequency scheme can be found, thereby improving the efficiency of the entire logistics process. Constructing and optimizing the composite objective function regarding shipping frequency helps reduce unnecessary inventory backlog, thereby reducing inventory costs. Using digital modeling parameters to perform simulation verification on the obtained optimal solution can evaluate the actual effect of the optimal solution and improve the turnover efficiency of logistics. Attached Figure Description

[0045] The disclosure of this application will become more readily understood with reference to the accompanying drawings. It will be readily understood by those skilled in the art that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this application. Furthermore, similar numbers in the drawings are used to denote similar components, wherein:

[0046] Figure 1 This is a schematic diagram of the main process of the inbound logistics optimization method in one embodiment of this application;

[0047] Figure 2 This is a schematic diagram of simulated annealing algorithm parameters in one embodiment of this application;

[0048] Figure 3 This is a flowchart illustrating the simulated annealing algorithm in one embodiment of this application;

[0049] Figure 4 This is a schematic diagram showing the coordinates corresponding to the location of the supply source in one embodiment of this application;

[0050] Figure 5 This is a schematic diagram of the material handling equipment and single shipment quantity in one embodiment of this application;

[0051] Figure 6 This is a schematic diagram showing the experimental comparison results between the simulated annealing algorithm and the original scheme in one embodiment of this application;

[0052] Figure 7 This is a schematic diagram of the main structure of the inbound logistics optimization device in one embodiment of this application;

[0053] Figure 8 This is a schematic diagram of the structure of an electronic device in one embodiment of this application. Detailed Implementation

[0054] Some embodiments of this application are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of this application and are not intended to limit the scope of protection of this application.

[0055] In the description of this application, "module" and "processor" can include hardware, software, or a combination of both. A module may include hardware circuitry, various suitable sensors, communication ports, and memory.

[0056] It may also include software components, such as program code, or a combination of software and hardware. The processor can be a central processing unit, microprocessor, graphics processor, digital signal processor, or any other suitable processor. The processor has data and / or signal processing capabilities. The processor can be implemented in software, in hardware, or a combination of both. Non-transitory computer-readable storage media includes any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, etc. The term "A and / or B" means all possible combinations of A and B, such as only A, only B, or A and B. The terms "at least one A or B" or "at least one of A and B" have a similar meaning to "A and / or B" and may include only A, only B, or A and B. The singular forms of the terms "a" or "this" may also include plural forms.

[0057] Most traditional warehouse logistics management systems are designed based on manual selection of the shortest path, which is only suitable for situations with a single shipping frequency and a single shipping source, resulting in low management efficiency. Therefore, this application proposes an inbound logistics optimization method, electronic equipment, and storage medium.

[0058] See appendix Figure 1 , Figure 1 This is a schematic diagram of the main process of an inbound logistics optimization method according to an embodiment of this application.

[0059] like Figure 1 As shown, the inbound logistics optimization method in this application embodiment mainly includes the following steps S10-S40.

[0060] Step S10: Obtain an initial parameter set based on historical logistics data. The initial parameter set includes objective function parameters, simulated annealing algorithm parameters, and digital modeling parameters.

[0061] Historical logistics data refers to historical shipping records, warehousing cost data, transportation expense documents, and material inventory change records collected from the enterprise's logistics management system. This includes delivery costs from multiple shipping sources to the factory area, historical shipping frequency, warehouse space utilization, and backflow scheduling costs, which are used to construct the initial parameter set.

[0062] The objective function parameters are cost-related parameters used to construct the objective function, including transportation and warehousing costs, inventory holdings, and shipping frequency and volume.

[0063] Simulated annealing algorithm parameters refer to the parameters used to drive the algorithm iteration, including the initial solution, initial temperature, cooling index, and perturbation factor.

[0064] Digital modeling parameters refer to the physical parameters used for simulation verification, including supplier location coordinates, material production quantity, tooling capacity, unit warehousing cost, etc.

[0065] Step S20: Construct a composite objective function about the shipping frequency based on the objective function parameters.

