Order distribution system and method for multi-warehouse supply of production raw materials

Abstract

The invention relates to the technical field of collaborative operation of a production system and a logistics system in an intelligent manufacturing scene, and discloses an order distribution system for multi-bin supply of production raw materials. A data analysis module of the system extracts data from data sources such as a production plan and warehouse information, and generates a production raw material demand order; the scheme solving module is based on a multi-objective optimization model, comprehensively considers factors such as inventory, conveying time and equipment load rate, and calculates an optimal delivery warehouse and quantity; the distribution execution module dispatches the logistics equipment according to an optimization result to complete a warehouse-out task; the monitoring prediction module learns and predicts historical and real-time order data by using a long short-term memory network, and dynamically adjusts an allocation strategy; and the user interaction module provides a human-computer interaction interface. According to the system, efficient and economical production raw material JIT supply is achieved through an intelligent means, the logistics efficiency and the resource utilization rate are remarkably improved, and reliable technical support is provided for production and logistics collaboration in an intelligent manufacturing scene.

Description

Technical Field

[0001] The present invention relates to the technical field of collaborative operation of production systems and logistics systems in the scenario of intelligent manufacturing, and specifically to an order allocation system and method for multi-warehouse supply of production raw materials. Background Art

[0002] In the scenario of intelligent manufacturing, the efficient supply of production raw materials is a key link to ensure the stable operation of the production system. Usually, the automated logistics system distributes production raw materials to the vicinity of production machines in a JIT (Just-In-Time) manner to meet the real-time needs of the production line. However, in actual applications, due to the capacity limitations of a single automated stereoscopic warehouse, regional distribution differences, and diverse requirements of production equipment, materials of the same specification may need to be stored separately in multiple warehouses. For example, some materials may be stored in the pallet warehouse of the stacker and the multi-through bin warehouse at the same time. Although this multi-warehouse storage mode solves the problem of insufficient capacity of a single warehouse, it also brings new technical challenges: how to select a suitable warehouse to process orders in a multi-warehouse environment to achieve efficient material outbound and distribution.

[0003] Currently, traditional order allocation methods mainly rely on manual designation or pre-setting of some simple outbound rules, such as selecting the warehouse with the largest inventory or the nearest warehouse. Although these methods are easy to operate, they have the following technical problems: Insufficient consideration of single factor: Existing methods usually only focus on a single factor (such as inventory quantity or regional distribution), while ignoring the comprehensive influence of other important factors, such as material transportation time, transportation cost, equipment load rate, etc. This single-dimensional decision-making method is difficult to achieve optimal logistics efficiency and cost control.

[0004] Unbalanced resource utilization: Due to the lack of overall optimization and scheduling of multi-warehouse resources, existing allocation strategies often lead to overloading of some warehouses, while other warehouses are idle. This not only reduces the utilization rate of equipment resources, but also may cause logistics bottlenecks and affect the overall production efficiency.

[0005] Lack of dynamic adaptability: Existing methods usually adopt fixed allocation rules and cannot be dynamically adjusted according to the real-time changing production order requirements, warehouse inventory status, and equipment operation conditions. This static allocation method is not flexible enough in the face of a complex production environment and is difficult to adapt to order demand fluctuations and warehouse status changes.

[0006] Lack of prediction ability: Traditional methods lack the ability to predict future order demands and cannot optimize order allocation strategies in advance, which may lead to excessive logistics pressure during peak periods or waste of resources during off-peak periods.

[0007] In summary, the current technical solutions have obvious limitations in a multi-warehouse environment and are difficult to meet the requirements for efficient and economical supply of production raw materials in the intelligent manufacturing scenario. Therefore, there is an urgent need for an order allocation system and method that can comprehensively consider various factors, dynamically adjust the allocation strategy, and have prediction capabilities to solve the above technical problems and improve the collaborative operation efficiency of the production system and the logistics system. Summary of the Invention

[0008] To solve the above problems, the present invention provides a multi-warehouse order allocation system for production raw materials that can comprehensively consider various factors such as inventory levels, material transportation time, and load rates of handling equipment in real time, and monitor the execution of order allocation in real time. Based on real-time and historical order data, it predicts future order demands, manually adjusts the parameters of the order allocation model, and optimizes the order allocation results to achieve efficient and economical just-in-time (JIT) supply of production raw materials in the intelligent manufacturing scenario.

[0009] The technical solution adopted by the present invention is as follows: An order allocation system for multi-warehouse supply of production raw materials, which includes a data analysis module, a solution solving module, an allocation execution module, and a monitoring and prediction module that are sequentially connected for data transmission, and a user interaction module that is connected for data transmission with the data analysis module, the solution solving module, the allocation execution module, and the monitoring and prediction module; The data analysis module is responsible for data extraction, cleaning, standardization, and calculation to generate production raw material demand orders; the solution solving module solves for the optimal outbound warehouse and quantity based on a multi-objective optimization model; the allocation execution module distributes the same type of raw material in the order to different warehouses according to the results of the solution solving module and schedules logistics equipment to complete the outbound operation; the monitoring and prediction module monitors the order execution situation and warehouse status in real time, predicts future order demands based on historical and real-time data, and optimizes the allocation strategy; the user interaction module provides a human-computer interaction interface, supports manual intervention and parameter adjustment, and optimizes the order allocation results.

[0010] Further, the data analysis module extracts data from a predetermined data source according to a set time point or manually triggered, generates a production raw material data set; then performs anomaly identification on the extracted data, and re-acquires the data when abnormal data is found; For normal data, it performs standardization conversion to unify the data format and unit; then performs structured conversion on the standardized data, organizes the data according to a preset logical relationship to form a clear data structure; finally, based on the set corresponding relationship between data, calculates the structured data to generate production raw material demand orders.