[0066] A composite objective function is an objective function constructed by combining the effects of multiple factors (such as shipping frequency, inventory area, etc.) and aims to minimize total cost or other optimization indicators.

[0067] Step S30: Iteratively optimize the composite objective function based on the simulated annealing algorithm parameters to obtain the optimal solution for the shipping frequency.

[0068] Step S40: Perform simulation verification on the optimal solution based on the digital modeling parameters to evaluate the optimal solution for the shipping frequency.

[0069] Simulation verification refers to using computer simulation methods to test and evaluate the theoretical optimal solution in real-world scenarios in order to verify its effectiveness and applicability.

[0070] Based on steps S10-S40 above, an initial parameter set is first obtained based on historical logistics data. This initial parameter set includes objective function parameters, simulated annealing algorithm parameters, and digital modeling parameters. A composite objective function regarding shipping frequency is then constructed based on the objective function parameters. The composite objective function is iteratively optimized using the simulated annealing algorithm parameters to obtain the optimal solution for shipping frequency. Finally, the optimal solution is simulated and verified using the digital modeling parameters to evaluate its effectiveness. By analyzing historical logistics data and combining iterative optimization with the simulated annealing algorithm, the optimal shipping frequency scheme can be identified, thereby improving the efficiency of the entire logistics process. Constructing and optimizing the composite objective function regarding shipping frequency helps reduce unnecessary inventory backlog, thus lowering inventory costs. Simulation verification of the obtained optimal solution using the digital modeling parameters evaluates its actual effect and improves logistics turnover efficiency.

[0071] The following provides further explanation of steps S10 to S40.

[0072] Regarding step S10 above, the objective function parameters and digital modeling parameters can be analyzed from historical logistics data using conventional methods in this field, which will not be elaborated here.

[0073] The parameters of the simulated annealing algorithm include the initial solution, initial temperature, and maximum number of iterations. For example, Figure 2 This can serve as an example of the parameters for the simulated annealing algorithm.

[0074] In one embodiment, obtaining an initial solution based on historical logistics data includes: obtaining the historical average shipping frequency of each material based on the historical logistics data; obtaining a material vector based on the historical average shipping frequency of each material; and using the material vector as the initial solution.

[0075] Specifically, the first step is to analyze historical logistics data. For each material, the number of shipments within a specified time period (e.g., the past year) is calculated, and the average value is determined. Then, based on the average shipment frequency for each material, a vector is constructed, where each element represents the shipment frequency for that material. For example, μ = {μ1, μ2, ..., μ...} n} can be used as an example of the material vector, where μ n This represents different types of materials. Finally, the material vector μ = {μ1, μ2, ..., μ...} is defined. n} is used as the initial solution in the parameters of the simulated annealing algorithm.

[0076] For the initial temperature, the above initial solution can be substituted into the objective function to calculate the objective function value. Then, the initial temperature can be set as a preset multiple of the objective function value. The preset multiple can be 15 times, 18 times, 20 times, 30 times, etc. There is no specific limitation. It can be adapted to the actual application scenario.

[0077] The maximum number of iterations can be preset. For example, 150, 180, 200, etc. can be used as examples of the maximum number of iterations.

[0078] The above is a further explanation of step S10. Step S20 will be further explained below.

[0079] Specifically, a composite objective function about the shipping frequency can be constructed based on the parameters of the objective function. The expression of the composite objective function is as follows:

[0080] Where k and γ are the unit storage cost and transportation cost of each type of dispatched material, respectively; c represents the inventory quantity of material i in the temporary storage area on that day; p This is the cost coefficient per unit stacking ratio; μ represents the current global stacking rate. i The planned delivery frequency for the i-th material; Let θ be the quantity of material i shipped each time; j The cost of reverse scheduling of material j due to unforeseen circumstances.

[0081] The above is a further explanation of step S20. Step S30 will be further explained below.

[0082] Specifically, step S30 can be implemented through steps S301 to S305.

[0083] Step S301: Randomly perturb the initial solution to generate candidate solutions.

[0084] In one specific embodiment of this application, the initial solution is randomly perturbed, including: using a neighborhood search strategy to randomly perturb the initial solution with a shipping frequency adjustment amount to generate the candidate solution, wherein the value range of the shipping frequency adjustment amount is a preset multiple of the standard deviation of historical shipping frequencies.

[0085] The neighborhood search strategy refers to generating new solutions (candidate solutions) within the neighborhood of the initial solution. For this scheme, the neighborhood specifically refers to the area adjacent to the current shipping frequency vector μ = {μ1, μ2, ..., μ...}. n A set of close possible solutions, for example, if a material is currently shipped 5 times / month, its neighborhood may include an adjustment range of 4-6 times / month.

[0086] The range of adjustment values ​​for shipment frequency is a preset multiple of the standard deviation of historical shipment frequency. The standard deviation of historical shipment frequency reflects the fluctuation range of the historical shipment frequency of the material (e.g., the standard deviation of the shipment frequency of a certain material in the past 12 months is 1.2 times / month). The preset multiple is usually set to 0.5 (i.e., 50%), which is a reasonable fluctuation threshold based on historical data statistics, ensuring that the adjustment is neither too large (avoiding being unrealistic) nor too small (ensuring search efficiency).

[0087] Specifically, by employing a neighborhood search strategy and randomly perturbing the initial solution using a shipping frequency adjustment, the generated candidate solution can be represented as: x′=x+Δx

[0088] Where x′ is a candidate solution; x is the initial solution; and Δx is the perturbation.

[0089] This strategy avoids wasting resources in meaningless solution spaces by limiting the search range, while ensuring that the new solution is related to the initial solution and conforms to the actual fluctuation pattern of delivery frequency in logistics scenarios.

[0090] Step S302: Determine the difference in the objective function based on the candidate solution and the initial solution.

[0091] Specifically, the difference between the candidate solution and the initial solution is used as the objective function difference.

[0092] Step S303: Determine whether to accept the candidate solution based on the difference in the objective function.

[0093] Step S303 can be achieved through the following steps S3031 to S3034.

[0094] Step S3031: Determine whether the difference in the objective function is less than or equal to zero. If yes, proceed to step S3032; otherwise, proceed to step S3033.

[0095] Step S3032: Directly accept candidate solutions.

[0096] Step S3033: Calculate the acceptance probability of the candidate solution and generate random numbers.

[0097] Specifically, the acceptance probability of a candidate solution can be:

[0098] Where P is the acceptance probability of the candidate solution, ΔS is the difference in the objective function, and T t This is the current temperature.

[0099] The random number can be any random value between [0,1].

[0100] Step S3034: Determine whether to accept the candidate solution based on the difference between the acceptance probability and the random number.

[0101] Step S3034 can be achieved through the following steps S30341 to S30343.

[0102] Step S30341: Determine whether the difference between the acceptance probability and the random number is greater than zero. If yes, proceed to step S30342 below; otherwise, proceed to step S30343 below.

[0103] Step S30342: Accept candidate solutions.

[0104] Step S30343: Retain the current solution.

[0105] Step S304: After accepting candidate solutions, update the initial temperature.

[0106] Step S304 can be achieved through the following steps S3041 to S3042.

[0107] Step S3041: Obtain the cooling index based on the current iteration number.

[0108] Specifically, the cooling index can be obtained through pre-setting, for example, setting it to 0.95 and then gradually increasing it to 0.99 for more refined searching.

[0109] In addition, the cooling index can be obtained based on the current iteration number. For example, when the current iteration number is in [0,30], the cooling index is 0.95; when the current iteration number is in (30,100], the cooling index is 0.98; and when the current iteration number is in (100,150], the cooling index is 0.99.

[0110] Step S3042: Update the initial temperature based on the product of the cooling index and the initial temperature.

[0111] Specifically, the product of the cooling index and the initial temperature can be used as the updated temperature value.

[0112] Step S305: When the maximum number of iterations is reached, output the optimal solution.

[0113] Specifically, repeat the above steps until the maximum number of iterations is reached, at which point the optimal solution is obtained.