[0011] Further, the production raw material data set includes: production plan, product production time, production quantity, product BOM table, warehouse information, as well as material specification information, material quantity information, and material packaging information of the corresponding warehouse.

[0012] Further, in the multi-warehouse supply scheduling and distribution system of production raw materials, the production raw material demand order is one of the core data; each order corresponds to one type of raw material, and this raw material may be shipped out from one or more warehouses and ultimately supplied to a production unit for use.

[0013] Further, the solution module aims to minimize the comprehensive cost of production raw material supply, and defines four constraint conditions: the first constraint condition, the second constraint condition, the third constraint condition, and the fourth constraint condition; the solution module takes the production raw material demand order data generated by the data analysis module as input, and determines the outbound warehouse and the corresponding quantity of each production raw material by solving the optimization model; The calculation formula is:

[0014] In the formula, represents the comprehensive cost of multi-warehouse supply of production raw materials, which is the optimization objective of the objective function; represents the total number of orders, that is, the number of production raw material demand orders to be allocated; represents the total number of warehouses, that is, the number of warehouses available for selection; represents the index of the order, , used to identify the th order; represents the index of the warehouse, , used to identify the th warehouse; represents the decision variable, taking values of 0 or 1, represents that order is processed by warehouse ; represents that order is not processed by warehouse ; represents the weight coefficient of different cost factors, satisfying , is the weight of inventory-related costs, is the weight of material transportation time-related costs, is the weight of handling equipment load rate-related costs; represents the inventory of the materials of order in warehouse ; represents the inventory of the materials of order in warehouse The time required for outbound delivery and reaching the destination; Indicates the warehouse The load rate of handling equipment; Indicates a double summation over all orders and warehouses, that is, comprehensively considering the allocation relationship between each order and each warehouse.

[0015] Furthermore, the first constraint is that each order can only be processed by one warehouse; The calculation formula is:

[0016] The second constraint is that the inventory in the warehouse needs to meet the order demand; The calculation formula is:

[0017] In the formula, Indicates the order The material demand quantity; The third constraint is that the time for the warehouse to process orders does not exceed the allowed time; The calculation formula is:

[0018] In the formula, Indicates the total allowed time for the warehouse to process all orders; The fourth constraint is that the load rate of the warehouse handling equipment does not exceed the allowed value; The calculation formula is:

[0019] In the formula, Indicates the order Handed over to the warehouse The load rate increment of the handling equipment during outbound delivery; Indicates the warehouse The maximum allowed load rate of the handling equipment.

[0020] Furthermore, the allocation execution module receives the allocation result of the solution solving module, generates specific outbound tasks; then schedules the warehouse control system WCS of each warehouse to command the logistics access equipment to perform outbound operations; finally, monitors the execution status of the outbound tasks to ensure that the materials are delivered to the production machine on time.

[0021] Furthermore, the monitoring and prediction module collects order execution data and warehouse status data in real time, including inventory quantity, equipment load rate, and order completion status; the monitoring and prediction module learns and predicts historical and real-time order data based on the long short-term memory network LSTM, predicts the order variety, quantity, and time that will appear in the future; according to the prediction results, adjusts the order allocation model parameters and optimizes the allocation strategy.

[0022] Furthermore, the monitoring and prediction module learns and predicts historical and real-time order data based on the Long Short-Term Memory network (LSTM), and predicts the order variety, quantity, and time that will appear in the future. The prediction steps are as follows: Step 1 Forget gate: Determine which information needs to be discarded from the previous state; The calculation formula is:

[0023] In the formula, is the output of the forget gate at the current time step, and its value range is [0, 1]; is the Sigmoid function, which is used to limit the output between 0 and 1; is the weight matrix of the forget gate, which is used to control the importance of the input; is the hidden state at the previous moment and the current input concatenated into a vector; is the bias term of the forget gate, which is used to adjust the output; Step 2 Input gate: Determine which new information needs to be stored in the cell state and generate a candidate cell state; The calculation formula is: Input gate output:

[0024] Candidate cell state:

[0025] In the formula, is the input gate output at the current time step , and its value range is [0, 1], which determines which new information will be written into the cell state; is the candidate cell state, which is generated by the hyperbolic tangent function and represents possible new information; 、 are the weight matrices of the input gate and the candidate cell state; 、 are the bias terms of the input gate and the candidate cell state; The cell state is the core of the LSTM, which stores long-term dependency information. Its update formula is:

[0026] In the formula, represents the cell state at the current time step ; represents the cell state at the previous time step ; Step 3 Output Gate: Determine which information needs to be output from the cell state to the hidden state; The calculation formula is:

[0027] Output of the output gate:

[0028] Update of the hidden state:

[0029] In the formula, is the output of the output gate at the current time step, and its value range is [0, 1]; is the weight matrix of the output gate; is the bias term of the output gate; is the hidden state at the current time step as the final output of the LSTM; According to the predicted future order data, manually adjust the parameters in the order allocation model to optimize the order allocation result.

[0030] An order allocation method for multi-warehouse supply of production raw materials. This order allocation method is based on the above-mentioned order allocation system for multi-warehouse supply of production raw materials and includes the following steps: Step S1 Data collection and analysis: The data analysis module extracts data such as production plans and warehouse information, performs anomaly identification and standardization processing, and generates production raw material demand orders; Step S2 Construct and solve a multi-objective optimization model: The solution module constructs a multi-objective optimization model based on the goal of minimizing the comprehensive cost and constraint conditions, and uses an optimization algorithm to solve the optimal outbound warehouse and quantity for each order; Step S3 Allocate tasks and execute outbound: The allocation and execution module schedules the logistics equipment of each warehouse according to the solution results, completes the outbound operation of raw materials and distributes them to the production machines; Step S4 Real-time monitoring and order prediction: The monitoring and prediction module collects order execution and warehouse status data in real time, uses the LSTM network to predict future order demands, and optimizes the allocation strategy; Step S5 Human-computer interaction and optimization: The user interaction module provides an intuitive operation interface, supports manual adjustment of model parameters and anomaly handling, and further optimizes the order allocation result.