[0114] For example, Figure 3 This can serve as a flowchart of a simulated annealing algorithm. Specifically, as follows... Figure 3 As shown, the objective function can be iteratively optimized using the simulated annealing algorithm described below to obtain the optimal solution for the shipping frequency.

[0115] First, the initial solution of the simulated annealing algorithm is represented by the average historical shipping frequency corresponding to each material type in the test set. Then, the shipping frequencies corresponding to different material types are defined as a vector, resulting in: μ = {μ1, μ2, ..., μ} n}

[0116] Next, a neighborhood search strategy is employed to advance the perturbation mechanism. This perturbation mechanism ensures that the simulated annealing algorithm can escape the limitations of local optima, serving as a crucial mechanism for re-searching. After the simulated annealing algorithm determines the current optimal solution for the system, the shipping frequency is adjusted proportionally. A new system solution is then generated: x′=x+Δx

[0117] Where x′ is a candidate solution; x is the current solution; and Δx is the perturbation.

[0118] The decision to accept a new solution is made based on the established acceptance criteria. In the simulated annealing algorithm, each iteration is a... Transformation of a stationary Markov chain. Specifically, in the nth iteration (n∈N), a Markov kernel G(x,dy) is used to generate candidate points yn (random numbers), and the acceptance probability Pn is calculated. If f(y) is then... n )≤f(x n When the stacking ratio is improved, the system chooses to accept the solution, Pn = 1 and xn + 1. At this point, the Monte Carlo criterion (Metropolis) intervenes, allowing the algorithm to escape local optima with a given probability, thus avoiding the disadvantage of convergence too quickly.

[0119] After the system accepts a new solution, the temperature is updated according to the initial cooling exponent α to reduce the system temperature and achieve the purpose of annealing. Meanwhile, the cooling exponent in the simulated annealing algorithm determines the convergence speed during the search. Therefore, this application dynamically sets α = 0.95 initially to allow the simulated annealing algorithm to quickly begin its operation within the search space. After a certain number of iterations, α is increased to allow the simulated annealing algorithm to perform a more refined search within the search space, thus better finding the optimal solution. The current temperature or the initial temperature is updated using Tn+1 = αTn.

[0120] Finally, based on the initial system termination conditions, when the maximum number of iterations reaches the set threshold or the algorithm iteration has no optimization effect (i.e., the system believes that the search strategy has no significant improvement effect), the vector set of all solutions is output to obtain the optimal delivery frequency scheme under the current material category; otherwise, the search returns to find a new solution.

[0121] The above is a further explanation of step S30. Step 40 will be further explained below.

[0122] Specifically, step S40 can be implemented through steps S401 to S404.

[0123] Step S401: Construct a logistics simulation model based on digital modeling parameters and optimal solutions.

[0124] Digital modeling parameters can include supplier coordinates (such as two-dimensional coordinates with the factory area as the origin), material scheduling requirements (such as monthly production plans), tooling capacity (such as a floor area of ​​2 square meters), and unit warehousing cost (20.3 yuan / square meter), etc.

[0125] The optimal solution refers to the shipping frequency vector output by the simulated annealing algorithm. This represents the optimal shipping frequency for each material.

[0126] Specifically, a logistics network model is established, centered on discrete event simulation, encompassing suppliers, transportation routes, temporary storage areas, and production lines. The delivery frequency from the optimal solution is used as an input parameter to drive the flow of materials within the supply chain. For example, the quantity of each delivery is calculated based on the delivery frequency, and converted into occupied area using tooling vehicle capacity; transportation time and costs are calculated based on supplier coordinates and transportation cost parameters; and inventory fluctuations in the temporary storage area are simulated through production scheduling requirements and delivery times.

[0127] Step S402: Use a logistics simulation model to perform simulation verification and obtain the actual performance value of the optimal solution.

[0128] The logistics simulation model constructed using the aforementioned steps is used to obtain the actual performance value of the optimal solution through multiple simulations and average values, specifically including the warehouse area occupancy ratio, total cost, and quality risk.

[0129] Step S403: Compare the actual performance value of the optimal solution with the simulation baseline value.

[0130] Specifically, based on historical logistics data, the existing shipping frequency scheme is run under the same simulation conditions, and key indicators are recorded as simulation baseline values. The actual performance of the optimal solution is then compared with the simulation baseline values. For example, taking total cost as an example, the total cost reduction rate = (original scheme cost - optimized scheme cost) / original scheme cost × 100%.

[0131] Step S404: Evaluate the optimal solution for the shipping frequency based on the comparison results.

[0132] Specifically, the optimal solution for shipping frequency can be evaluated from different dimensions by comparing the results. For example, if the warehouse area occupancy rate drops below 65% and the total cost decreases by more than 15%, the optimization plan is considered effective.

[0133] Next, step S40 will be explained in more detail.

[0134] After obtaining the optimal solution for the system, the logistics situation under this scenario is simulated using digital modeling technology to verify the optimal delivery frequency scheme.

[0135] The aforementioned optimal solution is used as the initial system solution for digital modeling. The digital model parameters are adjusted by combining supplier location coordinates, stacking cost coefficients, and production quantities for different material types. The optimal delivery frequency scheme obtained by the simulated annealing algorithm is verified to be superior to the current delivery scheme in the factory. An initial dataset is constructed during the basic parameter definition phase using the factory's warehouse area division and order demand. In this embodiment, data is collected and preprocessed based on the material types of commercial air conditioners, the average monthly delivery frequency, the average utilization rate of the factory's temporary storage area, and the average monthly production output to build the basic dataset. To ensure that the solution in the optimal scheme can be effectively verified, the threshold for the maximum number of iterations of the simulated annealing algorithm is set to 150, the initial temperature is set to 15 times the objective function value obtained from the initial solution, and the cooling constant is dynamically selected, with iterations performed in three stages.

[0136] Where t represents the number of iterations in the search process.

[0137] In digital modeling, the unit warehousing cost for each material is the same, at 20.3 yuan per square meter. The quantity shipped per transaction is inversely proportional to the frequency of shipments received by the system. Parameters are automatically updated when the system iterates and updates the accepted solutions. Transportation costs are positively correlated with supplier coordinates via Euclidean distance. Therefore, using commercial air conditioners as the center coordinates (0,0), the top 55% of suppliers by order volume are selected as the test set, corresponding to the selected shipping source locations. Figure 4 As shown.

[0138] After initialization and standardization based on initial parameters and supplier coordinates, the system further initializes the warehouse area, production line cycle time, production demand, and stacking costs using actual factory conditions. This verifies whether the simulated annealing algorithm-derived optimal delivery frequency scheme satisfies the correlation between stacking factors and delivery frequency. Specifically, the actual processing time (i.e., production cycle time) is substituted into the digital model to represent the processing time of that process. The maximum capacity of the production line is set based on the line length and roller speed, and the model's personnel shifts are set to day and night shifts. Furthermore, case tests are conducted based on the top 60% of models in the factory's production output. The default material consumption per unit for each model is 1, and based on... Figure 5 The supplier provides the factory with a bill of materials as the initial set of material types. For each machine model, the corresponding unit shipment quantity uses a tooling cart of the same volume as the loading tool (the tooling cart occupies a default floor area of ​​2 square meters), resulting in:

[0139] Among them, v m This refers to the capacity of the simulated tooling vehicle, v iThe capacity of the tooling car for transporting the current i-th material is given by , and the number of tooling cars required to transport the current i-th material is given by , where l represents the number of tooling cars required to transport all types of materials. Based on the above formula, various raw materials with different machine models can be digitally modeled with unified volume dimensions.

[0140] If the optimal solution obtained by the simulated annealing algorithm satisfies the current pain points of raw materials in the manufacturing industry, then according to the principles of the production and sales system, while increasing the frequency of supplier deliveries, it is necessary to ensure that the normal progress of the factory's production sequence is not affected. That is, the supply frequency of material types and the production cycle of their respective machine models should achieve a dynamic balance, ensuring that there are always materials available at the production line without occupying more space in the factory's raw material storage area. Therefore, if the optimal delivery frequency scheme obtained by the simulated annealing algorithm cannot meet the production sequence scheduling, it should be discarded directly.