[0031] The beneficial effects of the present invention are: 1. Minimization of comprehensive cost: The system realizes the minimization of the comprehensive cost of production raw material supply through a multi-objective optimization model, comprehensively considering various factors such as inventory level, material transportation time, and handling equipment load rate. Compared with traditional single-rule allocation methods, it significantly reduces logistics and warehousing costs.

[0032] 2. Balanced resource utilization: By constraining the load rate of warehouse handling equipment, the system can reasonably allocate tasks, avoid the situation of some warehouses being overloaded while others are idle, improve the utilization rate of equipment resources, and extend the service life of equipment.

[0033] 3. Dynamic logistics scheduling: The dynamic adaptability enhancement system combines real-time monitoring and prediction functions, and can dynamically adjust the allocation strategy according to the changes in production order requirements and warehouse status, adapt to the complex and changeable production environment, and ensure the flexibility and efficiency of logistics scheduling.

[0034] 4. Improved prediction ability: By using the long short-term memory network (LSTM) to learn and predict historical and real-time order data, the system can anticipate future order requirements in advance, optimize the allocation strategy, reduce the logistics pressure during peak periods, and avoid resource waste.

[0035] 5. Optimization of human-machine collaboration: The user interaction module supports manual intervention and parameter adjustment, enabling the system to combine manual experience on the basis of algorithm optimization, and further improving the accuracy and practicality of the allocation results.

[0036] 6. Efficient realization of JIT supply: Through intelligent scheduling and real-time execution monitoring, the system ensures that production raw materials are delivered to production machines in a JIT (Just-in-Time) manner, reduces inventory backlog and material waiting time, and improves the operating efficiency of the production line.

[0037] 7. Strong scalability: The modular design of the system enables it to have good scalability, and can be flexibly adjusted according to the enterprise scale and requirements, and is applicable to multi-warehouse collaborative operations in different industries and scenarios.

[0038] In summary, the order allocation system for multi-warehouse supply of production raw materials has significant advantages in reducing costs, improving efficiency, optimizing resource allocation, etc., and provides strong technical support for the production and logistics collaboration in the intelligent manufacturing scenario. Brief Description of the Drawings

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0040] Figure 1 It is a schematic connection diagram of the order allocation system for multi-warehouse supply of production raw materials of the present invention; Figure 2 It is a flowchart of the order allocation method for multi-warehouse supply of production raw materials of the present invention. Detailed Embodiments

[0041] The technical solutions in the embodiments of the present invention will be described clearly and completely below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] To solve the order allocation problem in the collaborative operation of multiple warehouses in the intelligent manufacturing scenario, this embodiment provides an order allocation system for the multi-warehouse supply of production raw materials. The order allocation system for the multi-warehouse supply of production raw materials can comprehensively consider the inventory, material transportation time, and handling equipment in real time, and monitor the execution of order allocation in real time. According to real-time and historical order data, it can predict future order demands, manually adjust the parameters of the order allocation model, and optimize the order allocation results to achieve efficient and economical JIT supply of production raw materials in the intelligent manufacturing scenario.

[0043] Specifically, as Figure 1 shown, the order allocation system for the multi-warehouse supply of production raw materials includes a data analysis module, a solution solving module, an allocation execution module, and a monitoring and prediction module that are sequentially connected for data transmission, and a user interaction module that is connected to the data analysis module, the solution solving module, the allocation execution module, and the monitoring and prediction module for data transmission.

[0044] Among them, the data analysis module is responsible for data extraction, cleaning, standardization, and calculation to generate production raw material demand orders. The hardware devices of the data analysis module include: a server for storing and processing a large amount of data; network devices such as switches and routers to ensure the stability and efficiency of data transmission; and data acquisition terminals connected to systems such as ERP, MES, and WMS for real-time acquisition of data such as production plans and warehouse information. The data analysis module is provided with data acquisition interfaces for docking with ERP, MES, and WMS systems to extract data such as production plans and inventory information; equipped with data cleaning tools for identifying abnormal data and correcting or re-acquiring it, a data standardization program for unifying the formats and units of data from different sources, and a data calculation engine for calculating the standardized data according to preset rules to generate production raw material demand orders.

[0045] The solution solving module solves the optimal outbound warehouse and quantity based on the multi-objective optimization model. The hardware devices of the solution solving module include: a high-performance computing server that supports fast solving of complex optimization algorithms; a storage device for storing the parameters, constraint conditions, and solution results of the optimization model. The solution solving module is equipped with an optimization algorithm library containing algorithms such as linear programming and mixed-integer programming for solving multi-objective optimization problems; a modeling tool for defining the objective function and constraint conditions and constructing a comprehensive cost minimization model; and a scheduling engine for generating a specific warehouse allocation plan based on the optimization results.

[0046] The allocation execution module distributes the same raw material in the order to different warehouses according to the result of the solution solving module, and schedules the logistics equipment to complete the outbound operation. The hardware devices of the allocation execution module include: a warehouse control system WCS that commands logistics access devices such as stackers and conveyors to execute tasks, logistics access devices such as stackers, automatic guided vehicles AGVs, and conveyor belts for material access and transportation, RFID barcode scanning devices for identifying material specifications and tracking logistics status, and a monitoring screen for displaying the operating status of warehouse equipment and task progress. The allocation execution module is equipped with a task scheduling program that generates specific outbound tasks according to the optimization results and assigns them to corresponding devices; a device control program that interacts with the WCS system to control the operation of logistics equipment; and a status monitoring program that real-time collects the operating status of equipment and the completion of tasks.