[0141] Based on the initial construction of model datasets with different site selections for multiple supply sources, six comparative experiments were conducted using the optimal solution obtained through simulated annealing algorithm and the area occupied by the current factory's shipping frequency. Specifically, as follows... Figure 6 As shown. By Figure 6 The comparison results show that the optimal solution obtained by the simulated annealing algorithm (SA algorithm), after verification by digital modeling, can effectively reduce the inventory area occupied by factors such as shipping frequency, raw material warehouse area, material type production quantity, and stacking cost coefficient, and control the warehouse area occupancy ratio between 59.9% and 67.7%. Moreover, since the modeling parameters are initialized by using the simulated annealing algorithm during the digital modeling process, the reliability of the search for the global optimal solution also increases as the disturbance process gradually decreases.

[0142] The manufacturing inbound logistics optimization method based on multi-scale digital modeling proposed in this application can effectively increase the frequency of raw material delivery from multiple suppliers. In manufacturing application scenarios, it removes the limitations of the existing single delivery frequency and delivery frequency from the perspective of inbound logistics, and reduces the accumulation rate of raw materials in the factory.

[0143] It should be noted that although the steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effect of this application, different steps do not necessarily have to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the scope of protection of this application.

[0144] Furthermore, this application also provides an inbound logistics optimization device.

[0145] See appendix Figure 7 , Figure 7 This is a main structural block diagram of an inbound logistics optimization device according to an embodiment of this application.

[0146] like Figure 7As shown, the inbound logistics optimization device in this embodiment mainly includes an acquisition module 11, a construction module 12, an optimization module 13, and a verification module 14. In some embodiments, one or more of the acquisition module 11, construction module 12, optimization module 13, and verification module 14 can be combined into a single module.

[0147] In some embodiments, the acquisition module 11 can be configured to acquire an initial parameter set based on historical logistics data, the initial parameter set including objective function parameters, simulated annealing algorithm parameters, and digital modeling parameters.

[0148] The construction module 12 can be configured to construct a composite objective function about the frequency of shipments based on the objective function parameters.

[0149] The optimization module 13 can be configured to iteratively optimize the composite objective function based on the simulated annealing algorithm parameters to obtain the optimal solution for the shipping frequency.

[0150] The verification module 14 can be configured to perform simulation verification on the optimal solution based on the digital modeling parameters in order to evaluate the optimal solution for the shipping frequency.

[0151] In one implementation, a description of the specific function can be found in steps S10 to S40.

[0152] The aforementioned inbound logistics optimization device is used to perform Figure 1 The inbound logistics optimization method embodiments shown are similar in technical principle, the technical problems solved and the technical effects produced. Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the inbound logistics optimization device can be referred to the content described in the embodiments of the inbound logistics optimization method, and will not be repeated here.

[0153] Furthermore, it should be understood that since the various modules are only provided to illustrate the functional units of the device described in this application, the physical devices corresponding to these modules may be the processor itself, or a part of the processor's software, hardware, or a combination of both. Therefore, the number of modules shown in the figures is merely illustrative.

[0154] Those skilled in the art will understand that the various modules in the device can be adaptively split or combined. Such splitting or combining of specific modules will not cause the technical solution to deviate from the principles of this application; therefore, the technical solutions after splitting or combining will fall within the protection scope of this application.

[0155] Those skilled in the art will understand that all or part of the processes in the method of the above-described embodiment can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium can include any entity or device capable of carrying the computer program code, a medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0156] Furthermore, this application also provides an electronic device, which may include at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program, which, when executed by the at least one processor, implements the inbound logistics optimization method described in any of the above embodiments. See also Figure 8 As shown, Figure 8 The structure of an electronic device, including a processor 100 and a memory 200, is illustrated by way of example.