[0047] The monitoring and prediction module real-time monitors the order execution situation and warehouse status, predicts future order demands based on historical and real-time data, and optimizes the allocation strategy. The hardware devices of the monitoring and prediction module include: a monitoring terminal for displaying information such as order execution progress and warehouse status, inventory sensors and load rate sensors for collecting real-time warehouse data, and a big data storage device for storing historical order data and real-time monitoring data. The monitoring and prediction module is built-in with a real-time monitoring program for collecting and displaying the order execution situation and warehouse status; a prediction model, namely the LSTM network, for predicting future order demands based on historical and real-time data; and at the same time is equipped with an optimization and adjustment program for dynamically adjusting the parameters of the order allocation model according to the prediction results.

[0048] The user interaction module provides a human-computer interaction interface, supports manual intervention and parameter adjustment, and optimizes the order allocation result. The hardware devices of the user interaction module include: a PC, tablet computer or touch screen for users to operate and view system information, and an audible and visual alarm for reminding abnormal situations. The user interaction module is equipped with a graphical user interface GUI for intuitively displaying information such as order allocation results, warehouse status, and logistics execution situation; a parameter adjustment tool for supporting users to manually adjust key parameters such as weight coefficients and constraint conditions; and an abnormal alarm program for issuing an alarm when an abnormality occurs and recording the abnormal log.

[0049] Further, the following specific descriptions are made for each module in this embodiment: The data analysis module is the core starting point of the entire multi-warehouse supply order allocation system for production raw materials, responsible for extracting, cleaning, standardizing, and calculating to generate production raw material demand orders from the original data. The functional implementation of this module is divided into the following key steps: First, data extraction is performed:

[0050] Data extraction can be triggered automatically based on a set time point or manually initiated by humans according to actual needs. The data comes from predetermined data sources, including but not limited to the following systems: The ERP system provides information such as production plans, product BOM tables, and material requirements; the MES system provides real-time information such as production equipment status and production progress; the WMS system provides information such as warehouse inventory levels, material specifications, storage locations, etc.; the logistics management system provides logistics-related information such as transportation time and handling equipment load rates. Extract various data related to the supply of production raw materials, including: specifying the production time, production quantity, etc. of the product, i.e., the production plan; listing the types and quantities of raw materials required for each product, i.e., the product BOM table; the inventory levels, material specifications, storage locations, packaging information, etc. of each warehouse, i.e., the warehouse information; the material transportation time, handling equipment load rates, etc., i.e., the logistics information.

[0051] Then, anomaly identification is performed: To ensure the quality and reliability of the data and avoid deviations in subsequent analysis and decision-making caused by abnormal data, anomaly identification is carried out. Anomaly identification includes: checking data integrity, such as whether there are missing values or incomplete fields; checking data rationality, such as whether the inventory level is negative and whether the production quantity exceeds a reasonable range; checking data consistency, such as whether the associated data between different data sources is consistent. For abnormal data, the system will mark it and try to obtain the correct data again; if the correct data cannot be obtained, an abnormal log will be recorded and relevant personnel will be notified for manual intervention.

[0052] Then, standardization conversion is performed: For normal data, convert data from different sources, formats, and units into a unified standard format for subsequent processing and analysis. Standardization conversion includes: unifying the data format, such as unifying the date format to "YYYY-MM-DD" and retaining two decimal places for numerical values; unifying the measurement units, such as unifying the inventory unit to "tons" or "pieces"; data coding mapping, such as mapping the material specification name to a unique code for easy system identification and processing. After standardization conversion, a standardized data set is output, with the formats and units of all fields being consistent for subsequent structure conversion and calculation.

[0053] Then, structure conversion is performed: Organize the standardized data according to the preset logical relationships to form a structured data model for subsequent calculations. Structure conversion includes: data grouping, for example, classifying all relevant data of the same order into a data structure; data association, for example, associating production plans, BOM tables, and inventory information through material codes. Data aggregation, for example, summarizing the inventory data of multiple warehouses by material types. After structure conversion, a structured data set is output, which contains clear hierarchical relationships and logical associations.

[0054] Then, perform data calculations: According to the preset corresponding relationships between data, calculate the structured data to generate production raw material demand orders. Data calculations include: calculating the demand quantity of each material based on the production plan and BOM table, that is, calculating the material demand quantity; determining the delivery destination of the material based on the location information of the production equipment, that is, calculating the delivery destination; combining logistics information to calculate the time required for the material to be shipped out of the warehouse and reach the production machine, that is, estimating the delivery time. The above data calculation process is a conventional calculation in this field, and the calculation formulas will not be elaborated in detail here. After data calculation, the output result is a production raw material demand order. Each order contains: a unique identifier, that is, the order number; the types of raw materials to be delivered, that is, the material types; the quantity of raw materials to be delivered, that is, the demand quantity; the location of the production machine to which the materials need to be delivered, that is, the delivery destination; the time when the materials need to reach the production machine, that is, the estimated delivery time. The production raw material demand order is one of the core data; each order corresponds to one type of raw material, and this raw material may be shipped out of one or more warehouses and ultimately supplied to one production unit for use.

[0055] Finally, perform output and transmission: The production raw material demand orders finally output by the data analysis module are transmitted to the solution module in the form of structured data. The transmission method can be to transmit the order data to the solution module through an API or other data transmission protocols, and record the key steps and abnormal situations during the order generation process for subsequent traceability.

[0056] The data analysis module generates high-quality production raw material demand orders through the extraction, cleaning, standardization, structuring, and calculation of the original data. Its core role is to provide an accurate and reliable data basis for subsequent order allocation and optimization, thereby ensuring the efficient operation and decision-making accuracy of the entire system.

[0057] The solution module is the core part of the entire multi-warehouse supply order allocation system for production raw materials, responsible for calculating the optimal outbound warehouse and quantity allocation plan through a mathematical optimization model. The solution module aims to minimize the comprehensive cost of production raw material supply and defines four constraint conditions: the first constraint condition, the second constraint condition, the third constraint condition, and the fourth constraint condition; the solution module takes the production raw material demand order data generated by the data analysis module as input, and determines the outbound warehouse and corresponding quantity of each production raw material by solving the optimization model.

[0058] First, for the minimization of the comprehensive cost, the calculation formula of the objective function is:

[0059] In the formula, represents the comprehensive cost of multi-warehouse supply of production raw materials, which is the optimization objective of the objective function; represents the total number of orders, that is, the quantity of production raw material demand orders to be allocated; represents the total number of warehouses, that is, the number of available warehouses; represents the index of the order, , used to identify the th order; represents the index of the warehouse, , used to identify the th warehouse; represents the decision variable, taking values of 0 or 1, represents that order is processed by warehouse , represents that order is not processed by warehouse ; represents the weight coefficient of different cost factors, satisfying , is the weight of inventory-related costs, is the weight of material transportation time-related costs, is the weight of handling equipment load rate-related costs; represents the inventory of the materials of order in warehouse ; represents the time required for the materials of order to be out of the warehouse in warehouse and delivered to the destination; represents the load rate of the handling equipment in warehouse ; represents the double summation over all orders and warehouses, that is, comprehensively considering the allocation relationship between each order and each warehouse.

[0060] By using the comprehensive cost of raw material supply Minimum is the goal. Comprehensively consider inventory cost , transportation time cost , handling equipment load rate cost There are three cost factors. The inventory cost weight is , the larger the inventory, the lower the cost of shipping from the warehouse. The transportation time cost weight is The longer the transportation time, the lower the logistics efficiency and the higher the cost. The weight of the handling equipment load rate cost is The higher the load rate of the handling equipment, the tighter the utilization of equipment resources and the higher the cost. Weight coefficient satisfy , used to balance the importance of different cost factors.

[0061] To ensure the feasibility of the allocation plan, the four constraints of the solution solving module are as follows: The first constraint is: each order can only be processed by one warehouse; The calculation formula is:

[0062]

[0063] By the first constraint, each order Must and can only be assigned to one warehouse , thus avoiding duplicate allocation or omission of orders.

[0064] The second constraint is: the warehouse inventory must meet the order requirements; The calculation formula is:

[0065] In the formula, Indicates order Material requirements;

[0066] By the second constraint, if the order Assign to warehouse ,Right now , then the warehouse Inventory Must be greater than or equal to order Material requirements , thereby ensuring that the warehouse has sufficient inventory to meet order requirements.

[0067] The third constraint is that the warehouse should not take more time to process the order than the allowed time; The calculation formula is:

[0068] In the formula, It indicates the total time allowed for the warehouse to process all orders; The third constraint is that the sum of the delivery time for all orders cannot exceed the total allowed time. , thereby ensuring the timeliness of logistics distribution and avoiding the impact of timeouts on production progress.

[0069] The fourth constraint is: the load rate of warehouse handling equipment does not exceed the allowed value; The calculation formula is:

[0070] In the formula, Indicates order Delivered to warehouse The load rate increment of the handling equipment during outbound delivery; Represents warehouse The maximum load rate allowed for handling equipment; By the fourth constraint, the warehouse The total load factor of the handling equipment cannot exceed the maximum load factor allowed. , avoid equipment overload and ensure the normal operation and service life of the equipment.

[0071] The input data of the solution solving module are: production raw material demand order data and warehouse related information; among them, the production raw material demand order data is obtained from the data analysis module, including the material type, demand quantity, delivery destination and other information of each order; the warehouse related information includes the inventory of each warehouse, transportation time, handling equipment load rate, etc. The output results of the solution solving module are: outbound warehouse and quantity, and allocation plan; outbound warehouse and quantity determine the outbound warehouse and corresponding outbound quantity corresponding to each order according to the solution results of the optimization model; the allocation plan is to generate a specific warehouse allocation plan as the input of the allocation execution module.

[0072] The solution solving module generates the optimal order allocation plan by comprehensively considering multiple factors such as inventory, delivery time, and equipment load rate, combined with strict constraints. The design and implementation of this module significantly improves the intelligent level of multi-warehouse supply of production raw materials.

[0073] The distribution execution module is a key link in the multi-warehouse supply order distribution system for production raw materials. It is responsible for converting the optimal distribution results generated by the solution solving module into actual logistics operations. This module completes the outbound task of production raw materials by scheduling the warehouse control system WCS and logistics equipment, and delivers them to the production machines on time.

[0074] The allocation execution module allocates the same raw materials in the production raw material demand order to different warehouses for outbound operations based on the optimization results of the solution solving module, and ensures that the materials are delivered to the production machines on time, thereby achieving efficient and accurate logistics scheduling and ensuring the JIT supply of production raw materials.

[0075] The input data of the allocation execution module include: optimized allocation results, warehouse status information, and logistics path information; among them, the optimized allocation results are the outbound warehouses and corresponding outbound quantities for each order obtained from the solution solving module; the warehouse status information includes real-time data such as the inventory quantity, equipment load rate, and material storage location of each warehouse; the logistics path information includes the material transportation path, estimated transportation time, etc.