[0157] Furthermore, this application also provides a computer-readable storage medium. In one embodiment of the computer-readable storage medium according to this application, the computer-readable storage medium can be configured to store a program that performs the inbound logistics optimization method of the above-described method embodiments. This program can be loaded and run by a processor to implement the above-described inbound logistics optimization method. For ease of explanation, only the parts related to the embodiments of this application are shown; for specific technical details not disclosed, please refer to the method section of the embodiments of this application. The computer-readable storage medium can be a memory device formed by various electronic devices. Optionally, in the embodiments of this application, the computer-readable storage medium is a non-transitory computer-readable storage medium.

[0158] The technical solution of this application has been described in conjunction with the specific embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. Without departing from the principles of this application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of this application.

Claims

1. A method for optimizing inbound logistics, characterized in that, The method includes: An initial parameter set is obtained based on historical logistics data. The initial parameter set includes objective function parameters, simulated annealing algorithm parameters, and digital modeling parameters. Construct a composite objective function about shipping frequency based on the parameters of the objective function; The composite objective function is iteratively optimized based on the parameters of the simulated annealing algorithm to obtain the optimal solution for the shipping frequency; The optimal solution for the shipping frequency is verified by simulation based on the digital modeling parameters in order to evaluate the optimal solution for the shipping frequency.

2. The inbound logistics optimization method according to claim 1, characterized in that, The simulated annealing algorithm parameters include the initial solution, initial temperature, and maximum number of iterations; the iterative optimization of the objective function based on the simulated annealing algorithm parameters includes: The initial solution is randomly perturbed to generate candidate solutions; The objective function difference is determined based on the candidate solution and the initial solution; Whether to accept the candidate solution is determined based on the difference in the objective function. After accepting the candidate solution, the initial temperature is updated; When the maximum number of iterations is reached, the optimal solution is output.

3. The inbound logistics optimization method according to claim 2, characterized in that, The initial solution is randomly perturbed, including: using a neighborhood search strategy to randomly perturb the initial solution with a shipping frequency adjustment amount to generate the candidate solution, wherein the value range of the shipping frequency adjustment amount is a preset multiple of the standard deviation of the historical shipping frequency.

4. The inbound logistics optimization method according to claim 2, characterized in that, Determining whether to accept the candidate solution based on the difference in the objective function includes: Determine whether the difference in the objective function is less than or equal to zero; If so, then the candidate solution is accepted directly; Otherwise, calculate the acceptance probability of the candidate solution and generate a random number; Whether to accept the candidate solution is determined based on the difference between the acceptance probability and the random number.

5. The inbound logistics optimization method according to claim 4, characterized in that, Determining whether to accept the candidate solution based on the difference between the acceptance probability and the random number includes: Determine whether the difference between the acceptance probability and the random number is greater than zero; If so, then accept the candidate solution; Otherwise, retain the current solution.

6. The inbound logistics optimization method according to claim 2, characterized in that, Updating the initial temperature includes: The cooling index is obtained based on the current iteration number; The initial temperature is updated based on the product of the cooling index and the initial temperature.

7. The inbound logistics optimization method according to claim 2, characterized in that, The initial solution is obtained based on historical logistics data, including: The historical average frequency of shipments for each material is obtained based on the historical logistics data. The material vector is obtained based on the historical average shipping frequency of each material. The material vector is used as the initial solution.

8. The inbound logistics optimization method according to claim 1, characterized in that, The optimal solution is simulated and verified based on the digital modeling parameters, including: A logistics simulation model is constructed based on the digital modeling parameters and the optimal solution; The logistics simulation model was used for simulation verification to obtain the actual performance value of the optimal solution. The actual performance value of the optimal solution is compared with the simulation baseline value; The optimal solution for the stated shipping frequency is evaluated based on the comparison results.

9. An electronic device, characterized in that, include: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores a computer program, which, when executed by the at least one processor, implements the inbound logistics optimization method according to any one of claims 1 to 8.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the inbound logistics optimization method as described in any one of claims 1 to 8.

Images