[0076] The execution flow of the allocation execution module is as follows: First, generate the outbound task:

[0077] According to the optimization allocation results, each order is broken down into specific outbound tasks. For example: Order Materials from warehouse Out of stock Unit, by warehouse Out of stock Unit. The outbound task is delivered to the warehouse's WCS system in a standardized format, including: material type, outbound quantity, storage location, target production machine and other information.

[0078] Then, dispatch logistics access equipment: Dispatch logistics storage and retrieval equipment, such as stackers, automatic guided vehicles (AGVs), conveyor belts, etc., to perform outbound tasks. According to task instructions, the WCS system controls the logistics storage and retrieval equipment to complete the following operations: locate materials, locate target materials according to storage location information; extract materials, use stackers or AGVs to take materials out of storage locations; load materials, load materials onto conveying equipment.

[0079] Then, dispatch logistics transportation equipment: Based on the logistics path information, the best transportation path for materials from the warehouse to the production machine is planned. Logistics transportation equipment, such as conveyor belts and elevators, transport materials to the target production machine and monitor the transportation status in real time to ensure that the materials are delivered on time.

[0080] Finally, task completion feedback: After the task is completed, update the warehouse inventory, equipment status and other information. If an abnormality occurs during the execution, such as equipment failure, path blockage, etc., an alarm will be issued in time and the emergency plan will be triggered.

[0081] Through the allocation execution module, materials are shipped from the designated warehouse and successfully delivered to the production machine; at the same time, data such as warehouse inventory, equipment status, and task completion are updated to provide a basis for subsequent scheduling. The allocation execution module converts the optimized allocation results into specific outbound operations by scheduling logistics storage and retrieval equipment and conveying equipment to ensure the efficient supply of production raw materials. The design and implementation of this module not only improves the automation and intelligence level of logistics execution, but also provides strong support for production and logistics collaboration in intelligent manufacturing scenarios.

[0082] The monitoring and prediction module is an important part of the multi-warehouse supply order distribution system for production raw materials. It is responsible for real-time monitoring of order execution and warehouse status, and based on historical and real-time data, uses the long short-term memory network LSTM to learn and optimize big data to predict possible future order demand. Through the prediction results, the order distribution model is further optimized to improve the intelligence level of the system and resource utilization efficiency.

[0083] The monitoring and prediction module monitors the execution of production raw material orders and warehouse status in real time. Based on real-time and historical order data, it uses the LSTM network to predict the demand for production raw materials. According to the prediction results, it manually adjusts the order allocation model parameters and optimizes the allocation strategy. This improves the foresight and flexibility of order allocation, ensures that the system can dynamically adapt to future changes in production demand, reduce peak logistics pressure, avoid waste of resources, and improve overall supply chain efficiency.

[0084] The input data of the monitoring and prediction module include: real-time data, historical data, and external data. Real-time data includes the current order execution progress, warehouse inventory, equipment load rate, logistics transportation status, etc.; historical data includes information such as order types, quantities, and time distribution in the past period of time; external data includes production plans, market trends, seasonal demand fluctuations, etc., which are used to assist prediction.

[0085] LSTM is a special recurrent neural network RNN ​​that can capture long-term dependencies in time series data. It implements cell state updates and information selection through three key steps: forget gate, input gate, and output gate. The monitoring prediction module learns and predicts historical and real-time order data based on the long short-term memory network LSTM, and predicts the types, quantities, and time of future orders. The prediction steps are as follows: Step 1: Forget gate: decide which information needs to be discarded from the previous state; The calculation formula is:

[0086] In the formula, is the forget gate output of the current time step, with a value range of [0,1]; is the Sigmoid function, which is used to limit the output between 0 and 1; is the weight matrix of the forget gate, which is used to control the importance of the input; is the hidden state at the previous moment and the current input The concatenated vector; is the bias term of the forget gate, which is used to adjust the output.

[0087] Step 2 Input gate: decides which new information needs to be stored in the cell state and generates candidate cell states; The calculation formula is: Input gate output:

[0088] Candidate cell states:

[0089] In the formula, is the current time step The input gate output, with a value range of [0,1], determines which new information will be written into the cell state; is the candidate cell state, which is determined by the hyperbolic tangent function Generate, representing possible new information; , is the weight matrix of the input gate and candidate cell state; , is the bias term for the input gate and candidate cell state.

[0090] The cell state is the core of LSTM, which stores long-term dependency information. Its update formula is:

[0091] In the formula, Indicates the current time step The cell state; Represents the previous time step The cell state.

[0092] Step 3 Output gate: determines which information needs to be output from the cell state to the hidden state; The calculation formula is: Output gate output:

[0093] Hide status updates:

[0094] In the formula, is the current time step The output gate output has a value range of [0,1]; is the weight matrix of the output gate; is the bias term of the output gate; is the current time step The hidden state of is used as the final output of LSTM.

[0095] The LSTM network predicts the order demand that may appear in the future by learning from historical and real-time data, including: order type, order quantity, and order time. The monitoring and prediction module generates forecast data of future order demand as the basis for optimizing the order allocation model; according to the forecast results, the parameters in the order allocation model are manually adjusted. , to optimize the allocation strategy. For example: increase the weight of inventory Prioritize warehouses with sufficient inventory; increase the weight of delivery time To optimize logistics efficiency; increase load factor weight To balance device resources.

[0096] The monitoring and prediction module achieves accurate prediction and dynamic optimization of future order demand through real-time monitoring and LSTM network prediction. This module not only improves the intelligence level of order allocation, but also provides strong technical support for production and logistics collaboration in intelligent manufacturing scenarios.

[0097] The user interaction module is an important part of the multi-warehouse supply order allocation system for raw materials. It is responsible for providing a human-computer interaction interface and supporting real-time interaction between users and the system. This module transmits human-computer interaction information by connecting the data analysis module, solution solving module, allocation execution module and monitoring prediction module, so that users can grasp the system operation status in real time and perform manual intervention and optimization adjustments when necessary.

[0098] The user interaction module provides an intuitive human-computer interaction interface, displays key information about the system operation, supports users to manually adjust order allocation model parameters, constraints, etc., and provides real-time feedback on the system operation status, including order execution progress, warehouse status, logistics equipment operation status, etc. It issues alarms in abnormal situations and records abnormal logs to enhance the transparency and controllability of the system, ensure that users can flexibly adjust system behavior according to actual conditions, and provide decision support tools to help users optimize order allocation strategies.

[0099] The input data of the user interaction module includes: system status information, prediction results, and user input. Among them, the system status information includes order execution progress, warehouse inventory, equipment load rate, logistics transportation status, etc.; the prediction results come from the future order demand prediction data of the monitoring prediction module; the user input is: the adjustment instructions or optimization suggestions entered by the user through the interactive interface.

[0100] The information displayed in the user interaction module includes: the allocation results of production raw material demand orders, such as outbound warehouse, quantity, delivery time, etc.; the real-time status of each warehouse, such as inventory, equipment load rate, task execution progress, etc.; the operating status of logistics equipment, such as the working conditions of stackers, AGVs, and conveyor belts; prediction results, such as the variety, quantity, and time distribution of future orders. Information display can be intuitively displayed in the form of charts, tables, maps, etc., and key indicators such as inventory, equipment load rate, etc. are dynamically displayed. When an abnormal alarm occurs, the user is reminded of the abnormal situation in the form of sound and light prompts or pop-up windows. Finally, the user interaction module generates a new order allocation plan based on the user's adjustment instructions, and updates the order execution progress, warehouse status, logistics equipment operation status and other information in real time. After the user confirms and handles the abnormality, the system resumes normal operation.

[0101] The user interaction module provides an intuitive graphical interface and powerful interactive functions, allowing users to understand the system operation status in real time and perform manual intervention and optimization adjustments when necessary. The design and implementation of this module not only improves the ease of use and flexibility of the system, but also provides reliable technical support for production and logistics collaboration in intelligent manufacturing scenarios.

[0102] Based on the above-mentioned order allocation system for production raw materials with multiple warehouses, this embodiment also proposes an order allocation method for production raw materials with multiple warehouses; Figure 2 As shown, the order allocation method for multi-warehouse supply of production raw materials includes the following steps:

[0103] Step S1 Data collection and analysis: The data analysis module extracts data such as production plans and warehouse information, performs abnormal identification and standardization processing, and generates production raw material demand orders; Step S2 constructs a multi-objective optimization model and solves it: the solution solving module uses an optimization algorithm to solve the optimal delivery warehouse and quantity for each order based on the comprehensive cost minimization objective and constraints; Step S3: Assign tasks and execute outbound delivery: the assignment execution module dispatches the logistics equipment of each warehouse according to the solution results, completes the outbound delivery operation of raw materials and delivers them to the production machines; Step S4: Real-time monitoring and order prediction: The monitoring and prediction module collects order execution and warehouse status data in real time, uses the LSTM network to predict future order demand, and optimizes the allocation strategy;

[0104] Step S5: Human-computer interaction and optimization: The user interaction module provides an intuitive operation interface, supports manual adjustment of model parameters and exception handling, and further optimizes order allocation results.

[0105] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. An order distribution system for multi-warehouse supply of production raw materials, characterized by: The order distribution system for multi-warehouse supply of production raw materials includes a data analysis module, a solution solving module, a distribution execution module and a monitoring prediction module connected with sequential data transmission, and a user interaction module connected with data analysis module, solution solving module, distribution execution module and monitoring prediction module; The data analysis module is responsible for data extraction, cleaning, standardization and calculation, and generates production raw material demand orders; the solution solving module solves the optimal outbound warehouse and quantity based on the multi-objective optimization model; the allocation execution module allocates the same raw materials in the order to different warehouses according to the results of the solution solving module, and dispatches logistics equipment to complete the outbound operation; the monitoring and prediction module monitors the order execution status and warehouse status in real time, predicts future order demand based on historical and real-time data, and optimizes the allocation strategy; The user interaction module provides a human-computer interaction interface, supports manual intervention and parameter adjustment, and optimizes order allocation results.

2. The order distribution system for multi-warehouse supply of production raw materials according to claim 1 is characterized by: The data analysis module extracts data from a predetermined data source according to a set time point or is manually triggered to generate a production raw material data set; then, the extracted data is identified for anomalies, and when abnormal data is found, it needs to be re-acquired; For normal data, standardization conversion is performed to unify the data format and unit; then the standardized data is structured and organized according to the preset logical relationship to form a clear data structure; finally, based on the set correspondence between data, the structured data is calculated to generate production raw material demand orders.

3. The order distribution system for multi-warehouse supply of production raw materials according to claim 2 is characterized by: The production raw material data set includes: production plan, product production time, production quantity, product BOM table, warehouse information, and material specification information, material quantity information and material packaging information of the corresponding warehouse.

4. The order distribution system for multi-warehouse supply of production raw materials according to claim 2 is characterized by: In the multi-warehouse supply scheduling and distribution system for production raw materials, the production raw material demand order is one of the core data; each order corresponds to a raw material, which may be shipped from one or more warehouses and finally supplied to a production unit for use.

5. The order distribution system for multi-warehouse supply of production raw materials according to claim 1 is characterized by: The solution solving module aims to minimize the comprehensive cost of raw material supply and defines four constraints: the first constraint, the second constraint, the third constraint and the fourth constraint. The solution solving module takes the raw material demand order data generated by the data analysis module as input and determines the outbound warehouse and corresponding quantity of each raw material by solving the optimization model. The calculation formula is: ； In the formula, It represents the comprehensive cost of multi-warehouse supply of raw materials for production, which is the optimization target of the objective function; Indicates the total number of orders, that is, the number of production raw material demand orders that need to be allocated; Indicates the total number of warehouses, that is, the number of warehouses available for selection; Represents the index of the order, , used to identify the Orders; Represents the index of the warehouse, , used to identify the warehouses; represents a decision variable, which takes a value of 0 or 1. Indicates order By Warehouse deal with, Indicates order Not by warehouse deal with; Represents the weight coefficients of different cost factors, satisfying , is the weight of inventory-related costs, is the weight of the material transportation time-related cost, The weight of the costs associated with the load factor of the handling equipment; Indicates order Materials in warehouse The amount of inventory in Indicates order Materials in warehouse The time required to leave the warehouse and arrive at the destination; Represents warehouse Loading rate of handling equipment; It means to perform double summation on all orders and warehouses, that is, comprehensively consider the distribution relationship between each order and each warehouse.

6. The order distribution system for multi-warehouse supply of production raw materials according to claim 5 is characterized by: The first constraint is: each order can only be processed by one warehouse; The calculation formula is: ； The second constraint is: the warehouse inventory must meet the order requirements; The calculation formula is: ； In the formula, Indicates order Material requirements; The third constraint is that the warehouse should not take more time to process the order than the allowed time; The calculation formula is: ； In the formula, It indicates the total time allowed for the warehouse to process all orders; The fourth constraint is: the load rate of warehouse handling equipment does not exceed the allowed value; The calculation formula is: ； In the formula, Indicates order Delivered to warehouse The load rate increment of the handling equipment during outbound delivery; Represents warehouse The maximum load rate allowed for handling equipment.

7. The order distribution system for multi-warehouse supply of production raw materials according to claim 1 is characterized by: The allocation execution module receives the allocation results of the solution solving module and generates specific outbound tasks; then it dispatches the warehouse control system WCS of each warehouse to command the logistics storage and retrieval equipment to perform outbound operations; finally, it monitors the execution status of the outbound tasks to ensure that the materials are delivered to the production machines on time.

8. The order distribution system for multi-warehouse supply of production raw materials according to claim 1 is characterized by: The monitoring and prediction module collects order execution data and warehouse status data in real time, including inventory, equipment load rate, and order completion status; the monitoring and prediction module learns and predicts historical and real-time order data based on the long short-term memory network LSTM, and predicts the type, quantity and time of future orders; according to the prediction results, the order allocation model parameters are adjusted to optimize the allocation strategy.

9. The order distribution system for multi-warehouse supply of production raw materials according to claim 1 is characterized by: The monitoring prediction module learns and predicts historical and real-time order data based on the long short-term memory network LSTM, and predicts the type, quantity and time of future orders. The prediction steps are as follows: Step 1: Forget gate: decide which information needs to be discarded from the previous state; The calculation formula is: ； In the formula, is the forget gate output of the current time step, with a value range of [0,1]; is the Sigmoid function, which is used to limit the output between 0 and 1; is the weight matrix of the forget gate, which is used to control the importance of the input; is the hidden state at the previous moment and the current input The concatenated vector; is the bias term of the forget gate, used to adjust the output; Step 2 Input gate: decides which new information needs to be stored in the cell state and generates candidate cell states; The calculation formula is: Input gate output: ; Candidate cell states: ; In the formula, is the current time step The input gate output, with a value range of [0,1], determines which new information will be written into the cell state; is the candidate cell state, which is determined by the hyperbolic tangent function Generate, representing possible new information; , is the weight matrix of the input gate and candidate cell state; , is the bias term for the input gate and candidate cell state; The cell state is the core of LSTM, which stores long-term dependency information. Its update formula is: ； In the formula, Indicates the current time step The cell state; Represents the previous time step The cell state; Step 3 Output gate: determines which information needs to be output from the cell state to the hidden state; The calculation formula is: Output gate output: ; Hide status updates: ; In the formula, is the current time step The output gate output has a value range of [0,1]; is the weight matrix of the output gate; is the bias term of the output gate; is the current time step The hidden state of is the final output of LSTM; Manually adjust the parameters in the order allocation model based on the predicted future order data , optimize order allocation results.

10. A method for allocating orders for production raw materials supplied from multiple warehouses, the method being based on the system for allocating orders for production raw materials supplied from multiple warehouses as claimed in claim 1, characterized in that: The following steps are involved: Step S1 Data collection and analysis: The data analysis module extracts data such as production plans and warehouse information, performs abnormal identification and standardization processing, and generates production raw material demand orders; Step S2 constructs a multi-objective optimization model and solves it: the solution solving module uses an optimization algorithm to solve the optimal delivery warehouse and quantity for each order based on the comprehensive cost minimization objective and constraints; Step S3: Assign tasks and execute outbound delivery: the assignment execution module dispatches the logistics equipment of each warehouse according to the solution results, completes the outbound delivery operation of raw materials and delivers them to the production machines; Step S4: Real-time monitoring and order prediction: The monitoring and prediction module collects order execution and warehouse status data in real time, uses the LSTM network to predict future order demand, and optimizes the allocation strategy; Step S5: Human-computer interaction and optimization: The user interaction module provides an intuitive operation interface, supports manual adjustment of model parameters and exception handling, and further optimizes order allocation results.

Images